CN113567132B - Motor rolling bearing fault model construction method based on digital twinning technology - Google Patents
Motor rolling bearing fault model construction method based on digital twinning technology Download PDFInfo
- Publication number
- CN113567132B CN113567132B CN202111021923.1A CN202111021923A CN113567132B CN 113567132 B CN113567132 B CN 113567132B CN 202111021923 A CN202111021923 A CN 202111021923A CN 113567132 B CN113567132 B CN 113567132B
- Authority
- CN
- China
- Prior art keywords
- rolling bearing
- model
- motor rolling
- fault
- vibration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/04—Bearings
- G01M13/045—Acoustic or vibration analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Abstract
The invention discloses a motor rolling bearing three-dimensional simulation fault model construction method based on a digital twinning technology, which comprises the steps of firstly, aiming at the influence of geometric structure parameters such as bearing radial clearance on vibration data in the construction process of a three-dimensional simulation model, proposing that the geometric structure parameters of the three-dimensional simulation model continuously approach the parameter values of an actual physical model by adopting a K-center-point-based parameter optimization method, and realizing the effective matching of the geometric structure parameters of a virtual simulation model and the actual physical model parameters; secondly, the construction of a virtual space test system model and the deviation correction of vibration data are realized by constructing a virtual test system vibration model; and finally, monitoring and diagnosing the state of the motor rolling bearing by utilizing the deep neural network. The fault simulation model provided by the invention can enable the vibration characteristics of the three-dimensional simulation model to approach the vibration characteristics of the actual physical model, and provides effective data support for dynamic fault deduction and performance prediction of the rolling bearing.
Description
Technical Field
The invention relates to the technical field of mechanical fault diagnosis, in particular to a motor rolling bearing fault model building method based on a digital twinning technology.
Background
The rapid development of digitalization and intellectualization of modern manufacturing industry leads to the promotion of intelligent operation and maintenance and health management technology of mechanical equipment. The intelligent diagnosis technology of deep learning provides a technical basis for fault diagnosis of a complex mechanical system, but the defects and the shortage of fault samples in engineering practice limit effective popularization of deep learning in practical application. Although the theoretical fault model constructed by the data mining technology and the deep neural network can provide a sufficient data sample set, the fault model is not beneficial to the dynamic deduction and reasoning of mechanical parts, and the explanation of a mechanical fault mechanism is lacked. Therefore, the three-dimensional fault simulation model based on the digital twin technology is established, not only can the dynamic deduction of the mechanical fault be realized, but also the data sample of the deep learning technology in the field of mechanical fault diagnosis can be guaranteed.
How to realize the consistency of the virtual space rolling bearing fault model vibration data and the physical space actually measured vibration data is a technical problem to be solved in the technical field. The following two problems need to be solved: the method is characterized in that the accuracy of geometric structure parameters of the bearing in the construction process of a reference model is first. The geometric structure parameter values of the bearing can be obtained by looking up a manual and a drawing, but some parameters such as the theoretical value of the radial clearance of the bearing are range values, the structural parameters of actual equipment can be influenced by installation, load, operation, detection modes and the like to generate radial clearance errors, the geometric structure parameter values are different in the three-dimensional model construction process, and the physical action relationships such as contact force and the like are different to influence vibration; the second is the consistency of the vibration data of the digital twin model. When the fault diagnosis model based on the digital twin is matched with the physical actual model based on the sensing data, if the influence of the sensor serving as a detection device on the vibration data is not considered, the processing process of the detection devices such as the vibration sensor on the vibration data of the physical model is ignored, the deviation of the compared data is easy to cause larger, the running speed of the digital twin model is reduced, and the storage pressure is increased.
Disclosure of Invention
Aiming at the problems, the invention discloses a motor rolling bearing fault model construction method based on a digital twinning technology. The invention aims to provide a motor rolling bearing fault model construction method based on a digital twinning technology, and a relatively accurate calculation result is obtained from a simulation model. The invention mainly adopts a method for constructing the fault model of the motor rolling bearing by combining geometric structure parameter optimization and vibration model construction so as to obtain a more accurate simulation calculation result. In order to achieve the purpose, the invention provides a motor rolling bearing fault model building method based on a digital twin technology, which comprises the following steps:
s1: acquisition and pretreatment of vibration data of actual physical model of motor rolling bearing
S1-1: monitoring actual vibration signals and working condition parameters in the actual operation process of a motor rolling bearing and acquiring vibration data z (t) of an actual physical model;
s1-2: carrying out denoising pretreatment on the actual vibration signal;
s1-3: calculating the vibration characteristic value of the actual physical model as f R (c 0 ) Wherein c is 0 The radial clearance of the motor rolling bearing is an actual physical model;
s2: establishing a three-dimensional simulation model of a motor rolling bearing, wherein the modeling method comprises the following steps:
s2-1: obtaining the geometric dimensions and structural characteristics of different components of the motor rolling bearing by referring to drawings and manuals;
s2-2: parameters of parts of different components of the motor rolling bearing are obtained by looking up a nameplate and a manual;
s2-3: setting physical action relations of different component parts of the motor rolling bearing respectively;
s2-4: selecting the value of the variable c of the geometric structure parameter of the motor rolling bearing j ；
S2-5: establishing a three-dimensional simulation model of a rolling bearing of a rolling motor of the motor in a fault-free mode;
s2-6: calculating a motor rolling bearing simulation vibration signal and a motor rolling bearing vibration characteristic value thereof through a three-dimensional simulation model, and recording the vibration characteristic value of the motor rolling bearing three-dimensional simulation model as f V (c j )；
S3: optimization and matching of geometric structure parameter variables of motor rolling bearing simulation model based on K-center point
S3-1: setting a geometric structure parameter variable set O = { c) of a simulated three-dimensional model 1 ，…，c k In which c is 1 Is a lower limit value of a parameter variable, c k The upper limit value of a parameter variable;
s3-2: selection c j Is the current center point of the object O;
s3-3: calculating the variable values c of different geometric structure parameters in the geometric structure parameter variable set O of the motor rolling bearing j Corresponding vibration characteristicsCharacteristic value f V (c j ) F of vibration characteristic value of actual physical model R (c 0 ) Square of distance
S3-4: constructing an objective function
S3-5: when the geometric structure parameters of the motor rolling bearing approach the parameter values of the actual physical model continuously, the iteration is continuously increased to enable the objective function mu to be increased n The value tends to be stable;
s3-6: when in use
When the condition is met, determining the geometric structure parameter value of the motor rolling bearing; otherwise, continuing the search until a condition is satisfied, wherein ε is a given sufficiently small amount;
s4: determining a three-dimensional simulation reference model of the motor rolling bearing in a fault-free mode according to the step S2 and the step S3
S5: three-dimensional fault simulation reference model for constructing motor rolling bearing
S5-1: acquiring fault forms of different fault types, fault positions, fault degrees and the like of the actual physical model of the motor rolling bearing in the step S1 in a dismounting and detecting mode;
s5-2: constructing a three-dimensional fault simulation model of the motor rolling bearing according to the characteristic parameters obtained in the step S2 and the step S3 and the actual physical fault model;
s5-3: simulating and calculating vibration signals x (t) of different faults of the motor rolling bearing;
s6: the actual physical test system is considered as an undistorted test system as a whole, and a virtual test system vibration model is constructed to approach a vibration signal obtained by the test device in an actual physical space, so that the vibration deviation generated by the detection device is reduced
S6-1: construction of vibration model y (t) = Ax (t-t) 0 ) Wherein the gain A is the result of step S1The amplitude ratio of the vibration data z (t) of the actual physical model to the vibration signal x (t) calculated by the simulation fault model in step S5 and the lag time t 0 The time difference between the vibration data z (t) of the actual physical model in the S1 and the vibration signal x (t) calculated by the simulation fault model in the S5 is obtained;
s6-2: constructing a virtual vibration data space Y (t) of a motor rolling bearing under multiple working conditions and multiple faults;
s7: state monitoring and diagnosis of motor rolling bearing by using deep neural network
S7-1: vibration data of the motor rolling bearing under different working conditions and faults are obtained through the S1, and a vibration data space Z (t) of an actual physical model is constructed;
s7-2: randomly selecting sample data of 25% of the vibration data space of the actual physical model to train, testing the residual sample data, determining a deep neural network diagnosis model, and determining a threshold value according to the average diagnosis accuracy rate and the standard deviation thereof;
s7-3: diagnosing the virtual space simulation vibration data Y (t) obtained by calculation in the step S6 by adopting the deep neural network diagnosis model in the step S7-2;
s7-4: judging whether the diagnosis accuracy rate reaches a threshold value, if not, returning to the step of adjusting and correcting the geometric structure parameters of the three-dimensional simulation fault model of the motor rolling bearing by adopting a parameter optimization method based on a K-central point to obtain a motor rolling bearing fault simulation model with higher fidelity;
s7-5: if the threshold value is reached, establishing a simulation fault database of the motor rolling bearing digital twin fault model, and providing data support for quantitative diagnosis and performance prediction of the motor rolling bearing.
Further, in step S1-2, the preprocessing method is FIR filter or wavelet denoising.
Further, in step S2-1, the geometric size and the structural characteristic include an outer ring diameter, an inner ring diameter, a width, a rolling element diameter, the number of rolling elements, a pitch diameter of a rolling bearing of the motor, a contact angle, an OR curvature, an IR curvature, an outer raceway radius, and an inner raceway radius; the parameters of the part comprise material, density, poisson's ratio and Young's modulus.
Further, in step S2-3, the physical action relationship includes a contact method and a friction property between the rolling element and the outer ring, between the rolling element and the inner ring, between the rolling element and the cage, and the like.
Further, in step S2-4, the geometric structure parameter variables of the motor rolling bearing include a play variable value, a waviness, a gap between the rolling element and the hole of the retainer, and the like.
Further, in step S2-4, the geometric structure parameter variable of the motor rolling bearing is the radial play variable value c of the motor rolling bearing j ，j＝1，…，k。
Compared with the prior art, the invention has the following effects:
the invention aims to provide a method for constructing a three-dimensional simulation fault model of a motor rolling bearing based on a digital twinning technology, which solves the problem of deviation of vibration data caused by geometric structure parameters and a detection system in a motor rolling bearing simulation model. According to the K-center-point-based parameter optimization method, the fidelity of the digital twin model of the motor rolling bearing is improved through the matching of the geometric structure parameters of the virtual simulation model and the parameters of the actual physical model, and the influence of the geometric structure parameters on the vibration data of the motor rolling bearing is further reduced; the vibration model construction technology provided by the invention can realize the construction of a virtual space test system model and the deviation correction of vibration data.
Drawings
To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the figures needed to be used in the description and implementation of the prior art.
FIG. 1 is a flow chart of a motor rolling bearing fault model construction method based on a digital twinning technology.
FIG. 2 is a schematic diagram of a parameter optimization method according to the present invention.
FIG. 3 is a schematic diagram of the vibration model construction of the present invention.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments, and all other embodiments obtained by those skilled in the art without any inventive work are within the scope of the present invention.
A motor rolling bearing fault model building method based on a digital twinning technology comprises the following steps:
s1: and acquiring and preprocessing vibration data of the actual physical model of the motor rolling bearing.
S1-1: and monitoring actual vibration signals and working condition parameters in the actual operation process of the motor rolling bearing and acquiring vibration data z (t). Because the physical model is interfered by surrounding environment, a detection device and the like in the actual operation process, the obtained vibration signal contains a large amount of noise signals, the actual measurement vibration signal needs to be subjected to denoising pretreatment, and the pretreatment method comprises an FIR filter, wavelet denoising and the like, but is not limited to the methods;
s1-2: the radial clearance of the motor rolling bearing of an actual physical model is assumed to be c 0 Calculating the radial clearance c by actually measuring the vibration signal 0 The vibration characteristic value of the motor rolling bearing corresponding to the lower step is recorded as f R (c 0 )。
S2: a three-dimensional simulation model of a motor rolling bearing is constructed, and the modeling method comprises the following steps:
s2-1: the geometric dimensions and structural characteristics of different components of the motor rolling bearing at least comprise the outer ring diameter, the inner ring diameter, the width, the rolling body diameter, the rolling body number, the pitch diameter of the motor rolling bearing, a contact angle, OR curvature, IR curvature, the outer raceway radius, the inner raceway radius and other parameters are consulted and obtained through drawings and manuals;
s2-2: different components of the motor rolling bearing at least comprise material, density, poisson's ratio, young modulus and other parameters, and are consulted and obtained through a nameplate and a manual;
s2-3: the physical action relations of different components of the motor rolling bearing at least comprise contact methods and friction properties of a rolling body and an outer ring, the rolling body and an inner ring, the rolling body and a retainer and the like which are respectively arranged.
S2-4: according to the manual and the drawing, the theoretical value of the radial clearance of the motor rolling bearing is a range value, and the radial clearance of the actual physical model is influenced by installation, load, operation and the like to generate errors. In order to enable the vibration characteristics of the three-dimensional simulation model to approach the vibration characteristics of the actual physical model, the radial clearance of the motor rolling bearing is required to be close to the radial clearance value of the actual physical model when the simulation model is built, so that the digital twin effect is achieved, and the optimization and matching of the radial clearance of the motor rolling bearing are realized by adopting a K-center point-based method in the implementation case. Selecting the radial clearance variable value c of the motor rolling bearing j ，j＝1，…，k。
S2-5: establishing a three-dimensional simulation model of the motor rolling bearing in a fault-free mode,
s2-6: calculating the simulation vibration signal of the motor rolling bearing and the vibration characteristic value of the motor rolling bearing through a three-dimensional simulation model, and recording the radial clearance variable value of the motor rolling bearing as c j While its vibration characteristic value is f V (c j )。
S3: and optimizing and matching geometric structure parameter variables of the motor rolling bearing simulation model based on the K-central point.
S3-1: radial clearance variable set O = { c) of motor rolling bearing with simulation three-dimensional model 1 ，…，c k A value range of the upper limit value and the lower limit value of the radial clearance of the motor rolling bearing model in the manual, c 1 A lower limit value of radial play of a rolling bearing of the motor, c k The upper limit value of the radial clearance of the motor rolling bearing is obtained;
s3-2: selection c j Is the current center point of the object O;
s3-3: calculating different radial play values c in geometric structure parameter radial play variable set O of motor rolling bearing j Corresponding vibration characteristic value f V (c j ) F from measured vibration characteristic value R (c 0 ) Square of distance
S3-4: constructing an objective function
S3-5: when the geometric structure parameters of the motor rolling bearing such as radial play c j Radial clearance c continuously approaching to actual physical model 0 While, the target function mu is continuously increased in iteration n The value tends to be stable;
s3-6: when in use
When the radial clearance value c of the rolling bearing of the motor meets the condition j Determining; otherwise, the search continues until a condition is satisfied, where ε is given a sufficiently small amount.
S4: and establishing a three-dimensional simulation reference model of the motor rolling bearing in a fault-free mode.
S5: and acquiring fault types, fault positions, fault degrees and other fault forms of different component parts of the motor rolling bearing in a mode of disassembling and checking the actual physical model to construct a three-dimensional simulation fault model of the motor rolling bearing. And simulating and calculating vibration signals of different faults of the motor rolling bearing.
S6: considering the deviation of the sensor as a detection device to the amplitude and the phase of the vibration data of the actual physical model, the embodiment constructs a vibration model by simulating the dynamic characteristics of the detection device, so that the vibration data generated by the simulation model approaches the vibration data output by the detection device, and the vibration deviation generated by the detection device is further reduced; meanwhile, the construction of the vibration model can simplify a digital twin model, so that the running speed is improved, and the storage pressure is reduced.
And (3) taking the whole actual physical test system into consideration as a non-distortion test system, and constructing a vibration model of the virtual test system.
S6-1: construction of vibration model y (t) = Ax (t-t) 0 ) Wherein the gain A is the sum of the sensor data z (t) of the actual physical fault model in step (1)The amplitude ratio and the lag time t of the vibration data x (t) calculated by the simulation fault model in the step (5) 0 Time difference between sensor data z (t) of the actual physical fault model in the step (1) and vibration data x (t) calculated by the simulation fault model in the step (5);
s6-2: and constructing a virtual vibration data space Y (t) of the motor rolling bearing under different working conditions and different faults.
S7: and monitoring and diagnosing the state of the motor rolling bearing by using the deep neural network.
S7-1: vibration data of a motor rolling bearing under different working conditions and faults are obtained through the step (1), and a vibration data space Z (t) of an actual physical model is constructed;
s7-2: randomly selecting sample data of 25% of the vibration data space of the actual physical model to train, testing the residual sample data, determining a deep neural network diagnosis model, and determining a threshold value according to the average diagnosis accuracy rate and the standard deviation thereof;
s7-3: diagnosing the virtual space simulation vibration data Y (t) obtained by calculation in the step (6) by adopting the deep neural network diagnosis model in the step 2);
s7-4: judging whether the diagnosis accuracy reaches a threshold value, if not, returning to the K-center point-based parameter optimization method to adjust and correct other geometric structure parameter variables of the three-dimensional simulation fault model of the motor rolling bearing so as to obtain the fault simulation model of the motor rolling bearing with higher fidelity;
s7-5: if the threshold value is reached, establishing a simulation fault database of the motor rolling bearing digital twin fault model, and providing data support for quantitative diagnosis and performance prediction of the motor rolling bearing.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered as the technical solutions and modifications within the scope of the present invention.
Claims (6)
1. A motor rolling bearing fault model building method based on a digital twinning technology is characterized by comprising the following steps:
s1: acquisition and pretreatment of vibration data of actual physical model of motor rolling bearing
S1-1: monitoring actual vibration signals and working condition parameters in the actual operation process of a motor rolling bearing and acquiring vibration data z (t) of an actual physical model;
s1-2: carrying out denoising pretreatment on the actual vibration signal;
s1-3: calculating the vibration characteristic value f of the actual physical model R (c 0 ) Wherein, c 0 The radial clearance of the motor rolling bearing is an actual physical model;
s2: establishing a three-dimensional simulation model of a motor rolling bearing, wherein the modeling method comprises the following steps:
s2-1: obtaining the geometric dimensions and structural characteristics of different components of the motor rolling bearing by referring to drawings and manuals;
s2-2: parameters of parts of different components of the motor rolling bearing are obtained by looking up a nameplate and a manual;
s2-3: respectively setting physical action relations of different component parts of the motor rolling bearing;
s2-4: selecting motor rolling bearing geometric structure parameter variable value c j ；
S2-5: establishing a three-dimensional simulation model of a motor rolling bearing in a fault-free mode;
s2-6: calculating a motor rolling bearing simulation vibration signal and a motor rolling bearing vibration characteristic value thereof through a three-dimensional simulation model, and recording the vibration characteristic value of the motor rolling bearing three-dimensional simulation model as f V (c j )；
S3: optimization and matching of geometric structure parameter variables of three-dimensional simulation model of motor rolling bearing based on K-center point
S3-1: setting a geometric structure parameter variable set O = { c) of a three-dimensional simulation model 1 ，…，c k In which c is 1 Is a lower limit value of a parameter variable, c k The upper limit value of a parameter variable;
s3-2: selection c j Is the current center point of object O;
s3-3: calculating the variable values c of different geometric structure parameters in the geometric structure parameter variable set O of the motor rolling bearing j Corresponding vibration characteristic value f V (c j ) F of vibration characteristic value from actual physical model R (c 0 ) Square of distance
S3-4: constructing an objective function
S3-5: when the geometric structure parameters of the motor rolling bearing continuously approach the parameter values of the actual physical model, the parameters are continuously iteratively increased to enable the objective function mu to be n The value tends to be stable;
s3-6: when in use
When the condition is met, determining the geometric structure parameter value of the motor rolling bearing; otherwise, continuing the search until a condition is satisfied, wherein ε is a given sufficiently small amount;
s4: determining a three-dimensional simulation reference model S5 under the fault-free mode of the motor rolling bearing according to the step S2 and the step S3: three-dimensional fault simulation reference model for constructing motor rolling bearing
S5-1: acquiring fault forms of different fault types, fault positions and fault degrees of the actual physical model of the motor rolling bearing in the step S1 in a dismounting and detecting mode;
s5-2: constructing a three-dimensional fault simulation reference model of the motor rolling bearing according to the information obtained in the step S2 and the step S3 and the actual physical fault model;
s5-3: simulating and calculating vibration signals x (t) of different faults of the motor rolling bearing;
s6: the actual physical test system is considered as an undistorted test system as a whole, and a virtual test system vibration model is constructed to approach a vibration signal obtained by the test device in an actual physical space, so that the vibration deviation generated by the detection device is reduced
S6-1: construction of vibration model y (t) = Ax (t-t) 0 ) Wherein the gain A is the amplitude ratio of the vibration data z (t) of the actual physical model in step S1 to the vibration signal x (t) calculated by the simulation fault model in step S5, and the lag time t 0 The time difference between the vibration data z (t) of the actual physical model in the S1 and the vibration signal x (t) calculated by the simulation fault model in the S5 is obtained;
s6-2: constructing virtual space simulation vibration data Y (t) of a motor rolling bearing under multiple working conditions and multiple faults;
s7: state monitoring and diagnosis of motor rolling bearing by using deep neural network
S7-1: vibration data of the motor rolling bearing under different working conditions and faults are obtained through the S1, and a vibration data space Z (t) of an actual physical model is constructed;
s7-2: randomly selecting sample data of 25% of the vibration data space of the actual physical model for training, testing the residual sample data, determining a deep neural network diagnosis model, and determining a threshold value according to the average diagnosis accuracy rate and the standard deviation thereof;
s7-3: diagnosing the virtual space simulation vibration data Y (t) obtained by calculation in the step S6 by adopting the deep neural network diagnosis model in the step S7-2;
s7-4: judging whether the diagnosis accuracy rate reaches a threshold value, if not, returning to the step of adjusting and correcting the geometric structure parameters of the three-dimensional simulation fault model of the motor rolling bearing by adopting a parameter optimization method based on a K-central point to obtain a motor rolling bearing fault simulation model with higher fidelity;
s7-5: if the threshold value is reached, establishing a simulation fault database of the motor rolling bearing digital twin fault model, and providing data support for quantitative diagnosis and performance prediction of the motor rolling bearing.
2. The method for constructing the fault model of the rolling bearing of the motor based on the digital twin technology as claimed in claim 1, wherein in the step S1-2, the denoising pre-processing is FIR filter denoising or wavelet denoising.
3. The method for constructing the fault model of the motor rolling bearing based on the digital twinning technology as claimed in claim 1, wherein in step S2-1, the geometric dimensions and the structural characteristics include an outer ring diameter, an inner ring diameter, a width, a rolling body diameter, the number of rolling bodies, a pitch diameter of the motor rolling bearing, a contact angle, an OR curvature, an IR curvature, an outer raceway radius and/OR an inner raceway radius; in step S2-2, the parameters of the part comprise material, density, poisson 'S ratio and/or Young' S modulus.
4. The method for constructing the fault model of the motor rolling bearing based on the digital twinning technology as claimed in claim 1, wherein in step S2-3, the physical action relationship comprises a contact method and friction properties of the rolling element and the outer ring, the rolling element and the inner ring and/or the rolling element and the retainer.
5. The method for constructing the fault model of the motor rolling bearing based on the digital twinning technology as claimed in claim 1, wherein in step S2-4, the geometric structure parameter variables of the motor rolling bearing comprise a play variable value, a waviness and/or a gap between the rolling element and the hole of the retainer.
6. The method for constructing the fault model of the motor rolling bearing based on the digital twinning technology as claimed in claim 1, wherein in the step S2-4, the geometric structure parameter variable of the motor rolling bearing is the radial play variable value c of the motor rolling bearing j ，j＝1，…，k。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111021923.1A CN113567132B (en) | 2021-09-01 | 2021-09-01 | Motor rolling bearing fault model construction method based on digital twinning technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111021923.1A CN113567132B (en) | 2021-09-01 | 2021-09-01 | Motor rolling bearing fault model construction method based on digital twinning technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113567132A CN113567132A (en) | 2021-10-29 |
| CN113567132B true CN113567132B (en) | 2022-10-21 |
Family
ID=78173348
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111021923.1A Active CN113567132B (en) | 2021-09-01 | 2021-09-01 | Motor rolling bearing fault model construction method based on digital twinning technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113567132B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114329849B (en) * | 2022-03-03 | 2022-06-21 | 河北工业大学 | Health management and control system and method for liquid filling forming equipment based on digital twinning |
| CN114383847B (en) * | 2022-03-23 | 2022-07-12 | 西南交通大学 | Rolling bearing full-life state monitoring method based on digital twinning |
| CN115575121B (en) * | 2022-09-26 | 2023-07-28 | 河南科技大学 | Construction method of rolling bearing dynamic model |
| CN117539168B (en) * | 2024-01-09 | 2024-03-26 | 江西江投能源技术研究有限公司 | Hydraulic turbine cavitation diagnosis system and method based on semi-physical simulation |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170286572A1 (en) * | 2016-03-31 | 2017-10-05 | General Electric Company | Digital twin of twinned physical system |
| CN110442936B (en) * | 2019-07-24 | 2021-02-23 | 中国石油大学(北京) | Equipment fault diagnosis method, device and system based on digital twin model |
| CN112487584A (en) * | 2020-12-03 | 2021-03-12 | 天津工业大学 | Dynamics-based rolling bearing digital twin modeling method |
| CN112762100B (en) * | 2021-01-14 | 2021-08-10 | 哈尔滨理工大学 | Bearing full-life-cycle monitoring method based on digital twinning |
| CN113092115B (en) * | 2021-04-09 | 2022-10-11 | 重庆大学 | Digital twin model construction method of digital-analog combined drive full-life rolling bearing |
| CN113221280B (en) * | 2021-05-14 | 2022-12-09 | 西安交通大学 | Rolling bearing modeling and model updating method and system based on digital twinning |
| CN113378329A (en) * | 2021-07-06 | 2021-09-10 | 长沙理工大学 | Axial plunger pump state monitoring method based on digital twinning |
-
2021
- 2021-09-01 CN CN202111021923.1A patent/CN113567132B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113567132A (en) | 2021-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113567132B (en) | Motor rolling bearing fault model construction method based on digital twinning technology | |
| Zhang et al. | Dynamic condition monitoring for 3D printers by using error fusion of multiple sparse auto-encoders | |
| WO2022037068A1 (en) | Method for diagnosis of fault in machine tool bearing | |
| Deng et al. | A calibration-based hybrid transfer learning framework for RUL prediction of rolling bearing across different machines | |
| CN110704801B (en) | Bridge cluster structure operation safety intelligent monitoring and rapid detection complete method | |
| WO2021027213A1 (en) | Detection method and apparatus, electronic device and computer-readable medium | |
| CN112036075A (en) | Abnormal data judgment method based on environmental monitoring data association relation | |
| CN112633339A (en) | Bearing fault intelligent diagnosis method, bearing fault intelligent diagnosis system, computer equipment and medium | |
| CN111024821A (en) | Composite material storage box health monitoring system and method | |
| CN111238815A (en) | Bearing fault identification method based on data enhancement under sample imbalance | |
| CN116793682A (en) | Bearing fault diagnosis method based on iCORAL-MMD and anti-migration learning | |
| CN110555235A (en) | Structure local defect detection method based on vector autoregressive model | |
| CN111367959A (en) | Zero-time-lag nonlinear expansion Granger causal analysis method | |
| Jiang et al. | A multisensor cycle-supervised convolutional neural network for anomaly detection on magnetic flux leakage signals | |
| Son et al. | Deep learning-based anomaly detection to classify inaccurate data and damaged condition of a cable-stayed bridge | |
| CN115994320A (en) | Intelligent friction pendulum vibration isolation support and state monitoring and fault diagnosis system | |
| CN114755017B (en) | Variable-speed bearing fault diagnosis method of cross-domain data driving unsupervised field shared network | |
| CN115563853A (en) | Rolling bearing fault diagnosis method based on digital twinning | |
| US20210397177A1 (en) | Fault diagnostics systems and methods | |
| CN114091525A (en) | Rolling bearing degradation trend prediction method | |
| Feng et al. | Online residual useful life prediction of large-size slewing bearings—A data fusion method | |
| Jia et al. | Multitask convolutional neural network for rolling element bearing fault identification | |
| CN113705721B (en) | Joint probability density function difference diagnosis method for beam bridge support group void diseases | |
| CN114383834B (en) | Ocean engineering structure micro damage judging method | |
| CN111753876B (en) | Product quality detection method based on deep neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |