CN112231975A - Data modeling method and system based on reliability analysis of railway power supply equipment - Google Patents
Data modeling method and system based on reliability analysis of railway power supply equipment Download PDFInfo
- Publication number
- CN112231975A CN112231975A CN202011090779.2A CN202011090779A CN112231975A CN 112231975 A CN112231975 A CN 112231975A CN 202011090779 A CN202011090779 A CN 202011090779A CN 112231975 A CN112231975 A CN 112231975A
- Authority
- CN
- China
- Prior art keywords
- data
- power supply
- neural network
- supply equipment
- railway power
- 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
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000004458 analytical method Methods 0.000 title claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 76
- 238000013528 artificial neural network Methods 0.000 claims abstract description 72
- 230000036541 health Effects 0.000 claims abstract description 67
- 230000009467 reduction Effects 0.000 claims abstract description 67
- 238000012360 testing method Methods 0.000 claims abstract description 54
- 230000000694 effects Effects 0.000 claims abstract description 17
- 239000000284 extract Substances 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000013527 convolutional neural network Methods 0.000 claims description 74
- 230000006870 function Effects 0.000 claims description 56
- 238000004422 calculation algorithm Methods 0.000 claims description 39
- 230000008569 process Effects 0.000 claims description 28
- 238000009826 distribution Methods 0.000 claims description 21
- 238000004140 cleaning Methods 0.000 claims description 16
- 238000012417 linear regression Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 abstract description 7
- 238000012544 monitoring process Methods 0.000 abstract description 5
- 238000013135 deep learning Methods 0.000 description 6
- 230000032683 aging Effects 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003475 lamination Methods 0.000 description 1
- 230000008531 maintenance mechanism Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
- G06F17/141—Discrete Fourier transforms
- G06F17/142—Fast Fourier transforms, e.g. using a Cooley-Tukey type algorithm
-
- 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
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Abstract
The invention provides a data modeling method and a data modeling system based on reliability analysis of railway power supply equipment. The training function module adopts a stacked noise reduction encoder to perform noise reduction processing on the historical operating data of the railway power supply equipment and extracts the main characteristics of the data; and inputting the processed data information into a BP neural network, and extracting a health factor (HI) diagram of the railway power supply equipment. The test function module inputs the running state data of the railway power supply equipment into the trained stacked noise reduction self-encoder and verifies the noise reduction effect of the stacked noise reduction self-encoder; and extracting main characteristic data of the running state of the railway power supply equipment, and automatically identifying the fault type of the railway power supply equipment. Through the cooperation of the training function module and the testing function module, a deep characteristic data set of the railway power supply equipment fault can be constructed, and the method has important significance for subsequently completing the on-line monitoring of the railway power supply equipment fault.
Description
Technical Field
The invention relates to a data modeling method and system based on reliability analysis of railway power supply equipment, and relates to the technical field of intelligent detection.
Background
With the increasing demand of national economy development and the progress of high-speed rail technology, the scale of railways in China shows a continuous expansion trend. The safety and stability of railway power supply equipment are the basis of reliable operation of railways. Once the railway power supply equipment fails, railway delay is caused, and normal production and life of people are influenced; and the safety accidents are caused, and the great economic loss and the adverse social influence are caused. Therefore, the health state of the railway power supply equipment is monitored in real time, early warning of potential faults of the equipment is achieved, damaged equipment is maintained and replaced in time, and the method has important significance for improving the reliable operation of the railway.
For a long time, the regular maintenance mechanism of the railway power supply equipment, which is implemented by the power enterprises, has the problems of insufficient maintenance, excessive maintenance and the like, so that not only is great resource waste caused, but also the reliability of the equipment power supply is influenced to a certain extent. Therefore, based on the history and the current running state of the equipment, the state maintenance work of the railway power supply equipment is imperative to be carried out by utilizing data such as online monitoring, offline experiments and the like. With the progress of communication, computer and control technology, the fault monitoring system is widely applied to railway power supply equipment at present, mass data are accumulated, and the problem that how to deeply analyze the data and further maintain the safe operation of the railway power supply equipment is urgently solved at the present stage is already a problem.
Due to the characteristics of various types, complex parameters, large monitoring data amount, various operating environments and the like, the equipment information acquired by the sensor is possibly polluted by environmental noise and signals from other coupling parts, and key information reflecting the equipment state is covered. Data acquired by the sensors are label-free data (do not contain health states corresponding to the equipment), the data cannot directly enter the deep learning network for learning, and how to acquire a health factor (HI) diagram of the whole life cycle of the railway power supply equipment is a precondition for deep learning network training. In addition, the aging failure process of the railway power supply equipment is influenced by various factors, and at the moment, if the equipment failure process is physically modeled by means of expert experience and manual feature extraction, the efficiency is inevitably low, the aging process of the equipment cannot be comprehensively and accurately described, and how to automatically extract the fault features of the railway power supply equipment is also a difficult problem for realizing the reliability evaluation of the railway power supply equipment.
Disclosure of Invention
The purpose of the invention is as follows: an object is to provide a data modeling method based on reliability analysis of railway power supply equipment, so as to solve the above problems in the prior art. A further object is to propose a system implementing the above method.
The technical scheme is as follows: a data modeling method based on reliability analysis of railway power supply equipment comprises the following steps:
step 1, constructing a stack type noise reduction automatic encoder network to perform noise reduction cleaning on original railway power supply equipment historical data;
step 2, adding a health label to historical data of the railway power supply equipment subjected to noise reduction cleaning;
step 3, cleaning original historical abnormal data through a stack type noise reduction automatic encoder network and performing linear regression on a BP neural network to obtain clean and low-dimensional data with a health label;
step 4, inputting the railway power supply equipment test set into a stack type noise reduction automatic encoder network for noise reduction treatment to obtain clean equipment running state data;
and 5, performing fast Fourier transform on the processed data, inputting the data into a BP neural network, and verifying the accuracy of the fault characteristics of the railway power supply equipment extracted by the trained convolutional neural network.
In a further embodiment, a stacked noise reduction automatic encoder network is constructed to perform noise reduction cleaning on the original railway power supply equipment historical data. Dividing historical data information of the railway power supply equipment into a training set and a testing set, inputting data of the training set into a constructed network for training, setting the square sum of difference values of input data and output results as a penalty function, and updating weight parameters of the network by adopting a random gradient descent algorithm; and inputting the test set data into the trained network, and verifying the noise reduction effect of the stack type noise reduction automatic encoder network. The above process is repeated until the accuracy of the test reaches more than 95%. The trained network can realize noise reduction processing on the state data of the railway power supply equipment.
In a further embodiment, a health tag is added to the historical data of the railway power supply equipment subjected to noise reduction cleaning, the initial 10% of the data is considered as a health state, the health tag is set to be 1, the final 10% of the data is considered as a failure state, and the health tag is set to be 0. Inputting the labeled data into the constructed BP neural network, taking the square sum of the difference value between the output value of the BP neural network and the label value as a penalty function, updating the weight parameter of the BP neural network by adopting a random gradient descent algorithm, and repeatedly carrying out the training process until the accuracy rate of the test reaches more than 95%. And then inputting the remaining 80% of data into a BP neural network, wherein the obtained result is the health label corresponding to the data. And drawing all the data and the corresponding health labels into a map to obtain a health factor (HI) map of the railway power supply equipment.
In a further embodiment, clean and low-dimensional data with health labels can be obtained through cleaning of the original historical abnormal data by the stack type noise reduction automatic encoder network and linear regression of the BP neural network. Dividing the washed historical data of the railway power supply equipment according to the time length L, carrying out fast Fourier transform, inputting the obtained spectrogram into a convolutional neural network for training, extracting deep fault characteristics of the railway power supply equipment, and assigning weight parameters in the convolutional network.
In a further embodiment, the test set of the railway power supply equipment is input into the stacked noise reduction automatic encoder network trained in the step 1 for noise reduction processing, so as to obtain clean equipment running state data. And (3) performing fast Fourier transform on the processed data, inputting the data into the convolutional neural network trained in the step (3), and verifying the accuracy of the fault characteristics of the railway power supply equipment extracted by the trained convolutional neural network.
In a further embodiment, a stacked noise reduction autoencoder network is constructed. For the noise-reduction self-encoder, the historical data of the railway power supply equipment is constructed into a matrix X, X ═ { X (1), X (2), X (3), … X (N) }, X (i) ∈ RMAnd adding a certain amount of 'damage noise' into the matrix X to obtain data X containing noise, wherein X-qD (X | X) is satisfied, and qD is a noise distribution form, namely 'damage noise' is added according to qD distribution. The chi is encoded by the auto-encoder to yield y, which is expected to approximate or reconstruct the original input X. In this process, a joint distribution is defined:
wherein when fθWhen (χ) ≠ y,
is set to 0, q0(X) is an empirical distribution determined from N sets of input data. Thus, y is a deterministic function of χ for noisy inputs, let θ be the joint distribution q0(X, χ, y), then θ is the link parameter between χ and y, and the cost function for the gradient descent optimization is:
where L (X, X') is the "reconstruction error", the degree of network reconstruction is judged. And optimizing the cost function step by step through a random gradient descent algorithm, and maximally reconstructing the original input X from the damage input X. The specific implementation process of the noise reduction self-encoder can be described as follows: randomly zeroing partial elements of an input matrix X according to a certain proportion to change the partial elements into chi, and then coding the chi to obtain a hidden layer expression y, wherein y is fθ(χ)＝sigmoid(Wχ+ b), θ ═ W, b. Reconstructing the input from the hidden layer y yields the output X', X ═ gθ′(y)＝sigmoid(W1y+b1)，θ′＝{W1，b1And calculating a reconstruction error L (X, X ') by using the values of X ' and X '. And finally, optimizing the cost function of the encoder step by step through a random gradient descent algorithm, and maximally reconstructing the original input X from the damaged input X.
In a further embodiment, linear regression is performed on the historical data of the railway power supply equipment after noise reduction through a BP neural network, and a health factor graph of the railway power supply equipment is extracted: dividing historical data of the railway power supply equipment, wherein the initial 10% of data is considered as a healthy state, a healthy label is set to be 1, the final 10% of data is considered as a failed state, and the healthy label is set to be 0; the data are further divided into a training set and a test set, a BP neural network is constructed, a network learning rate epsilon is set, and a model is randomly initialized to connect a weight W and an offset b; setting batch training number, iteration number and the like in a forward propagation algorithm, inputting training set data into a BP neural network, executing the forward propagation algorithm, and calculating a cost function by utilizing the output of the BP neural network:
wherein h isw，b(x (i)) is the output of the BP neural network, and y (i) is the health label of the equipment;
adopting a random gradient descent algorithm to execute back propagation calculation, inputting test set data into the trained BP neural network, and verifying the effect of the BP neural network; inputting the rest 80% of the historical data of the railway power supply equipment into a verified BP neural network, wherein the output value of the BP neural network is the health value corresponding to the railway power supply equipment, and finally obtaining the health factor graph of the railway power supply equipment.
In a further embodiment, clean and low-dimensional data with health labels can be obtained through cleaning of the original historical abnormal data by the stack type noise reduction automatic encoder network and linear regression of the BP neural network. Dividing the washed historical data of the railway power supply equipment according to the time length L, performing fast Fourier transform on the divided data to obtain a spectrogram, inputting the spectrogram into a convolutional neural network for training, extracting deep fault characteristics of the railway power supply equipment, and assigning values to weight parameters in the convolutional neural network. The specific implementation process is as follows:
building a convolutional neural network, setting a network learning rate epsilon by adopting a stacked convolutional neural network in consideration of the complexity of the operating environment of the railway power supply equipment and the sample training scale, and randomly initializing a model connection weight W and an offset b;
the cleaned data are denoted as X ═ X (X)1，X2，X3，…Xn) And dividing the test set and the training set, inputting the training set data into a convolutional neural network to execute a forward propagation algorithm, wherein the convolutional neural network comprises a convolutional layer and a full-link layer, and the convolutional layer is calculated as follows:
where D is depth, F is filter size, wd，m，nRepresents the weight of the mth row and nth column of the filterbRepresenting the bias term of the filtering, ai，jThe ith row and jth column elements of the d-th layer representing the image, and f is the activation function (Relu). And after the convolution layer is calculated, calculating the full connection layer, and calculating a cost function according to the output of the full connection layer:
wherein, gw，b(x (i)) is the output of the convolutional neural network, and y (i) is the health label of the device.
Performing back propagation calculation by adopting a random gradient descent algorithm, and updating the weight coefficient of each layer of the convolutional neural network;
and inputting the test set data into the trained convolutional neural network, verifying the training effect of the convolutional neural network, and if the accuracy of the output result of the convolutional neural network is low, readjusting the parameters to perform the above process until the accuracy reaches more than 95%.
A data modeling system for realizing the method comprises two functional modules, a training functional module and a testing functional module. The training function module adopts a stacked noise reduction encoder to perform noise reduction processing on the historical operating data of the railway power supply equipment and extracts the main characteristics of the data; inputting the processed data information into a BP neural network, and extracting a health factor (HI) diagram of the railway power supply equipment; and acquiring a frequency spectrum graph of the processed data by adopting fast Fourier transform, and inputting the frequency spectrum graph into the constructed convolutional neural network by combining with a health factor (HI) graph, so as to automatically extract deep fault characteristics of the railway power supply equipment. The test function module inputs the running state data (test set) of the railway power supply equipment into the trained stacked noise reduction self-encoder, and verifies the noise reduction effect of the stacked noise reduction self-encoder; and extracting main characteristic data of the running state of the railway power supply equipment, performing fast Fourier transform on the main characteristic data, inputting the main characteristic data into a trained convolutional neural network, and automatically identifying the fault type of the railway power supply equipment. Through the cooperation of the training function module and the testing function module, the deep level characteristics of the railway power supply equipment faults can be extracted.
In a further embodiment, the training function module further constructs a historical data construction matrix of the railway power supply equipment into X:
X＝{x(1)，x(2)，x(3)，…x(N)}，x(i)∈RM；
adding a predetermined amount of damage noise into the matrix X to obtain data X containing noise, and satisfying X-qD (X | X), wherein qD represents a noise distribution form;
the y is obtained by encoding χ with an auto-encoder, in this process, a joint distribution is defined:
wherein when fθWhen (χ) ≠ y,
is set to 0, q0(X) is an empirical distribution determined from N sets of input data;
thus, y is a deterministic function of χ for noisy inputs, let θ be the joint distribution q0(X, χ, y), then θ is the link parameter between χ and y, and the cost function for the gradient descent optimization is:
wherein L (X, X') represents a reconstruction error, and the degree of network reconstruction is judged; optimizing a cost function through a random gradient descent algorithm, and maximally reconstructing an original input X from the damage input X;
the training function module further performs linear regression on the historical data of the railway power supply equipment after noise reduction through a BP neural network, and extracts a health factor graph of the railway power supply equipment:
dividing historical data of the railway power supply equipment, wherein the initial 10% of data is considered as a healthy state, a healthy label is set to be 1, the final 10% of data is considered as a failed state, and the healthy label is set to be 0;
the data are further divided into a training set and a test set, a BP neural network is constructed, a network learning rate epsilon is set, and a model is randomly initialized to connect a weight W and an offset b;
setting batch training number, iteration number and the like in a forward propagation algorithm, inputting training set data into a BP neural network, executing the forward propagation algorithm, and calculating a cost function by utilizing the output of the BP neural network:
wherein h isw，b(x (i)) is the output of the BP neural network, and y (i) is the health label of the equipment;
adopting a random gradient descent algorithm to execute back propagation calculation, inputting test set data into the trained BP neural network, and verifying the effect of the BP neural network;
inputting the rest 80% of the historical data of the railway power supply equipment into a verified BP neural network, wherein the output value of the BP neural network is the health value corresponding to the railway power supply equipment, and finally obtaining a health factor graph of the railway power supply equipment;
the test function module further obtains clean and low-dimensional data with health labels through cleaning of the original historical abnormal data by the stack type noise reduction automatic encoder network and linear regression of the BP neural network; dividing the washed historical data of the railway power supply equipment according to the time length L, performing fast Fourier transform on the divided data to obtain a spectrogram, inputting the spectrogram into a convolutional neural network for training, extracting deep fault characteristics of the railway power supply equipment, and assigning weight parameters in the convolutional neural network; building a convolutional neural network, setting a network learning rate epsilon by adopting a stacked convolutional neural network in consideration of the complexity of the operating environment of the railway power supply equipment and the sample training scale, and randomly initializing a model connection weight W and an offset b;
the cleaned data are denoted as X ═ X (X)1，X2，X3，…Xn) And dividing the test set and the training set, inputting the training set data into a convolutional neural network to execute a forward propagation algorithm, wherein the convolutional neural network comprises a convolutional layer and a full-link layer, and the convolutional layer is calculated as follows:
where D is depth, F is filter size, wd，m，nRepresents the weight of the mth row and nth column of the filterbRepresenting the bias term of the filtering, ai，jRepresenting ith row and jth column elements of a d layer of the image, wherein f is an activation function (Relu);
and after the convolution layer is calculated, calculating the full connection layer, and calculating a cost function according to the output of the full connection layer:
wherein, gw，b(x (i)) is the output of the convolutional neural network, and y (i) is the health label of the device;
performing back propagation calculation by adopting a random gradient descent algorithm, and updating the weight coefficient of each layer of the convolutional neural network;
and inputting the test set data into the trained convolutional neural network, verifying the training effect of the convolutional neural network, and if the accuracy of the output result of the convolutional neural network is low, readjusting the parameters to perform the above process until the accuracy reaches more than 95%.
The invention has the beneficial effects that:
1. the data of the railway power supply equipment is cleaned by adopting the stack type sparse automatic encoder, so that when the most essential characteristics of the data are kept, the interference of environmental noise or other coupling components on data signals is reduced, and the accuracy of fault state identification of the railway power supply equipment is improved.
2. The BP neural network is adopted to carry out linear regression processing on the historical data of the railway power supply equipment, the running state data of the railway power supply equipment can be directly marked with a health state label to obtain a health factor (HI) diagram of the railway power supply equipment, the label data of the railway power supply equipment is obtained without adopting an experiment or simulation method, the data processing efficiency is improved, and meanwhile the authenticity of the data is improved.
3. The aging failure process of the railway power supply equipment is a very complex process and is influenced by various factors such as the operating environment, the working state and the like, and at the moment, the physical modeling of the failure process of the railway power supply equipment is difficult to be carried out in a mode of manually extracting features. The convolutional neural network can automatically extract deep fault characteristics of the railway power supply equipment and can describe the aging and failure processes of the railway power supply equipment more comprehensively and accurately.
4. The method has the advantages that railway power supply equipment test set data are input into a trained convolutional network, accuracy of fault characteristics of the railway power supply equipment extracted by the trained convolutional neural network can be automatically verified, test results are fed back to a training stage, the training process of the convolutional neural network is adjusted, and finally a complete railway power supply equipment fault characteristic data set is constructed.
Drawings
FIG. 1 is a data modeling method based on reliability analysis of railway power supply equipment.
Fig. 2 is a flow chart of a stacked noise reduction self-encoder implementation constructed in accordance with the present invention.
Fig. 3 is a diagram of the railroad supply equipment health factor (HI) extracted by the BP neural network of the present invention.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the present invention. It will be apparent, however, to one skilled in the art, that the present invention may be practiced without one or more of these specific details. In other instances, well-known features have not been described in order to avoid obscuring the invention.
As shown in fig. 1, the invention provides a data modeling method based on reliability analysis of railway power supply equipment, which comprises the following steps:
(1) and constructing a stack type noise reduction automatic encoder network to perform noise reduction cleaning on the original railway power supply equipment historical data. Dividing historical data information of the railway power supply equipment into a training set and a testing set, inputting data of the training set into a constructed network for training, setting the square sum of difference values of input data and output results as a penalty function, and updating weight parameters of the network by adopting a random gradient descent algorithm; and inputting the test set data into the trained network, and verifying the noise reduction effect of the stack type noise reduction automatic encoder network. The above process is repeated until the accuracy of the test reaches more than 95%. The trained network can realize noise reduction processing on the state data of the railway power supply equipment.
(2) Adding a health label to historical data of the railway power supply equipment subjected to noise reduction cleaning, wherein the initial 10% of the data is considered as a health state, the health label is set to be 1, the final 10% of the data is considered as a failure state, and the health label is set to be 0. Inputting the labeled data into the constructed BP neural network, taking the square sum of the difference value between the output value of the BP neural network and the label value as a penalty function, updating the weight parameter of the BP neural network by adopting a random gradient descent algorithm, and repeatedly carrying out the training process until the accuracy rate of the test reaches more than 95%. And then inputting the remaining 80% of data into a BP neural network, wherein the obtained result is the health label corresponding to the data. And drawing all the data and the corresponding health labels into a map to obtain a health factor (HI) map of the railway power supply equipment.
(3) The clean and low-dimensional data with health labels can be obtained by cleaning the original historical abnormal data through the stack type noise reduction automatic encoder network and linear regression of the BP neural network. Dividing the washed historical data of the railway power supply equipment according to the time length L, carrying out fast Fourier transform, inputting the obtained spectrogram into a convolutional neural network for training, extracting deep fault characteristics of the railway power supply equipment, and assigning weight parameters in the convolutional network.
(4) And (3) inputting the railway power supply equipment test set into the stack type noise reduction automatic encoder network finished by the training in the step (1) for noise reduction treatment to obtain clean equipment running state data. And (4) performing fast Fourier transform on the processed data, inputting the processed data into the convolutional neural network finished by the training in the step (3), and verifying the accuracy of the fault characteristics of the railway power supply equipment extracted by the trained convolutional neural network.
Based on the method, the invention further provides a data modeling system which comprises two functional modules, a training functional module and a testing functional module. The training function module adopts a stacked noise reduction encoder to perform noise reduction processing on the historical operating data of the railway power supply equipment and extracts the main characteristics of the data; inputting the processed data information into a BP neural network, and extracting a health factor (HI) diagram of the railway power supply equipment; and acquiring a frequency spectrum graph of the processed data by adopting fast Fourier transform, and inputting the frequency spectrum graph into the constructed convolutional neural network by combining with a health factor (HI) graph, so as to automatically extract deep fault characteristics of the railway power supply equipment. The test function module inputs the running state data (test set) of the railway power supply equipment into the trained stacked noise reduction self-encoder, and verifies the noise reduction effect of the stacked noise reduction self-encoder; and extracting main characteristic data of the running state of the railway power supply equipment, performing fast Fourier transform on the main characteristic data, inputting the main characteristic data into a trained convolutional neural network, and automatically identifying the fault type of the railway power supply equipment. Through the cooperation of the training function module and the testing function module, the deep level characteristics of the railway power supply equipment faults can be extracted.
As shown in fig. 2, a network of stacked noise reduction auto-encoders is constructed. For the noise-reduction self-encoder, the historical data of the railway power supply equipment is constructed into a matrix X, X ═ { X (1), X (2), X (3), … X (N) }, X (i) ∈ RMAdding a certain amount of 'damage noise' into the matrix X to obtain data X containing noise, wherein X-qD (X | X) is satisfied, and qD is a noise distribution form, namely 'damage noise' is according to qDThe addition is distributed. The chi is encoded by the auto-encoder to yield y, which is expected to approximate or reconstruct the original input X. In this process, a joint distribution is defined:
wherein when fθWhen (χ) ≠ y,
is set to 0, q0(X) is an empirical distribution determined from N sets of input data. Thus, y is a deterministic function of χ for noisy inputs, let θ be the joint distribution q0(X, χ, y), then θ is the link parameter between χ and y, and the cost function for the gradient descent optimization is:
where L (X, X') is the "reconstruction error", the degree of network reconstruction is judged. And optimizing the cost function step by step through a random gradient descent algorithm, and maximally reconstructing the original input X from the damage input X. The specific implementation process of the noise reduction self-encoder can be described as follows: randomly zeroing partial elements of an input matrix X according to a certain proportion to change the partial elements into chi, and then coding the chi to obtain a hidden layer expression y, wherein y is fθ(χ)＝sigmoid(Wχ+ b), θ ═ W, b. Reconstructing the input from the hidden layer y yields the output X', X ═ gθ′(y)＝sigmoid(W1y+b1)，θ′＝{W1，b1And calculating a reconstruction error L (X, X ') by using the values of X ' and X '. And finally, optimizing the cost function of the encoder step by step through a random gradient descent algorithm, and maximally reconstructing the original input X from the damaged input X.
The label data is a precondition for training the deep learning network, and is a key for improving the prediction accuracy of the deep learning network. The historical data of the railway power supply equipment only comprises the running state of each equipment and does not comprise the corresponding health state of the equipment, and the original unlabeled data cannot be used for training a deep learning network, namely a convolutional neural network. The traditional method adopts an experiment or simulation mode to extract label data (namely the equipment running state and the corresponding health state) of each equipment, but the difference between the laboratory environment or the simulation environment and the real running environment of the equipment is very large, the accuracy of deep learning network diagnosis trained by the laboratory or the simulation data is low, and the application requirements cannot be met.
As shown in fig. 3, a railway power supply equipment health factor (HI) map acquisition process. The specific implementation process is as follows:
1) dividing historical data of the railway power supply equipment, wherein the initial 10% of data is considered as a healthy state, a healthy label is set to be 1, the final 10% of data is considered as a failed state, and the healthy label is set to be 0;
2) dividing the data into a training set and a testing set;
2) constructing a BP neural network, setting a network learning rate epsilon, and randomly initializing a model connection weight W and an offset b;
3) setting batch training number, iteration number and the like in a forward propagation algorithm, inputting training set data into a BP neural network, executing the forward propagation algorithm, and calculating a cost function by utilizing the output of the BP neural network:
wherein h isw，b(x (i)) is the output of the BP neural network, and y (i) is the health label of the device.
4) Adopting a random gradient descent algorithm to execute back propagation calculation, and updating the network weight parameters according to the following formula:
5) inputting the test set data into the trained BP neural network, and verifying the effect of the BP neural network;
6) inputting the rest 80% of the historical data of the railway power supply equipment into a verified BP neural network, wherein the output value of the BP neural network is the corresponding health value of the railway power supply equipment, and thus, a health factor (HI) diagram of the railway power supply equipment is obtained.
The clean and low-dimensional data with health labels can be obtained by cleaning the original historical abnormal data through the stack type noise reduction automatic encoder network and linear regression of the BP neural network. Dividing the washed historical data of the railway power supply equipment according to the time length L, performing fast Fourier transform on the divided data to obtain a spectrogram, inputting the spectrogram into a convolutional neural network for training, extracting deep fault characteristics of the railway power supply equipment, and assigning values to weight parameters in the convolutional neural network. The specific implementation flow is as follows.
1) Building a convolutional neural network, setting a network learning rate epsilon by adopting a stacked convolutional neural network in consideration of the complexity of the operating environment of the railway power supply equipment and the sample training scale, and randomly initializing a model connection weight W and an offset b;
2) the cleaned data are denoted as X ═ X (X)1，X2，X3，…Xn) And dividing the test set and the training set, inputting the training set data into a convolutional neural network to execute a forward propagation algorithm, wherein the convolutional neural network comprises a convolutional layer and a full-link layer, and the convolutional layer is calculated as follows:
where D is depth, F is filter size, wd，m，nRepresents the weight of the mth row and nth column of the filterbRepresenting the bias term of the filtering, ai，jThe ith row and jth column elements of the d-th layer representing the image, and f is the activation function (Relu). Roll of paperAnd after the lamination calculation is finished, calculating the full connection layer, and calculating a cost function according to the output of the full connection layer:
wherein, gw，b(x (i)) is the output of the convolutional neural network, and y (i) is the health label of the device.
3) Performing back propagation calculation by adopting a random gradient descent algorithm, and updating the weight coefficient of each layer of the convolutional neural network;
4) and inputting the test set data into the trained convolutional neural network, verifying the training effect of the convolutional neural network, and if the accuracy of the output result of the convolutional neural network is low, readjusting the parameters to perform the above process until the accuracy reaches more than 95%.
Through the above process, both the training phase and the testing phase of the algorithm are completed. Through the matching use of the two stages, a fault feature set of historical data of the railway power supply equipment is established, and the method has important significance for the follow-up completion of the on-line monitoring of the faults of the railway power supply equipment.
As noted above, while the present invention has been shown and described with reference to certain preferred embodiments, it is not to be construed as limited thereto. Various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A data modeling method based on reliability analysis of railway power supply equipment is characterized by comprising the following steps:
step 1, constructing a stack type noise reduction automatic encoder network to perform noise reduction cleaning on original railway power supply equipment historical data;
step 2, adding a health label to historical data of the railway power supply equipment subjected to noise reduction cleaning;
step 3, cleaning original historical abnormal data through a stack type noise reduction automatic encoder network and performing linear regression on a BP neural network to obtain clean and low-dimensional data with a health label;
step 4, inputting the railway power supply equipment test set into a stack type noise reduction automatic encoder network for noise reduction treatment to obtain clean equipment running state data;
and 5, performing fast Fourier transform on the processed data, inputting the data into a BP neural network, and verifying the accuracy of the fault characteristics of the railway power supply equipment extracted by the trained convolutional neural network.
2. The data modeling method based on the reliability analysis of the railway power supply equipment according to claim 1, characterized in that the step 1 further comprises:
1-1, dividing historical data information of railway power supply equipment into a training set and a testing set, inputting data of the training set into a constructed network for training, setting the sum of squares of difference values of input data and output results as a penalty function, and updating weight parameters of the network by adopting a random gradient descent algorithm;
step 1-2, inputting test set data into a trained network, and verifying the noise reduction effect of the stack type noise reduction automatic encoder network;
and 1-3, repeating the steps 1 to 2 until the accuracy of the test reaches more than 95%.
3. The data modeling method based on the reliability analysis of the railway power supply equipment according to claim 1, wherein the step 2 is further as follows:
step 2-1, regarding the initial 10% of data as a healthy state, setting a healthy label as 1, regarding the final 10% of data as a failed state, and setting the healthy label as 0;
step 2-2, inputting the labeled data into a constructed BP neural network, taking the square sum of the difference value between the output value of the BP neural network and the label value as a penalty function, updating the weight parameter of the BP neural network by adopting a random gradient descent algorithm, and repeatedly carrying out the training process until the accuracy rate of the test reaches more than 95%;
2-3, inputting the remaining 80% of data into a BP neural network, wherein the obtained result is a health label corresponding to the data; and drawing all the data and the corresponding health labels into a map to obtain a health factor map of the railway power supply equipment.
4. The data modeling method based on the reliability analysis of the railway power supply equipment according to claim 1, wherein the step 3 is further as follows: dividing the washed historical data of the railway power supply equipment according to the time length L, carrying out fast Fourier transform, inputting the obtained spectrogram into a convolutional neural network for training, extracting deep fault characteristics of the railway power supply equipment, and assigning weight parameters in the convolutional network.
5. The data modeling method based on the reliability analysis of the railway power supply equipment according to claim 2, characterized in that the step 4 is further as follows:
step 4-1, inputting the railway power supply equipment test set into the stack type noise reduction automatic encoder network trained in the step 1-1 to perform noise reduction treatment, and obtaining clean equipment running state data;
and 4-2, performing fast Fourier transform on the processed data, inputting the processed data into the convolutional neural network trained in the step 3, and verifying the accuracy of the fault characteristics of the railway power supply equipment extracted by the trained convolutional neural network.
6. The data modeling method based on the reliability analysis of the railway power supply equipment according to claim 2, characterized in that the step 1-2 further comprises:
step 1-2a, constructing a matrix of historical data of the railway power supply equipment into X by a stack type noise reduction encoder:
X＝{x(1)，x(2)，x(3)，…x(N)}，x(i)∈RM；
adding a predetermined amount of damage noise into the matrix X to obtain data X containing noise, and satisfying X-qD (X | X), wherein qD represents a noise distribution form;
1-2b, obtaining y by encoding χ through an automatic encoder, and defining joint distribution in the process:
wherein when fθWhen (χ) ≠ y,
is set to 0, q0(X) is an empirical distribution determined from N sets of input data;
thus, y is a deterministic function of χ for noisy inputs, let θ be the joint distribution q0(X, χ, y), then θ is the link parameter between χ and y, and the cost function for the gradient descent optimization is:
wherein L (X, X') represents a reconstruction error, and the degree of network reconstruction is judged; and optimizing a cost function through a random gradient descent algorithm, and maximally reconstructing an original input X from the damage input X.
7. The data modeling method based on the reliability analysis of the railway power supply equipment according to claim 3, characterized in that the step 2-3 further comprises performing linear regression on the noise-reduced historical data of the railway power supply equipment through a BP neural network to extract a health factor graph of the railway power supply equipment:
2-3a, dividing historical data of the railway power supply equipment, wherein the initial 10% of data is regarded as a healthy state, a healthy label is set to be 1, the final 10% of data is regarded as a failed state, and the healthy label is set to be 0;
step 2-3b, further dividing the data into a training set and a test set, constructing a BP neural network, setting a network learning rate epsilon, and randomly initializing a model connection weight W and an offset b;
step 2-3c, setting batch training numbers, iteration times and the like in the forward propagation algorithm, inputting training set data into the BP neural network, executing the forward propagation algorithm, and calculating a cost function by utilizing the output of the BP neural network:
wherein h isw，b(x (i)) is the output of the BP neural network, and y (i) is the health label of the equipment;
step 2-3d, performing back propagation calculation by adopting a random gradient descent algorithm, inputting test set data into the trained BP neural network, and verifying the effect of the BP neural network;
and 2-3e, inputting the rest 80% of the historical data of the railway power supply equipment into a verified BP neural network, wherein the output value of the BP neural network is the health value corresponding to the railway power supply equipment, and finally obtaining the health factor graph of the railway power supply equipment.
8. The data modeling method based on the reliability analysis of the railway power supply equipment according to claim 2, characterized in that the step 1-1 further comprises:
step 1-1a, building a convolutional neural network, setting a network learning rate epsilon by adopting a stacked convolutional neural network in consideration of the complexity of the running environment of railway power supply equipment and the sample training scale, and randomly initializing a model connection weight W and an offset b;
step 1-1b, the cleaned data is recorded as X ═ X (X)1，X2，X3，…Xn) And dividing the test set and the training set, inputting the training set data into a convolutional neural network to execute a forward propagation algorithm, wherein the convolutional neural network comprises a convolutional layer and a full-link layer, and the convolutional layer is calculated as follows:
where D is depth, F is filter size, wd，m，nRepresents the weight of the mth row and nth column of the filterbRepresenting the bias term of the filtering, ai，jRepresenting ith row and jth column elements of a d layer of the image, wherein f is an activation function (Relu);
step 1-1c, calculating the full connection layer after the convolution layer is calculated, and calculating a cost function according to the output of the full connection layer:
wherein, gw，b(x (i)) is the output of the convolutional neural network, and y (i) is the health label of the device;
step 1-1d, performing back propagation calculation by adopting a random gradient descent algorithm, and updating the weight coefficient of each layer of the convolutional neural network;
and 1-1e, inputting the test set data into the trained convolutional neural network, verifying the training effect of the convolutional neural network, and if the accuracy of the output result of the convolutional neural network is low, readjusting the parameters to perform the above process until the accuracy reaches more than 95%.
9. A data modeling system for realizing the method of any one of claims 1-8 is characterized by comprising a training function module and a testing function module, wherein the training function module adopts a stacked noise reduction encoder to perform noise reduction processing on historical operating data of railway power supply equipment and extracts main features of the data; inputting the processed data information into a BP neural network, and extracting a health factor graph of the railway power supply equipment; acquiring a spectrogram of the processed data by adopting fast Fourier transform, and inputting the spectrogram into the constructed convolutional neural network by combining with a health factor graph, so as to automatically extract deep fault characteristics of the railway power supply equipment;
the test function module inputs the running state data of the railway power supply equipment into the trained stacked noise reduction self-encoder and verifies the noise reduction effect of the stacked noise reduction self-encoder; and extracting main characteristic data of the running state of the railway power supply equipment, performing fast Fourier transform on the main characteristic data, inputting the main characteristic data into a trained convolutional neural network, and automatically identifying the fault type of the railway power supply equipment.
10. The data modeling system of claim 9, wherein the training function module further constructs a railway power supply equipment historical data into a matrix of X:
X＝{x(1)，x(2)，x(3)，…x(N)}，x(i)∈RM；
adding a predetermined amount of damage noise into the matrix X to obtain data X containing noise, and satisfying X-qD (X | X), wherein qD represents a noise distribution form;
the y is obtained by encoding χ with an auto-encoder, in this process, a joint distribution is defined:
wherein when fθWhen (χ) ≠ y,
is set to 0, q0(X) is an empirical distribution determined from N sets of input data;
thus, y is a deterministic function of χ for noisy inputs, let θ be the joint distribution q0(X, χ, y), then θ is the link parameter between χ and y, and the cost function for the gradient descent optimization is:
wherein L (X, X') represents a reconstruction error, and the degree of network reconstruction is judged; optimizing a cost function through a random gradient descent algorithm, and maximally reconstructing an original input X from the damage input X;
the training function module further performs linear regression on the historical data of the railway power supply equipment after noise reduction through a BP neural network, and extracts a health factor graph of the railway power supply equipment:
dividing historical data of the railway power supply equipment, wherein the initial 10% of data is considered as a healthy state, a healthy label is set to be 1, the final 10% of data is considered as a failed state, and the healthy label is set to be 0;
the data are further divided into a training set and a test set, a BP neural network is constructed, a network learning rate epsilon is set, and a model is randomly initialized to connect a weight W and an offset b;
setting batch training number, iteration number and the like in a forward propagation algorithm, inputting training set data into a BP neural network, executing the forward propagation algorithm, and calculating a cost function by utilizing the output of the BP neural network:
wherein h isw，b(x (i)) is the output of the BP neural network, and y (i) is the health label of the equipment;
adopting a random gradient descent algorithm to execute back propagation calculation, inputting test set data into the trained BP neural network, and verifying the effect of the BP neural network;
inputting the rest 80% of the historical data of the railway power supply equipment into a verified BP neural network, wherein the output value of the BP neural network is the health value corresponding to the railway power supply equipment, and finally obtaining a health factor graph of the railway power supply equipment;
the test function module further obtains clean and low-dimensional data with health labels through cleaning of the original historical abnormal data by the stack type noise reduction automatic encoder network and linear regression of the BP neural network; dividing the washed historical data of the railway power supply equipment according to the time length L, performing fast Fourier transform on the divided data to obtain a spectrogram, inputting the spectrogram into a convolutional neural network for training, extracting deep fault characteristics of the railway power supply equipment, and assigning weight parameters in the convolutional neural network; building a convolutional neural network, setting a network learning rate epsilon by adopting a stacked convolutional neural network in consideration of the complexity of the operating environment of the railway power supply equipment and the sample training scale, and randomly initializing a model connection weight W and an offset b;
the cleaned data are denoted as X ═ X (X)1，X2，X3，…Xn) And dividing the test set and the training set, inputting the training set data into a convolutional neural network to execute a forward propagation algorithm, wherein the convolutional neural network comprises a convolutional layer and a full-link layer, and the convolutional layer is calculated as follows:
where D is depth, F is filter size, wd，m，nRepresents the weight of the mth row and nth column of the filterbRepresenting the bias term of the filtering, ai，jRepresenting ith row and jth column elements of a d layer of the image, wherein f is an activation function (Relu);
and after the convolution layer is calculated, calculating the full connection layer, and calculating a cost function according to the output of the full connection layer:
wherein, gw，b(x (i)) is the output of the convolutional neural network, and y (i) is the health label of the device;
performing back propagation calculation by adopting a random gradient descent algorithm, and updating the weight coefficient of each layer of the convolutional neural network;
and inputting the test set data into the trained convolutional neural network, verifying the training effect of the convolutional neural network, and if the accuracy of the output result of the convolutional neural network is low, readjusting the parameters to perform the above process until the accuracy reaches more than 95%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011090779.2A CN112231975A (en) | 2020-10-13 | 2020-10-13 | Data modeling method and system based on reliability analysis of railway power supply equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011090779.2A CN112231975A (en) | 2020-10-13 | 2020-10-13 | Data modeling method and system based on reliability analysis of railway power supply equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112231975A true CN112231975A (en) | 2021-01-15 |
Family
ID=74113445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011090779.2A Pending CN112231975A (en) | 2020-10-13 | 2020-10-13 | Data modeling method and system based on reliability analysis of railway power supply equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112231975A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112948163A (en) * | 2021-03-26 | 2021-06-11 | 中国航空无线电电子研究所 | Method for evaluating influence of equipment on functional fault based on BP neural network |
| CN113269400A (en) * | 2021-04-25 | 2021-08-17 | 贵州电网有限责任公司 | Low-voltage distribution network equipment state evaluation method based on historical operation and maintenance information |
| CN113625094A (en) * | 2021-09-11 | 2021-11-09 | 沈阳工业大学 | Subway platform screen door fault diagnosis system |
| CN114239932A (en) * | 2021-12-01 | 2022-03-25 | 深圳供电局有限公司 | Transformer life prediction method and device, computer equipment and storage medium |
| CN114553681A (en) * | 2022-03-08 | 2022-05-27 | 中国人民解放军国防科技大学 | Equipment state abnormity detection method and device and computer equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6119112A (en) * | 1997-11-19 | 2000-09-12 | International Business Machines Corporation | Optimum cessation of training in neural networks |
| CN104835103A (en) * | 2015-05-11 | 2015-08-12 | 大连理工大学 | Mobile network health evaluation method based on neural network and fuzzy comprehensive evaluation |
| CN107609648A (en) * | 2017-07-21 | 2018-01-19 | 哈尔滨工程大学 | A kind of combination stacks the genetic algorithm of the sparse autocoder of noise reduction |
| CN108229557A (en) * | 2017-12-29 | 2018-06-29 | 中国人民解放军陆军装甲兵学院 | The acceleration training method and system of a kind of neural network with label |
| CN109222963A (en) * | 2018-11-21 | 2019-01-18 | 燕山大学 | A kind of anomalous ecg method for identifying and classifying based on convolutional neural networks |
| CN109774740A (en) * | 2019-02-03 | 2019-05-21 | 湖南工业大学 | A kind of wheel tread damage fault diagnostic method based on deep learning |
| CN111175054A (en) * | 2020-01-08 | 2020-05-19 | 沈阳航空航天大学 | Aeroengine fault diagnosis method based on data driving |
| CN111220958A (en) * | 2019-12-10 | 2020-06-02 | 西安宁远电子电工技术有限公司 | Radar target Doppler image classification and identification method based on one-dimensional convolutional neural network |
| CN111401583A (en) * | 2020-03-18 | 2020-07-10 | 北京天泽智云科技有限公司 | Escalator full life cycle health management system based on predictive maintenance |
| CN111638465A (en) * | 2020-05-29 | 2020-09-08 | 浙大宁波理工学院 | Lithium battery health state estimation method based on convolutional neural network and transfer learning |
-
2020
- 2020-10-13 CN CN202011090779.2A patent/CN112231975A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6119112A (en) * | 1997-11-19 | 2000-09-12 | International Business Machines Corporation | Optimum cessation of training in neural networks |
| CN104835103A (en) * | 2015-05-11 | 2015-08-12 | 大连理工大学 | Mobile network health evaluation method based on neural network and fuzzy comprehensive evaluation |
| CN107609648A (en) * | 2017-07-21 | 2018-01-19 | 哈尔滨工程大学 | A kind of combination stacks the genetic algorithm of the sparse autocoder of noise reduction |
| CN108229557A (en) * | 2017-12-29 | 2018-06-29 | 中国人民解放军陆军装甲兵学院 | The acceleration training method and system of a kind of neural network with label |
| CN109222963A (en) * | 2018-11-21 | 2019-01-18 | 燕山大学 | A kind of anomalous ecg method for identifying and classifying based on convolutional neural networks |
| CN109774740A (en) * | 2019-02-03 | 2019-05-21 | 湖南工业大学 | A kind of wheel tread damage fault diagnostic method based on deep learning |
| CN111220958A (en) * | 2019-12-10 | 2020-06-02 | 西安宁远电子电工技术有限公司 | Radar target Doppler image classification and identification method based on one-dimensional convolutional neural network |
| CN111175054A (en) * | 2020-01-08 | 2020-05-19 | 沈阳航空航天大学 | Aeroengine fault diagnosis method based on data driving |
| CN111401583A (en) * | 2020-03-18 | 2020-07-10 | 北京天泽智云科技有限公司 | Escalator full life cycle health management system based on predictive maintenance |
| CN111638465A (en) * | 2020-05-29 | 2020-09-08 | 浙大宁波理工学院 | Lithium battery health state estimation method based on convolutional neural network and transfer learning |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112948163A (en) * | 2021-03-26 | 2021-06-11 | 中国航空无线电电子研究所 | Method for evaluating influence of equipment on functional fault based on BP neural network |
| CN112948163B (en) * | 2021-03-26 | 2023-09-19 | 中国航空无线电电子研究所 | Method for evaluating influence of equipment on functional failure based on BP neural network |
| CN113269400A (en) * | 2021-04-25 | 2021-08-17 | 贵州电网有限责任公司 | Low-voltage distribution network equipment state evaluation method based on historical operation and maintenance information |
| CN113625094A (en) * | 2021-09-11 | 2021-11-09 | 沈阳工业大学 | Subway platform screen door fault diagnosis system |
| CN114239932A (en) * | 2021-12-01 | 2022-03-25 | 深圳供电局有限公司 | Transformer life prediction method and device, computer equipment and storage medium |
| CN114553681A (en) * | 2022-03-08 | 2022-05-27 | 中国人民解放军国防科技大学 | Equipment state abnormity detection method and device and computer equipment |
| CN114553681B (en) * | 2022-03-08 | 2024-02-02 | 中国人民解放军国防科技大学 | Device state abnormality detection method and device and computer device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112231975A (en) | Data modeling method and system based on reliability analysis of railway power supply equipment | |
| CN112232404B (en) | Reliability calculation method and system based on historical abnormality and operation and maintenance information of railway power supply equipment | |
| CN112629863B (en) | Bearing fault diagnosis method for dynamic joint distribution alignment network under variable working conditions | |
| CN106895975B (en) | Method for Bearing Fault Diagnosis based on Stacked SAE deep neural network | |
| CN110555230B (en) | Rotary machine residual life prediction method based on integrated GMDH framework | |
| CN111666982B (en) | Electromechanical equipment fault diagnosis method based on deep neural network | |
| US20190285517A1 (en) | Method for evaluating health status of mechanical equipment | |
| Guo et al. | An unsupervised feature learning based health indicator construction method for performance assessment of machines | |
| CN109000930B (en) | Turbine engine performance degradation evaluation method based on stacking denoising autoencoder | |
| CN111325403B (en) | Method for predicting residual life of electromechanical equipment of highway tunnel | |
| CN103310051A (en) | Method for predicting failure rate of vehicle-mounted information terminal in entire life cycle | |
| CN113188807B (en) | Automatic abs result judging algorithm | |
| Li et al. | Gear pitting fault diagnosis using raw acoustic emission signal based on deep learning | |
| CN115587290A (en) | Aero-engine fault diagnosis method based on variational self-coding generation countermeasure network | |
| CN115146842A (en) | Multivariate time series trend prediction method and system based on deep learning | |
| CN116430164A (en) | Cable online monitoring method based on distributed temperature measurement and fault waveform analysis | |
| CN111241629B (en) | Intelligent prediction method for performance change trend of hydraulic pump of airplane based on data driving | |
| CN113269400B (en) | Low-voltage distribution network equipment state evaluation method based on historical operation and maintenance information | |
| Techane et al. | Rotating machinery prognostics and application of machine learning algorithms: Use of deep learning with similarity index measure for health status prediction | |
| CN116204781A (en) | Rotary machine fault migration diagnosis method and system | |
| CN116910574A (en) | Mechanical equipment diagnosis method and device based on meta-learning and time convolution network | |
| CN112560252B (en) | Method for predicting residual life of aeroengine | |
| Luo et al. | A novel method for remaining useful life prediction of roller bearings involving the discrepancy and similarity of degradation trajectories | |
| CN114417704A (en) | Wind turbine generator health assessment method based on improved stack type self-coding | |
| CN114792026A (en) | Method and system for predicting residual life of aircraft engine equipment |
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 |