CN116739154A

CN116739154A - Fault prediction method and related equipment thereof

Info

Publication number: CN116739154A
Application number: CN202310611808.2A
Authority: CN
Inventors: 郑嘉乐; 李唤; 饶仲文; 张可力; 刘跃群; 王赟章
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2023-05-26
Filing date: 2023-05-26
Publication date: 2023-09-12

Abstract

The application discloses a fault prediction method and related equipment, wherein in the process of predicting faults of equipment, considered factors are comprehensive, so that the finally obtained fault prediction result of the equipment can have higher accuracy. The method of the application comprises the following steps: acquiring historical fault information of target equipment, wherein the historical fault information is used for indicating N faults of the target equipment in the 1 st time to the T-1 st time, T is more than or equal to 2, and N is more than or equal to 2; based on the historical fault information, acquiring causal relations among N faults and weights of the N faults, wherein the weights of the N faults are used for indicating importance degrees of the N faults; based on the historical fault information, the causal relationship among the N faults and the weights of the N faults, the probability of the N faults of the target equipment in the T moment is obtained.

Description

Fault prediction method and related equipment thereof

Technical Field

The embodiment of the application relates to the technical field of artificial intelligence (artificial intelligence, AI), in particular to a fault prediction method and related equipment thereof.

Background

The equipment failure prediction refers to that the failure of equipment does not occur yet, whether the equipment is likely to have a certain or a certain failure is predicted based on certain information of the equipment through a neural network model in the AI technology, so that a failure prediction result is informed to an equipment engineer, and the equipment engineer can repair the equipment in time based on the failure prediction result.

In the related art, the history fault information of the device may be acquired first, the history fault information being used to indicate a plurality of faults that have occurred in the past of the device, and the history fault information being input into the neural network model. The neural network model may then perform a series of processes on the historical fault information to obtain a probability that the device will have the plurality of faults in the future, i.e., a fault prediction result for the device. Thus, the fault prediction for the device is completed.

In the above process, the neural network model only considers the contribution degree of a plurality of faults of the equipment, which have occurred in the past, in the fault prediction process in the process of predicting the faults of the equipment, that is, in the process of processing the historical fault information of the equipment, and considered factors are single, so that the finally obtained fault prediction result of the equipment is inaccurate.

Disclosure of Invention

The embodiment of the application provides a fault prediction method and related equipment, and factors considered in the process of predicting the faults of equipment are comprehensive, so that the finally obtained fault prediction result of the equipment can have higher accuracy.

The embodiment of the application provides a fault prediction method, which is realized through a target model and comprises the following steps:

when the fault prediction is required to be carried out on the target equipment, the historical fault information of the target equipment can be acquired first and is input into the target model, wherein the historical fault information of the target equipment is used for indicating N faults of the target equipment from the 1 st moment to the T-1 st moment, and T is more than or equal to 2, and N is more than or equal to 2.

After the historical fault information of the target equipment is obtained, the historical fault information of the target equipment can be input into a target model, and the target model can process the historical fault information of the target equipment, so that the causal relationship between N faults and the weights of the N faults, which occur in the 1 st moment to the T-1 st moment, of the target equipment are obtained. The weights of the N faults are used for indicating the functions exerted by the N faults in the process of predicting the faults of the target equipment, namely the importance degree of the N faults.

After the causal relationship among the N faults and the weights of the N faults are obtained, the target model can process the historical fault information of the target equipment, the causal relationship among the N faults and the weights of the N faults, so that the probability of the N faults of the target equipment in the T moment, namely the fault prediction result of the target equipment, is obtained. Thus, the fault prediction for the target device is completed.

From the above method, it can be seen that: when the fault prediction is required for the target equipment, the historical fault information of the target equipment can be acquired first and is input into the target model, wherein the historical fault information of the target equipment is used for indicating N faults of the target equipment from the 1 st moment to the T-1 st moment. Then, the target model may process the historical fault information of the target device, thereby obtaining causal relationships between the N faults and weights of the N faults. Finally, the target model may process historical fault information of the target device, causal relationships between the N faults, and weights of the N faults, thereby obtaining probabilities of the N faults occurring in the target device at the T-th moment. In the foregoing process, in the process of performing fault prediction on the target device, the target model considers not only the causal relationship between N faults occurring in the 1 st time to the T-1 st time of the target device, but also the weights of the N faults (that is, the importance degree of the N faults in the fault prediction process on the target device), where the considered factors are relatively comprehensive, so that the finally obtained fault prediction result (that is, the probability of the N faults occurring in the T time of the target device) of the target device can have relatively high accuracy.

In one possible implementation, based on the historical fault information, obtaining the causal relationship between the N faults and the weights of the N faults includes: extracting first characteristics of the historical fault information to obtain causal relations among N faults; sub-historical fault information is extracted from the historical fault information, and the sub-historical fault information is used for indicating P faults of target equipment in the time from T-w to T-1, wherein N faults comprise P faults, N is more than or equal to P is more than or equal to 1, and T is more than or equal to w is more than or equal to 1; and carrying out second feature extraction on the causal relationship among the N faults and the sub-historical fault information to obtain weights of the N faults. In the foregoing implementation manner, after the historical fault information of the target device is received, the target model may perform the first feature extraction on the historical fault information of the target device, so as to obtain a causal relationship between N faults of the target device that occur in the 1 st to T-1 st moments. After the causal relationship between the N faults is obtained, the target model can extract sub-historical fault information of the target equipment from the historical fault information of the target equipment, wherein the sub-historical fault information of the target equipment is used for indicating P faults of the target equipment from the T-w moment to the T-1 moment. After the causal relationship among the N faults and the sub-historical fault information of the target equipment are obtained, the target model can conduct second feature extraction on the causal relationship among the N faults and the sub-historical fault information, and therefore weights of the N faults are accurately obtained.

In one possible implementation, based on the historical fault information, the causal relationships between the N faults, and the weights of the N faults, obtaining the probability that the target device has N faults in the T-th time includes: based on the causal relationship among N faults and the weights of the N faults, acquiring the causal relationship among M faults in the N faults, wherein N is more than or equal to M is more than or equal to 1; based on the historical fault information and causal relationships among M faults, the probability of N faults of the target equipment in the T moment is obtained. In the foregoing implementation manner, the objective model may process the causal relationships between the N faults and the weights of the N faults, so as to obtain the causal relationships between M faults in the N faults, where the causal relationships between the M faults may also be referred to as a fault evidence chain of the objective device, and be used to provide explanation for the fault prediction result of the objective device. After the causal relationship among the M faults is obtained, the target model can also process the historical fault information of the target equipment and the causal relationship among the M faults, so that the probability of N faults of the target equipment in the T moment is obtained, namely the fault prediction result of the target equipment. The chain of fault evidence for the target device and the result of the fault prediction for the target device may then be provided as two outputs of the target model, thereby providing the user with a visual illustration of the fault prediction service for the target device and the fault prediction for the target device.

In one possible implementation, based on the causal relationships between the N faults and the weights of the N faults, obtaining the causal relationships between the M faults in the N faults includes: and in the causal relationship among the N faults, eliminating the N-M faults with the weight smaller than the first weight threshold value, and obtaining the causal relationship among M faults in the N faults. In the foregoing implementation manner, after obtaining the sub-historical fault information of the target device, the weights of the N faults and the causal relationship between the N faults, the target model may reject N-M faults with weights smaller than the first weight threshold in the causal relationship between the N faults, so as to obtain the causal relationship between M faults in the N faults, and it is worth noting that at this time, the causal relationship between the M faults is accompanied with the weights of the M faults, that is, the fault evidence chain of the target device includes not only the causal relationship between the M faults but also the weights of the M faults, so that explanation of fault prediction with more details can be provided for the user.

In one possible implementation, based on the historical fault information and the causal relationship between the M faults, obtaining the probability that the target device has N faults at the T-th time includes: and carrying out third feature extraction on the causal relationship among the M faults and the sub-historical fault information to obtain the probability of N faults of the target equipment in the T moment. In the foregoing implementation manner, after the causal relationship between M faults is obtained, the target model may perform third feature extraction on the causal relationship between M faults and sub-historical fault information of the target device, so as to accurately obtain the probability that the target device has N faults at the T-th moment.

In one possible implementation, the first feature extraction or the second feature extraction comprises at least one of: feature extraction based on a recurrent neural network and feature extraction based on a convolutional neural network. In the foregoing implementation, the target model may include at least one of a recurrent neural network and a convolutional neural network, so the first feature extraction or the second feature extraction implemented by the target model includes at least one of a feature extraction based on the recurrent neural network and a feature extraction based on the convolutional neural network.

In one possible implementation, the third feature extraction comprises at least one of: feature extraction based on a cyclic neural network, feature extraction based on a time convolution network and feature extraction based on a multi-layer perceptron. In the foregoing implementation, the target model may include at least one of a recurrent neural network, a time convolution network, and a multi-layer perceptron, so the third feature extraction or the fourth feature extraction implemented by the target model includes at least one of a feature extraction based on the recurrent neural network, a feature extraction based on the time convolution network, and a feature extraction based on the multi-layer perceptron.

A second aspect of an embodiment of the present application provides a model training method, including: acquiring historical fault information of target equipment, wherein the historical fault information is used for indicating N faults of the target equipment in the 1 st time to the T-1 st time, T is more than or equal to 2, and N is more than or equal to 2; the historical fault information is input into a model to be trained, the probability of N faults of target equipment in the T moment is obtained, and the model to be trained is used for: based on the historical fault information, acquiring causal relations among N faults and weights of the N faults, wherein the weights of the N faults are used for indicating importance degrees of the N faults; based on historical fault information, causal relationships among N faults and weights of the N faults, obtaining the probability of N faults of target equipment in the T moment; and training the model to be trained based on the probability, thereby obtaining the target model.

The target model obtained through training by the method has a fault prediction function. Specifically, when the fault prediction is required for the target device, the historical fault information of the target device may be acquired first and the historical fault information of the target device is input into the target model, where the historical fault information of the target device is used to indicate N faults that occur in the 1 st to T-1 st moments. Then, the target model may process the historical fault information of the target device, thereby obtaining causal relationships between the N faults and weights of the N faults. Finally, the target model may process historical fault information of the target device, causal relationships between the N faults, and weights of the N faults, thereby obtaining probabilities of the N faults occurring in the target device at the T-th moment. In the foregoing process, in the process of performing fault prediction on the target device, the target model considers not only the causal relationship between N faults occurring in the 1 st time to the T-1 st time of the target device, but also the weights of the N faults (that is, the importance degree of the N faults in the fault prediction process on the target device), where the considered factors are relatively comprehensive, so that the finally obtained fault prediction result (that is, the probability of the N faults occurring in the T time of the target device) of the target device can have relatively high accuracy.

In one possible implementation, the model to be trained is used for: extracting first characteristics of the historical fault information to obtain causal relations among N faults; sub-historical fault information is extracted from the historical fault information, and the sub-historical fault information is used for indicating P faults of target equipment in the time from T-w to T-1, wherein N faults comprise P faults, N is more than or equal to P is more than or equal to 1, and T is more than or equal to w is more than or equal to 1; and carrying out second feature extraction on the causal relationship among the N faults and the sub-historical fault information to obtain weights of the N faults.

In one possible implementation, the model to be trained is used for: based on the causal relationship among N faults and the weights of the N faults, acquiring the causal relationship among M faults in the N faults, wherein N is more than or equal to M is more than or equal to 1; based on the historical fault information and causal relationships among M faults, the probability of N faults of the target equipment in the T moment is obtained.

In one possible implementation, the model to be trained is used for: and in the causal relationship among the N faults, eliminating the N-M faults with the weight smaller than the first weight threshold value, and obtaining the causal relationship among M faults in the N faults.

In one possible implementation, the model to be trained is used for: and carrying out third feature extraction on the causal relationship among the M faults and the sub-historical fault information to obtain the probability of N faults of the target equipment in the T moment.

In one possible implementation, the model to be trained is further configured to: in the causal relationship among M faults, M-K faults with the weight smaller than a second weight threshold are removed, and the causal relationship among K faults in the M faults is obtained, wherein M is larger than K and is larger than or equal to 1; performing fourth feature extraction on causal relations among K faults and sub-historical fault information to obtain new probabilities of N faults of target equipment in the T moment; training the model to be trained based on the probability, thereby obtaining a target model comprises the following steps: and training the model to be trained based on the probability and the new probability, thereby obtaining the target model.

In one possible implementation, the first feature extraction or the second feature extraction comprises at least one of: feature extraction based on a recurrent neural network and feature extraction based on a convolutional neural network.

In one possible implementation, the third feature extraction or the fourth feature extraction comprises at least one of: feature extraction based on a cyclic neural network, feature extraction based on a time convolution network and feature extraction based on a multi-layer perceptron.

A third aspect of an embodiment of the present application provides a fault prediction apparatus, the apparatus including a target model, the apparatus including: the first acquisition module is used for acquiring historical fault information of the target equipment, wherein the historical fault information is used for indicating N faults of the target equipment in the 1 st time to the T-1 st time, T is more than or equal to 2, and N is more than or equal to 2; the second acquisition module is used for acquiring causal relations among N faults and weights of the N faults based on the historical fault information, wherein the weights of the N faults are used for indicating importance degrees of the N faults; and the third acquisition module is used for acquiring the probability of N faults of the target equipment in the T moment based on the historical fault information, the causal relationship among the N faults and the weights of the N faults.

From the above device, it can be seen that: when the fault prediction is required for the target equipment, the historical fault information of the target equipment can be acquired first and is input into the target model, wherein the historical fault information of the target equipment is used for indicating N faults of the target equipment from the 1 st moment to the T-1 st moment. Then, the target model may process the historical fault information of the target device, thereby obtaining causal relationships between the N faults and weights of the N faults. Finally, the target model may process historical fault information of the target device, causal relationships between the N faults, and weights of the N faults, thereby obtaining probabilities of the N faults occurring in the target device at the T-th moment. In the foregoing process, in the process of performing fault prediction on the target device, the target model considers not only the causal relationship between N faults occurring in the 1 st time to the T-1 st time of the target device, but also the weights of the N faults (that is, the importance degree of the N faults in the fault prediction process on the target device), where the considered factors are relatively comprehensive, so that the finally obtained fault prediction result (that is, the probability of the N faults occurring in the T time of the target device) of the target device can have relatively high accuracy.

In one possible implementation manner, the second obtaining module is configured to: extracting first characteristics of the historical fault information to obtain causal relations among N faults; sub-historical fault information is extracted from the historical fault information, and the sub-historical fault information is used for indicating P faults of target equipment in the time from T-w to T-1, wherein N faults comprise P faults, N is more than or equal to P is more than or equal to 1, and T is more than or equal to w is more than or equal to 1; and carrying out second feature extraction on the causal relationship among the N faults and the sub-historical fault information to obtain weights of the N faults.

In one possible implementation manner, the third obtaining module is configured to: based on the causal relationship among N faults and the weights of the N faults, acquiring the causal relationship among M faults in the N faults, wherein N is more than or equal to M is more than or equal to 1; based on the historical fault information and causal relationships among M faults, the probability of N faults of the target equipment in the T moment is obtained.

In one possible implementation manner, the third obtaining module is configured to reject N-M faults with weights smaller than the first weight threshold in the causal relationships among the N faults, so as to obtain the causal relationships among M faults in the N faults.

In one possible implementation manner, the third obtaining module is configured to perform third feature extraction on the causal relationship between M faults and the sub-historical fault information, so as to obtain the probability that the target device has N faults in the T-th moment.

In one possible implementation, the third feature extraction comprises at least one of: feature extraction based on a cyclic neural network, feature extraction based on a time convolution network and feature extraction based on a multi-layer perceptron.

A fourth aspect of an embodiment of the present application provides a model training apparatus, including: the acquisition module is used for acquiring historical fault information of the target equipment, wherein the historical fault information is used for indicating N faults of the target equipment in the 1 st time to the T-1 st time, T is more than or equal to 2, and N is more than or equal to 2; the processing module is used for inputting the historical fault information into a model to be trained to obtain the probability of N faults of the target equipment at the T moment, and the model to be trained is used for: based on the historical fault information, acquiring causal relations among N faults and weights of the N faults, wherein the weights of the N faults are used for indicating importance degrees of the N faults; based on historical fault information, causal relationships among N faults and weights of the N faults, obtaining the probability of N faults of target equipment in the T moment; and the training module is used for training the model to be trained based on the probability so as to obtain a target model.

The target model obtained by training the device has a fault prediction function. Specifically, when the fault prediction is required for the target device, the historical fault information of the target device may be acquired first and the historical fault information of the target device is input into the target model, where the historical fault information of the target device is used to indicate N faults that occur in the 1 st to T-1 st moments. Then, the target model may process the historical fault information of the target device, thereby obtaining causal relationships between the N faults and weights of the N faults. Finally, the target model may process historical fault information of the target device, causal relationships between the N faults, and weights of the N faults, thereby obtaining probabilities of the N faults occurring in the target device at the T-th moment. In the foregoing process, in the process of performing fault prediction on the target device, the target model considers not only the causal relationship between N faults occurring in the 1 st time to the T-1 st time of the target device, but also the weights of the N faults (that is, the importance degree of the N faults in the fault prediction process on the target device), where the considered factors are relatively comprehensive, so that the finally obtained fault prediction result (that is, the probability of the N faults occurring in the T time of the target device) of the target device can have relatively high accuracy.

In one possible implementation, the model to be trained is further configured to: in the causal relationship among M faults, M-K faults with the weight smaller than a second weight threshold are removed, and the causal relationship among K faults in the M faults is obtained, wherein M is larger than K and is larger than or equal to 1; performing fourth feature extraction on causal relations among K faults and sub-historical fault information to obtain new probabilities of N faults of target equipment in the T moment; and the training module is used for training the model to be trained based on the probability and the new probability, so as to obtain the target model.

A third aspect of an embodiment of the present application provides a failure prediction apparatus, including a memory and a processor; the memory stores code, the processor being configured to execute the code, the fault prediction device performing the method as described in the first aspect or any one of the possible implementations of the first aspect when the code is executed.

A fourth aspect of an embodiment of the present application provides a model training apparatus, the apparatus comprising a memory and a processor; the memory stores code, the processor is configured to execute the code, and when the code is executed, the model training apparatus performs the method as described in the second aspect or any one of the possible implementations of the second aspect.

A fifth aspect of the embodiments of the present application provides a circuitry comprising processing circuitry configured to perform the method of any one of the first aspect, the second aspect or any one of the possible implementations of the second aspect.

A sixth aspect of the embodiments of the present application provides a chip system, the chip system comprising a processor for invoking a computer program or computer instructions stored in a memory to cause the processor to perform a method as described in any one of the first aspect, any one of the possible implementations of the first aspect, the second aspect, or any one of the possible implementations of the second aspect.

In one possible implementation, the processor is coupled to the memory through an interface.

In one possible implementation, the system on a chip further includes a memory having a computer program or computer instructions stored therein.

A seventh aspect of embodiments of the present application provides a computer storage medium storing a computer program which, when executed by a computer, causes the computer to carry out the method according to any one of the first aspect, the second aspect or any one of the possible implementations of the second aspect.

An eighth aspect of embodiments of the present application provides a computer program product storing instructions that, when executed by a computer, cause the computer to carry out a method as claimed in any one of the first aspect, the second aspect or any one of the possible implementations of the second aspect.

In the embodiment of the application, when the fault prediction is required for the target equipment, the historical fault information of the target equipment can be acquired first and is input into the target model, and the historical fault information of the target equipment is used for indicating N faults of the target equipment from the 1 st moment to the T-1 st moment. Then, the target model may process the historical fault information of the target device, thereby obtaining causal relationships between the N faults and weights of the N faults. Finally, the target model may process historical fault information of the target device, causal relationships between the N faults, and weights of the N faults, thereby obtaining probabilities of the N faults occurring in the target device at the T-th moment. In the foregoing process, in the process of performing fault prediction on the target device, the target model considers not only the causal relationship between N faults occurring in the 1 st time to the T-1 st time of the target device, but also the weights of the N faults (that is, the importance degree of the N faults in the fault prediction process on the target device), where the considered factors are relatively comprehensive, so that the finally obtained fault prediction result (that is, the probability of the N faults occurring in the T time of the target device) of the target device can have relatively high accuracy.

Drawings

FIG. 1 is a schematic diagram of a structure of an artificial intelligence main body frame;

FIG. 2a is a schematic diagram of a failure prediction system according to an embodiment of the present application;

FIG. 2b is a schematic diagram of another structure of a failure prediction system according to an embodiment of the present application;

FIG. 2c is a schematic diagram of a device for fault prediction according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a system 100 architecture according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a structure of a target model according to an embodiment of the present application;

FIG. 5 is a schematic flow chart of a fault prediction method according to an embodiment of the present application;

FIG. 6 is a schematic diagram of a decision interpretation module according to an embodiment of the present application;

FIG. 7 is a schematic diagram of a decision chain optimization module according to an embodiment of the present application;

FIG. 8 is a schematic diagram of a causal graph and evidence chain provided by an embodiment of the present application;

FIG. 9 is a schematic flow chart of a model training method according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of a fault prediction device according to an embodiment of the present application;

FIG. 11 is a schematic structural diagram of a model training apparatus according to an embodiment of the present application;

fig. 12 is a schematic structural diagram of an execution device according to an embodiment of the present application;

FIG. 13 is a schematic structural view of a training device according to an embodiment of the present application;

fig. 14 is a schematic structural diagram of a chip according to an embodiment of the present application.

Detailed Description

The terms first, second and the like in the description and in the claims and in the above-described figures, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances and are merely illustrative of the manner in which embodiments of the application have been described in connection with the description of the objects having the same attributes. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of elements is not necessarily limited to those elements, but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.

In the above process, the neural network model performs complex processing on the historical fault information for indicating the faults that have occurred in the device, so as to obtain contribution degrees of the faults, and further performs processing based on the contribution degrees of the faults, so as to obtain the probability of the faults of the device in the future. Therefore, in the process of predicting the faults of the equipment, the neural network model only considers the contribution degree of the faults in the fault predicting process, and considered factors are single, so that the finally obtained fault predicting result of the equipment is inaccurate.

Further, the neural network model provided by the related art is a black box, and the failure prediction result of the device can only be approximated by a linear model in a mathematical field, so that the parameters of the linear model can be used as the contribution degree of a plurality of failures in the failure prediction process, so that, although the relationship between the historical failure information and the failure prediction result of the device can be roughly explained (i.e. one or more failures of the device are predicted and why the failures of the device are roughly explained), the relationship between the historical failure information and the failure prediction result of the device cannot be carefully explained.

To solve the above-described problems, embodiments of the present application provide a fault prediction method that can be implemented in combination with artificial intelligence (artificial intelligence, AI) technology. AI technology is a technical discipline that utilizes digital computers or digital computer controlled machines to simulate, extend and extend human intelligence, and obtains optimal results by sensing environments, acquiring knowledge and using knowledge. In other words, artificial intelligence technology is a branch of computer science that attempts to understand the essence of intelligence and to produce a new intelligent machine that can react in a similar way to human intelligence. Data processing using artificial intelligence is a common application of artificial intelligence.

First, the overall workflow of the artificial intelligence system will be described, referring to fig. 1, fig. 1 is a schematic structural diagram of an artificial intelligence subject framework, and the artificial intelligence subject framework is described below in terms of two dimensions, namely, an "intelligent information chain" (horizontal axis) and an "IT value chain" (vertical axis). Where the "intelligent information chain" reflects a list of processes from the acquisition of data to the processing. For example, there may be general procedures of intelligent information awareness, intelligent information representation and formation, intelligent reasoning, intelligent decision making, intelligent execution and output. In this process, the data undergoes a "data-information-knowledge-wisdom" gel process. The "IT value chain" reflects the value that artificial intelligence brings to the information technology industry from the underlying infrastructure of personal intelligence, information (provisioning and processing technology implementation), to the industrial ecological process of the system.

(1) Infrastructure of

The infrastructure provides computing capability support for the artificial intelligence system, realizes communication with the outside world, and realizes support through the base platform. Communicating with the outside through the sensor; the computing power is provided by a smart chip (CPU, NPU, GPU, ASIC, FPGA and other hardware acceleration chips); the basic platform comprises a distributed computing framework, a network and other relevant platform guarantees and supports, and can comprise cloud storage, computing, interconnection and interworking networks and the like. For example, the sensor and external communication obtains data that is provided to a smart chip in a distributed computing system provided by the base platform for computation.

(2) Data

The data of the upper layer of the infrastructure is used to represent the data source in the field of artificial intelligence. The data relate to graphics, images, voice and text, and also relate to the internet of things data of the traditional equipment, including service data of the existing system and sensing data such as force, displacement, liquid level, temperature, humidity and the like.

(3) Data processing

Data processing typically includes data training, machine learning, deep learning, searching, reasoning, decision making, and the like.

Wherein machine learning and deep learning can perform symbolized and formalized intelligent information modeling, extraction, preprocessing, training and the like on data.

Reasoning refers to the process of simulating human intelligent reasoning modes in a computer or an intelligent system, and carrying out machine thinking and problem solving by using formal information according to a reasoning control strategy, and typical functions are searching and matching.

Decision making refers to the process of making decisions after intelligent information is inferred, and generally provides functions of classification, sequencing, prediction and the like.

(4) General capability

After the data has been processed, some general-purpose capabilities can be formed based on the result of the data processing, such as algorithms or a general-purpose system, for example, translation, text analysis, computer vision processing, speech recognition, image recognition, etc.

(5) Intelligent product and industry application

The intelligent product and industry application refers to products and applications of an artificial intelligent system in various fields, is encapsulation of an artificial intelligent overall solution, and realizes land application by making intelligent information decisions, and the application fields mainly comprise: intelligent terminal, intelligent transportation, intelligent medical treatment, autopilot, smart city etc.

Next, several application scenarios of the present application are described.

Fig. 2a is a schematic structural diagram of a fault prediction system according to an embodiment of the present application, where the fault prediction system includes a user device and a data processing device. The user equipment comprises intelligent terminals such as a mobile phone, a personal computer or an information processing center. The user equipment is the initiating terminal of the fault prediction, and is used as the initiating terminal of the fault prediction request, and the user usually initiates the request through the user equipment.

The data processing device may be a device or a server having a data processing function, such as a cloud server, a web server, an application server, and a management server. The data processing equipment receives a fault prediction request from the intelligent terminal through the interactive interface, and performs machine learning, deep learning, searching, reasoning, decision-making and other fault prediction modes through a memory for storing data and a processor link for data processing. The memory in the data processing device may be a generic term comprising a database storing the history data locally, either on the data processing device or on another network server.

In the failure prediction system shown in fig. 2a, the user device may receive an instruction of a user, for example, the user device may acquire the historical failure information of the target device input/selected by the user, and then initiate a request to the data processing device, so that the data processing device performs failure prediction processing on the historical failure information of the target device from the user device, thereby obtaining a failure prediction result for the target device. For example, the user device may acquire the historical fault information of the target device (the information is used to indicate a plurality of faults that have occurred in the past) input by the user, and then the user device may initiate a fault prediction request to the data processing device, so that the data processing device performs a series of processes on the historical fault information of the target device based on the fault prediction request, thereby obtaining a fault prediction result of the target device, that is, a probability that a plurality of faults occur in the future.

In fig. 2a, a data processing device may perform a failure prediction method of an embodiment of the present application.

Fig. 2b is another schematic structural diagram of a fault prediction system according to an embodiment of the present application, in fig. 2b, a user device directly serves as a data processing device, and the user device can directly obtain an input from a user and directly process the input by hardware of the user device, and a specific process is similar to that of fig. 2a, and reference is made to the above description and will not be repeated here.

In the fault prediction system shown in fig. 2b, the user device may receive an instruction from a user, for example, the user device may obtain historical fault information of the target device (the information is used to indicate multiple faults that have occurred in the past) input by the user, and then the user device may perform a series of processing on the historical fault information of the target device, so as to obtain a fault prediction result of the target device, that is, a probability that multiple faults occur in the future in the target device.

In fig. 2b, the user equipment itself may perform the fault prediction method according to the embodiment of the present application.

Fig. 2c is a schematic diagram of a related device for fault prediction according to an embodiment of the present application.

The user device in fig. 2a and 2b may be the local device 301 or the local device 302 in fig. 2c, and the data processing device in fig. 2a may be the executing device 210 in fig. 2c, where the data storage system 250 may store data to be processed of the executing device 210, and the data storage system 250 may be integrated on the executing device 210, or may be disposed on a cloud or other network server.

The processors in fig. 2a and 2b may perform data training/machine learning/deep learning through a neural network model or other models (e.g., a model based on a support vector machine), and perform a fault prediction application on the image using the model obtained by the data final training or learning, thereby obtaining corresponding processing results.

Fig. 3 is a schematic diagram of a system 100 architecture provided by an embodiment of the present application, in fig. 3, an execution device 110 configures an input/output (I/O) interface 112 for data interaction with an external device, and a user may input data to the I/O interface 112 through a client device 140, where the input data may include in an embodiment of the present application: each task to be scheduled, callable resources, and other parameters.

In the preprocessing of the input data by the execution device 110, or in the process of performing a processing related to computation or the like (for example, performing a functional implementation of a neural network in the present application) by the computation module 111 of the execution device 110, the execution device 110 may call the data, the code or the like in the data storage system 150 for the corresponding processing, or may store the data, the instruction or the like obtained by the corresponding processing in the data storage system 150.

Finally, the I/O interface 112 returns the processing results to the client device 140 for presentation to the user.

It should be noted that the training device 120 may generate, based on different training data, a corresponding target model/rule for different targets or different tasks, where the corresponding target model/rule may be used to achieve the targets or complete the tasks, thereby providing the user with the desired result. Wherein the training data may be stored in database 130 and derived from training samples collected by data collection device 160.

In the case shown in FIG. 3, the user may manually give input data, which may be manipulated through an interface provided by the I/O interface 112. In another case, the client device 140 may automatically send the input data to the I/O interface 112, and if the client device 140 is required to automatically send the input data requiring the user's authorization, the user may set the corresponding permissions in the client device 140. The user may view the results output by the execution device 110 at the client device 140, and the specific presentation may be in the form of a display, a sound, an action, or the like. The client device 140 may also be used as a data collection terminal to collect input data of the input I/O interface 112 and output results of the output I/O interface 112 as new sample data as shown in the figure, and store the new sample data in the database 130. Of course, instead of being collected by the client device 140, the I/O interface 112 may directly store the input data input to the I/O interface 112 and the output result output from the I/O interface 112 as new sample data into the database 130.

It should be noted that fig. 3 is only a schematic diagram of a system architecture provided by an embodiment of the present application, and the positional relationship among devices, apparatuses, modules, etc. shown in the drawing is not limited in any way, for example, in fig. 3, the data storage system 150 is an external memory with respect to the execution device 110, and in other cases, the data storage system 150 may be disposed in the execution device 110. As shown in fig. 3, the neural network may be trained in accordance with the training device 120.

The embodiment of the application also provides a chip, which comprises the NPU. The chip may be provided in an execution device 110 as shown in fig. 3 for performing the calculation of the calculation module 111. The chip may also be provided in the training device 120 as shown in fig. 3 to complete the training work of the training device 120 and output the target model/rule.

The neural network processor NPU is mounted as a coprocessor to a main central processing unit (centralprocessing unit, CPU) (host CPU) which distributes tasks. The core part of the NPU is an operation circuit, and the controller controls the operation circuit to extract data in a memory (a weight memory or an input memory) and perform operation.

In some implementations, the arithmetic circuitry includes a plurality of processing units (PEs) internally. In some implementations, the operational circuit is a two-dimensional systolic array. The arithmetic circuitry may also be a one-dimensional systolic array or other electronic circuitry capable of performing mathematical operations such as multiplication and addition. In some implementations, the operational circuitry is a general-purpose matrix processor.

For example, assume that there is an input matrix a, a weight matrix B, and an output matrix C. The arithmetic circuit takes the data corresponding to the matrix B from the weight memory and caches the data on each PE in the arithmetic circuit. The operation circuit takes the matrix A data and the matrix B from the input memory to perform matrix operation, and the obtained partial result or the final result of the matrix is stored in an accumulator (accumulator).

The vector calculation unit may further process the output of the operation circuit, such as vector multiplication, vector addition, exponential operation, logarithmic operation, magnitude comparison, etc. For example, the vector computation unit may be used for network computation of non-convolutional/non-FC layers in a neural network, such as pooling, batch normalization (batch normalization), local response normalization (local response normalization), and the like.

In some implementations, the vector computation unit can store the vector of processed outputs to a unified buffer. For example, the vector calculation unit may apply a nonlinear function to an output of the arithmetic circuit, such as a vector of accumulated values, to generate the activation value. In some implementations, the vector calculation unit generates a normalized value, a combined value, or both. In some implementations, the vector of processed outputs can be used as an activation input to an arithmetic circuit, for example for use in subsequent layers in a neural network.

The unified memory is used for storing input data and output data.

The weight data is transferred to the input memory and/or the unified memory directly by the memory cell access controller (direct memory accesscontroller, DMAC), the weight data in the external memory is stored in the weight memory, and the data in the unified memory is stored in the external memory.

And a bus interface unit (bus interface unit, BIU) for implementing interaction among the main CPU, the DMAC and the instruction fetch memory through a bus.

The instruction fetching memory (instruction fetch buffer) is connected with the controller and used for storing instructions used by the controller;

and the controller is used for calling the instruction which refers to the cache in the memory and controlling the working process of the operation accelerator.

Typically, the unified memory, input memory, weight memory, and finger memory are On-Chip (On-Chip) memories, and the external memory is a memory external to the NPU, which may be a double data rate synchronous dynamic random access memory (double data rate synchronous dynamic random accessmemory, DDR SDRAM), a high bandwidth memory (high bandwidth memory, HBM), or other readable and writable memory.

Because the embodiments of the present application relate to a large number of applications of neural networks, for convenience of understanding, related terms and related concepts of the neural networks related to the embodiments of the present application will be described below.

(1) Neural network

The neural network may be composed of neural units, which may refer to an arithmetic unit having xs and intercept 1 as inputs, and the output of the arithmetic unit may be:

Where s=1, 2, … … n, n is a natural number greater than 1, ws is the weight of xs, and b is the bias of the neural unit. f is an activation function (activation functions) of the neural unit for introducing a nonlinear characteristic into the neural network to convert an input signal in the neural unit to an output signal. The output signal of the activation function may be used as an input to the next convolutional layer. The activation function may be a sigmoid function. A neural network is a network formed by joining together a number of the above-described single neural units, i.e., the output of one neural unit may be the input of another. The input of each neural unit may be connected to a local receptive field of a previous layer to extract features of the local receptive field, which may be an area composed of several neural units.

The operation of each layer in a neural network can be described by the mathematical expression y=a (wx+b): the operation of each layer in a physical layer neural network can be understood as the transformation of input space into output space (i.e., row space to column space of the matrix) is accomplished by five operations on the input space (set of input vectors), including: 1. dimension increasing/decreasing; 2. zoom in/out; 3. rotating; 4. translating; 5. "bending". Wherein operations of 1, 2, 3 are completed by Wx, operation of 4 is completed by +b, and operation of 5 is completed by a (). The term "space" is used herein to describe two words because the object being classified is not a single thing, but rather a class of things, space referring to the collection of all individuals of such things. Where W is a weight vector, each value in the vector representing a weight value of a neuron in the layer neural network. The vector W determines the spatial transformation of the input space into the output space described above, i.e. the weights W of each layer control how the space is transformed. The purpose of training the neural network is to finally obtain a weight matrix (a weight matrix formed by a plurality of layers of vectors W) of all layers of the trained neural network. Thus, the training process of the neural network is essentially a way to learn and control the spatial transformation, and more specifically to learn the weight matrix.

Since it is desirable that the output of the neural network is as close as possible to the value actually desired, the weight vector of each layer of the neural network can be updated by comparing the predicted value of the current network with the actually desired target value and then according to the difference between the two (of course, there is usually an initialization process before the first update, that is, the pre-configuration parameters of each layer in the neural network), for example, if the predicted value of the network is higher, the weight vector is adjusted to be predicted to be lower, and the adjustment is continued until the neural network can predict the actually desired target value. Thus, it is necessary to define in advance "how to compare the difference between the predicted value and the target value", which is a loss function (loss function) or an objective function (objective function), which are important equations for measuring the difference between the predicted value and the target value. Taking the loss function as an example, the higher the output value (loss) of the loss function is, the larger the difference is, and the training of the neural network becomes the process of reducing the loss as much as possible.

(2) Back propagation algorithm

The neural network can adopt a Back Propagation (BP) algorithm to correct the parameter in the initial neural network model in the training process, so that the reconstruction error loss of the neural network model is smaller and smaller. Specifically, the input signal is transmitted forward until the output is generated with error loss, and the parameters in the initial neural network model are updated by back propagation of the error loss information, so that the error loss is converged. The back propagation algorithm is a back propagation motion that dominates the error loss, and aims to obtain parameters of the optimal neural network model, such as a weight matrix.

(3) Causal graph (cause-effect graph)

A causal graph is a directed graph describing the influence relationships between different variables, and may include a plurality of nodes and edges between nodes, where a node may refer to a variable (e.g., a fault according to an embodiment of the present application), and an edge between nodes may refer to a relationship between variables (e.g., a fault according to an embodiment of the present application).

(4) Evidence chain

The evidence chain is a single linked list that can be used to indicate causal relationships between different variables (e.g., faults according to embodiments of the present application).

The method provided by the application is described below from the training side of the neural network and the application side of the neural network.

The model training method provided by the embodiment of the application relates to the processing of a data sequence, and can be particularly applied to methods such as data training, machine learning, deep learning and the like, and intelligent information modeling, extraction, preprocessing, training and the like of symbolizing and formalizing training data (for example, the historical fault information of target equipment in the model training method provided by the embodiment of the application) are performed, so that a trained neural network (for example, a target model in the model training method provided by the embodiment of the application) is finally obtained; in addition, the fault prediction method provided by the embodiment of the present application may use the trained neural network to input data (for example, the historical fault information of the target device in the fault prediction method provided by the embodiment of the present application) into the trained neural network, so as to obtain output data (for example, the fault prediction result of the target device in the fault prediction method provided by the embodiment of the present application). It should be noted that, the model training method and the fault prediction method provided by the embodiments of the present application are applications based on the same concept, and may be understood as two parts in a system or two stages of an overall process: such as a model training phase and a model application phase.

The fault prediction method provided by the embodiment of the present application may be implemented by using a target model, and fig. 4 is a schematic structural diagram of the target model provided by the embodiment of the present application, where as shown in fig. 4, the target model includes: the system comprises a decision interpretation module and a decision chain optimization module, wherein the input end of the decision interpretation module is used as the input end of the whole target model, the output end of the decision interpretation module is connected with the input end of the decision chain optimization module, and the output end of the decision chain optimization module is used as the output end of the whole target model. In order to understand the workflow of the target model, the workflow of the target model is described below in conjunction with fig. 5, and fig. 5 is a schematic flow chart of a fault prediction method according to an embodiment of the present application, as shown in fig. 5, where the method includes:

501. historical fault information of target equipment is obtained, wherein the historical fault information is used for indicating N faults of the target equipment in the 1 st time to the T-1 st time, T is more than or equal to 2, and N is more than or equal to 2.

In this embodiment, when the failure prediction is required for the target device, the historical failure information of the target device may be obtained first, where the historical failure information of the target device may include at least one failure occurring at time 1 of the target device and the occurrence times of the failures, at least one failure occurring at time 2 of the target device and the occurrence times of the failures. In this way, the historical fault information of the target device may be used to indicate N faults that occur in the target device from time 1 to time T-1 (N is a positive integer greater than or equal to 2, and the N faults are different from each other, so the N faults may be understood as all types of faults that occur in the target device from time 1 to time T-1).

For example, as shown in fig. 6 (fig. 6 is a schematic diagram of a decision interpretation module provided in an embodiment of the present application), in the historical fault information X of the target device _1:T-1 Wherein X is _1:T-1 The following data were included: the target device has failed v2 at time 1 and has occurred 3 times. The target device has failed v2 and v3 at time 2 and has occurred 1 and 2 times, respectively. The target device fails at time 3..the target device fails v2 and v3 at time T-2 and 1 times, respectively. The target device fails v1 and v2 at time T-1 and 3 times, respectively. From this, X is seen _1:T-1 May be used to indicate faults v1, v2, and v3 that the target device has occurred in time 1 to time T-1.

It should be understood that in this embodiment, the fault occurred in the target device may be represented as an alarm event occurred in the target device, and accordingly, the historical fault information of the target device may be represented as a historical alarm event sequence (typically, a time sequence) of the target device. Of course, failure of the target device and historical failure information of the target device may be presented in other manners, without limitation.

It is also understood that the time involved in this embodiment may be understood as a day, an hour, or a moment, etc. having a certain length of time segment, for example, the 1 st time may be understood as the 1 st day, the 2 nd time may be understood as the 2 nd day.

502. Based on the historical fault information, a causal relationship between N faults and weights of the N faults are obtained, wherein the weights of the N faults are used for indicating importance degrees of the N faults.

After the historical fault information of the target equipment is obtained, the historical fault information of the target equipment can be input into a target model, and the target model can process the historical fault information of the target equipment, so that the causal relationship between N faults (the causal relationship between N faults is usually presented in the form of a causal graph) and the weights of the N faults, which occur in the target equipment from the 1 st moment to the T-1 st moment, are obtained. The weights of the N faults are used for indicating the functions exerted by the N faults in the process of predicting the faults of the target equipment, namely the importance degree of the N faults, in general, the larger the weights of the faults are, the more important the faults are, the smaller the weights of the faults are, and the less important the faults are.

Specifically, the objective model may obtain causal relationships between N faults and weights of the N faults by:

(1) After the historical fault information of the target equipment is received, the decision interpretation module of the target model can conduct first feature extraction on the historical fault information of the target equipment, so that causal relations among N faults of the target equipment in the 1 st time to the T-1 st time are obtained. Further, since the decision interpretation module may include at least one of a recurrent neural network and a convolutional neural network, the first feature extraction implemented by the decision interpretation module may include at least one of a recurrent neural network-based feature extraction and a convolutional neural network-based feature extraction.

As still another example, in the case of X _1:T-1 After input to the decision interpretation module, the decision interpretation module can interpret X _1:T-1 Extracting features to obtain causal graphIncluding a causal relationship between the fault V1 and the fault V1 (the relationship being directed to the fault V1 by the fault V1 and having a value of 1, indicating that the fault V1 caused its own generation), a causal relationship between the fault V1 and the fault V2 (the relationship being directed to the fault V2 by the fault V1 and having a value of 0, indicating that the fault V1 did not cause its own generation), a causal relationship between the fault V3 and the fault V2 (the relationship being directed to the fault V2 by the fault V3 and having a value of 0, indicating that the fault V3 did not cause its own generation), and a causal relationship between the fault V3 and the fault V3 (the relationship being directed to the fault V3 by the fault V3 and having a value of 1, indicating that the fault V3 caused its own generation).

(2) After the causal relationship between the N faults is obtained, the decision interpretation module can extract sub-historical fault information of the target equipment from the historical fault information of the target equipment, wherein the sub-historical fault information of the target equipment is used for indicating P faults of the target equipment from the T-w moment to the T-1 moment. Since w is a positive integer less than T and greater than or equal to 1, the T-w times are typically times after the 1 st time, and the N faults include P faults. P is typically a positive integer less than or equal to N and greater than or equal to 1, so P faults that occur in the target device from time T-w to time T-1 are mutually different faults, and these P faults may be some or all of the N faults that occur in the target device from time 1 to time T-1.

As still the above example, at X _1:T-1 In the method, the decision interpretation module can extract sub-historical fault information X of the target equipment from the sub-historical fault information X _T-w:T-1 ，X _T-w:T-1 The following data were included: the target device fails v3 at time T-w and 2 times, the target device fails v2 and v3 at time T-2 and 2 times and 1 time, respectively. The target device fails v1 and v2 at time T-1 and 3 times, respectively. From this, X is seen _T-w:T-1 May be used to indicate faults v1, v2, and v3 that the target device had occurred in the time T-w to time T-1.

(3) After the causal relationship among the N faults and the sub-historical fault information of the target equipment are obtained, the decision interpretation module can conduct second feature extraction on the causal relationship among the N faults and the sub-historical fault information, so that weights of the N faults are obtained. After the weights of the N faults are obtained, the decision interpretation module can send the sub-historical fault information of the target equipment, the weights of the N faults and the causal relationship among the N faults to the decision chain optimization module. Further, since the decision interpretation module may include at least one of a recurrent neural network and a convolutional neural network, the second feature extraction implemented by the decision interpretation module may include at least one of a recurrent neural network-based feature extraction and a convolutional neural network-based feature extraction.

Still as in the above example, aX is as follows _T-w:T-1 After that, the decision interpretation module can be applied to->X is as follows _T-w:T-1 Extracting features to obtain weight μ _T-1 ，μ _T-1 The method comprises the steps of weighing fault v1, weighing fault v2 and weighing fault v3, wherein the weighing fault v1 is 0.3, the weighing fault v2 is 0.1, and the weighing fault v3 is 0.5. Thereafter, the decision interpretation module may interpret X _T-w:T-1 Mu, and _T-1 and sending the result to a decision chain optimization module.

503. Based on the historical fault information, the causal relationship among the N faults and the weights of the N faults, the probability of the N faults of the target equipment in the T moment is obtained.

Specifically, the target model may obtain probabilities of N failures of the target device at the T-th time by:

(1) The objective model may first process the causal relationships between the N faults and the weights of the N faults, thereby obtaining the causal relationships between the M faults in the N faults. Since M is a positive integer greater than or equal to 1 and less than or equal to N, the M faults are different faults, and may be some or all of N faults that occur in the target device from time 1 to time T-1. Notably, the causal relationship between the M faults may also be referred to as a chain of fault evidence for the target device, which is used to provide a visual interpretation of the fault prediction results for the target device as one of the outputs of the target model.

(2) After the causal relationship among the M faults is obtained, the target model can also process the historical fault information of the target equipment and the causal relationship among the M faults, so that the probability of N faults of the target equipment in the T moment, namely the fault prediction result of the target equipment, is obtained, and the fault prediction result of the target equipment is output as the other one of the target models.

More specifically, the objective model may obtain causal relationships between M faults by:

after obtaining the sub-historical fault information of the target device, the weights of the N faults and the causal relationship between the N faults, the decision chain optimization module may reject the N-M faults with the weight smaller than the first weight threshold (the size of the threshold may be set according to the actual requirement and is not limited here) from the causal relationship between the N faults, so as to obtain the causal relationship between the M faults, and it is worth noting that at this time, the causal relationship between the M faults is attached with the weights of the M faults, that is, the fault evidence chain of the target device includes not only the causal relationship between the M faults but also the weights of the M faults, so that the fault evidence chain of the target device may explain not only a fault (the fault is usually a fault in the M faults, and is located at the end of the M faults), but also explain that the rest faults (other than the M faults) and the rest faults (other than the M faults) cause the fault (the rest faults) in the M faults) at the time point in the causal relationship (the T moment) and the rest of the fault evidence chain of the target device may also contribute to the fault in the causal relationship.

Still as the above example, as shown in fig. 7 (fig. 7 is a schematic diagram of a decision chain optimization module provided in an embodiment of the present application), a decision chain optimization module is obtainedX _T-w:T-1 Mu, and _T-1 after that, the decision chain optimization module can be at +.>In (3) failure with weight less than 0.15

Culling, i.e. culling the fault v 2. Then a new causal graph can be obtainedIncluding the causal relationship between the fault v1 and the fault v1 (the relationship is 0.3 because the weight of the fault v1 is superimposed), the causal relationship between the fault v1 and the fault v3 (the relationship is 0 because the relationship is 0), the causal relationship between the fault v3 and the fault v1 (the relationship is 0.5 because the weight of the fault v3 is superimposed), the causal relationship between the fault v3 and the fault v3 (the relationship is 0)

The relationship takes a value of 0.5 because the weight of fault v3 is superimposed). It can be seen that the light source is,an optimal fault evidence chain for the target device is provided, fault v3 points to fault v1, and the fault v3 causes generation of fault v1, and the contribution degree of fault v3 in the process is 0.5.

More specifically, the target model may obtain probabilities of N failures of the target device at the T-th time by:

after the causal relationship among the M faults is obtained, the decision chain optimization module may perform third feature extraction on the causal relationship among the M faults and the sub-history fault information of the target device, so as to obtain the probability of N faults of the target device at the T-th moment, and it may be understood that the M faults in the fault evidence chain include the fault with the highest probability among the N faults, that is, the fault most likely occurring in the T-th moment of the target device. Further, since the decision chain optimization module may include at least one of a recurrent neural network, a time convolution network, and a multi-layer perceptron, the third feature extraction implemented by the decision interpretation module may include at least one of a recurrent neural network-based feature extraction, a time convolution network-based feature extraction, and a multi-layer perceptron-based feature extraction.

Still as in the above example, aAfter that, the decision chain optimization module can optimize X _T-w:T-1 And +.>Feature extraction is performed to obtain a failure prediction result +.>The probability of the target device at the T moment of failure v1, the probability of the target device at the T moment of failure v2 and the probability of the target device at the T moment of failure v3 are included.

In addition, the target model provided by the embodiment of the application can be compared with a neural network model provided by the related technology, and the comparison result is shown in table 1:

TABLE 1

	Index I	Index II
			Prior Art	0.68606	0.22222
Embodiments of the application	0.705548	0.47827

Based on the results of table 1, the test is performed on the same data set, and compared with the model provided by the related art, the target model provided by the embodiment of the application has better performance in various indexes, that is, the target model provided by the embodiment of the application has better performance, and can provide better fault prediction service for users.

To further understand the causal graph and the chain of fault evidence involved in embodiments of the present application, both are further described below in conjunction with fig. 8. As shown in fig. 8 (fig. 8 is a schematic diagram of a causal graph and a proof chain provided by an embodiment of the present application), a causal graph may be obtained by a target model in the process of predicting an alarm event based on a historical alarm event sequence, where the causal graph includes causal relationships among a plurality of alarm events. Then, based on different needs of the user, the target model can predict the warning event evidence chain of 5 months 30 in 2019, and can also predict the warning event evidence chain of 18 days 11 months in 2018.

Further, the target device may output not only the failure prediction result of the target device (i.e., the probability that the target device has N failures in the T-th moment), but also a failure evidence chain of the target device (i.e., a causal relationship between M failures among the N failures), and since the failure evidence chain of the target device includes a causal relationship between a certain failure most likely to occur among the N failures and the rest of the failures that cause the failure, the failure evidence chain of the target device may sufficiently and carefully explain the relationship between the failure prediction result of the target device and the historical failure information of the target device.

The foregoing is a detailed description of the fault prediction method provided by the embodiment of the present application, and the model training method provided by the embodiment of the present application will be described below, and fig. 9 is a schematic flow chart of the model training method provided by the embodiment of the present application, as shown in fig. 9, where the method includes:

901. historical fault information of target equipment is obtained, wherein the historical fault information is used for indicating N faults of the target equipment in the 1 st time to the T-1 st time, T is more than or equal to 2, and N is more than or equal to 2.

In this embodiment, when the model to be trained is required to be trained, a batch of training data may be first obtained, where the batch of training data includes historical fault information of the target device, where the historical fault information of the target device is used to indicate N faults that occur in the target device from the 1 st time to the T-1 st time, where T is greater than or equal to 2, and N is greater than or equal to 2. It should be noted that the true probability of the target device to generate N faults at the T-th time is known.

902. The historical fault information is input into a model to be trained, the probability of N faults of target equipment in the T moment is obtained, and the model to be trained is used for: based on the historical fault information, acquiring causal relations among N faults and weights of the N faults, wherein the weights of the N faults are used for indicating importance degrees of the N faults; based on the historical fault information, the causal relationship among the N faults and the weights of the N faults, the probability of the N faults of the target equipment in the T moment is obtained.

After the historical fault information of the target equipment is obtained, the historical fault information can be input into the model to be trained. Then, the model to be trained can acquire causal relationships among the N faults and weights of the N faults based on the historical fault information, wherein the weights of the N faults are used for indicating importance degrees of the N faults. The model to be trained may then obtain (predictive) probabilities of the target device experiencing N faults in the T-th moment based on the historical fault information, causal relationships between the N faults, and weights of the N faults.

In one possible implementation, the model to be trained is further configured to: in the causal relationship among M faults, M-K faults with the weight smaller than a second weight threshold are removed, and the causal relationship among K faults in the M faults is obtained; and carrying out fourth feature extraction on the causal relationship among K faults and the sub-historical fault information to obtain new probabilities of N faults of the target equipment in the T moment. It should be noted that after the causal relationship between the M faults is obtained, the model to be trained may reject M-K faults (K is a positive integer greater than or equal to 1 and less than M) with a weight smaller than the second weight threshold (the threshold is usually greater than the first weight threshold, the size of the threshold may be set according to the actual requirement, where no limitation is made), so as to obtain the causal relationship between K faults in the M faults, and it is noted that the causal relationship between the K faults is attached with the weight of the K faults, so that the causal relationship between the K faults is used as a new fault evidence chain of the target device, that is, the new fault evidence chain of the target device includes not only the causal relationship between the K faults, but also the weight of the K faults, which are usually part of the M faults. And then, the to-be-trained model can carry out fourth feature extraction on the causal relationship among K faults and the sub-historical fault information of the target equipment, so as to obtain new (prediction) probabilities of N faults of the target equipment in the T moment, namely new fault prediction results of the target equipment.

For the description of step 902, reference may be made to the relevant description of steps 502 to 503 in the embodiment shown in fig. 5, which is not repeated here.

903. And training the model to be trained based on the probability, thereby obtaining the target model.

After obtaining the probability of the target device having N faults in the T-th moment, training the model to be trained by using the probability of the target device having N faults in the T-th moment until the model training condition is satisfied, thereby obtaining the target model in the embodiment shown in fig. 5.

Specifically, the model to be trained may be trained by:

after obtaining the probability of the target device generating N faults in the T moment and the new probability of the target device generating N faults in the T moment, since the actual probability of the target device generating N faults in the T moment is known, the probability of the target device generating N faults in the T moment and the actual probability of the target device generating N faults in the T moment can be calculated through a preset first loss function, so as to obtain a first loss, wherein the first loss is used for indicating the difference between the probability of the target device generating N faults in the T moment and the actual probability of the target device generating N faults in the T moment, and the new probability of the target device generating N faults in the T moment is calculated through a preset second loss function, so that a second loss is obtained, and the second loss is used for indicating the difference between the probability of the target device generating N faults in the T moment and the new probability of the target device generating N faults in the T moment. The first loss and the second loss may then be utilized to construct a target loss.

After the target loss is obtained, the parameters of the model to be trained can be updated by using the target loss, the model to be trained after the parameters are updated is obtained, and the model to be trained after the parameters are updated is continuously trained by using the next batch of training data until the model training condition is met (for example, the target loss meets the optimization purpose, wherein the optimization purpose of the first loss is to make the first loss as small as possible, the optimization purpose of the second loss is to make the second loss as large as possible, and the like), so as to obtain the target model.

The target model obtained through training in the embodiment of the application has a fault prediction function. Specifically, when the fault prediction is required for the target device, the historical fault information of the target device may be acquired first and the historical fault information of the target device is input into the target model, where the historical fault information of the target device is used to indicate N faults that occur in the 1 st to T-1 st moments. Then, the target model may process the historical fault information of the target device, thereby obtaining causal relationships between the N faults and weights of the N faults. Finally, the target model may process historical fault information of the target device, causal relationships between the N faults, and weights of the N faults, thereby obtaining probabilities of the N faults occurring in the target device at the T-th moment. In the foregoing process, in the process of performing fault prediction on the target device, the target model considers not only the causal relationship between N faults occurring in the 1 st time to the T-1 st time of the target device, but also the weights of the N faults (that is, the importance degree of the N faults in the fault prediction process on the target device), where the considered factors are relatively comprehensive, so that the finally obtained fault prediction result (that is, the probability of the N faults occurring in the T time of the target device) of the target device can have relatively high accuracy.

The foregoing is a detailed description of the fault prediction method and the model training method provided by the embodiment of the present application, and the fault prediction device and the model training device provided by the embodiment of the present application will be described below. Fig. 10 is a schematic structural diagram of a fault prediction device according to an embodiment of the present application, as shown in fig. 10, where the device includes:

the first obtaining module 1001 is configured to obtain historical fault information of the target device, where the historical fault information is used to indicate N faults that occur in the target device from the 1 st time to the T-1 st time, where T is greater than or equal to 2, and N is greater than or equal to 2;

a second obtaining module 1002, configured to obtain, based on the historical fault information, a causal relationship between N faults and weights of the N faults, where the weights of the N faults are used to indicate importance degrees of the N faults;

a third obtaining module 1003, configured to obtain, based on the historical fault information, the causal relationship between the N faults, and the weights of the N faults, probabilities that the target device generates the N faults at the T-th moment.

In one possible implementation, the second obtaining module 1002 is configured to: extracting first characteristics of the historical fault information to obtain causal relations among N faults; sub-historical fault information is extracted from the historical fault information, and the sub-historical fault information is used for indicating P faults of target equipment in the time from T-w to T-1, wherein N faults comprise P faults, N is more than or equal to P is more than or equal to 1, and T is more than or equal to w is more than or equal to 1; and carrying out second feature extraction on the causal relationship among the N faults and the sub-historical fault information to obtain weights of the N faults.

In one possible implementation, the third obtaining module 1003 is configured to: based on the causal relationship among N faults and the weights of the N faults, acquiring the causal relationship among M faults in the N faults, wherein N is more than or equal to M is more than or equal to 1; based on the historical fault information and causal relationships among M faults, the probability of N faults of the target equipment in the T moment is obtained.

In one possible implementation manner, the third obtaining module 1003 is configured to reject N-M faults with weights smaller than the first weight threshold in the causal relationships between N faults, to obtain the causal relationships between M faults in the N faults.

In one possible implementation manner, the third obtaining module 1003 is configured to perform third feature extraction on the causal relationship between M faults and the sub-historical fault information, so as to obtain the probability that the target device has N faults in the T-th moment.

Fig. 11 is a schematic structural diagram of a model training apparatus according to an embodiment of the present application, as shown in fig. 11, where the apparatus includes:

the acquisition module 1101 is configured to acquire historical fault information of the target device, where the historical fault information is used to indicate N faults that occur in the target device from the 1 st time to the T-1 st time, where T is greater than or equal to 2, and N is greater than or equal to 2;

the processing module 1102 is configured to input historical fault information to a model to be trained, to obtain probabilities of N faults of the target device at a T-th moment, where the model to be trained is configured to: based on the historical fault information, acquiring causal relations among N faults and weights of the N faults, wherein the weights of the N faults are used for indicating importance degrees of the N faults; based on historical fault information, causal relationships among N faults and weights of the N faults, obtaining the probability of N faults of target equipment in the T moment;

The training module 1103 is configured to train the model to be trained based on the probability, thereby obtaining a target model.

In one possible implementation, the model to be trained is further configured to: in the causal relationship among M faults, M-K faults with the weight smaller than a second weight threshold are removed, and the causal relationship among K faults in the M faults is obtained, wherein M is larger than K and is larger than or equal to 1; performing fourth feature extraction on causal relations among K faults and sub-historical fault information to obtain new probabilities of N faults of target equipment in the T moment; the training module 1103 is configured to train the model to be trained based on the probability and the new probability, thereby obtaining the target model.

It should be noted that, because the content of information interaction and execution process between the modules/units of the above-mentioned apparatus is based on the same concept as the method embodiment of the present application, the technical effects brought by the content are the same as the method embodiment of the present application, and specific content may refer to the description in the foregoing illustrated method embodiment of the present application, and will not be repeated herein.

The embodiment of the application also relates to an execution device, and fig. 12 is a schematic structural diagram of the execution device provided by the embodiment of the application. As shown in fig. 12, the execution device 1200 may be embodied as a mobile phone, a tablet, a notebook, a smart wearable device, a server, etc., which is not limited herein. The execution device 1200 may be configured with the fault prediction apparatus described in the corresponding embodiment of fig. 10, so as to implement the function of fault prediction in the corresponding embodiment of fig. 5. Specifically, the execution apparatus 1200 includes: a receiver 1201, a transmitter 1202, a processor 1203 and a memory 1204 (where the number of processors 1203 in the execution apparatus 1200 may be one or more, one processor is exemplified in fig. 12), wherein the processor 1203 may include an application processor 12031 and a communication processor 12032. In some embodiments of the application, the receiver 1201, the transmitter 1202, the processor 1203, and the memory 1204 may be connected by a bus or other means.

The memory 1204 may include read only memory and random access memory, and provides instructions and data to the processor 1203. A portion of the memory 1204 may also include non-volatile random access memory (non-volatile random access memory, NVRAM). The memory 1204 stores a processor and operating instructions, executable modules or data structures, or a subset thereof, or an extended set thereof, wherein the operating instructions may include various operating instructions for implementing various operations.

The processor 1203 controls the operation of the execution apparatus. In a specific application, the individual components of the execution device are coupled together by a bus system, which may include, in addition to a data bus, a power bus, a control bus, a status signal bus, etc. For clarity of illustration, however, the various buses are referred to in the figures as bus systems.

The method disclosed in the above embodiment of the present application may be applied to the processor 1203 or implemented by the processor 1203. The processor 1203 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the method described above may be performed by integrated logic circuitry in hardware or instructions in software in the processor 1203. The processor 1203 may be a general purpose processor, a digital signal processor (digital signal processing, DSP), a microprocessor or a microcontroller, and may further include an application specific integrated circuit (application specific integrated circuit, ASIC), a field-programmable gate array (FPGA-programmable gate array) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The processor 1203 may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present application. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 1204, and the processor 1203 reads the information in the memory 1204 and performs the steps of the above method in combination with its hardware.

The receiver 1201 may be used to receive input numeric or character information and to generate signal inputs related to performing relevant settings and function control of the device. The transmitter 1202 may be configured to output numeric or character information via a first interface; the transmitter 1202 may also be configured to send instructions to the disk stack via the first interface to modify data in the disk stack; transmitter 1202 may also include a display device such as a display screen.

In an embodiment of the present application, in an instance, the processor 1203 is configured to obtain, through the target model in the corresponding embodiment of fig. 5, a failure prediction result of the target device.

The embodiment of the application also relates to training equipment, and fig. 13 is a schematic structural diagram of the training equipment provided by the embodiment of the application. As shown in fig. 13, the exercise device 1300 is implemented by one or more servers, the exercise device 1300 may vary considerably in configuration or performance, and may include one or more central processing units (central processing units, CPU) 1313 (e.g., one or more processors) and memory 1332, one or more storage media 1330 (e.g., one or more mass storage devices) storing applications 1342 or data 1344. Wherein the memory 1332 and storage medium 1330 may be transitory or persistent. The program stored on the storage medium 1330 may include one or more modules (not shown), each of which may include a series of instruction operations on the training device. Still further, central processor 1313 may be configured to communicate with storage medium 1330, executing a series of instruction operations in storage medium 1330 on exercise device 1300.

Exercise device 1300 may also include one or more power sources 1326, one or more wired or wireless network interfaces 1350, one or more input/output interfaces 1358; or one or more operating systems 1341, such as Windows ServerTM, mac OS XTM, unixTM, linuxTM, freeBSDTM, etc.

Specifically, the training apparatus may perform the model training method in the corresponding embodiment of fig. 9, thereby obtaining the target model.

The embodiment of the application also relates to a computer storage medium in which a program for performing signal processing is stored which, when run on a computer, causes the computer to perform the steps as performed by the aforementioned performing device or causes the computer to perform the steps as performed by the aforementioned training device.

Embodiments of the present application also relate to a computer program product storing instructions that, when executed by a computer, cause the computer to perform steps as performed by the aforementioned performing device or cause the computer to perform steps as performed by the aforementioned training device.

The execution device, training device or terminal device provided in the embodiment of the present application may be a chip, where the chip includes: a processing unit, which may be, for example, a processor, and a communication unit, which may be, for example, an input/output interface, pins or circuitry, etc. The processing unit may execute the computer-executable instructions stored in the storage unit to cause the chip in the execution device to perform the data processing method described in the above embodiment, or to cause the chip in the training device to perform the data processing method described in the above embodiment. Optionally, the storage unit is a storage unit in the chip, such as a register, a cache, etc., and the storage unit may also be a storage unit in the wireless access device side located outside the chip, such as a read-only memory (ROM) or other type of static storage device that may store static information and instructions, a random access memory (random access memory, RAM), etc.

Specifically, referring to fig. 14, fig. 14 is a schematic structural diagram of a chip provided in an embodiment of the present application, where the chip may be represented as a neural network processor NPU 1400, and the NPU 1400 is mounted as a coprocessor on a main CPU (Host CPU), and the Host CPU distributes tasks. The core part of the NPU is an operation circuit 1403, and the operation circuit 1403 is controlled by a controller 1404 to extract matrix data in a memory and perform multiplication operation.

In some implementations, the arithmetic circuit 1403 internally includes a plurality of processing units (PEs). In some implementations, the operation circuit 1403 is a two-dimensional systolic array. The operation circuit 1403 may also be a one-dimensional systolic array or other electronic circuit capable of performing mathematical operations such as multiplication and addition. In some implementations, the operation circuit 1403 is a general-purpose matrix processor.

For example, assume that there is an input matrix a, a weight matrix B, and an output matrix C. The arithmetic circuit fetches the data corresponding to the matrix B from the weight memory 1402 and buffers the data on each PE in the arithmetic circuit. The arithmetic circuit takes matrix a data from the input memory 1401 and performs matrix operation with matrix B, and the partial result or the final result of the matrix obtained is stored in an accumulator (accumulator) 1408.

The unified memory 1406 is used for storing input data and output data. The weight data is directly transferred to the weight memory 1402 through the memory cell access controller (Direct Memory Access Controller, DMAC) 1405. The input data is also carried into the unified memory 1406 via the DMAC.

BIU is Bus Interface Unit, bus interface unit 1413, for the AXI bus to interact with the DMAC and finger memory (Instruction Fetch Buffer, IFB) 1409.

The bus interface unit 1413 (Bus Interface Unit, abbreviated as BIU) is configured to fetch the instruction from the external memory by the instruction fetch memory 1409, and to fetch the raw data of the input matrix a or the weight matrix B from the external memory by the memory unit access controller 1405.

The DMAC is mainly used to transfer input data in the external memory DDR to the unified memory 1406 or to transfer weight data to the weight memory 1402 or to transfer input data to the input memory 1401.

The vector calculation unit 1407 includes a plurality of operation processing units, and further processes such as vector multiplication, vector addition, exponential operation, logarithmic operation, size comparison, and the like are performed on the output of the operation circuit 1403 if necessary. The method is mainly used for non-convolution/full-connection layer network calculation in the neural network, such as Batch Normalization (batch normalization), pixel-level summation, up-sampling of a predicted label plane and the like.

In some implementations, the vector computation unit 1407 can store the vector of processed outputs to the unified memory 1406. For example, the vector calculation unit 1407 may perform a linear function; or, a nonlinear function is applied to the output of the operation circuit 1403, for example, linear interpolation of the predicted tag plane extracted by the convolutional layer, and for example, vector of accumulated values, to generate an activation value. In some implementations, the vector computation unit 1407 generates normalized values, pixel-level summed values, or both. In some implementations, the vector of processed outputs can be used as an activation input to the arithmetic circuit 1403, e.g., for use in subsequent layers in a neural network.

An instruction fetch memory (instruction fetch buffer) 1409 connected to the controller 1404 and used for storing instructions used by the controller 1404;

the unified memory 1406, the input memory 1401, the weight memory 1402, and the finger memory 1409 are all On-Chip memories. The external memory is proprietary to the NPU hardware architecture.

The processor mentioned in any of the above may be a general-purpose central processing unit, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the above-mentioned programs.

It should be further noted that the above-described apparatus embodiments are merely illustrative, and that the units described as separate units may or may not be physically separate, and that units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the embodiment of the device provided by the application, the connection relation between the modules represents that the modules have communication connection, and can be specifically implemented as one or more communication buses or signal lines.

From the above description of the embodiments, it will be apparent to those skilled in the art that the present application may be implemented by means of software plus necessary general purpose hardware, or of course by means of special purpose hardware including application specific integrated circuits, special purpose CPUs, special purpose memories, special purpose components, etc. Generally, functions performed by computer programs can be easily implemented by corresponding hardware, and specific hardware structures for implementing the same functions can be varied, such as analog circuits, digital circuits, or dedicated circuits. However, a software program implementation is a preferred embodiment for many more of the cases of the present application. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a readable storage medium, such as a floppy disk, a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk or an optical disk of a computer, etc., comprising several instructions for causing a computer device (which may be a personal computer, a training device, a network device, etc.) to perform the method according to the embodiments of the present application.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product.

The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via a wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be stored by a computer or a data storage device such as a training device, a data center, or the like that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., a floppy Disk, a hard Disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a Solid State Disk (SSD)), or the like.

Claims

1. A method of fault prediction, the method implemented by a target model, the method comprising:

acquiring historical fault information of target equipment, wherein the historical fault information is used for indicating N faults of the target equipment in the 1 st time to the T-1 st time, T is more than or equal to 2, and N is more than or equal to 2;

based on the historical fault information, acquiring causal relationships among the N faults and weights of the N faults, wherein the weights of the N faults are used for indicating importance degrees of the N faults;

and acquiring the probability of the N faults of the target equipment in the T moment based on the historical fault information, the causal relationship among the N faults and the weights of the N faults.

2. The method of claim 1, wherein the obtaining causal relationships between the N faults and weights of the N faults based on the historical fault information comprises:

extracting first characteristics of the historical fault information to obtain causal relations among the N faults;

sub-historical fault information is extracted from the historical fault information, and is used for indicating P faults of target equipment in the T-w time to the T-1 time, wherein the N faults comprise the P faults, N is more than or equal to P is more than or equal to 1, and T is more than or equal to 1;

And carrying out second feature extraction on the causal relationship among the N faults and the sub-historical fault information to obtain weights of the N faults.

3. The method according to claim 1 or 2, wherein the obtaining the probability of the N faults occurring in the target device at the T-th moment based on the historical fault information, the causal relationship between the N faults, and the weights of the N faults comprises:

based on the causal relationship among the N faults and the weights of the N faults, acquiring the causal relationship among M faults in the N faults, wherein N is more than or equal to M is more than or equal to 1;

and acquiring the probability of the N faults of the target equipment in the T moment based on the historical fault information and the causal relation among the M faults.

4. A method according to claim 3, wherein said obtaining causal relationships between M of the N faults based on causal relationships between the N faults and weights of the N faults comprises:

and in the causal relationship among the N faults, eliminating the N-M faults with the weight smaller than a first weight threshold value, and obtaining the causal relationship among M faults in the N faults.

5. The method of claim 4, wherein the obtaining the probability that the target device has the N faults in a T-th time based on the historical fault information and causal relationships between the M faults comprises:

and carrying out third feature extraction on the causal relationship among the M faults and the sub-historical fault information to obtain the probability of the N faults of the target equipment in the T moment.

6. The method of claim 2, wherein the first feature extraction or the second feature extraction comprises at least one of: feature extraction based on a recurrent neural network and feature extraction based on a convolutional neural network.

7. The method of claim 5, wherein the third feature extraction comprises at least one of: feature extraction based on a cyclic neural network, feature extraction based on a time convolution network and feature extraction based on a multi-layer perceptron.

8. A method of model training, the method comprising:

Inputting the historical fault information into a model to be trained to obtain the probability of the N faults of the target equipment in the T moment, wherein the model to be trained is used for: based on the historical fault information, acquiring causal relationships among the N faults and weights of the N faults, wherein the weights of the N faults are used for indicating importance degrees of the N faults; acquiring the probability of the N faults of the target equipment in the T moment based on the historical fault information, the causal relationship among the N faults and the weights of the N faults;

and training the model to be trained based on the probability, so as to obtain a target model.

9. The method of claim 8, wherein the model to be trained is for:

10. The method according to claim 8 or 9, wherein the model to be trained is for:

11. The method of claim 10, wherein the model to be trained is for:

12. The method of claim 11, wherein the model to be trained is for:

13. The method of claim 12, wherein the model to be trained is further configured to:

M-K faults with the weight smaller than a second weight threshold are removed from the causal relation among the M faults, so that the causal relation among K faults in the M faults is obtained, and M is larger than K and is larger than or equal to 1;

performing fourth feature extraction on the causal relationship among the K faults and the sub-historical fault information to obtain new probabilities of the N faults of the target equipment in the T moment;

training the model to be trained based on the probability, thereby obtaining a target model comprises the following steps:

and training the model to be trained based on the probability and the new probability, thereby obtaining a target model.

14. The method of claim 9, wherein the first feature extraction or the second feature extraction comprises at least one of: feature extraction based on a recurrent neural network and feature extraction based on a convolutional neural network.

15. The method of claim 13, wherein the third feature extraction or fourth feature extraction comprises at least one of: feature extraction based on a cyclic neural network, feature extraction based on a time convolution network and feature extraction based on a multi-layer perceptron.

16. A fault prediction apparatus, the apparatus comprising a target model, the apparatus comprising:

the first acquisition module is used for acquiring historical fault information of target equipment, wherein the historical fault information is used for indicating N faults of the target equipment in the 1 st time to the T-1 st time, T is more than or equal to 2, and N is more than or equal to 2;

the second acquisition module is used for acquiring causal relations among the N faults and weights of the N faults based on the historical fault information, wherein the weights of the N faults are used for indicating importance degrees of the N faults;

and a third obtaining module, configured to obtain a probability that the N faults occur in the target device at a T-th moment based on the historical fault information, the causal relationship between the N faults, and the weights of the N faults.

17. A model training apparatus, the apparatus comprising:

the acquisition module is used for acquiring historical fault information of target equipment, wherein the historical fault information is used for indicating N faults of the target equipment from the 1 st moment to the T-1 st moment, T is more than or equal to 2, and N is more than or equal to 2;

the processing module is used for inputting the historical fault information into a model to be trained to obtain the probability of the N faults of the target equipment in the T moment, and the model to be trained is used for: based on the historical fault information, acquiring causal relationships among the N faults and weights of the N faults, wherein the weights of the N faults are used for indicating importance degrees of the N faults; acquiring the probability of the N faults of the target equipment in the T moment based on the historical fault information, the causal relationship among the N faults and the weights of the N faults;

And the training module is used for training the model to be trained based on the probability so as to obtain a target model.

18. A fault prediction device, the device comprising a memory and a processor; the memory stores code, the processor being configured to execute the code, the fault prediction device performing the method of any of claims 1 to 15 when the code is executed.

19. A computer storage medium storing one or more instructions which, when executed by one or more computers, cause the one or more computers to implement the method of any one of claims 1 to 15.

20. A computer program product, characterized in that it stores instructions that, when executed by a computer, cause the computer to implement the method of any one of claims 1 to 15.