CN111056395B - Band-type brake fault diagnosis method based on multipoint pressure sensor - Google Patents
Band-type brake fault diagnosis method based on multipoint pressure sensor Download PDFInfo
- Publication number
- CN111056395B CN111056395B CN201911353305.XA CN201911353305A CN111056395B CN 111056395 B CN111056395 B CN 111056395B CN 201911353305 A CN201911353305 A CN 201911353305A CN 111056395 B CN111056395 B CN 111056395B
- Authority
- CN
- China
- Prior art keywords
- layer
- signal
- pressure sensor
- band
- data
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0087—Devices facilitating maintenance, repair or inspection tasks
- B66B5/0093—Testing of safety devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0006—Monitoring devices or performance analysers
- B66B5/0018—Devices monitoring the operating condition of the elevator system
- B66B5/0031—Devices monitoring the operating condition of the elevator system for safety reasons
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0006—Monitoring devices or performance analysers
- B66B5/0037—Performance analysers
Abstract
The invention provides a band-type brake fault diagnosis method based on a multipoint pressure sensor, and belongs to the technical field of packaging shells. The band-type brake fault diagnosis method based on the multipoint pressure sensor S1: acquiring first signal data; s2: training a signal prediction model; s3: the first signal data is classified. According to the method, any set of brake shoe signals to be identified is given, the brake shoe signals are input into a trained signal prediction model, deep learning characteristics of samples are extracted, and the signals of the set are effectively judged to be in a normal state or a fault state through a twice training method, so that the pressure state of a band-type brake can be known from the classified condition, the stress distribution condition of the band-type brake shoe can be intuitively displayed in real time, and the running state of a band-type brake device can be monitored in real time.
Description
Technical Field
The invention belongs to the technical field of band-type brake fault diagnosis, and relates to a band-type brake fault diagnosis method based on a multipoint pressure sensor.
Background
The brake device is widely applied to industrial and civil traction type elevators, because accidents such as industrial loss and personal safety problems caused by faults of the brake device occur occasionally, the overall performance of the brake is continuously changed along with the accumulation of working times, and the dynamic characteristics and fault mechanisms of domestic brakes are not deeply researched, so that an effective brake device fault diagnosis system is lacked, and the reliable operation of the brake device cannot be fundamentally ensured only by the regular inspection of maintenance personnel. This conventional periodic inspection method exhibits the following disadvantages: 1) the requirement on maintenance workers is high, and long-time training and long-time experience accumulation are required; 2) the economic benefit is poor, and the industrial loss caused by failure to find the brake fault in time is huge; 4) The safety coefficient is low, and casualties are easily caused when faults occur. Therefore, the brake fault diagnosis method based on the dynamic characteristics and the fault mechanism of the brake is deeply researched, and has important significance for improving the safety level of the traction type elevator, shortening the maintenance time and reducing the maintenance investment.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a band-type brake fault diagnosis method based on a multipoint pressure sensor, and the technical problems to be solved by the invention are as follows: how to provide a band-type brake fault diagnosis method based on a multipoint pressure sensor.
The purpose of the invention can be realized by the following technical scheme:
a band-type brake fault diagnosis method based on a multipoint pressure sensor comprises the following steps:
s1: detecting the pressure of a band-type brake through a multipoint pressure sensor to obtain first signal data comprising the pressure value of the band-type brake;
s2: establishing a signal prediction model based on a LeNet-5 neural network and training the signal prediction model;
s3: the first signal data is classified by the trained signal prediction model.
Preferably, step S1 collects first signal data including a left shoe sensor signal of a left shoe of the band brake and a right shoe sensor signal of a right shoe of the band brake through a 24-point pressure sensor of 4 × 6, the first signal data being classified according to a normal state and a fault state.
Preferably, step S1 includes preprocessing the first signal data, combining a plurality of 4 x 6 signals, and combining the combined signals into a 48 x 48 signal matrix using 48 sets of signals, wherein a set of signals includes a left shoe sensor signal and a right shoe sensor signal.
Preferably, the signal prediction model comprises seven layers; the first layer is an input layer, the first layer is original signal data, the picture size of the first layer is 48 × 1, and the channel is 1; the second layer is a convolutional layer, the input of the second layer is the output of the output layer, the filter size of the second layer is 5 x 5, the depth is 32, the second layer is filled with all 0 s, and the output matrix size of the second layer is 48 x 32; the third layer is a pooled layer, the input of the third layer is a 48 x 32 node matrix of the second layer output, the filter size of the third layer is 2 x 2, the step size of the length and width is 2, and the output matrix size of the third layer is 24 x 32; the fourth layer is a convolutional layer, the input of the fourth layer is the output of the third layer, the filter size of the fourth layer is 5 x 5, the depth is 64, the fourth layer is filled with all 0 s, and the output matrix size of the fourth layer is 24 x 64; the fifth layer is a pooling layer, the input of the fifth layer is a 24 x 64 node matrix of the fourth layer output, the filter size of the fifth layer is 2 x 2, the length and width steps are 2, and the output matrix size of the fifth layer is 12 x 64; the sixth layer is a fully-connected layer, the input of the sixth layer is the output of the fifth layer, the number of input nodes of the sixth layer is 12 × 64, the number of input nodes of the sixth layer is 9216, and the number of output nodes of the sixth layer is 512; the seventh layer is a full connection layer, the number of input nodes of the seventh layer is 512, and the number of output nodes of the seventh layer is 4.
Preferably, the training process of the signal prediction model includes: inputting a training sample set; extracting signal characteristics to carry out classification training; wherein the training sample set and the testing sample set are both 48 x 48 pixels in size.
Preferably, the pressure sensor is a flexible film array pressure sensor, in step S1, the flexible film array pressure sensor acquires first signal data and then transmits the first signal data to the sensor signal conditioning device, the sensor signal conditioning device converts the first signal data into first conversion data after acquiring multiple channels of signals by the flexible film array pressure sensor, the controller transmits the first conversion data to a measurement signal processing and analyzing system which is internally provided with a signal prediction model based on a LeNet-5 neural network, the measurement signal processing and analyzing system trains the signal prediction model through preset data, and the measurement signal processing and analyzing system classifies the first conversion data through the trained signal prediction model.
Preferably, the brake system further comprises a pressure tester for detecting first test data of the internal contracting brake, the controller compares the first test data with the first signal data to obtain a difference value between the first test data and the first signal data, if the difference value is greater than a preset value, the controller feeds back a signal that the error is large, and if the difference value is less than or equal to the preset value, the controller feeds back a signal that the error is large.
Preferably, the pressure sensor further comprises a detection circuit for detecting detection data of the pressure sensor by a unit force detection algorithm, the unit force detection algorithm comprising: the AI range of the flexible film pressure sensor is set to be 0-5VDCThe flexible film pressure sensor comprises a flexible film pressure sensor, and further comprises an MODBUS register used for storing first signal data detected by the flexible film pressure sensor, wherein the reading of the MODBUS register is 0-50000, the pressure of a band-type brake unit detected by the flexible film pressure sensor is Fs, and Fs = C/(RH VI/(V)+-VI)) -F0, wherein VI = (AI/50000). V+RH is the variable resistance value, C is the conductance-pressure conversion coefficient, the dimension is kg, S, F0 is the initial pressure, V+Is 5VDC。
Preferably, the measurement signal processing and analyzing system interacts with the controller through a MODBUS protocol to acquire real-time measurement data, and an HMI of the measurement signal processing and analyzing system displays a classification result of the signal prediction model on the first signal data.
Preferably, the total braking force of the band-type brake is F1，F1=
Wherein
Is the sum of the stress of the sensor units, Ar is the pressure-bearing ratio, and the braking torque of the band-type brake when the mechanism stops running is F2，Tb=2F2And R mu, wherein Tb is the static braking torque, R is the radius of the brake wheel of the band-type brake, and mu is the friction coefficient.
The method comprises the steps of firstly detecting the pressure of a band-type brake through a multipoint pressure sensor to obtain first signal data including the pressure value of the band-type brake, then establishing a LeNet-5 neural network-based signal prediction model and training the signal prediction model, finally classifying the first signal data through the trained signal prediction model, inputting any set of brake shoe signals to be identified into the trained signal prediction model, extracting deep learning characteristics of a sample, and effectively judging whether the set of signals belong to a normal state or a fault state through a twice training method, so that the pressure state of the band-type brake can be known from the classified condition, the stress distribution condition of the band-type brake shoe can be visually shown in real time, and the real-time monitoring of the running state of a band-type brake device can be realized.
Drawings
FIG. 1 is a schematic structural diagram of a 4 x 6 pressure sensor array layout designed according to the force distribution of a brake pad of the brake;
FIG. 2 is a schematic diagram of a flexible film array pressure sensor of the present invention when detecting data and sending the data to a sensor signal conditioning device, and after collecting multiple signals, sending the data to a measurement signal processing and analyzing system;
FIG. 3 is a schematic diagram of the detection circuit of the present invention;
FIG. 4 is a graph showing the variation of a full-scale test when the detection circuit of the present invention detects the detection data of the pressure sensor through a unit force detection algorithm;
fig. 5 is a graph showing the variation of the repeated isobaric validation tests of the measurement signal processing and analyzing system of the present invention in simulating the operating state of the brake.
Detailed Description
The following are specific embodiments of the present invention and are further described with reference to the drawings, but the present invention is not limited to these embodiments.
Referring to fig. 1, fig. 2, fig. 3, fig. 4, and fig. 5, a method for diagnosing a brake fault based on a multipoint pressure sensor in the present embodiment includes the following steps:
s1: detecting the pressure of a band-type brake through a multipoint pressure sensor to obtain first signal data comprising the pressure value of the band-type brake;
s2: establishing a signal prediction model based on a LeNet-5 neural network and training the signal prediction model;
s3: the first signal data are classified through the trained signal prediction model, any set of brake shoe signals to be identified are given and input into the trained deep learning model, deep learning characteristics of samples are extracted, and the signals of the set are effectively judged to be in a normal state or a fault state through a twice training method.
The method comprises the steps of firstly detecting the pressure of a band-type brake through a multipoint pressure sensor to obtain first signal data including the pressure value of the band-type brake, then establishing a LeNet-5 neural network-based signal prediction model and training the signal prediction model, finally classifying the first signal data through the trained signal prediction model, inputting any set of brake shoe signals to be identified into the trained signal prediction model, extracting deep learning characteristics of a sample, and effectively judging whether the set of signals belong to a normal state or a fault state through a twice training method, so that the pressure state of the band-type brake can be known from the classified condition, the stress distribution condition of the band-type brake shoe can be visually shown in real time, and the real-time monitoring of the running state of a band-type brake device can be realized.
Step S1 collects first signal data including a left shoe sensor signal of a left shoe of the band brake and a right shoe sensor signal of a right shoe of the band brake through a 24-point pressure sensor of 4 × 6, the first signal data being classified according to a normal state and a failure state.
Step S1 may include preprocessing the first signal data, combining a plurality of 4 x 6 signals, and combining the signals into a 48 x 48 signal matrix using 48 sets of signals, wherein a set of signals includes a left shoe sensor signal and a right shoe sensor signal.
The signal prediction model may include seven layers; the first layer is an input layer, the first layer is original signal data, the picture size of the first layer is 48 × 1, and the channel is 1; the second layer is a convolutional layer, the input of the second layer is the output of the output layer, the filter size of the second layer is 5 x 5, the depth is 32, the second layer is filled with all 0 s, and the output matrix size of the second layer is 48 x 32; the third layer is a pooled layer, the input of the third layer is a 48 x 32 node matrix of the second layer output, the filter size of the third layer is 2 x 2, the step size of the length and width is 2, and the output matrix size of the third layer is 24 x 32; the fourth layer is a convolutional layer, the input of the fourth layer is the output of the third layer, the filter size of the fourth layer is 5 x 5, the depth is 64, the fourth layer is filled with all 0 s, and the output matrix size of the fourth layer is 24 x 64; the fifth layer is a pooling layer, the input of the fifth layer is a 24 x 64 node matrix of the fourth layer output, the filter size of the fifth layer is 2 x 2, the length and width steps are 2, and the output matrix size of the fifth layer is 12 x 64; the sixth layer is a fully-connected layer, the input of the sixth layer is the output of the fifth layer, the number of input nodes of the sixth layer is 12 × 64, the number of input nodes of the sixth layer is 9216, and the number of output nodes of the sixth layer is 512; the seventh layer is a full connection layer, the number of input nodes of the seventh layer is 512, and the number of output nodes of the seventh layer is 4.
The training process of the signal prediction model may include: inputting a training sample set; extracting signal characteristics to carry out classification training; wherein the training sample set and the testing sample set are both 48 x 48 pixels in size.
Referring to fig. 2, the pressure sensor may be a flexible film array pressure sensor, in step S1, the flexible film array pressure sensor acquires first signal data and then transmits the first signal data to the sensor signal conditioning device, the sensor signal conditioning device converts the first signal data into first conversion data after acquiring multiple channels of signals from the flexible film array pressure sensor, the controller transmits the first conversion data to a measurement signal processing and analyzing system having a signal prediction model based on a LeNet-5 neural network, the measurement signal processing and analyzing system trains the signal prediction model according to preset data, and the measurement signal processing and analyzing system classifies the first conversion data according to the trained signal prediction model.
The flexible film array pressure sensor is composed of a plurality of resistance type film pressure sensor units, and can statically and dynamically test the force between 2 surfaces in the direction vertical to the plane of the sensor. The sensor is prepared by printing silver electrode, force sensitive, insulating and glue on double-sided polyester substrate, packaging the upper and lower 2 layers of substrate face to face, pressing FPC interface device on the electrode, and selecting 26 pins with 1.0mm spacing. Each sensor cell can be considered as a resistor, and in a static (no force, no bending) condition, the resistance of the sensor is large (> 1M Ω). A corresponding decrease in the resistance of the sensor results after a force is applied to the active area of the sensor, the resistance becoming smaller the greater the force applied. Unlike dynamometers, strain gauges, and the like, thin film sensors typically have a force measurement accuracy in the range of about + -5% to + -25%, and existing sensor fabrication techniques do not guarantee the uniformity of each sensor in the array. The application combines the consistency of a force application system and a measurement correction method to improve the consistency of array units: the former helps to absorb errors introduced by force distribution through force application structure optimization to solve the problem of consistency of a force application system; the latter adopts array variable resistance measurement correction method to make the voltage division ratio of every detection unit in the array consistent. When the flexible film pressure sensor bears pressure, the pressure value has good positive correlation with the conductivity of the device.
The unit measuring range is an important model selection parameter of the flexible film array pressure sensor, and is calculated according to the following steps and methods: total pressure (Kg) = { [ brake torque (NM)/moment arm (M) ]/9.8}/μ, where the brake torque takes a nominal maximum value, μ is the brake pad friction coefficient, typically 0.35, brake pad unit area pressure (Kg/cm 2) = total pressure (Kg)/brake pad area, maximum pressure that the sensor sensitive area may experience = brake pad unit area pressure (Kg/cm 2) = sensor cell design size (cm 2), and the span nominal value (Kg) is taken as the sizing parameter based on the calculation result.
The method for diagnosing the fault of the band-type brake based on the multipoint pressure sensor in the embodiment may further include a pressure tester configured to detect first test data of the band-type brake, the controller compares the first test data with the first signal data to obtain a difference between the first test data and the first signal data, if the difference is greater than a preset value, the controller feeds back a "error is greater" signal, if the difference is less than or equal to the preset value, the controller feeds back a "pass" signal, and qualified data and error data may be obtained in real time. The pressure tester tests whether the reading of the pressure sensor is accurate.
Referring to fig. 3, as the method for diagnosing a band-type brake fault based on a multipoint pressure sensor in the present embodiment may further include a detection circuit for detecting detection data of the pressure sensor through a unit force detection algorithm, the unit force detection algorithm may include: the AI range of the flexible film pressure sensor can be set to 0-5VDCThe flexible film pressure sensor comprises a flexible film pressure sensor, and can further comprise an MODBUS register used for storing first signal data detected by the flexible film pressure sensor, wherein the reading of the MODBUS register is 0-50000, the pressure of a band-type brake unit detected by the flexible film pressure sensor is Fs, and Fs = C/(RH VI/(V)+-VI)) -F0, wherein VI = (AI/50000). V+RH is the variable resistance value, C is the conductance-pressure conversion coefficient, the dimension is kg, S, F0 is the initial pressure, V+Is 5VDC. When the flexible film pressure sensor bears pressure, the pressure value has good positive correlation with the conductivity of the device. The sensor is used as a variable resistor, the size of the resistor can be calculated by simply adopting a resistor voltage division mode through testing voltage, and the real-time resistor of the sensor can also be calculated through an operational circuit of an operational amplifier. And the calibration of the system is calculated and obtained according to F0= C/(RH VI 0/(V + -VI0)) and is used for eliminating deformation during installation of the sensor array and initial pressure generated by an assembly process. Referring to FIG. 4, Fs = C/(RH VI/(V + -VI)) -F0 is taken as a unitThe force detection algorithm simulates initial pressure of about 2kg applied during testing, unit force verifies that the test result is changed as a curve shown in figure 4 in the full range of the algorithm, and the test result shows that the algorithm design meets the expectation.
The measurement signal processing and analyzing system can be used for interactively acquiring real-time measurement data with the controller through an MODBUS protocol, and an HMI of the measurement signal processing and analyzing system displays a classification result of the signal prediction model on the first signal data. Referring to fig. 5, an initial pressure of about 2kg is applied during the test, and the repeated isobaric verification test result of the simulation of the working state of the brake is shown as the curve change shown in fig. 5, and the test result shows that the flexible film pressure sensor has good repeatability.
The pressure on the surface of the brake wheel when the brake is closed is the total braking force of the band-type brake, and the total braking force of the band-type brake can be F1，F1= 
Wherein
Is the sum of the stress of the sensor units, Ar is the bearing ratio, namely the sum of the stress areas of the sensors/the stress area of the friction lining, and the braking torque of the band-type brake when the mechanism stops operating at the end of the braking process is F2，Tb=2F2And R mu, wherein Tb is the static braking torque, R is the radius of the brake wheel of the band-type brake, and mu is the friction coefficient.
The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (6)
1. A band-type brake fault diagnosis method based on a multipoint pressure sensor is characterized by comprising the following steps:
s1: detecting the pressure of a band-type brake through a multipoint pressure sensor to obtain first signal data comprising the pressure value of the band-type brake;
s2: establishing a signal prediction model based on a LeNet-5 neural network and training the signal prediction model;
s3: classifying the first signal data through the trained signal prediction model;
step S1, collecting first signal data through a 24-point pressure sensor of 4-6 points, wherein the first signal data comprise a left brake shoe sensor signal of a left brake shoe of a band-type brake and a right brake shoe sensor signal of a right brake shoe of the band-type brake, and the first signal data are classified according to a normal state and a fault state;
step S1 includes preprocessing the first signal data, combining a plurality of 4 x 6 signals, and combining 48 x 48 signal matrices by combining 48 sets of signals, wherein a set of signals includes a left shoe sensor signal and a right shoe sensor signal;
the signal prediction model comprises seven layers; the first layer is an input layer, the first layer is original signal data, the picture size of the first layer is 48 × 1, and the channel is 1; the second layer is a convolutional layer, the input of the second layer is the output of the output layer, the filter size of the second layer is 5 x 5, the depth is 32, the second layer is filled with all 0 s, and the output matrix size of the second layer is 48 x 32; the third layer is a pooled layer, the input of the third layer is a 48 x 32 node matrix of the second layer output, the filter size of the third layer is 2 x 2, the step size of the length and width is 2, and the output matrix size of the third layer is 24 x 32; the fourth layer is a convolutional layer, the input of the fourth layer is the output of the third layer, the filter size of the fourth layer is 5 x 5, the depth is 64, the fourth layer is filled with all 0 s, and the output matrix size of the fourth layer is 24 x 64; the fifth layer is a pooling layer, the input of the fifth layer is a 24 x 64 node matrix of the fourth layer output, the filter size of the fifth layer is 2 x 2, the length and width steps are 2, and the output matrix size of the fifth layer is 12 x 64; the sixth layer is a fully-connected layer, the input of the sixth layer is the output of the fifth layer, the number of input nodes of the sixth layer is 12 × 64, the number of input nodes of the sixth layer is 9216, and the number of output nodes of the sixth layer is 512; the seventh layer is a full connection layer, the number of input nodes of the seventh layer is 512, and the number of output nodes of the seventh layer is 4;
the training process of the signal prediction model comprises the following steps: inputting a training sample set; extracting signal characteristics to carry out classification training; wherein the training sample set and the testing sample set are both 48 x 48 pixels in size.
2. The method for diagnosing the internal contracting brake fault based on the multipoint pressure sensor as claimed in claim 1, wherein: the pressure sensor is a flexible film array pressure sensor, the flexible film array pressure sensor detects unit force of a brake so as to obtain first signal data in step S1, the flexible film array pressure sensor sends the first signal data to the sensor signal conditioning device, the sensor signal conditioning device converts the first signal data into first conversion data after the flexible film array pressure sensor carries out multi-channel signal acquisition, the controller sends the first conversion data to a measurement signal processing and analyzing system which is internally provided with a signal prediction model based on a LeNet-5 neural network, the measurement signal processing and analyzing system trains the signal prediction model through preset data, and the measurement signal processing and analyzing system classifies the first conversion data through the trained signal prediction model.
3. The method for diagnosing the contracting brake fault based on the multipoint pressure sensor as claimed in claim 2, wherein: the controller compares the first test data with the first signal data to obtain a difference value between the first test data and the first signal data, feeds back a signal with a large error if the difference value is larger than a preset value, and feeds back a signal with a qualified error if the difference value is smaller than or equal to the preset value.
4. The method for diagnosing the contracting brake fault based on the multipoint pressure sensor as claimed in claim 3, wherein: further comprises a detection number for detecting the pressure sensor by the unit force detection algorithmAccording to the detection circuit, the unit force detection algorithm comprises: the AI range of the flexible film pressure sensor is set to be 0-5VDCThe flexible film pressure sensor comprises a flexible film pressure sensor, and further comprises an MODBUS register used for storing first signal data detected by the flexible film pressure sensor, wherein the reading of the MODBUS register is 0-50000, the pressure of a band-type brake unit detected by the flexible film pressure sensor is Fs, and Fs = C/(RH VI/(V)+-VI)) -F0, wherein VI = (AI/50000). V+RH is the variable resistance value, C is the conductance-pressure conversion coefficient, the dimension is kg, S, F0 is the initial pressure, V+Is 5VDC。
5. The method for diagnosing the contracting brake fault based on the multipoint pressure sensor as claimed in claim 4, wherein: and the unit force measurement signal processing and analyzing system is interacted with the controller through an MODBUS protocol to acquire real-time measurement data, and an HMI of the measurement signal processing and analyzing system displays a classification result of the signal prediction model on the first signal data.
6. The method for diagnosing the contracting brake fault based on the multipoint pressure sensor as claimed in claim 5, wherein: the total braking force of the band-type brake is F1，F1=
Wherein
Is the sum of the stress of the sensor units, Ar is the pressure-bearing ratio, and the braking torque of the band-type brake when the mechanism stops running is F2，Tb=2F2And R mu, wherein Tb is the static braking torque, R is the radius of the brake wheel of the band-type brake, and mu is the friction coefficient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911353305.XA CN111056395B (en) | 2019-12-25 | 2019-12-25 | Band-type brake fault diagnosis method based on multipoint pressure sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911353305.XA CN111056395B (en) | 2019-12-25 | 2019-12-25 | Band-type brake fault diagnosis method based on multipoint pressure sensor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111056395A CN111056395A (en) | 2020-04-24 |
| CN111056395B true CN111056395B (en) | 2021-09-03 |
Family
ID=70303731
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911353305.XA Active CN111056395B (en) | 2019-12-25 | 2019-12-25 | Band-type brake fault diagnosis method based on multipoint pressure sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111056395B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112630654A (en) * | 2020-12-11 | 2021-04-09 | 广东博智林机器人有限公司 | Band-type brake detection system and method |
| CN114775457A (en) * | 2022-03-16 | 2022-07-22 | 浙江广厦建设职业技术大学 | Detection device for repairing ancient bridge and detection method thereof |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108197014A (en) * | 2017-12-29 | 2018-06-22 | 东软集团股份有限公司 | Method for diagnosing faults, device and computer equipment |
| CN109406118A (en) * | 2018-10-15 | 2019-03-01 | 华中科技大学 | A kind of mechanical failure prediction method based on level convolutional neural networks |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN205772570U (en) * | 2016-06-02 | 2016-12-07 | 中钢集团武汉安全环保研究院有限公司 | A kind of brake condition monitoring and failure judgment device |
| US10671083B2 (en) * | 2017-09-13 | 2020-06-02 | Tusimple, Inc. | Neural network architecture system for deep odometry assisted by static scene optical flow |
| US20190095762A1 (en) * | 2017-09-25 | 2019-03-28 | Gyrfalcon Technology Inc. | Communications Between Internet of Things Devices Using A Two-dimensional Symbol Containing Multiple Ideograms |
| CN108178037A (en) * | 2017-12-30 | 2018-06-19 | 武汉大学 | A kind of elevator faults recognition methods based on convolutional neural networks |
| CN109969895B (en) * | 2019-04-15 | 2021-07-23 | 淄博东升电梯工程有限公司 | Fault prediction method based on elevator operation parameters, terminal and readable storage medium |
| CN110006585B (en) * | 2019-05-06 | 2023-10-24 | 上海掌门科技有限公司 | Data acquisition device and method of pressure sensor |
-
2019
- 2019-12-25 CN CN201911353305.XA patent/CN111056395B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108197014A (en) * | 2017-12-29 | 2018-06-22 | 东软集团股份有限公司 | Method for diagnosing faults, device and computer equipment |
| CN109406118A (en) * | 2018-10-15 | 2019-03-01 | 华中科技大学 | A kind of mechanical failure prediction method based on level convolutional neural networks |
Non-Patent Citations (1)
| Title |
|---|
| 深度学习在设备故障预测与健康管理中的作用;陈志强等;《仪器仪表学报》;20190930;第206-223页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111056395A (en) | 2020-04-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111056395B (en) | Band-type brake fault diagnosis method based on multipoint pressure sensor | |
| CN104573850A (en) | Method for evaluating state of thermal power plant equipment | |
| CN109838696A (en) | Pipeline fault diagnostic method based on convolutional neural networks | |
| CN101504333B (en) | Progressive health monitoring method for cable structure median cord system based on strain monitoring | |
| CN109710983B (en) | Diesel engine cylinder layered fault diagnosis method based on key performance indexes | |
| CN109230952B (en) | Method and system for monitoring tension and performance degradation of elevator traction steel belt | |
| GB2593851A (en) | Bearing reaction influence line curvature-based continuous beam damage identification method | |
| CN104880217B (en) | A kind of fault sensor signal reconstruct method based on the measured value degree of association | |
| CN106546439B (en) | A kind of combined failure diagnostic method of hydraulic AGC system | |
| CN112668526A (en) | Bolt group loosening positioning monitoring method based on deep learning and piezoelectric active sensing | |
| CN108204892B (en) | Roller set equipment fault detection method based on flexible array type pressure sensor | |
| CN107843370B (en) | Device and method for testing running resistance of rail train | |
| CN1120366C (en) | Fault detecting and diagnosing method based on non-linear spectral analysis | |
| US20190244467A1 (en) | Remote monitoring of a person and an automatic distribution of prescription drugs | |
| US20210231231A1 (en) | Pinch valve monitoring | |
| CN103235206A (en) | Transformer fault diagnosis method | |
| CN112816122B (en) | Bolt tightness degree monitoring method based on deep learning and piezoelectric active sensing | |
| CN113109666B (en) | Rail circuit fault diagnosis method based on deep convolutional neural network | |
| CN105699043B (en) | A kind of wind tunnel sensors that improve measure stability and the method for precision | |
| CN112660957B (en) | Early warning method and early warning system for elevator operation risk | |
| CN111931407A (en) | Structure reliability evaluation prediction method and system based on long-term monitoring data | |
| CN113705721A (en) | Joint probability density function difference diagnosis method for bridge support group void diseases | |
| Li et al. | Sensor fault localization with accumulated residual contribution rate for bridge SHM | |
| CN112109727B (en) | Braking force calibration method for unmanned vehicle in open-pit mine area | |
| CN113570478B (en) | Bridge health state intelligent evaluation method based on edge calculation |
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 |