CN110617966A - Bearing fault diagnosis method based on semi-supervised generation countermeasure network - Google Patents

Bearing fault diagnosis method based on semi-supervised generation countermeasure network Download PDF

Info

Publication number
CN110617966A
CN110617966A CN201910899768.XA CN201910899768A CN110617966A CN 110617966 A CN110617966 A CN 110617966A CN 201910899768 A CN201910899768 A CN 201910899768A CN 110617966 A CN110617966 A CN 110617966A
Authority
CN
China
Prior art keywords
classifier
samples
dimensional
layer
generator
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
Application number
CN201910899768.XA
Other languages
Chinese (zh)
Inventor
陶洪峰
王鹏
魏强
庄志和
周龙辉
王连云
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangnan University
Original Assignee
Jiangnan University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangnan University filed Critical Jiangnan University
Priority to CN201910899768.XA priority Critical patent/CN110617966A/en
Publication of CN110617966A publication Critical patent/CN110617966A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M13/00—Testing of machine parts
    • G01M13/04—Bearings
    • G01M13/045—Acoustic or vibration analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G06F18/2155—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the incorporation of unlabelled data, e.g. multiple instance learning [MIL], semi-supervised techniques using expectation-maximisation [EM] or naïve labelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • 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

Abstract

The invention relates to a bearing fault diagnosis method based on a semi-supervised generation countermeasure network, which comprises the following steps: obtaining vibration signals of a bearing in different states, and dividing the vibration signals into a plurality of samples; randomly dividing the samples into a training set and a testing set, and constructing a small number of label samples with different faults in the training set; constructing a one-dimensional semi-supervised generation confrontation network model; inputting a training set into the confrontation network for training; the trained countermeasure network is used for testing the diagnosis of concentrated bearing faults. The method directly inputs the originally acquired vibration signal, directly outputs the concentrated bearing fault category after training, and realizes an end-to-end optimal diagnosis model; the capability of one-dimensional semi-supervised generation of the confrontation network for extracting features is enhanced by using the one-dimensional convolution layer and the one-dimensional deconvolution layer; the invention is a semi-supervised training mode, does not need a large number of manual label samples, greatly saves time and labor cost, and has strong bearing fault diagnosis effect and anti-noise capability and good stability.

Description

Bearing fault diagnosis method based on semi-supervised generation countermeasure network
Technical Field
The invention relates to the technical field of bearing fault diagnosis, in particular to a bearing fault diagnosis method based on a semi-supervised generation countermeasure network.
Background
In mechanical systems and electric systems, rolling bearings are one of important basic components, and under various complex conditions, defects of various forms such as deformation, abrasion, corrosion, cracks and the like of rolling elements often occur easily. Damaged rolling bearings may cause significant economic losses in the production process in engineering practice and may even cause personnel safety accidents. Therefore, the method has important significance for the research on the fault diagnosis of the rolling bearing.
The failure types of the rolling bearing are classified according to the failure modes, mainly comprise peeling, abrasion, corrosion and the like, the reasons for the failures are quite complex, the structural design problems are solved, and the failure of the bearing can be caused by improper assembly, use and maintenance in the operation process. During the operation of the bearing, if some parts are in failure, the failure point and the contact part thereof can generate impact pulses along with the rotation of the bearing, and the pulses can form a pulse modulation phenomenon on the natural frequency of the bearing. The failure occurs in different parts of the bearing, and the impact pulse forms of the failure are different, particularly the frequency of the contact part passing through the damaged part is different, and the frequency is called as the characteristic frequency of the failure. Therefore, the failure of the rolling bearing can be classified into 4 types of failure of the inner ring, failure of the outer ring, failure of the rolling element, and failure of the cage, according to the location where the failure occurs.
In the prior art, the method mainly used for diagnosing the bearing fault is to acquire a vibration signal, an acoustic emission signal, an electromagnetic signal, an ultrasonic signal and the like of equipment, and obtain the relevant fault information of the bearing from the signals by a certain method. The method can be concretely summarized into two steps of feature extraction and fault identification. In the aspect of feature extraction, features of an original signal in a time domain, a frequency domain and a time-frequency domain have been widely researched, and the features include signal processing methods such as wavelet transformation, short-time fourier transformation, empirical mode decomposition and the like. In the aspect of fault identification, the method is realized by artificial intelligence methods such as a support vector machine, an artificial neural network, a k-nearest neighbor rule and the like. Furthermore, in recent years, deep learning has been widely applied to the field of bearing fault diagnosis, since it can construct a deep neural network, can automatically learn low-level features, and gradually form a more abstract high-level representation.
Whether the traditional fault diagnosis method or the deep learning-based bearing fault diagnosis method is mostly supervised learning, and a large number of data labels are needed. However, in practical problems, the obtained original data is mostly label-free data, and manual marking of fault samples requires extensive expert experience and consumes a lot of time and labor cost.
Disclosure of Invention
The bearing fault diagnosis method based on the semi-supervised generation countermeasure network is reasonable in structure, so that bearing fault diagnosis is realized based on fewer label samples, time and labor cost are greatly saved, and the bearing fault diagnosis method based on the semi-supervised generation countermeasure network is high in diagnosis accuracy, strong in anti-noise capability and good in stability.
The technical scheme adopted by the invention is as follows:
a bearing fault diagnosis method based on a semi-supervised generation countermeasure network comprises the following steps:
the first step is as follows: acquiring a bearing vibration signal through vibration signal acquisition equipment, wherein the vibration signal is one-dimensional time sequence data and has the characteristics of periodicity and time sequence;
the second step is that: taking discrete data acquired by one bearing rotation circle as a sample, and dividing a data set acquired in the first step into a plurality of samples;
the third step: randomly dividing the samples in the second step into a training set and a testing set, and enabling the number ratio of the samples in the training set to the samples in the testing set to be 9: 1; determining the number of samples with labels in a training set, and labeling the samples with the labels;
the fourth step: inputting the training set in the third step into a pre-established one-dimensional semi-supervised generated countermeasure network for iterative training, and adjusting the network weight by using an Adam algorithm in iteration;
the one-dimensional semi-supervised generation confrontation network mainly comprises a generator and a classifier; the generator generates a set of false samples matching the statistical distribution in the training set; the generator and the classifier both comprise an input layer, an intermediate layer and an output layer;
the structure of the generator is as follows: the input of an input layer is 128-dimensional Gaussian noise with the mean value of-1 and the variance of 1 Gaussian distribution, the activation function of an output layer of the generator is a Tanh function, the middle layer of the generator comprises two fully-connected layers and four one-dimensional deconvolution layers, convolution kernels of the one-dimensional deconvolution layers are set to be 5x1, and the four one-dimensional deconvolution layers are located between the two fully-connected layers; the activation function between the one-dimensional deconvolution layers is a ReLU function, and batch normalization processing is performed after each deconvolution;
the loss function of the generator is:
Lnew＝Ez～p(z)[log(1-C(G(z)))]+0.01*Lmatch
wherein: l ismatchThe loss function of the generator under the characteristic matching method is shown as the following equation:x is the sample in the training set, pdata(x) The data distribution of x, q (x) is the characteristic value of x in the middle layer of the classifier, p (z) is the data distribution of z, and q (G (z)) is the characteristic value of the sample in the false sample set in the middle layer of the classifier; c (g (z)) is the probability that a sample in the set of false samples belongs to a certain fault category;
the structure of the classifier is as follows: the input of an input layer is a sample set mixed by a training set and a false sample set, the activation function of an output layer of the classifier is a Softmax function, a middle layer of the classifier comprises a full connection layer and five one-dimensional convolutional layers, the convolutional core of the first one-dimensional convolutional layer is set to be 5x1, the convolutional cores of the other four one-dimensional convolutional layers are set to be 3x1, and the full connection layer is positioned behind the five one-dimensional convolutional layers; the activation function between the one-dimensional convolution layers is a LeakyReLU function, and batch normalization processing is performed after convolution is completed each time;
the loss function of the classifier is:
wherein:
Lunsup＝Lunlabel+Lgen
Lgen＝-Ex～Glog[pmod(y＝m+1|x)
x is the real sample collected; y is a label; e is desired; p is a radical ofmod(y|x,y<m +1) represents the probability that x is a certain label; p is a radical ofmod(y +1| x) represents the probability that x is a false sample; l issupRepresenting a loss function when the classifier trains the labeled samples; l isunsupRepresenting a loss function when the classifier trains unlabeled exemplars, the unlabeled exemplars including unlabeled exemplars in the training set and false exemplars generated by the generator; l isunlabelRepresenting a loss function when no label sample exists in a classifier training set; l isgenRepresenting a loss function when the classifier trains the samples in the false sample set;
the iterative training comprises the following steps:
1) sampling in Gaussian noise to generate a vector z, inputting the vector to a generator, and outputting the vector through a one-dimensional deconvolution layer and a full-link layer to obtain a false sample set G (z);
2) inputting samples in a training set and samples in a false sample set into a classifier according to batches, extracting features through a one-dimensional convolution layer and a full connection layer, and outputting normalized probability values C (x) and C (G (z)) through a Softmax function;
3) updating the weight parameter of the one-dimensional semi-supervised generated countermeasure network:
3.1) fixing the generator parameters to train a classifier; if the input in the classifier is the unlabeled sample in the training set, L is addedunlabelAs a loss function, if the input of the classifier is the labeled sample in the training set, then L is setsupAs a loss function, if the input to the classifier is a sample generated by the generator, L will begenAs a loss function; adjusting parameters of the classifier by using an Adam algorithm;
3.2) fixing the classifier parameters to train the generator; the generator performs feature matching on the sample training set and the false sample set G (z) by LnewAs a loss function, and adjusting the parameters of the generator by using an Adam algorithm;
4) repeating 1) to 3) until a predetermined number of iterations is reached;
the fifth step: inputting the test set in the third step into the one-dimensional semi-supervised generation antagonistic network trained in the fourth step, enabling the test set samples to enter a classifier trained in the fourth step, extracting features through a one-dimensional convolution layer and a full connection layer, performing batch normalization processing, outputting results through an output layer of the classifier, namely finishing fault category judgment of the test set samples, and outputting diagnosis results;
the capability of one-dimensional semi-supervised generation of the confrontation network for extracting features is enhanced by using the one-dimensional convolution layer and the one-dimensional deconvolution layer; and performing iterative training on the classifier by utilizing a training set consisting of labeled samples and unlabeled samples and combining a false sample set generated by the generator, so that the classifier performs fault classification on the unlabeled samples in the test set.
The invention has the following beneficial effects:
the invention has compact and reasonable structure and convenient operation, directly inputs the original vibration signal, automatically learns the low-level characteristics through the constructed deep network, gradually forms more abstract high-level representation, and finally directly outputs the bearing fault category, thereby realizing an end-to-end optimal diagnosis model; the one-dimensional convolutional layer and the one-dimensional anti-convolutional layer are combined with the semi-supervised generation countermeasure network, so that the countermeasure network is more suitable for processing one-dimensional time sequence data, the capability of the one-dimensional semi-supervised generation countermeasure network for extracting deep characteristics of bearing signals is enhanced, and good diagnosis effect and noise resistance are achieved; and a semi-supervised training mode based on a small number of label samples greatly saves time and labor cost.
Drawings
Fig. 1 is a block diagram of a one-dimensional semi-supervised generation countermeasure network of the present invention.
Fig. 2 is a flow chart of the fault diagnosis method of the present invention.
Fig. 3 is a diagram of a full connection layer network structure of the present invention.
FIG. 4 is a network structure diagram of a one-dimensional convolutional layer according to the present invention.
Fig. 5 is a network architecture diagram of the generator of the present invention.
FIG. 6 is a network architecture diagram of the classifier of the present invention.
FIG. 7 is a graph showing the trend of the accuracy of the diagnostic result evaluation according to the present invention with different numbers of labeled samples.
FIG. 8 is a training set feature data distribution graph after the 5 th iteration of the present invention.
FIG. 9 is a training set feature data distribution graph after the 25 th iteration of the present invention.
FIG. 10 is a training set feature data distribution graph after the 100 th iteration of the present invention.
FIG. 11 is a graph of the training set feature data distribution after the 300 th iteration of the present invention.
FIG. 12 is a trend chart of the accuracy of the diagnostic result evaluation under different noises according to the present invention.
Detailed Description
The following describes embodiments of the present invention with reference to the drawings.
As shown in fig. 1, a bearing fault diagnosis method based on a semi-supervised generation countermeasure network of the present embodiment includes the following steps:
the first step is as follows: collecting signals: acquiring a bearing vibration signal through vibration signal acquisition equipment, wherein the vibration signal is one-dimensional time sequence data and has the characteristics of periodicity and time sequence along with the rotation of a bearing;
the second step is that: dividing samples: taking discrete data acquired by one bearing rotation circle as a sample, and dividing a data set acquired in the first step into a plurality of samples;
the third step: dividing a training set and a testing set: randomly dividing the samples in the second step into a training set and a testing set, and enabling the number ratio of the samples in the training set to the samples in the testing set to be 9: 1; determining the number of samples with labels in a training set, and labeling the samples with the labels; namely, the training set comprises labeled samples and unlabeled samples, and the testing set comprises unlabeled samples;
the fourth step: training: inputting the training set in the third step into a pre-established one-dimensional semi-supervised generated countermeasure network for iterative training;
the method comprises the steps that a one-dimensional semi-supervised generation countermeasure network, which is abbreviated as 1D-SGAN, mainly comprises a generator and a classifier; the generator generates a false sample set matched with the statistical distribution in the training set; the generator and the classifier respectively comprise an input layer, an intermediate layer and an output layer;
the structure of the generator is as follows: the input of an input layer is 128-dimensional Gaussian noise with the obedient mean value of-1 and the variance of 1 Gaussian distribution, the activation function of an output layer of a generator is a Tanh function, the middle layer of the generator comprises two fully-connected layers and four one-dimensional deconvolution layers, and the convolution kernels of the one-dimensional deconvolution layers are all set to be 5x 1; and the four one-dimensional deconvolution layers are located between the two fully-connected layers, as shown in fig. 5, where size represents the convolution kernel size, num represents the convolution kernel number, and s represents the convolution step size; the activation function between the one-dimensional deconvolution layers is a ReLU function, and batch normalization processing is performed after each deconvolution; the ReLU function helps the generator to realize nonlinear representation and enables the network to be trained more conveniently; the Tanh function is used to limit the generator output to [ -1,1 ];
the loss function of the generator is:
Lnew＝Ez～p(z)[log(1-C(G(z)))]+0.01*Lmatch
wherein: l ismatchThe loss function of the generator under the characteristic matching method is shown as the following equation:x is the sample in the training set, pdata(x) The data distribution of x, q (x) is the characteristic value of x in the middle layer of the classifier, p (z) is the data distribution of z, and q (G (z)) is the characteristic value of the sample in the false sample set in the middle layer of the classifier; c (g (z)) is the probability that a sample in the set of false samples belongs to a certain fault category;
the structure of the classifier is as follows: the input of the input layer is a sample set mixed by a training set and a false sample set, the activation function of the output layer of the classifier is a Softmax function, the middle layer of the classifier comprises a full connection layer and five one-dimensional convolutional layers, the convolution kernel of the first one-dimensional convolutional layer is set to be 5x1, the convolution kernels of the other four one-dimensional convolutional layers are set to be 3x1, and the full connection layer is positioned behind the five one-dimensional convolutional layers, as shown in FIG. 6; the activation function between the one-dimensional convolution layers is a LeakyReLU function, and batch normalization processing is performed after convolution is completed each time; the LeakyReLU function helps the classifier to prevent the problem of gradient disappearance, and Softmax is used for predicting the corresponding category of the sample;
the loss function of the classifier is:
wherein:
Lunsup＝Lunlabel+Lgen
Lgen＝-Ex～Glog[pmod(y＝m+1|x)
x is the real sample collected; y is a label; e is desired; p is a radical ofmod(y|x,y<m +1) represents the probability that x is a certain label, i.e. the probability of a fault indicated by a certain label; p is a radical ofmod(y +1| x) represents the probability that x is a false sample; l issupRepresenting a loss function when the classifier trains the labeled samples; l isunsupRepresenting a loss function when the classifier trains unlabeled exemplars, the unlabeled exemplars including unlabeled exemplars in the training set and false exemplars generated by the generator; l isunlabelRepresenting a loss function when no label sample exists in a classifier training set; l isgenRepresenting the loss function of the classifier in training samples in the set of false samples.
Fig. 3 is a network structure diagram of a full connection layer, and fig. 4 is a network structure diagram of a one-dimensional convolutional layer;
as can be seen from fig. 3 and 4, the calculation of the fully connected layer corresponds to summing the entirety of the input X; the one-dimensional convolutional layer is equivalent to translation summation on X, and each obtained f node value retains a certain continuity attribute; compared with a fully connected layer, a one-dimensional convolutional layer is more suitable for processing one-dimensional time series data.
Fig. 2 shows a flow chart of training and testing.
The iterative training of the one-dimensional semi-supervised generation countermeasure network comprises the following steps:
1) sampling in Gaussian noise to generate a vector z, inputting the vector to a generator, and outputting the vector through a one-dimensional deconvolution layer and a full-link layer to obtain a false sample set G (z);
2) inputting samples in a training set and samples in a false sample set into a classifier according to batches, extracting features through a one-dimensional convolution layer and a full connection layer, and outputting normalized probability values C (x) and C (G (z)) through a Softmax function;
3) updating the weight parameter of the one-dimensional semi-supervised generated countermeasure network:
3.1) fixing the generator parameters to train a classifier; if the input in the classifier is the unlabeled sample in the training set, L is addedunlabelAs a loss function, if the classifier inputs the labeled bands in the training setSample, then LsupAs a loss function, if the input to the classifier is a sample generated by the generator, L will begenAs a loss function; adjusting parameters of the classifier by using an Adam algorithm;
3.2) fixing the classifier parameters to train the generator; the generator performs feature matching on the sample training set and the false sample set G (z) by LnewAs a loss function, and adjusting the parameters of the generator by using an Adam algorithm;
4) repeating 1) to 3) until a predetermined number of iterations is reached.
The fifth step: and (3) diagnosis: inputting the test set in the third step into the one-dimensional semi-supervised generation antagonistic network trained in the fourth step, enabling the test set samples to enter the classifier trained in the fourth step, extracting features through the one-dimensional convolution layer and the full-connection layer, performing batch normalization processing, outputting results through the output layer of the classifier, namely finishing fault category judgment of the test set samples, and outputting diagnosis results.
By using the one-dimensional convolution layer and the one-dimensional deconvolution layer, the processing of an original vibration signal, namely bearing time sequence data is realized, and the capability of extracting characteristics of a one-dimensional semi-supervised generated countermeasure network is enhanced, so that the bearing fault diagnosis effect is good, and the anti-noise capability is strong; performing iterative training on the classifier by utilizing a training set consisting of labeled samples and unlabeled samples and combining a false sample set generated by a generator, so that the classifier performs fault classification on the unlabeled samples in a test set, and an end-to-end optimal diagnosis model is realized; and a semi-supervised training mode based on the label sample greatly saves time and labor cost.
The classifier of the 1D-SGAN is intended to distinguish whether the input data is labeled true samples, unlabeled true samples, or false samples produced by the generator in the training set, which tries to produce false samples that can spoof the classifier; supposing that for an m-class classification problem, the 1D-SGAN can attach a 'generation' label to a sample generated by a generator as an m + 1-th class, the output dimension of the classifier is increased from m to m +1, and the classifier is continuously trained to identify the difference between the generated sample, a labeled true sample and an unlabeled true sample, so that effective information in the unlabeled sample is learned, and further semi-supervised learning is realized.
When the one-dimensional semi-supervised generated confrontation network is subjected to iterative training, the confrontation network after each iteration is used for predicting a training set, and each iteration means that the 1D-SGAN is trained once by using the training set containing labeled samples and unlabeled samples. And (3) reducing the dimension of the features extracted by the classifier of the training set by using TSNE to obtain two-dimensional attributes so as to visualize the data distribution of the extracted features.
And testing the test set to obtain the accuracy of the one-dimensional semi-supervised generation confrontation network diagnosis.
If the total number of the types of the faults in the test set is m, the number of samples in each type is known and is c1, c 2.. once, cm, respectively, and the classifier predicts the correct number of samples in each type to be x1, x 2.. once, xm, respectively, the diagnosis accuracy is as follows:
example (b):
take the data set provided by the website of the bearing data center of Kaiser university as an example
One-dimensional semi-supervised generation based countermeasure network diagnosis process
The bearing model is SKF6205, the rotating speed is 1797rpm, the damage positions are an inner ring, a rolling body and an outer ring respectively, the damage diameters are 0.007 inch, 0.014 inch and 0.021 inch respectively, and 9 fault states and 1 normal state are totally counted; the acquisition frequency of the vibration signal is 12kHz, so that about 400 sampling points are obtained for one rotation of the bearing, which is calculated as follows:
acquiring 121991 sampling points on an inner ring with the damage diameter of 0.007 inches by using vibration signal acquisition equipment; then the first 120000 sampling points are selected, and the 400 sampling points are taken as one sample, and then 300 samples are obtained; and dividing the samples into a training set and a test set according to the ratio of 9:1, wherein the number of the samples in the training set is 270, and the number of the samples in the test set is 30. This is the sample collection for one failure condition of the bearing, and the bearing has 10 different conditions in total of 9 failure conditions and 1 normal condition, and the final training set of samples is 270 × 10 — 2700 samples, and the test set of samples is 30 × 10 — 300 samples.
If 100 samples are randomly selected in the training set to be labeled, the rest 2600 samples are unlabeled.
Inputting samples in a training set in batches into a one-dimensional semi-supervised generated countermeasure network for iterative training; for 100 samples per batch, the optimization algorithm selects the Adam algorithm with a learning rate set to 0.0002, a momentum set to 0.5, and a number of iterations set to 300.
After the training is finished, the 1D-SGAN is used for testing the test set after 300 times of iterative training, and the specific details of the diagnosis result are shown in Table 1.
TABLE 11D-SGAN Fault diagnosis results
Second, the diagnosis superiority verification
In order to verify the superiority of the bearing few-labeled sample fault diagnosis and compare the influence of different numbers of labeled samples on the One-dimensional Semi-supervised generated countermeasure network (1D-SGAN for short), the 1D-SGAN is compared with the original Semi-supervised generated countermeasure network (SGAN for short) and Semi-supervised Self-training (SST) of a Semi-supervised classification method.
The generator and classifier model of the original SGAN are all multilayer perceptrons, except an input layer and an output layer, the middle of the original SGAN contains a plurality of fully-connected layers, and the original SGAN is mainly suitable for processing samples which are input in an image form.
The semi-supervised classification method comprises the steps of firstly training an initial classifier by using a labeled data set, labeling some non-labeled data by using the classifier, putting some new labels with the highest credibility into the labeled data set, and then performing the next training on the new labeled data set until a cut-off condition is met.
When the number of the samples with the labels is increased, the number of the samples without the labels is correspondingly reduced, and the total number of the samples in the training set is ensured to be unchanged. For example, when the number of labeled samples is 200, the number of unlabeled samples is 2500. Each method was trained with the same training set and tested with the same test set.
As shown in fig. 7, it can be seen that the fault classification capabilities of the 1D-SGAN and the SGAN are less affected by the number of labeled samples, and the SST is more affected. With the increase of the number of labeled samples in the training set, the classification capability of the SST is greatly enhanced, and the diagnosis accuracy rate is increased from 70.667% to 88.000%, but still has a larger difference from the other two methods. In addition, under the condition that the number of the samples with the labels is only 100, the original SGAN has good performance on fault classification, the accuracy rate is 95.667% at least, but the performance of the 1D-SGAN is more excellent and can reach 99.333%, so that the superiority in fault diagnosis when the number of the samples with the labels is less for the bearing is verified.
Thirdly, verifying the feature extraction capability of the classifier
Using TSNE to perform dimension reduction on the features extracted by the classifier in the training set to obtain two-dimensional attributes as an X-axis and a Y-axis, and visually extracting data distribution of the features, as shown in fig. 8, 9, 10 and 11, where Normal represents a Normal condition of the bearing, BA represents a fault of the rolling element, IR represents a fault of the inner ring, OR represents a fault of the outer ring, and data represents a damage diameter, that is: BA007 indicated failure of the bearing rolling elements with a damaged diameter of 0.007 inches, IR014 indicated failure of the bearing inner race with a damaged diameter of 0.014 inches, OR021 indicated failure of the bearing outer race with a damaged diameter of 0.021 inches. It can be seen that, when training begins, the feature points of different categories are approximately distributed in a certain range, but more points are mixed with each other; the feature data of the training set are distributed more clearly and less points of confusion distribution are distributed more and more with the increase of the number of iterations, which means that the capability of the classifier of the model for extracting features is enhanced, and when 300 iterations are completed, it can be seen from fig. 11 that the classifier can well extract important features in the sample.
Fourth, verification of noise immunity
In a practical industrial environment, noise is often not caused by a single source, but is a complex of noise from many different sources, unknown and variable. The real noise is considered as a combination of random variables of very many different probability distributions, each of which is independent, and their normalized sum approaches a gaussian distribution as the number of noise sources increases according to the central limit theorem. Therefore, the noise in the actual environment is approximated with white gaussian noise.
In order to verify the robustness to noise, the test data added with Gaussian white noise with different signal-to-noise ratios is tested by using the 1D-SGAN which is trained under the condition that the number of the samples with the labels is 100.
Three different algorithms (SST, SGAN, 1D-SGAN) were tested on the test set with different noise added.
The accuracy rates of the evaluation indexes of the test results of the three algorithms under different noises are shown in fig. 12, and it can be seen that the diagnosis accuracy rates of the three algorithms gradually decrease with the decrease of the signal-to-noise ratio, that is, the enhancement of the noises. The 1D-SGAN still has higher accuracy rate for the case that the signal-to-noise ratio is more than 5dB, but at 0dB, the accuracy rate is only 60.333 percent, which is reduced by 19.000 percent relative to 5dB, and the standard of practical application can not be achieved. The original SGAN has better robustness for the condition that the signal-to-noise ratio is more than 10dB, the SST is limited by the limitation of the algorithm of the original SGAN, the original signal has no good performance, and after different noises are added, the diagnosis accuracy indexes are all lower than 70%. In contrast, 1D-SGAN has better robustness than SST and SGAN.
The bearing fault diagnosis method based on the label samples is capable of achieving bearing fault diagnosis based on fewer label samples, and is high in fault recognition accuracy, good in noise robustness and good in stability.
The above description is intended to be illustrative and not restrictive, and the scope of the invention is defined by the appended claims, which may be modified in any manner within the scope of the invention.

Claims (1)

1. A bearing fault diagnosis method based on a semi-supervised generation countermeasure network is characterized by comprising the following steps: the method comprises the following steps:
the first step is as follows: acquiring a bearing vibration signal through vibration signal acquisition equipment, wherein the vibration signal is one-dimensional time sequence data and has the characteristics of periodicity and time sequence;
the second step is that: taking discrete data acquired by one bearing rotation circle as a sample, and dividing a data set acquired in the first step into a plurality of samples;
the third step: randomly dividing the samples in the second step into a training set and a testing set, and enabling the number ratio of the samples in the training set to the samples in the testing set to be 9: 1; determining the number of samples with labels in a training set, and labeling the samples with the labels;
the fourth step: inputting the training set in the third step into a pre-established one-dimensional semi-supervised generated countermeasure network for iterative training, and adjusting the network weight by using an Adam algorithm in iteration;
the one-dimensional semi-supervised generation confrontation network mainly comprises a generator and a classifier; the generator generates a set of false samples matching the statistical distribution in the training set; the generator and the classifier both comprise an input layer, an intermediate layer and an output layer;
the structure of the generator is as follows: the input of an input layer is 128-dimensional Gaussian noise with the mean value of-1 and the variance of 1 Gaussian distribution, the activation function of an output layer of the generator is a Tanh function, the middle layer of the generator comprises two fully-connected layers and four one-dimensional deconvolution layers, convolution kernels of the one-dimensional deconvolution layers are set to be 5x1, and the four one-dimensional deconvolution layers are located between the two fully-connected layers; the activation function between the one-dimensional deconvolution layers is a ReLU function, and batch normalization processing is performed after each deconvolution;
the loss function of the generator is:
Lnew＝Ez～p(z)[log(1-C(G(z)))]+0.01*Lmatch
wherein: l ismatchThe loss function of the generator under the characteristic matching method is shown as the following equation:x is the sample in the training set, pdata(x) The data distribution of x, q (x) is the characteristic value of x in the middle layer of the classifier, p (z) is the data distribution of z, and q (G (z)) is the characteristic value of the sample in the false sample set in the middle layer of the classifier; c (g (z)) is the probability that a sample in the set of false samples belongs to a certain fault category;
the structure of the classifier is as follows: the input of an input layer is a sample set mixed by a training set and a false sample set, the activation function of an output layer of the classifier is a Softmax function, a middle layer of the classifier comprises a full connection layer and five one-dimensional convolutional layers, the convolutional core of the first one-dimensional convolutional layer is set to be 5x1, the convolutional cores of the other four one-dimensional convolutional layers are set to be 3x1, and the full connection layer is positioned behind the five one-dimensional convolutional layers; the activation function between the one-dimensional convolution layers is a LeakyReLU function, and batch normalization processing is performed after convolution is completed each time;
the loss function of the classifier is:
wherein:
Lunsup＝Lunlabel+Lgen
Lgen＝-Ex～Glog[pmod(y＝m+1|x)]
x is the real sample collected;y is a label; e is desired; p is a radical ofmod(y | x, y < m +1) represents the probability that x is a certain label; p is a radical ofmod(y +1| x) represents the probability that x is a false sample; l issupRepresenting a loss function when the classifier trains the labeled samples; l isunsupRepresenting a loss function when the classifier trains unlabeled exemplars, the unlabeled exemplars including unlabeled exemplars in the training set and false exemplars generated by the generator; l isunlabelRepresenting a loss function when no label sample exists in a classifier training set; l isgenRepresenting a loss function when the classifier trains the samples in the false sample set;
the iterative training comprises the following steps:
1) sampling in Gaussian noise to generate a vector z, inputting the vector to a generator, and outputting the vector through a one-dimensional deconvolution layer and a full-link layer to obtain a false sample set G (z);
2) inputting samples in a training set and samples in a false sample set into a classifier according to batches, extracting features through a one-dimensional convolution layer and a full connection layer, and outputting normalized probability values C (x) and C (G (z)) through a Softmax function;
3) updating the weight parameter of the one-dimensional semi-supervised generated countermeasure network:
3.1) fixing the generator parameters to train a classifier; if the input in the classifier is the unlabeled sample in the training set, L is addedunlabelAs a loss function, if the input of the classifier is the labeled sample in the training set, then L is setsupAs a loss function, if the input to the classifier is a sample generated by the generator, L will begenAs a loss function; adjusting parameters of the classifier by using an Adam algorithm;
3.2) fixing the classifier parameters to train the generator; the generator performs feature matching on the sample training set and the false sample set G (z) by LnewAs a loss function, and adjusting the parameters of the generator by using an Adam algorithm;
4) repeating 1) to 3) until a predetermined number of iterations is reached;
the fifth step: inputting the test set in the third step into the one-dimensional semi-supervised generation antagonistic network trained in the fourth step, enabling the test set samples to enter a classifier trained in the fourth step, extracting features through a one-dimensional convolution layer and a full connection layer, performing batch normalization processing, outputting results through an output layer of the classifier, namely finishing fault category judgment of the test set samples, and outputting diagnosis results;
the capability of one-dimensional semi-supervised generation of the confrontation network for extracting features is enhanced by using the one-dimensional convolution layer and the one-dimensional deconvolution layer; and performing iterative training on the classifier by utilizing a training set consisting of labeled samples and unlabeled samples and combining a false sample set generated by the generator, so that the classifier performs fault classification on the unlabeled samples in the test set.
CN201910899768.XA 2019-09-23 2019-09-23 Bearing fault diagnosis method based on semi-supervised generation countermeasure network Pending CN110617966A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910899768.XA CN110617966A (en) 2019-09-23 2019-09-23 Bearing fault diagnosis method based on semi-supervised generation countermeasure network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910899768.XA CN110617966A (en) 2019-09-23 2019-09-23 Bearing fault diagnosis method based on semi-supervised generation countermeasure network

Publications (1)

Publication Number Publication Date
CN110617966A true CN110617966A (en) 2019-12-27

Family

ID=68923941

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910899768.XA Pending CN110617966A (en) 2019-09-23 2019-09-23 Bearing fault diagnosis method based on semi-supervised generation countermeasure network

Country Status (1)

Country Link
CN (1) CN110617966A (en)

Cited By (36)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111079705A (en) * 2019-12-31 2020-04-28 北京理工大学 Vibration signal classification method
CN111275024A (en) * 2020-03-22 2020-06-12 东北电力大学 Fault diagnosis method for rolling bearing of variable-working-condition fan driven by limited data containing noise label
CN111310048A (en) * 2020-02-25 2020-06-19 西安电子科技大学 News recommendation method based on multilayer perceptron
CN111337243A (en) * 2020-02-27 2020-06-26 上海电力大学 ACGAN-based wind turbine generator planet wheel gearbox fault diagnosis method
CN111553297A (en) * 2020-05-06 2020-08-18 东华大学 Method and system for diagnosing production fault of polyester filament based on 2D-CNN and DBN
CN111582396A (en) * 2020-05-13 2020-08-25 江南大学 Fault diagnosis method based on improved convolutional neural network
CN111914705A (en) * 2020-07-20 2020-11-10 华中科技大学 Signal generation method and device for improving health state evaluation accuracy of reactor
CN111930728A (en) * 2020-06-30 2020-11-13 广州洪森科技有限公司 Method and system for predicting characteristic parameters and fault rate of equipment
CN112039687A (en) * 2020-07-14 2020-12-04 南京邮电大学 Small sample feature-oriented fault diagnosis method based on improved generation countermeasure network
CN112200244A (en) * 2020-10-09 2021-01-08 西安交通大学 Intelligent detection method for anomaly of aerospace engine based on hierarchical countermeasure training
CN112232395A (en) * 2020-10-08 2021-01-15 西北工业大学 Semi-supervised image classification method for generating confrontation network based on joint training
CN112257862A (en) * 2020-09-30 2021-01-22 重庆大学 Semi-supervised identification method based on relational network marker sample expansion
CN112308038A (en) * 2020-11-25 2021-02-02 哈尔滨工业大学 Mechanical equipment fault signal identification method based on classroom type generation confrontation network model
CN112329520A (en) * 2020-09-23 2021-02-05 西南交通大学 Truck bearing fault identification method based on generation countermeasure learning
CN112381248A (en) * 2020-11-27 2021-02-19 广东电网有限责任公司肇庆供电局 Power distribution network fault diagnosis method based on deep feature clustering and LSTM
CN112668459A (en) * 2020-12-25 2021-04-16 合肥工业大学 Rolling bearing fault diagnosis method based on supervised contrast learning and convolutional neural network
CN112964793A (en) * 2021-02-09 2021-06-15 常州大学 Intelligent pipeline pitting damage identification method based on image identification and acoustic identification
CN113066528A (en) * 2021-04-12 2021-07-02 山西大学 Protein classification method based on active semi-supervised graph neural network
CN113128338A (en) * 2021-03-15 2021-07-16 西安理工大学 Intelligent diagnosis method for printing machine roller fault under small sample
CN113191429A (en) * 2021-04-29 2021-07-30 国网河北省电力有限公司电力科学研究院 Power transformer bushing fault diagnosis method and device
CN113239970A (en) * 2021-04-16 2021-08-10 首钢集团有限公司 Model training method, equipment vibration abnormity detection method and device
CN113324758A (en) * 2021-05-27 2021-08-31 西安交通大学 Bearing fault diagnosis method based on semi-supervised countermeasure network
CN113376516A (en) * 2021-06-07 2021-09-10 科润智能控制股份有限公司 Medium-voltage vacuum circuit breaker operation fault self-diagnosis and early-warning method based on deep learning
CN113486931A (en) * 2021-06-21 2021-10-08 南京航空航天大学 Rolling bearing enhancement diagnosis method based on PDA-WGANGP
CN113505664A (en) * 2021-06-28 2021-10-15 上海电力大学 Fault diagnosis method for planetary gear box of wind turbine generator
CN113537010A (en) * 2021-07-05 2021-10-22 华北电力大学（保定） Fifteen-phase asynchronous motor rolling bearing fault diagnosis method based on single-channel diagram data enhancement and migration training residual error network
CN113723650A (en) * 2020-05-25 2021-11-30 中国石油化工股份有限公司 Chemical process abnormity monitoring system based on semi-supervised model and model optimization device
CN113721113A (en) * 2021-09-02 2021-11-30 广西大学 Fault line selection method based on semi-supervised generation countermeasure network
CN113723649A (en) * 2020-05-25 2021-11-30 中国石油化工股份有限公司 Chemical process abnormity monitoring method based on semi-supervised model and model optimization method
CN113869208A (en) * 2021-09-28 2021-12-31 江南大学 Rolling bearing fault diagnosis method based on SA-ACWGAN-GP
CN113884290A (en) * 2021-09-28 2022-01-04 江南大学 Voltage regulator fault diagnosis method based on self-training semi-supervised generation countermeasure network
CN114169396A (en) * 2021-11-05 2022-03-11 华中科技大学 Training data generation model construction method and application for aircraft fault diagnosis
CN114739673A (en) * 2022-03-18 2022-07-12 河北工业大学 Bearing vibration signal characteristic interpretable dimension reduction and fault diagnosis method
CN114913396A (en) * 2022-07-15 2022-08-16 西北工业大学 Motor bearing fault diagnosis method
CN115796238A (en) * 2022-12-02 2023-03-14 中国地质大学（武汉） Implicit data enhancement based mechanical fault diagnosis method and device for small sample
CN116894215A (en) * 2023-07-20 2023-10-17 江南大学 Gear box fault diagnosis method based on semi-supervised dynamic graph attention

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108680807A (en) * 2018-05-17 2018-10-19 国网山东省电力公司青岛供电公司 The Diagnosis Method of Transformer Faults and system of network are fought based on condition production
WO2018209894A1 (en) * 2017-05-19 2018-11-22 Huawei Technologies Co., Ltd. Semi-supervised regression with generative adversarial networks
CN109489946A (en) * 2018-09-21 2019-03-19 华中科技大学 A kind of fault diagnosis method and system of rotating machinery
US20190122120A1 (en) * 2017-10-20 2019-04-25 Dalei Wu Self-training method and system for semi-supervised learning with generative adversarial networks
CN109740677A (en) * 2019-01-07 2019-05-10 湖北工业大学 It is a kind of to improve the semisupervised classification method for generating confrontation network based on principal component analysis
EP3486838A1 (en) * 2017-11-15 2019-05-22 Palo Alto Research Center Incorporated System and method for semi-supervised conditional generative modeling using adversarial networks
CN110097103A (en) * 2019-04-22 2019-08-06 西安电子科技大学 Based on the semi-supervision image classification method for generating confrontation network
CN110110745A (en) * 2019-03-29 2019-08-09 上海海事大学 Based on the semi-supervised x-ray image automatic marking for generating confrontation network
CN110186680A (en) * 2019-05-30 2019-08-30 盐城工学院 A kind of confrontation differentiation domain adapts to one-dimensional convolutional neural networks intelligent failure diagnosis method

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018209894A1 (en) * 2017-05-19 2018-11-22 Huawei Technologies Co., Ltd. Semi-supervised regression with generative adversarial networks
US20190122120A1 (en) * 2017-10-20 2019-04-25 Dalei Wu Self-training method and system for semi-supervised learning with generative adversarial networks
EP3486838A1 (en) * 2017-11-15 2019-05-22 Palo Alto Research Center Incorporated System and method for semi-supervised conditional generative modeling using adversarial networks
CN108680807A (en) * 2018-05-17 2018-10-19 国网山东省电力公司青岛供电公司 The Diagnosis Method of Transformer Faults and system of network are fought based on condition production
CN109489946A (en) * 2018-09-21 2019-03-19 华中科技大学 A kind of fault diagnosis method and system of rotating machinery
CN109740677A (en) * 2019-01-07 2019-05-10 湖北工业大学 It is a kind of to improve the semisupervised classification method for generating confrontation network based on principal component analysis
CN110110745A (en) * 2019-03-29 2019-08-09 上海海事大学 Based on the semi-supervised x-ray image automatic marking for generating confrontation network
CN110097103A (en) * 2019-04-22 2019-08-06 西安电子科技大学 Based on the semi-supervision image classification method for generating confrontation network
CN110186680A (en) * 2019-05-30 2019-08-30 盐城工学院 A kind of confrontation differentiation domain adapts to one-dimensional convolutional neural networks intelligent failure diagnosis method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
刘坤等: "基于半监督生成对抗网络X光图像分类算法", 《光学学报》 *

Cited By (56)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111079705B (en) * 2019-12-31 2023-07-25 北京理工大学 Vibration signal classification method
CN111079705A (en) * 2019-12-31 2020-04-28 北京理工大学 Vibration signal classification method
CN111310048A (en) * 2020-02-25 2020-06-19 西安电子科技大学 News recommendation method based on multilayer perceptron
CN111337243B (en) * 2020-02-27 2022-04-01 上海电力大学 ACGAN-based wind turbine generator planet wheel gearbox fault diagnosis method
CN111337243A (en) * 2020-02-27 2020-06-26 上海电力大学 ACGAN-based wind turbine generator planet wheel gearbox fault diagnosis method
CN111275024A (en) * 2020-03-22 2020-06-12 东北电力大学 Fault diagnosis method for rolling bearing of variable-working-condition fan driven by limited data containing noise label
CN111275024B (en) * 2020-03-22 2023-03-21 东北电力大学 Fault diagnosis method for rolling bearing of variable-working-condition fan driven by limited data containing noise label
CN111553297A (en) * 2020-05-06 2020-08-18 东华大学 Method and system for diagnosing production fault of polyester filament based on 2D-CNN and DBN
CN111553297B (en) * 2020-05-06 2022-03-15 东华大学 Method and system for diagnosing production fault of polyester filament based on 2D-CNN and DBN
CN111582396B (en) * 2020-05-13 2023-05-02 江南大学 Fault diagnosis method based on improved convolutional neural network
CN111582396A (en) * 2020-05-13 2020-08-25 江南大学 Fault diagnosis method based on improved convolutional neural network
CN113723650A (en) * 2020-05-25 2021-11-30 中国石油化工股份有限公司 Chemical process abnormity monitoring system based on semi-supervised model and model optimization device
CN113723649A (en) * 2020-05-25 2021-11-30 中国石油化工股份有限公司 Chemical process abnormity monitoring method based on semi-supervised model and model optimization method
CN111930728A (en) * 2020-06-30 2020-11-13 广州洪森科技有限公司 Method and system for predicting characteristic parameters and fault rate of equipment
CN111930728B (en) * 2020-06-30 2023-11-24 广州洪森科技有限公司 Method and system for predicting characteristic parameters and failure rate of equipment
CN112039687A (en) * 2020-07-14 2020-12-04 南京邮电大学 Small sample feature-oriented fault diagnosis method based on improved generation countermeasure network
CN111914705A (en) * 2020-07-20 2020-11-10 华中科技大学 Signal generation method and device for improving health state evaluation accuracy of reactor
CN112329520A (en) * 2020-09-23 2021-02-05 西南交通大学 Truck bearing fault identification method based on generation countermeasure learning
CN112329520B (en) * 2020-09-23 2023-01-31 西南交通大学 Truck bearing fault identification method based on generation countermeasure learning
CN112257862B (en) * 2020-09-30 2023-12-05 重庆大学 Semi-supervised identification method based on relation network marking sample expansion
CN112257862A (en) * 2020-09-30 2021-01-22 重庆大学 Semi-supervised identification method based on relational network marker sample expansion
CN112232395B (en) * 2020-10-08 2023-10-27 西北工业大学 Semi-supervised image classification method for generating countermeasure network based on joint training
CN112232395A (en) * 2020-10-08 2021-01-15 西北工业大学 Semi-supervised image classification method for generating confrontation network based on joint training
CN112200244B (en) * 2020-10-09 2022-12-09 西安交通大学 Intelligent detection method for anomaly of aerospace engine based on hierarchical countermeasure training
CN112200244A (en) * 2020-10-09 2021-01-08 西安交通大学 Intelligent detection method for anomaly of aerospace engine based on hierarchical countermeasure training
CN112308038A (en) * 2020-11-25 2021-02-02 哈尔滨工业大学 Mechanical equipment fault signal identification method based on classroom type generation confrontation network model
CN112308038B (en) * 2020-11-25 2022-09-27 哈尔滨工业大学 Mechanical equipment fault signal identification method based on classroom type generation confrontation network model
CN112381248A (en) * 2020-11-27 2021-02-19 广东电网有限责任公司肇庆供电局 Power distribution network fault diagnosis method based on deep feature clustering and LSTM
CN112668459A (en) * 2020-12-25 2021-04-16 合肥工业大学 Rolling bearing fault diagnosis method based on supervised contrast learning and convolutional neural network
CN112668459B (en) * 2020-12-25 2022-09-13 合肥工业大学 Rolling bearing fault diagnosis method based on supervised contrast learning and convolutional neural network
CN112964793B (en) * 2021-02-09 2024-01-09 常州大学 Intelligent pipeline pitting damage identification method based on image identification and acoustic identification
CN112964793A (en) * 2021-02-09 2021-06-15 常州大学 Intelligent pipeline pitting damage identification method based on image identification and acoustic identification
CN113128338B (en) * 2021-03-15 2024-02-02 西安理工大学 Intelligent diagnosis method for printer roller faults under small sample
CN113128338A (en) * 2021-03-15 2021-07-16 西安理工大学 Intelligent diagnosis method for printing machine roller fault under small sample
CN113066528B (en) * 2021-04-12 2022-07-19 山西大学 Protein classification method based on active semi-supervised graph neural network
CN113066528A (en) * 2021-04-12 2021-07-02 山西大学 Protein classification method based on active semi-supervised graph neural network
CN113239970A (en) * 2021-04-16 2021-08-10 首钢集团有限公司 Model training method, equipment vibration abnormity detection method and device
CN113191429A (en) * 2021-04-29 2021-07-30 国网河北省电力有限公司电力科学研究院 Power transformer bushing fault diagnosis method and device
CN113324758A (en) * 2021-05-27 2021-08-31 西安交通大学 Bearing fault diagnosis method based on semi-supervised countermeasure network
CN113376516A (en) * 2021-06-07 2021-09-10 科润智能控制股份有限公司 Medium-voltage vacuum circuit breaker operation fault self-diagnosis and early-warning method based on deep learning
CN113486931B (en) * 2021-06-21 2023-05-26 南京航空航天大学 Rolling bearing enhanced diagnosis method based on PDA-WGANGP
CN113486931A (en) * 2021-06-21 2021-10-08 南京航空航天大学 Rolling bearing enhancement diagnosis method based on PDA-WGANGP
CN113505664A (en) * 2021-06-28 2021-10-15 上海电力大学 Fault diagnosis method for planetary gear box of wind turbine generator
CN113537010B (en) * 2021-07-05 2023-09-01 华北电力大学（保定） Fifteen-phase asynchronous motor rolling bearing fault diagnosis method based on single-channel diagram data enhancement and migration training residual error network
CN113537010A (en) * 2021-07-05 2021-10-22 华北电力大学（保定） Fifteen-phase asynchronous motor rolling bearing fault diagnosis method based on single-channel diagram data enhancement and migration training residual error network
CN113721113B (en) * 2021-09-02 2023-10-24 广西大学 Fault line selection method based on semi-supervised generation countermeasure network
CN113721113A (en) * 2021-09-02 2021-11-30 广西大学 Fault line selection method based on semi-supervised generation countermeasure network
CN113884290B (en) * 2021-09-28 2022-08-02 江南大学 Voltage regulator fault diagnosis method based on self-training semi-supervised generation countermeasure network
CN113884290A (en) * 2021-09-28 2022-01-04 江南大学 Voltage regulator fault diagnosis method based on self-training semi-supervised generation countermeasure network
CN113869208A (en) * 2021-09-28 2021-12-31 江南大学 Rolling bearing fault diagnosis method based on SA-ACWGAN-GP
CN114169396A (en) * 2021-11-05 2022-03-11 华中科技大学 Training data generation model construction method and application for aircraft fault diagnosis
CN114739673A (en) * 2022-03-18 2022-07-12 河北工业大学 Bearing vibration signal characteristic interpretable dimension reduction and fault diagnosis method
CN114913396A (en) * 2022-07-15 2022-08-16 西北工业大学 Motor bearing fault diagnosis method
CN115796238A (en) * 2022-12-02 2023-03-14 中国地质大学（武汉） Implicit data enhancement based mechanical fault diagnosis method and device for small sample
CN116894215A (en) * 2023-07-20 2023-10-17 江南大学 Gear box fault diagnosis method based on semi-supervised dynamic graph attention
CN116894215B (en) * 2023-07-20 2024-03-12 江南大学 Gear box fault diagnosis method based on semi-supervised dynamic graph attention

Similar Documents

Publication Publication Date Title
CN110617966A (en) Bearing fault diagnosis method based on semi-supervised generation countermeasure network
Qin et al. The optimized deep belief networks with improved logistic sigmoid units and their application in fault diagnosis for planetary gearboxes of wind turbines
Pan et al. A novel deep learning network via multiscale inner product with locally connected feature extraction for intelligent fault detection
Yin et al. Wasserstein generative adversarial network and convolutional neural network (WG-CNN) for bearing fault diagnosis
CN107657250B (en) Bearing fault detection and positioning method and detection and positioning model implementation system and method
CN106682688A (en) Pile-up noise reduction own coding network bearing fault diagnosis method based on particle swarm optimization
CN112763214B (en) Rolling bearing fault diagnosis method based on multi-label zero-sample learning
Chen et al. Machine fault classification using deep belief network
CN110991424A (en) Fault diagnosis method based on minimum entropy deconvolution and stacking sparse self-encoder
CN113673346B (en) Motor vibration data processing and state identification method based on multiscale SE-Resnet
CN115017945A (en) Mechanical fault diagnosis method and system based on enhanced convolutional neural network
Fei The hybrid method of VMD-PSR-SVD and improved binary PSO-KNN for fault diagnosis of bearing
Li et al. Gear pitting fault diagnosis using raw acoustic emission signal based on deep learning
SE542335C2 (en) Method and system for vehicle analysis
Tao et al. Fault diagnosis of rolling bearing using deep belief networks
Al Tobi et al. Using MLP‐GABP and SVM with wavelet packet transform‐based feature extraction for fault diagnosis of a centrifugal pump
Afrasiabi et al. Two-stage deep learning-based wind turbine condition monitoring using SCADA data
Lee et al. A feature selection approach hybrid grey wolf and heap-based optimizer applied in bearing fault diagnosis
Han et al. Data-enhanced stacked autoencoders for insufficient fault classification of machinery and its understanding via visualization
Lee et al. An explainable deep learning-based prognostic model for rotating machinery
Shi et al. A novel rotating machinery fault diagnosis method based on adaptive deep belief network structure and dynamic learning rate under variable working conditions
CN114925809A (en) Printing machine bearing fault diagnosis method and device based on LSTM
CN115290326A (en) Rolling bearing fault intelligent diagnosis method
CN115356599B (en) Multi-mode urban power grid fault diagnosis method and system
CN116541771A (en) Unbalanced sample bearing fault diagnosis method based on multi-scale feature fusion

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20191227

RJ01 Rejection of invention patent application after publication