CN114894483A - Bearing fault diagnosis method and device, computer equipment and storage medium - Google Patents
Bearing fault diagnosis method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114894483A CN114894483A CN202210639348.XA CN202210639348A CN114894483A CN 114894483 A CN114894483 A CN 114894483A CN 202210639348 A CN202210639348 A CN 202210639348A CN 114894483 A CN114894483 A CN 114894483A
- Authority
- CN
- China
- Prior art keywords
- fault
- bearing
- training
- oscillogram
- module
- 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.)
- Pending
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 238000012360 testing method Methods 0.000 claims description 93
- 238000012549 training Methods 0.000 claims description 79
- 238000013528 artificial neural network Methods 0.000 claims description 69
- 238000010586 diagram Methods 0.000 claims description 43
- 230000006870 function Effects 0.000 claims description 24
- 238000000605 extraction Methods 0.000 claims description 20
- 238000012216 screening Methods 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000012935 Averaging Methods 0.000 claims description 4
- 238000012790 confirmation Methods 0.000 claims description 3
- 238000009877 rendering Methods 0.000 claims description 2
- 238000013480 data collection Methods 0.000 abstract description 6
- 238000013473 artificial intelligence Methods 0.000 abstract description 5
- 238000011897 real-time detection Methods 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 abstract description 2
- 238000005096 rolling process Methods 0.000 description 14
- 238000004891 communication Methods 0.000 description 4
- 238000000354 decomposition reaction Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000006698 induction Effects 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000002405 diagnostic procedure Methods 0.000 description 2
- 238000009760 electrical discharge machining Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000010304 firing Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000004026 adhesive bonding Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The embodiment of the application belongs to the technical field of bearing detection in artificial intelligence, and relates to a bearing fault diagnosis method and device, computer equipment and a storage medium. This application fully draws the characteristic of equipment data collection under lacking the trouble sample, and real-time detection equipment's state judges which kind of trouble appears in equipment, has realized end-to-end diagnostic mode to antifriction bearing, simultaneously, utilizes the cavity convolution to draw the time domain picture, can enlarge the reception field and carry out accurate location to the trouble under the condition of not introducing extra parameter, can reduce the impression of noise to diagnosis in the industrial environment.
Description
Technical Field
The present application relates to the field of bearing detection technology in artificial intelligence, and in particular, to a bearing fault diagnosis method and apparatus, a computer device, and a storage medium.
Background
The equipment fault diagnosis is to judge the running state, the running life, the fault occurrence time and the type of the equipment. Fault diagnosis is mainly classified into two categories according to whether a fault occurs: before equipment fails, the running state of the equipment needs to be evaluated; after the equipment fails, the position, reason and degree of the equipment failure need to be judged, and maintenance decision is made. Methods for fault handling that are currently common in the industry include diagnostic methods based on expert systems, data-driven methods typified by artificial intelligence, multivariate statistical methods, and signal processing. The diagnosis method based on the expert system utilizes rich experience knowledge of experts, does not need mathematical modeling, has strong interpretability and is widely used in industry. However, the complicated equipment has more inference rules, and is easy to have the problems of matching conflict, combination explosion and low inference speed.
Rolling bearings are used as important parts of large-scale equipment and widely applied to the industrial fields of chemical industry, aviation, traffic and the like. The rolling bearing can cause the whole equipment to be incapable of normal operation and even damaged once the rolling bearing fails. The rolling bearing is abnormal mainly caused by abrasion, plastic deformation and gluing OF parts, and the states OF the parts can be classified into normal states (NC), inner raceway faults (IF), outer raceway faults (OF) and rolling element faults (RF) according to whether the parts are in fault or not and the parts in fault.
With the development of computer and artificial intelligence technologies, intelligent diagnostic methods represented by artificial intelligence are receiving more and more attention. The intelligent diagnosis method provides a powerful tool for solving more complicated equipment fault diagnosis. In order to obtain accurate training results, the models usually need to input a large amount of training data, but in reality, most equipment faults occur slowly, and it is difficult to collect enough training samples. Therefore, a method is needed to accurately diagnose a fault with a small number of fault samples.
Disclosure of Invention
The embodiment of the application aims to provide a bearing fault diagnosis method, a bearing fault diagnosis device, computer equipment and a storage medium, so as to solve the problem that a fault can be accurately diagnosed through a small number of fault samples.
In order to solve the above technical problem, an embodiment of the present application provides a bearing fault diagnosis method, which adopts the following technical solutions:
acquiring an original vibration signal to be detected, which is acquired when a bearing test board detects a bearing to be detected;
drawing a time domain waveform diagram corresponding to the original vibration signal to be tested to obtain a waveform diagram of the bearing to be tested;
calling a trained twin neural network and N fault type oscillograms, wherein the twin neural network comprises two sub-neural networks with the same structure and shared weight, each sub-neural network is composed of a hole convolution network and 10 layers of ResNet in series, each fault type oscillogram uniquely corresponds to one fault type, and N is a positive integer;
respectively and independently combining each fault type oscillogram with the oscillograms of the bearing to be tested to obtain N groups of oscillograms to be tested;
sequentially inputting the oscillogram groups to be detected to the trained twin neural network for image feature extraction operation to obtain N groups of image feature groups to be detected;
respectively calculating the similarity of the N groups of image feature groups to be tested according to an Euclidean distance algorithm to obtain N test results;
screening a target fault type oscillogram with the highest similarity to the oscillogram of the bearing to be tested according to the N test results;
and taking the fault type corresponding to the target sample time domain oscillogram as a fault diagnosis result of the bearing to be detected.
In order to solve the above technical problem, an embodiment of the present application further provides a bearing fault diagnosis device, which adopts the following technical scheme:
the signal acquisition module is used for acquiring an original vibration signal to be detected, which is acquired when the bearing test board detects a bearing to be detected;
the drawing module is used for drawing a time domain waveform diagram corresponding to the original vibration signal to be tested to obtain a waveform diagram of the bearing to be tested;
the device comprises a calling module, a judging module and a judging module, wherein the calling module is used for calling a trained twin neural network and N fault type oscillograms, the twin neural network comprises two sub-neural networks with the same structure and shared weight, the sub-neural networks are formed by serially connecting a cavity convolution network and 10 layers of ResNet, each fault type oscillogram uniquely corresponds to one fault type, and N is a positive integer;
the combination module is used for independently combining each fault type oscillogram and the bearing oscillogram to be tested respectively to obtain N groups of oscillograms to be tested;
the first image feature extraction module is used for sequentially inputting the oscillogram groups to be detected to the trained twin neural network for image feature extraction operation to obtain N groups of image feature groups to be detected;
the similarity calculation module is used for calculating the similarity of the N groups of image feature groups to be tested according to the Euclidean distance algorithm to obtain N test results;
the screening module is used for screening a target fault type oscillogram with the highest similarity to the oscillogram of the bearing to be tested according to the N test results;
and the result confirmation module is used for taking the fault type corresponding to the target sample time domain oscillogram as the fault diagnosis result of the bearing to be detected.
In order to solve the above technical problem, an embodiment of the present application further provides a computer device, which adopts the following technical solutions:
comprising a memory having computer readable instructions stored therein and a processor which when executed implements the steps of the bearing fault diagnosis method as described above.
In order to solve the above technical problem, an embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solutions:
the computer readable storage medium has stored thereon computer readable instructions which, when executed by a processor, implement the steps of the bearing fault diagnosis method as described above.
The application provides a bearing fault diagnosis method, which comprises the following steps: acquiring an original vibration signal to be detected, which is acquired when a bearing test board detects a bearing to be detected; drawing a time domain waveform diagram corresponding to the original vibration signal to be tested to obtain a waveform diagram of the bearing to be tested; calling a trained twin neural network and N fault type oscillograms, wherein the twin neural network comprises two sub-neural networks with the same structure and shared weight, each sub-neural network is composed of a hole convolution network and 10 layers of ResNet in series, each fault type oscillogram uniquely corresponds to one fault type, and N is a positive integer; respectively and independently combining each fault type oscillogram with the oscillograms of the bearing to be tested to obtain N groups of oscillograms to be tested; sequentially inputting the oscillogram groups to be detected to the trained twin neural network for image feature extraction operation to obtain N groups of image feature groups to be detected; respectively calculating the similarity of the N groups of image feature groups to be tested according to an Euclidean distance algorithm to obtain N test results; screening a target fault type oscillogram with the highest similarity to the oscillogram of the bearing to be tested according to the N test results; and taking the fault type corresponding to the target sample time domain oscillogram as a fault diagnosis result of the bearing to be detected. Compared with the prior art, the characteristics of the equipment data collection are fully extracted under the condition that a fault sample is lacked, the state of the equipment is detected in real time, which kind of faults occur in the equipment is judged, an end-to-end diagnosis mode is realized for a rolling bearing, meanwhile, a time domain graph is extracted by utilizing cavity convolution, the fault can be accurately positioned by enlarging a receptive field under the condition that extra parameters are not introduced, and the impression of noise on diagnosis in an industrial environment can be reduced.
Drawings
In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flowchart of an implementation of a bearing fault diagnosis method according to an embodiment of the present disclosure;
FIG. 3 is a schematic structural diagram of an embodiment of a twin neural network provided in an embodiment of the present application;
FIG. 4 is a flowchart illustrating an embodiment of obtaining a waveform diagram of a bearing to be tested according to an embodiment of the present disclosure;
FIG. 5 is a flowchart of one embodiment of obtaining a trained twin neural network according to an embodiment of the present disclosure;
FIG. 6 is a flow chart of one embodiment of obtaining a sample combination according to an embodiment of the present disclosure;
FIG. 7 is a diagram illustrating an embodiment of a composition training sample provided in accordance with an embodiment of the present application;
FIG. 8 is a schematic diagram of one embodiment of a compositional test sample provided in one embodiment of the present application;
fig. 9 is a schematic structural diagram of a bearing fault diagnosis device provided in the second embodiment of the present application;
fig. 10 is a schematic structural diagram of an embodiment of obtaining a waveform diagram of a bearing to be measured according to the second embodiment of the present application;
FIG. 11 is a schematic structural diagram of an embodiment of obtaining a trained twin neural network according to the second embodiment of the present application;
FIG. 12 is a schematic structural diagram of an embodiment of obtaining a sample combination according to the second embodiment of the present application;
FIG. 13 is a schematic block diagram of one embodiment of a computer device according to the present application.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof, in the description and claims of this application and the description of the above figures are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the above-described drawings are used for distinguishing between different objects and not for describing a particular order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have various communication client applications installed thereon, such as a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, mpeg compression standard Audio Layer 3), MP4 players (Moving Picture Experts Group Audio Layer IV, mpeg compression standard Audio Layer 4), laptop portable computers, desktop computers, and the like.
The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.
It should be noted that the bearing fault diagnosis method provided in the embodiments of the present application is generally executed by a server/terminal device, and accordingly, the bearing fault diagnosis apparatus is generally disposed in the server/terminal device.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Example one
With continuing reference to fig. 2, a flowchart of an implementation of a bearing fault diagnosis method provided in an embodiment of the present application is shown, and for convenience of description, only the portion related to the present application is shown.
The bearing fault diagnosis method comprises the following steps:
step S201: and acquiring an original vibration signal to be detected, which is acquired when the bearing test board detects the bearing to be detected.
In the present embodiment, the bearing test stand consists of a 2 horsepower induction motor, a torque sensor/encoder, load motor and control electronics. To obtain data for a failed bearing, a single point failure was introduced into the test bearing using electrical discharge machining. Specifically, the test bearing is mounted on an induction firing shaft, and during operation of the bearing, vibration data is collected using an accelerator sensor that is attached to the housing using a magnetic bottom. The vibration signal is collected by a 16-channel DAT recorder, the sampling frequency of the digital signal is 12khz, the sampling frequency of the driving end is 48khz, and it should be understood that the example of detecting the bearing to be detected by the bearing test bench is only for convenience of understanding and is not limited to the present application.
In the embodiment of the application, the fault data of the 12k driving end under the load of 1hp (the motor speed is 1772RPM) is selected as the initial vibration signal to be measured.
Step S202: and drawing a time domain waveform diagram corresponding to the original vibration signal to be detected to obtain a waveform diagram of the bearing to be detected.
Step S203: and calling the trained twin neural network and N fault type oscillograms, wherein the twin neural network comprises two sub-neural networks with the same structure and shared weight, each sub-neural network is formed by serially connecting a hole convolution network and 10 layers of ResNet, each fault type oscillogram uniquely corresponds to one fault type, and N is a positive integer.
In the embodiment of the present application, as shown in fig. 3, two identical neural networks are established in the twin neural network through identical network structures and shared weights, and each neural network is composed of a hole Convolution network (Atrous Convolution) and 10 layers of ResNet in series.
In the embodiment of the application, the CNN is used for convolution, so that the limitation of the reception field is received, and the fault diagnosis effect is easily interfered by high-frequency noise in an industrial environment. The characteristics of the time domain graph are extracted by utilizing the cavity convolution, so that the fault can be accurately positioned by enlarging the receptive field under the condition of not introducing additional parameters.
Step S204: and respectively and independently combining each fault type oscillogram with the oscillogram of the bearing to be tested to obtain N groups of oscillograms to be tested.
Step S205: and inputting the oscillogram groups to be detected into the trained twin neural network in sequence to perform image feature extraction operation, thereby obtaining N groups of image feature groups to be detected.
Step S206: and respectively calculating the similarity of the N groups of image feature groups to be tested according to the Euclidean distance algorithm to obtain N test results.
Step S207: and screening a target fault type oscillogram with the highest similarity to the oscillogram of the bearing to be tested according to the N test results.
Step S208: and taking the fault type corresponding to the target sample time domain oscillogram as a fault diagnosis result of the bearing to be detected.
In practical application, a test task is composed of N pairs of samples, and each pair of time-frequency graphs contains one same test sample
And a training sample x j (j ═ 1,2, … N), where j represents the jth fault condition. The N test samples are each randomly sampled from a sample of the N fault states. Then test the sample
Sample x of j-th working condition jn Can be expressed as
Which condition c the test sample belongs to can be expressed as:
in the embodiment of the application, in a scene of the rolling bearing, the characteristics of the data acquired by the equipment are fully extracted under the condition of lacking a fault sample, the state of the equipment is detected in real time, which kind of fault occurs in the equipment is judged, and an end-to-end diagnosis mode is realized for the rolling bearing.
In an embodiment of the present application, a bearing fault diagnosis method is provided, including: acquiring an original vibration signal to be detected, which is acquired when a bearing test board detects a bearing to be detected; drawing a time domain waveform diagram corresponding to the original vibration signal to be detected to obtain a waveform diagram of the bearing to be detected; calling a trained twin neural network and N fault type oscillograms, wherein the twin neural network comprises two sub-neural networks with the same structure and shared weight, each sub-neural network is composed of a cavity convolution network and 10 layers of ResNet in series, each fault type oscillogram uniquely corresponds to one fault type, and N is a positive integer; respectively and independently combining each fault type oscillogram with the oscillograms of the bearings to be tested to obtain N groups of oscillograms to be tested; sequentially inputting the oscillogram groups to be detected into the trained twin neural network for image feature extraction operation to obtain N groups of image feature groups to be detected; respectively calculating the similarity of N groups of image feature groups to be tested according to an Euclidean distance algorithm to obtain N test results; screening a target fault type oscillogram with the highest similarity to the oscillogram of the bearing to be tested according to the N test results; and taking the fault type corresponding to the target sample time domain oscillogram as a fault diagnosis result of the bearing to be detected. Compared with the prior art, the characteristics of the equipment data collection are fully extracted under the condition that a fault sample is lacked, the state of the equipment is detected in real time, which kind of faults occur in the equipment is judged, an end-to-end diagnosis mode is realized for a rolling bearing, meanwhile, a time domain graph is extracted by utilizing cavity convolution, the fault can be accurately positioned by enlarging a receptive field under the condition that extra parameters are not introduced, and the impression of noise on diagnosis in an industrial environment can be reduced.
Continuing to refer to fig. 4, a flowchart of a specific implementation of obtaining a waveform diagram of a bearing to be tested according to an embodiment of the present application is shown, and for convenience of description, only the relevant portions of the present application are shown.
In some optional implementations of this embodiment, after step S201, the method further includes: step S401, step S202 includes: step S402.
Step S401: and performing wavelet conversion operation on the original vibration signal to be detected according to the discrete wavelet function to obtain the de-noised vibration signal to be detected.
Step S402: and drawing a time domain oscillogram corresponding to the de-noised vibration signal to be detected to obtain a bearing oscillogram to be detected.
In this application embodiment, the vibrations acceleration signal of gathering through the sensor is comparatively mixed and disorderly, can not reach fine failure diagnosis effect usually. The signal can be effectively denoised by using wavelet transform. Common one-dimensional discrete wavelet functions comprise a Haar wavelet, a Daubechies wavelet and a Coifle wavelet, and through tests, the 'db 3' in the Daubechies wavelet is selected as a wavelet decomposition function, the layer number 3 is selected as a decomposition layer number, and an approximate coefficient of a third layer is extracted.
With continued reference to fig. 5, a flowchart of a specific implementation of obtaining a trained twin neural network provided in an embodiment of the present application is shown, and for convenience of illustration, only the relevant portions of the present application are shown.
In some optional implementations of this embodiment, before step S203, the method further includes:
step S501: acquiring N groups of sample sets, wherein the sample sets comprise training data and test data;
step S502: respectively inputting training data and test data of the same group into an original twin neural network for image feature extraction to obtain training feature data and test feature data;
step S503: calculating training characteristic data and a training Euclidean distance of the test characteristic data according to a Euclidean example algorithm;
step S504: inputting the training Euclidean distance to a sigmoid layer for normalization operation to obtain similar training similarity probability;
step S505: constructing a regular cross entropy loss function according to the training similarity probability;
step S506: and carrying out model training operation on the original twin neural network according to the regular cross entropy loss function to obtain the trained twin neural network.
In the embodiment of the application, the training task is composed of a set of a pair of randomly extracted time domain graph sample pairs, and each pair of sample pairs comprises two fault types from the same type or different types. For ith time domain graph
To indicate, the corresponding labels are denoted
Inputting a training task into a model to obtain the similarity probability p of two training samples i The trained model can be obtained by performing multiple rounds of training using the optimizer and the loss function specified below.
With continued reference to fig. 6, a flowchart of a specific implementation of obtaining a sample combination provided in an embodiment of the present application is shown, and for convenience of illustration, only the relevant portions of the present application are shown.
In some optional implementations of this embodiment, before step S501, the method further includes:
step S601: acquiring N fault vibration signals corresponding to the N fault types;
step S602: performing wavelet conversion operation on the N fault vibration signals according to a discrete wavelet function to obtain N de-noising fault vibration signals;
step S603: respectively carrying out equipartition operation on each denoising fault vibration signal to obtain N groups of fault training signals and fault testing signals;
step S604: respectively drawing time domain oscillograms corresponding to the fault training signals and the fault testing signals to obtain N groups of training oscillograms and testing oscillograms;
step S605: training data is constructed in the training waveform diagram according to the moving pane, and test data is constructed in the test waveform diagram according to the non-overlapping pane.
In the embodiment OF the present application, a common normal state (NC), inner race fault (IF), outer race fault (OF), and rolling element fault (RF) are assumed, depending on the fault state. Consider that each fault condition includes three types: 0.007 inches, 0.014 inches, 0.021 inches, so there are 10 failure types in total. The fault type specification is shown in the following table:
table 1 description of fault types
And drawing the decomposed sensor signals into a time domain waveform diagram. The data set for each type of failure constitutes a data set. A total of 10 training data sets and 10 test data sets are generated. The specific construction mode is as follows: the data for each fault condition is divided into two parts, half of the vibration signal data is used to generate training data, and the other half of the vibration signal data is used to generate test data. Each training sample is composed of 2048 points of moving window panes with the moving step size of 150 points, as shown in fig. 7. The test sample consists of moving panes of the same size, which do not overlap each other, as shown in fig. 8.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware associated with computer readable instructions, which can be stored in a computer readable storage medium, and when executed, can include processes of the embodiments of the methods described above. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
Example two
With further reference to fig. 9, as an implementation of the method shown in fig. 2, the present application provides an embodiment of a bearing fault diagnosis apparatus, which corresponds to the embodiment of the method shown in fig. 2, and which can be applied to various electronic devices.
As shown in fig. 9, the bearing failure diagnosis apparatus 200 of the present embodiment includes: the image processing system comprises a signal acquisition module 201, a drawing module 202, a calling module 203, a combination module 204, a first image feature extraction module 205, a similarity calculation module 206, a screening module 207 and a result confirmation module 208. Wherein:
the signal acquisition module 201 is used for acquiring an original vibration signal to be detected, which is acquired when the bearing test board detects a bearing to be detected;
the drawing module 202 is used for drawing a time domain waveform diagram corresponding to the original vibration signal to be tested to obtain a waveform diagram of the bearing to be tested;
the calling module 203 is used for calling the trained twin neural network and N fault type oscillograms, wherein the twin neural network comprises two sub-neural networks with the same structure and shared weight, each sub-neural network is formed by serially connecting a hole convolution network and 10 layers of ResNet, each fault type oscillogram uniquely corresponds to one fault type, and N is a positive integer;
the combination module 204 is used for separately combining each fault type oscillogram with the bearing oscillogram to be tested to obtain N groups of oscillograms to be tested;
the first image feature extraction module 205 is configured to sequentially input the oscillogram groups to be detected to the trained twin neural network for image feature extraction operation, so as to obtain N groups of image feature groups to be detected;
the similarity calculation module 206 is configured to calculate similarities of the N groups of image feature groups to be tested according to an euclidean distance algorithm, so as to obtain N test results;
the screening module 207 is used for screening a target fault type oscillogram with the highest similarity to the oscillogram of the bearing to be tested according to the N test results;
and the result confirming module 208 is configured to use the fault type corresponding to the target sample time domain waveform diagram as a fault diagnosis result of the bearing to be tested.
In the present embodiment, the bearing test stand consists of a 2 horsepower induction motor, a torque sensor/encoder, load motor and control electronics. To obtain data for a failed bearing, a single point failure was introduced into the test bearing using electrical discharge machining. Specifically, the test bearing is mounted on an induction firing shaft, and during operation of the bearing, vibration data is collected using an accelerator sensor that is attached to the housing using a magnetic bottom. The vibration signal is collected by a 16-channel DAT recorder, the sampling frequency of the digital signal is 12khz, the sampling frequency of the driving end is 48khz, and it should be understood that the example of detecting the bearing to be detected by the bearing test bench is only for convenience of understanding and is not limited to the present application.
In the embodiment of the application, the fault data of the 12k driving end under the load of 1hp (the motor speed is 1772RPM) is selected as the initial vibration signal to be measured.
In the embodiment of the present application, as shown in fig. 3, two identical neural networks are established in the twin neural network through identical network structures and shared weights, and each neural network is composed of a hole Convolution network (Atrous Convolution) and 10 layers of ResNet in series.
In the embodiment of the application, the CNN is used for convolution, so that the limitation of the reception field is received, and the fault diagnosis effect is easily interfered by high-frequency noise in an industrial environment. The characteristics of the time domain graph are extracted by utilizing the cavity convolution, so that the fault can be accurately positioned by enlarging the receptive field under the condition of not introducing additional parameters.
In practical application, a test task is composed of N pairs of samples, and each pair of time-frequency graphs contains one same test sample
And a training sample x j (j ═ 1,2, … N), where j represents the jth fault condition. The N test samples are each randomly sampled from a sample of the N fault states. Then test the sample
Sample x of j-th working condition jn Can be expressed as
Which of the conditions c the test sample belongs to can be expressed as:
in the embodiment of the application, in a scene of the rolling bearing, the characteristics of the data acquired by the equipment are fully extracted under the condition of lacking a fault sample, the state of the equipment is detected in real time, which kind of fault occurs in the equipment is judged, and an end-to-end diagnosis mode is realized for the rolling bearing.
In an embodiment of the present application, there is provided a bearing fault diagnosis apparatus 200 including: the signal acquisition module 201 is used for acquiring an original vibration signal to be detected, which is acquired when the bearing test board detects a bearing to be detected; the drawing module 202 is used for drawing a time domain waveform diagram corresponding to the original vibration signal to be tested to obtain a waveform diagram of the bearing to be tested; the calling module 203 is used for calling the trained twin neural network and N fault type oscillograms, wherein the twin neural network comprises two sub-neural networks with the same structure and shared weight, each sub-neural network is formed by serially connecting a hole convolution network and 10 layers of ResNet, each fault type oscillogram uniquely corresponds to one fault type, and N is a positive integer; the combination module 204 is used for separately combining each fault type oscillogram with the bearing oscillogram to be tested to obtain N groups of oscillograms to be tested; the first image feature extraction module 205 is configured to sequentially input the oscillogram groups to be detected to the trained twin neural network for image feature extraction operation, so as to obtain N groups of image feature groups to be detected; the similarity calculation module 206 is configured to calculate similarities of the N groups of image feature groups to be tested according to an euclidean distance algorithm, so as to obtain N test results; the screening module 207 is used for screening a target fault type oscillogram with the highest similarity to the oscillogram of the bearing to be tested according to the N test results; and the result confirming module 208 is configured to use the fault type corresponding to the target sample time domain waveform diagram as a fault diagnosis result of the bearing to be tested. Compared with the prior art, the characteristics of the equipment data collection are fully extracted under the condition that a fault sample is lacked, the state of the equipment is detected in real time, which kind of faults occur in the equipment is judged, an end-to-end diagnosis mode is realized for a rolling bearing, meanwhile, a time domain graph is extracted by utilizing cavity convolution, the fault can be accurately positioned by enlarging a receptive field under the condition that extra parameters are not introduced, and the impression of noise on diagnosis in an industrial environment can be reduced.
Continuing to refer to fig. 10, a schematic structural diagram of a specific implementation of obtaining a waveform diagram of a bearing to be tested according to the second embodiment of the present application is shown, and for convenience of description, only the relevant portions of the application are shown.
In some optional implementations of the present embodiment, the bearing fault diagnosis apparatus 200 further includes: the wavelet transform module 209 and the rendering module 202 comprise: render submodule 2021, wherein:
the wavelet conversion module 209 is configured to perform a wavelet conversion operation on the original vibration signal to be detected according to the discrete wavelet function to obtain a denoised vibration signal to be detected;
the drawing submodule 2021 is configured to draw a time domain waveform diagram corresponding to the denoised vibration signal to be measured, so as to obtain a waveform diagram of the bearing to be measured.
In this application embodiment, the vibrations acceleration signal of gathering through the sensor is comparatively mixed and disorderly, can not reach fine failure diagnosis effect usually. The signal can be effectively denoised by using wavelet transform. Common one-dimensional discrete wavelet functions comprise a Haar wavelet, a Daubechies wavelet and a Coifle wavelet, and through tests, the 'db 3' in the Daubechies wavelet is selected as a wavelet decomposition function, the layer number 3 is selected as a decomposition layer number, and an approximate coefficient of a third layer is extracted.
Continuing to refer to fig. 11, a schematic structural diagram of a specific implementation of the second embodiment of the present application for obtaining a trained twin neural network is shown, and for convenience of illustration, only the relevant portions of the present application are shown.
In some optional implementations of the present embodiment, the bearing fault diagnosis apparatus 200 further includes:
a sample set obtaining module 210, configured to obtain N sets of sample sets, where a sample set includes training data and test data;
the second image feature extraction module 211 is configured to input training data and test data of the same group to the primitive twin neural network for image feature extraction, so as to obtain training feature data and test feature data;
the Euclidean distance calculation module 212 is used for calculating the training Euclidean distance of the training characteristic data and the testing characteristic data according to the Euclidean example algorithm;
the normalization module 213 is configured to input the training euclidean distance to a sigmoid layer for normalization operation, so as to obtain a similar training similarity probability;
a loss function construction module 214, configured to construct a regular cross entropy loss function according to the training similarity probability;
and the model training module 215 is configured to perform model training operation on the original twin neural network according to the regular cross entropy loss function to obtain a trained twin neural network.
In the embodiment of the application, the training task is composed of a set of a pair of randomly extracted time domain graph sample pairs, and each pair of sample pairs comprises two fault types from the same type or different types. For ith time domain graph
To indicate, the corresponding labels are denoted
Inputting a training task into a model to obtain the similarity probability p of two training samples i The trained model can be obtained by performing multiple rounds of training using the optimizer and the loss function specified below.
Continuing to refer to fig. 12, a schematic structural diagram of a specific implementation of obtaining a sample combination provided in example two of the present application is shown, and for convenience of illustration, only the relevant portions of the present application are shown.
In some optional implementations of the present embodiment, the bearing fault diagnosis apparatus 200 further includes:
a fault signal acquisition module 216, configured to acquire N fault vibration signals corresponding to the N fault types;
the wavelet transformation module 217 is configured to perform wavelet transformation operation on the N fault vibration signals according to a discrete wavelet function to obtain N denoising fault vibration signals;
the averaging module 218 is configured to perform averaging operation on each denoising fault vibration signal to obtain N groups of fault training signals and fault test signals;
a fault drawing module 219, configured to draw time domain oscillograms corresponding to the fault training signal and the fault testing signal, respectively, to obtain N sets of training oscillograms and testing oscillograms;
and the data construction module 220 is configured to construct training data in the training oscillogram according to the moving pane, and construct test data in the test oscillogram according to the non-overlapping pane.
In the embodiment OF the present application, a common normal state (NC), inner race fault (IF), outer race fault (OF), and rolling element fault (RF) are assumed, depending on the fault state. Consider that each fault condition includes three types: 0.007 inches, 0.014 inches, 0.021 inches, so there are 10 fault types. The fault type specification is shown in the following table:
table 1 description of fault types
And drawing the decomposed sensor signals into a time domain waveform diagram. The data set for each type of failure constitutes a data set. A total of 10 training data sets and 10 test data sets are generated. The specific construction mode is as follows: the data for each fault condition is divided into two parts, half of the vibration signal data is used to generate training data, and the other half of the vibration signal data is used to generate test data. Each training sample is composed of 2048 points of moving window panes with the moving step size of 150 points, as shown in fig. 7. The test sample consists of moving panes of the same size, which do not overlap each other, as shown in fig. 8.
In order to solve the technical problem, an embodiment of the present application further provides a computer device. Referring to fig. 13, fig. 13 is a block diagram of a basic structure of a computer device according to the present embodiment.
The computer device 300 includes a memory 310, a processor 320, and a network interface 330 communicatively coupled to each other via a system bus. It is noted that only computer device 300 having components 310 and 330 is shown, but it is understood that not all of the shown components are required and that more or fewer components may alternatively be implemented. As will be understood by those skilled in the art, the computer device is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.
The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer equipment can carry out man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like.
The memory 310 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the storage 310 may be an internal storage unit of the computer device 300, such as a hard disk or a memory of the computer device 300. In other embodiments, the memory 310 may also be an external storage device of the computer device 300, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, provided on the computer device 300. Of course, the memory 310 may also include both internal and external storage devices of the computer device 300. In this embodiment, the memory 310 is generally used for storing an operating system installed in the computer device 300 and various application software, such as computer readable instructions of a bearing fault diagnosis method. In addition, the memory 310 may also be used to temporarily store various types of data that have been output or are to be output.
The processor 320 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 320 is generally operative to control overall operation of the computer device 300. In this embodiment, the processor 320 is configured to execute computer readable instructions stored in the memory 310 or process data, such as computer readable instructions for executing the bearing fault diagnosis method.
The network interface 330 may include a wireless network interface or a wired network interface, and the network interface 330 is generally used to establish a communication connection between the computer device 300 and other electronic devices.
The application provides a computer equipment, the characteristic of fully extracting equipment data collection under lacking the trouble sample, which kind of trouble appears in the state of real-time detection equipment, judgement equipment, realized end-to-end diagnostic mode to antifriction bearing, simultaneously, utilize the cavity convolution to extract the time domain picture, can enlarge the impression of feeling wild to carrying out accurate location to the trouble under the condition of not introducing extra parameter, can reduce noise among the industrial environment impression to the diagnosis.
The present application further provides another embodiment, which is to provide a computer-readable storage medium storing computer-readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the bearing fault diagnosis method as described above.
The application provides a computer readable storage medium, fully extracts the characteristics of equipment data collection under lacking the trouble sample, and real-time detection equipment's state judges which kind of trouble appears in equipment, has realized end-to-end diagnosis mode to antifriction bearing, simultaneously, utilizes the cavity convolution to extract the time domain picture, can enlarge the sense field and carry out accurate location to the trouble under the condition of not introducing extra parameter, can reduce the impression of noise to diagnosis among the industrial environment.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
It is to be understood that the above-described embodiments are merely illustrative of some, but not restrictive, of the broad invention, and that the appended drawings illustrate preferred embodiments of the invention and do not limit the scope of the invention. This application is capable of embodiments in many different forms and is provided for the purpose of enabling a thorough understanding of the disclosure of the application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that the present application may be practiced without modification or with equivalents of some of the features described in the foregoing embodiments. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields and are within the protection scope of the present application.
Claims (10)
1. A bearing fault diagnosis method, comprising the steps of:
acquiring an original vibration signal to be detected, which is acquired when a bearing test board detects a bearing to be detected;
drawing a time domain waveform diagram corresponding to the original vibration signal to be tested to obtain a waveform diagram of the bearing to be tested;
calling a trained twin neural network and N fault type oscillograms, wherein the twin neural network comprises two sub-neural networks with the same structure and shared weight, each sub-neural network is composed of a hole convolution network and 10 layers of ResNet in series, each fault type oscillogram uniquely corresponds to one fault type, and N is a positive integer;
respectively and independently combining each fault type oscillogram with the oscillograms of the bearing to be tested to obtain N groups of oscillograms to be tested;
sequentially inputting the oscillogram groups to be detected to the trained twin neural network for image feature extraction operation to obtain N groups of image feature groups to be detected;
respectively calculating the similarity of the N groups of image feature groups to be tested according to an Euclidean distance algorithm to obtain N test results;
screening a target fault type oscillogram with the highest similarity to the oscillogram of the bearing to be tested according to the N test results;
and taking the fault type corresponding to the target sample time domain oscillogram as a fault diagnosis result of the bearing to be detected.
2. The bearing fault diagnosis method according to claim 1, wherein after the step of obtaining the original vibration signal to be tested collected when the bearing test bench tests the bearing to be tested, the method further comprises the following steps:
performing wavelet conversion operation on the original vibration signal to be detected according to a discrete wavelet function to obtain a de-noised vibration signal to be detected;
the step of drawing a time domain oscillogram corresponding to the original vibration signal to be tested to obtain a oscillogram of the bearing to be tested specifically comprises the following steps:
and drawing a time domain oscillogram corresponding to the de-noised vibration signal to be detected to obtain the oscillogram of the bearing to be detected.
3. The bearing fault diagnosis method according to claim 1, characterized in that before the step of invoking the trained twin neural network and the N fault type oscillograms, the method specifically comprises:
acquiring N groups of sample sets, wherein the sample sets comprise training data and test data;
respectively inputting training data and test data of the same group into an original twin neural network for image feature extraction to obtain training feature data and test feature data;
calculating the training Euclidean distance of the training characteristic data and the testing characteristic data according to a Euclidean example algorithm;
inputting the training Euclidean distance to a sigmoid layer for normalization operation to obtain similar training similarity probability;
constructing a regular cross entropy loss function according to the training similarity probability;
and carrying out model training operation on the original twin neural network according to the regular cross entropy loss function to obtain the trained twin neural network.
4. The bearing fault diagnosis method according to claim 3, characterized in that before said step of obtaining N sets of sample sets, wherein said sample sets comprise training data and test data, further comprising the steps of:
acquiring N fault vibration signals corresponding to the N fault types;
performing wavelet conversion operation on the N fault vibration signals according to a discrete wavelet function to obtain N de-noising fault vibration signals;
respectively carrying out equipartition operation on each denoising fault vibration signal to obtain N groups of fault training signals and fault testing signals;
respectively drawing time domain oscillograms corresponding to the fault training signals and the fault testing signals to obtain N groups of training oscillograms and testing oscillograms;
and constructing the training data in the training oscillogram according to the moving window pane, and constructing the test data in the test oscillogram according to the non-overlapping window pane.
5. A bearing failure diagnosis device characterized by comprising:
the signal acquisition module is used for acquiring an original vibration signal to be detected, which is acquired when the bearing test board detects a bearing to be detected;
the drawing module is used for drawing a time domain waveform diagram corresponding to the original vibration signal to be tested to obtain a waveform diagram of the bearing to be tested;
the device comprises a calling module, a judging module and a judging module, wherein the calling module is used for calling a trained twin neural network and N fault type oscillograms, the twin neural network comprises two sub-neural networks with the same structure and shared weight, the sub-neural networks are formed by serially connecting a cavity convolution network and 10 layers of ResNet, each fault type oscillogram uniquely corresponds to one fault type, and N is a positive integer;
the combination module is used for independently combining each fault type oscillogram with the bearing oscillogram to be tested to obtain N groups of oscillogram groups to be tested;
the first image feature extraction module is used for sequentially inputting the oscillogram groups to be detected to the trained twin neural network for image feature extraction operation to obtain N groups of image feature groups to be detected;
the similarity calculation module is used for calculating the similarity of the N groups of image feature groups to be tested according to the Euclidean distance algorithm to obtain N test results;
the screening module is used for screening a target fault type oscillogram with the highest similarity to the oscillogram of the bearing to be tested according to the N test results;
and the result confirmation module is used for taking the fault type corresponding to the target sample time domain oscillogram as the fault diagnosis result of the bearing to be detected.
6. The bearing fault diagnosis device according to claim 5, characterized in that the device further comprises: a wavelet transform module, the rendering module comprising: drawing a submodule, wherein:
the wavelet conversion module is used for performing wavelet conversion operation on the original vibration signal to be detected according to a discrete wavelet function to obtain a de-noised vibration signal to be detected;
and the drawing submodule is used for drawing a time domain oscillogram corresponding to the de-noised vibration signal to be tested to obtain the oscillogram of the bearing to be tested.
7. The bearing fault diagnosis device according to claim 5, characterized in that the device further comprises:
the device comprises a sample set acquisition module, a data acquisition module and a data processing module, wherein the sample set acquisition module is used for acquiring N groups of sample sets, and the sample sets comprise training data and test data;
the second image feature extraction module is used for inputting the training data and the test data of the same group into the original twin neural network for image feature extraction to obtain training feature data and test feature data;
the Euclidean distance calculation module is used for calculating the training Euclidean distance of the training characteristic data and the testing characteristic data according to the Euclidean example algorithm;
the normalization module is used for inputting the training Euclidean distance to a sigmoid layer to carry out normalization operation to obtain similar training similarity probability;
the loss function construction module is used for constructing a regular cross entropy loss function according to the training similarity probability;
and the model training module is used for carrying out model training operation on the original twin neural network according to the regular cross entropy loss function to obtain the trained twin neural network.
8. The bearing fault diagnosis device according to claim 7, characterized in that the device further comprises:
the fault signal acquisition module is used for acquiring N fault vibration signals corresponding to the N fault types;
the wavelet conversion module is used for performing wavelet conversion operation on the N fault vibration signals according to a discrete wavelet function to obtain N de-noising fault vibration signals;
the averaging module is used for carrying out averaging operation on each denoising fault vibration signal to obtain N groups of fault training signals and fault testing signals;
the fault drawing module is used for respectively drawing time domain oscillograms corresponding to the fault training signals and the fault testing signals to obtain N groups of training oscillograms and testing oscillograms;
and the data construction module is used for constructing the training data in the training oscillogram according to the moving pane and constructing the test data in the test oscillogram according to the non-overlapping pane.
9. Computer apparatus comprising a memory having computer readable instructions stored therein and a processor which when executed implements the steps of the bearing fault diagnosis method of any one of claims 1 to 4.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon computer readable instructions which, when executed by a processor, implement the steps of the bearing fault diagnosis method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210639348.XA CN114894483A (en) | 2022-06-07 | 2022-06-07 | Bearing fault diagnosis method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210639348.XA CN114894483A (en) | 2022-06-07 | 2022-06-07 | Bearing fault diagnosis method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114894483A true CN114894483A (en) | 2022-08-12 |
Family
ID=82728039
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210639348.XA Pending CN114894483A (en) | 2022-06-07 | 2022-06-07 | Bearing fault diagnosis method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114894483A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112734734A (en) * | 2021-01-13 | 2021-04-30 | 北京联合大学 | Railway tunnel crack detection method based on improved residual error network |
| CN113191215A (en) * | 2021-04-12 | 2021-07-30 | 西安理工大学 | Rolling bearing fault diagnosis method integrating attention mechanism and twin network structure |
| CN113627317A (en) * | 2021-08-06 | 2021-11-09 | 安徽工业大学 | Motor bearing fault diagnosis method based on single sample learning |
| CN113655348A (en) * | 2021-07-28 | 2021-11-16 | 国网湖南省电力有限公司 | Power equipment partial discharge fault diagnosis method based on deep twin network, system terminal and readable storage medium |
-
2022
- 2022-06-07 CN CN202210639348.XA patent/CN114894483A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112734734A (en) * | 2021-01-13 | 2021-04-30 | 北京联合大学 | Railway tunnel crack detection method based on improved residual error network |
| CN113191215A (en) * | 2021-04-12 | 2021-07-30 | 西安理工大学 | Rolling bearing fault diagnosis method integrating attention mechanism and twin network structure |
| CN113655348A (en) * | 2021-07-28 | 2021-11-16 | 国网湖南省电力有限公司 | Power equipment partial discharge fault diagnosis method based on deep twin network, system terminal and readable storage medium |
| CN113627317A (en) * | 2021-08-06 | 2021-11-09 | 安徽工业大学 | Motor bearing fault diagnosis method based on single sample learning |
Non-Patent Citations (3)
| Title |
|---|
| 王翔;柯飂挺;任佳;: "样本重构多尺度孪生卷积网络的化工过程故障检测", 仪器仪表学报, no. 11, 10 January 2020 (2020-01-10) * |
| 钟跃崎: "人工智能技术原理与应用", vol. 1, 30 September 2020, 东华大学出版社, pages: 223 - 225 * |
| 韩春雷;武兵;熊晓燕;任俊锜;刘智飞: "基于SDP和DG-ResNet的齿轮箱轴承故障诊断研究", 机电工程, vol. 38, no. 11, 20 November 2021 (2021-11-20), pages 1398 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113379123A (en) | Fault prediction method, device, server and storage medium based on digital twin | |
| Gao et al. | ASM1D-GAN: An intelligent fault diagnosis method based on assembled 1D convolutional neural network and generative adversarial networks | |
| CN112447189A (en) | Voice event detection method and device, electronic equipment and computer storage medium | |
| CN112995414B (en) | Behavior quality inspection method, device, equipment and storage medium based on voice call | |
| CN112468659A (en) | Quality evaluation method, device, equipment and storage medium applied to telephone customer service | |
| CN117407771B (en) | Bearing health state assessment method and device based on digital twin and related equipment | |
| CN112967225A (en) | Automatic detection system, method, equipment and medium based on artificial intelligence | |
| CN111680642A (en) | Terrain classification method and device | |
| CN113125135A (en) | Fault diagnosis method for rotary machine, storage medium, and electronic device | |
| CN115982965A (en) | Carbon fiber material damage detection method and device for denoising diffusion sample increment learning | |
| CN114612531A (en) | Image processing method and device, electronic equipment and storage medium | |
| CN114894483A (en) | Bearing fault diagnosis method and device, computer equipment and storage medium | |
| Zhang et al. | Intelligent fault diagnosis using image representation of multi-domain features | |
| CN115164932B (en) | Vehicle travel distance determination method, device, computer equipment and storage medium | |
| CN115248377B (en) | Asynchronous motor rotor broken bar fault detection method, computer equipment and medium | |
| CN115221350A (en) | Event audio detection method and system based on small sample metric learning | |
| CN113780238B (en) | Abnormality detection method and device for multi-index time sequence signal and electronic equipment | |
| CN116895286A (en) | Printer fault monitoring method and related device | |
| CN113060614A (en) | Fault diagnosis method and device for elevator driving host and readable storage medium | |
| CN115314239A (en) | Analysis method and related equipment for hidden malicious behaviors based on multi-model fusion | |
| CN110175456A (en) | Software action sampling method, relevant device and software systems | |
| CN113792549B (en) | User intention recognition method, device, computer equipment and storage medium | |
| CN117253286B (en) | Human body action prediction method and related products | |
| CN118940118A (en) | Axial flow pump fault diagnosis method and device, electronic equipment and medium | |
| Yang et al. | Rolling bearing fault diagnosis method based on anti-noise ViT model |
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 |