Four-quadrant rectifier fault diagnosis method and device based on energy entropy optimization multi-feature fusion, medium and equipment

Abstract

The invention belongs to the field of high-speed train fault diagnosis, and discloses a four-quadrant rectifier fault diagnosis method and device based on energy entropy optimization multi-feature fusion, a medium and equipment, and the method comprises the steps: firstly, carrying out the wavelet packet decomposition of a fault signal through employing different wavelet functions, and selecting an optimal frequency band according to the energy-information entropy ratio of a frequency band coefficient; secondly, calculating the energy entropy of each coefficient in the optimal frequency band to obtain a plurality of energy entropy features; and finally, carrying out local tangent space arrangement on the plurality of fault features in a spatial position, optimizing data distribution of the plurality of features, reducing abnormal values, and eliminating redundancy among the plurality of features. The result shows that the average diagnosis accuracy rate of the four-quadrant rectifier is 99.0625% through multi-feature optimization fusion. Compared with other methods, the fault diagnosis method provided by the invention has higher diagnosis rate and stronger robustness for output voltage, noise, training and testing.

Description

Technical Field

[0001] The present invention relates to the field of high-speed train fault diagnosis, and in particular to a four-quadrant rectifier fault diagnosis method, device, medium and equipment based on energy entropy optimization and multi-feature fusion. Background Art

[0002] The four-quadrant rectifier is an important component of the heavy-duty train traction drive system. The pulse width modulation (PWM) method is used to enable the rectifier to work in both the rectification state and the inverter state. [1] , the power factor is close to 1, and in the process of traction and regenerative braking, the power consumption is reduced, and the conversion rate and utilization rate of power are improved. During the operation of heavy-load trains, the four-quadrant rectifier is often subjected to high temperature, high voltage, overcurrent and other problems, and it is easy to fail. [2] Its failure will lead to unstable intermediate voltage of traction converter, distortion of input current, increase of harmonics, and failure of regenerative braking, which seriously affect the safe operation of trains. Therefore, efficient fault diagnosis methods can effectively avoid catastrophic accidents of trains and improve the operation and maintenance capabilities of trains.

[0003] The fault diagnosis of four-quadrant rectifier belongs to the category of fault diagnosis of power converter. Its fault sources mainly come from insulated gate bipolar transistor (IGBT) and power diode. The existing fault diagnosis methods mainly include model-based method, signal-based method and data-driven method.

[0004] The model-based approach is a method that aims to establish a mathematical model of the system, and by detecting the difference between the actual signal and the signal predicted by the model, the diagnostic system has a faster response speed. [3] . Reference [4] combines the system's hybrid logic dynamic model with a sliding mode observer to establish a state estimator, completing the detection and location of the open-circuit fault of the switching device. Reference [5] uses four observers to diagnose the open-circuit faults of four IGBTs in the rectifier. Although these methods have obvious advantages in diagnostic speed, the establishment of the model and the determination of parameters limit their applicability. The signal-based method does not require a mathematical model of the system. It extracts the symptoms and characteristics of the measured signal through signal processing technology to obtain the diagnostic results. [6]Reference [7] determines the threshold of each residual based on the analytical redundancy relationship under rectifier fault conditions and the mean and variance levels of each residual under normal conditions to complete the fault diagnosis of IGBT. Reference [8] detects and locates the open circuit fault of IGBT under all switching frequencies and different load conditions by analyzing the instantaneous input voltage of the rectifier. Although these methods improve the diagnosis rate, they require rich prior knowledge and theoretical analysis of fault signals.

[0005] With the development of artificial intelligence and big data, fault diagnosis methods have begun to focus on data-driven methods. Data-driven methods avoid dependence on system models and analysis of prior knowledge of signals. They diagnose fault types through signal processing, feature extraction, and pattern recognition, and have strong robustness and dynamic characteristics. [9] . Reference

[10] uses a convolutional neural network to directly use the excitation current as the input feature to achieve the extraction and classification of rectifier fault features. Reference

[11] uses the particle swarm algorithm to optimize the deep belief network structure for fault feature extraction of the generator rotating rectifier. Although references

[10] and

[11] have achieved a high fault diagnosis rate, they both use deep learning theory to directly train and identify fault signals, ignoring the problems of large computational complexity and complex model design. Therefore, in the data-driven method, simple and sensitive fault features can reduce the computational burden of pattern recognition and improve the fault diagnosis rate.

[0006] Reference

[12] uses wavelet packet decomposition to calculate the wavelet packet entropy features of the frequency band coefficients, optimizes the fault features through principal component analysis (PCA), and realizes the open circuit fault diagnosis of IGBT. However, PCA has a good effect on the fusion of linear data, but a poor fusion effect on nonlinear data. Reference

[13] fuses the energy spectrum entropy features through kernel principal component analysis (KPCA), and finally uses the wavelet neural network method to identify the fault category. Although KPCA can be used for the fusion of nonlinear data, the influence of the choice of kernel function in KPCA on the fusion effect is ignored. Reference

[14] uses the location analysis method to fuse the energy entropy features and identifies the fault category through the stacked sparse autoencoders (SSAE) network method, but the setting of the location parameters has certain complexity and uncertainty, and the use of deep learning algorithms increases the difficulty of the fault diagnosis method.

[0007] The fault signal of the four-quadrant rectifier of a heavy-duty train has the characteristics of nonlinearity and non-stationarity. In order to extract efficient fault features, it is necessary to consider not only the effective decomposition of the signal but also the sensitivity of the features. Wavelet packet decomposition can not only achieve multi-resolution decomposition in the time-frequency domain to obtain high-frequency and low-frequency components, but also has a certain robustness to noise. Although references

[12] and

[14] use wavelet packet decomposition, they ignore the different decomposition effects of different wavelet functions on the signal, which affects the fault diagnosis results. Entropy-based features can be used to characterize the nonlinear characteristics caused by transient changes in the system, thereby quantifying the dynamic changes of the fault signal and distinguishing different operating states. Therefore, entropy-based features have the advantages of good clustering ability, high classification accuracy, and strong robustness. Although references

[12] -

[14] all use entropy features, the method for obtaining simple sensitive fault features needs to be improved. Summary of the invention

[0008] The embodiments of the present invention provide a four-quadrant rectifier fault diagnosis method, device, medium, and equipment based on energy entropy optimization and multi-feature fusion to solve the problem of low fault diagnosis accuracy for simple sensitive fault features in the prior art. In order to have a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary is not a general review, nor is it intended to identify key / important components or describe the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a preface to the detailed description that follows.

[0009] According to a first aspect of an embodiment of the present invention, a four-quadrant rectifier fault diagnosis method based on energy entropy optimization and multi-feature fusion is provided.

[0010] In one embodiment, the method comprises the following steps: Collect input current signals of fault modes under different working conditions to form an original sample set; Different wavelet functions are used to perform wavelet packet multi-resolution decomposition on the input current signal of the fault mode to obtain different frequency band information. The wavelet function suitable for the fault signal is selected according to the energy-information entropy ratio of each group of frequency bands. The corresponding frequency band is the optimal frequency band, and the energy entropy of each frequency band coefficient is calculated. According to the energy entropy of each frequency band coefficient, the energy entropy characteristics of the optimal frequency band are obtained, and the energy entropy characteristics corresponding to different working conditions and different fault modes are constructed; The multiple redundant and conflicting energy entropy features are optimized in local tangent space arrangement in the data space to obtain the optimal energy entropy feature; Support vector machine is used for pattern recognition to obtain the fault diagnosis results of four-quadrant rectifier.

[0011] On the basis of the above scheme, different wavelet functions are used to perform wavelet packet multi-resolution decomposition on the input current signal of the fault mode to obtain different frequency band information, and a wavelet function suitable for the fault signal is selected according to the energy-information entropy ratio of each group of frequency bands. The corresponding frequency band is the optimal frequency band, and the steps of calculating the energy entropy of each frequency band coefficient specifically include: (1) Calculation of multi-band coefficients of different wavelet functions: Assuming the fault signal , using 9 Daubechies (dbN, N= 2,3,…10) wavelet functions commonly used for signal decomposition and reconstruction, the fault signal is decomposed by wavelet packet to obtain 9 groups of frequency band information; (1) In the formula, Indicates the use of db N Wavelet function, signal passes through wavelet packet r After layer decomposition, we get m In the frequency band n The coefficients of the frequency bands; (2) Select a suitable wavelet function: The frequency band energy value corresponding to the wavelet function after wavelet packet decomposition: (2) After a system failure occurs, the uncertainty of each failure mode is related to the number of times the corresponding failure mode occurs. If a failure mode of the rectifier is Y i The probability of this failure mode occurring is P ( Y i ), then the information entropy of the frequency band coefficient obtained after the signal of the fault mode is decomposed is : (3) The energy-information entropy ratio of the corresponding frequency band is R : (4) The larger the energy-information entropy ratio is, the more suitable the selected wavelet function is for the fault signal, and the frequency band obtained after decomposition is the optimal frequency band; (3) Calculate the energy entropy characteristics of the optimal frequency band: The fault signal is decomposed by wavelet packet r After layer decomposition, m frequency band coefficients, and calculate the energy entropy of each frequency band coefficient of the frequency band respectively; (5) (6) (7) In the formula, n The energy value of the frequency band coefficient is E ( n ), the probability distribution is p (n), the energy entropy is T (n); Therefore, based on the optimal wavelet function, the energy entropy characteristic of the optimal frequency band obtained by decomposing the fault signal through wavelet packets is: T ( n ): (8) (4) Constructing the domain matrix of energy entropy characteristics: Due to the energy entropy characteristics T for m dimensional matrix, T n is any data point in the matrix, m is the number of data points, and the number of nearest neighbors for each data point is determined as k , forming a neighborhood matrix; (9) In the formula, For the n The data point j Neighboring points, n =1,2,…, N ; j =1,2,…, k ; (5) Calculate local coordinates: At the data point T n Find the orthogonal basis in the field matrix Q i To constitute g dimensional tangent space, in the neighborhood, calculate each point T nj Orthogonal projection to tangent space λ nj , then find the neighborhood matrix T mn The local coordinates of n : (10) (6) Establish global coordinates: Set global coordinates , for energy entropy characteristics T ( n ) is arranged in tangent space to obtain the global coordinate system. The global coordinates reflect the geometric structure of the local coordinate matrix and should meet the following requirements: (11) In the formula, is the mapping matrix to be determined; is the reconstruction error; yes The centralization matrix; (7) Calculate the permutation matrix: Assume , S is a 0-1 selection matrix, is the energy entropy characteristic data point T n The weight matrix of , the permutation matrix is : (12) (8) Minimize reconstruction error: Solve the minimum eigenvalue of the permutation matrix. The eigenvector corresponding to the second to (g+1)th minimum eigenvalue obtained by calculating the permutation matrix is ​​the energy entropy feature T ( n ) is the global coordinate of each data point in the image, which is also the feature vector of the energy entropy feature after being optimized by local tangent space arrangement. : (13).

[0012] On the basis of the above scheme, the step of performing local tangent space arrangement optimization on multiple redundant and conflicting energy entropy features in the data space to obtain the optimal energy entropy feature specifically includes: (1) Selection of optimal wavelet basis function: Considering the degree of fault feature mining and computational cost, the fault signal is decomposed by wavelet packet. The Daubechies wavelet system, which is commonly used for signal decomposition and reconstruction, is selected. The wavelet basis functions of the Daubechies wavelet system are used to decompose the signal by wavelet packet to obtain multiple groups of frequency bands for each sample and each fault mode. The energy-information entropy ratio of each group of frequency bands is calculated and compared. The maximum ratio indicates that the selected wavelet function is optimal, and the frequency band obtained by decomposing the corresponding fault signal is optimal. (2) Extraction of energy entropy features and data analysis: For each operating condition, the multiple fault modes are decomposed into wavelet packets using their own optimal wavelet functions to obtain multiple frequency bands, and the energy entropy characteristics of each frequency band coefficient are calculated; (3) Optimization of energy entropy characteristics: In the feature extraction process, the feature data presents a normal distribution, and the extracted multiple energy entropy feature data are arranged in a local tangent space.

[0013] On the basis of the above scheme, the step of using a support vector machine to perform pattern recognition and obtain the fault diagnosis result of the four-quadrant rectifier specifically includes: Support vector machine is used as the classifier of fault features, in which the kernel function selects the radial basis function which is robust to noise. Gaussian white noise is added to the collected original signal to simulate the real working environment of the four-quadrant rectifier. Through signal decomposition and feature extraction, the optimized energy entropy feature is used as the input of the classifier SVM. The test results are compared with the actual results of the trained SVM classifier to give the fault diagnosis results.

[0014] Based on the above solution, the step of using a support vector machine as a classifier of fault features specifically includes: The fault feature vector is randomly divided into training samples and test samples, and the support vector machine classifier is used for fault diagnosis. The training samples are used to train the support vector machine, and the test samples are used to verify the performance of the trained support vector machine classifier, so as to obtain the diagnosis result.

[0015] According to a second aspect of an embodiment of the present invention, a four-quadrant rectifier fault diagnosis device based on energy entropy optimization and multi-feature fusion is provided.

[0016] In one embodiment, the apparatus comprises: A data acquisition module is used to collect input current signals of fault modes under different working conditions to form an original sample set; The signal processing module is used to use different wavelet functions to perform wavelet packet multi-resolution decomposition on the input current signal of the fault mode to obtain different frequency band information, and select the wavelet function suitable for the fault signal according to the energy-information entropy ratio of each group of frequency bands. The corresponding frequency band is the optimal frequency band, and the energy entropy of each frequency band coefficient is calculated; A feature extraction module is used to obtain the energy entropy characteristics of the optimal frequency band according to the energy entropy of each frequency band coefficient, and to construct energy entropy characteristics corresponding to different working conditions and different fault modes; The feature optimization fusion module is used to optimize the local tangent space arrangement of multiple redundant and conflicting energy entropy features in the data space to obtain the optimal energy entropy feature; The pattern recognition module is used to perform pattern recognition using a support vector machine to obtain a fault diagnosis result of a four-quadrant rectifier.

[0017] According to a third aspect of an embodiment of the present invention, a computer-readable storage medium is provided.

[0018] In some embodiments, the computer-readable storage medium includes a computer program for storing a computer program, wherein the computer program, when executed by a processor, implements the four-quadrant rectifier fault diagnosis method based on energy entropy optimization and multi-feature fusion.

[0019] According to a fourth aspect of an embodiment of the present invention, a computer device is provided.

[0020] In some embodiments, the computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0021] The technical solution provided by the embodiment of the present invention may have the following beneficial effects: The present invention proposes a fault diagnosis method based on energy entropy optimization and multi-feature fusion for the four-quadrant rectifier with high failure rate in the traction drive system of heavy-duty trains. Firstly, different wavelet functions are used to decompose the fault signal into wavelet packets, and the optimal frequency band is selected according to the energy-information entropy ratio of the frequency band coefficients; secondly, the energy entropy of each coefficient in the optimal frequency band is calculated to obtain multiple energy entropy features; finally, the multiple fault features are arranged locally in spatial position, the data distribution of multiple features is optimized, the outliers are reduced, and the redundancy between multiple features is eliminated. The results show that the optimized fusion of multiple features makes the average diagnostic accuracy of the four-quadrant rectifier 99.0625%. Compared with other methods, this method has a higher diagnosis rate and stronger robustness for output voltage, noise, training and test ratio.

[0022] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0024] Figure 1 is a schematic diagram of a single-phase PWM rectifier circuit structure according to an exemplary embodiment; Figure 2 is an open circuit fault simulation model shown according to an exemplary embodiment; Figure 3 is a diagram showing the current before and after the fault is triggered according to an exemplary embodiment. I The waveform diagram of Figure 3 (a) is the waveform of VT1 open circuit failure at 1.5s. Figure 3 (b) At 1.5s, VT1 and VT2 both have open circuit failures. Figure 3 (c) The waveform of VD1 open circuit failure at 1.5s; Figure 4 is a flow chart of a multi-energy entropy feature optimization fusion algorithm according to an exemplary embodiment; Figure 5 It is a structural schematic diagram of a fault diagnosis device for energy entropy optimization and multi-feature fusion according to an exemplary embodiment; Figure 6 is a schematic diagram showing energy entropy characteristics of 15 fault modes according to an exemplary embodiment; Figure 7 is a schematic diagram showing energy entropy characteristic data distribution according to an exemplary embodiment; Figure 8 is a schematic diagram showing an optimized energy entropy feature according to an exemplary embodiment; Fig. 9 is a schematic diagram showing the distribution of energy entropy characteristic data after optimization according to an exemplary embodiment; Fig.10 is a schematic diagram showing the optimization effect of energy entropy characteristics according to an exemplary embodiment; Fig.11 is a schematic diagram showing a comparison of robustness to noise according to an exemplary embodiment; Fig.12 is a schematic diagram showing a robustness comparison of a training and a test ratio according to an exemplary embodiment; Fig.13 is a schematic diagram showing a comparison of different methods according to an exemplary embodiment; Fig.14 The figure is a schematic diagram showing the structure of a computer device according to an exemplary embodiment. DETAILED DESCRIPTION

[0025] The following description and accompanying drawings fully illustrate the specific embodiments of this article so that those skilled in the art can practice them. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments of this article includes the entire scope of the claims, as well as all available equivalents of the claims. Herein, the terms "first", "second", etc. are only used to distinguish one element from another, without requiring or implying any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the structure, device or equipment including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also include elements inherent to such structure, device or equipment. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the structure, device or equipment including the elements. Each embodiment is described in a progressive manner herein, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the embodiments can be referred to each other.

[0026] The terms "longitudinal", "lateral", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. in this document indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing this document and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In the description of this document, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a mechanical connection or an electrical connection, it can also be the internal communication of two elements, it can be a direct connection, or it can be an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0027] As used herein, the term "plurality" means two or more than two, unless otherwise specified.

[0028] In this document, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.

[0029] In this article, the term "and / or" is a description of the association relationship between objects, indicating that three relationships may exist. For example, A and / or B means: A or B, or, A and B.

[0030] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0031] Figure 1 An embodiment of the four-quadrant rectifier circuit structure of the present invention is shown.

[0032] The four-quadrant rectifier is an important device for power conversion of heavy-duty train HXD3 electric locomotive. The structure of the transmission system consists of a pantograph, a main circuit breaker, a main transformer, a four-quadrant rectifier, a traction inverter, a traction motor, a wheelset and a gearbox. When the intermediate DC side voltage is zero, the 1450V / 50Hz AC voltage derived from the secondary winding of the traction transformer supplies power to the intermediate support capacitor through a charging resistor. When the intermediate DC voltage reaches 2000V, the charging contactor cuts off the charging resistor, the intermediate circuit pre-charging is completed, the gate blockade of the rectifier switching device is released, and the traction winding directly supplies power to the four-quadrant rectifier. When the intermediate DC voltage reaches 2800V, the inverter starts working.

[16] .

[0033] The four-quadrant rectifier is also called a single-phase PWM rectifier. The circuit structure is as follows: Figure 1As shown in the figure, the main sources of failure are open circuit and short circuit failures of IGBT (represented by VT) and power diode (represented by VD). Among them, short circuit failure can be easily detected by the monitoring and protection devices of the system.

[17] Open circuit faults do not cause significant changes in the waveforms of current and voltage, and cannot be detected for a long time. They are often ignored and can easily lead to secondary failures of other components, causing greater losses to the system.

[18] Therefore, the fault diagnosis of the four-quadrant rectifier usually targets the open-circuit faults of the IGBT and the power diode.

[0034] In order to analyze the impact of open-circuit faults of IGBT and power diode on the system, an open-circuit fault simulation model is established, such as Figure 2 As shown. The open circuit fault is simulated by removing the gate signal of the IGBT and the anode current of the power diode. For example, at 1.5s, the gate signal of VT1 and the anode current of VD1 are removed respectively to realize the open circuit fault of VT1 and VD1. The present invention selects the existing input current sensor signal for the fault acquisition signal without adding sensors, and stipulates that the direction of the input current I flowing to the rectifier is I>0, otherwise I<0.

[0035] At 1.5s, an open circuit fault is injected into VT1, and the current before and after the fault is triggered is I The waveform is as Figure 3 (a). When I>0, due to the anti-parallel effect of diode VD1, the current flows through VD1, and the VT1 open circuit fault has no effect on the operation of the rectifier. Therefore, in the first half of the cycle after the fault occurs, the current I waveform does not change. When I<0, the current I cannot pass through diode VD1, and the waveform of the second half of the cycle after the fault occurs is distorted. Therefore, the open circuit fault symptom of VT1 only appears when I<0, and the system cannot work normally.

[0036] At 1.5s, an open circuit fault is injected into VT1 and VT3 at the same time. The current before and after the fault is triggered I The waveform is as Figure 3 (b). When I>0, VT3 provides a channel for the traction winding UN to charge the intermediate capacitor Cd. When VT3 has an open circuit fault, the current I is distorted. When I<0, the open circuit faults of VT1 and VT3 both hinder the energy feedback process. Therefore, when VT1 and VT3 have an open circuit fault, whether I>0 or I<0, the waveform of the current I will be distorted, the amplitude will be reduced, and the fault symptoms will appear in the positive and negative half cycles.

[0037] At 1.5s, an open circuit fault is injected into VD1, and the current before and after the fault is triggered I The waveform is as Figure 3(c) When VD1 has an open circuit fault, the positive half-wave shape of the input current I is distorted because the rectifier branch cannot be turned on. Therefore, the diode open circuit fault affects the normal operation of the rectifier, and it is necessary to accurately diagnose the diode fault.

[0038] During the actual operation of the train, IGBT or power diode may have open circuit faults. Different combinations of switch devices form different fault modes and produce different fault phenomena. This application studies 15 open circuit fault modes (normal mode and 14 fault modes) of the four-quadrant rectifier. The fault modes corresponding to the fault types and their fault labels are shown in Table 1.

[0039]

[0040] An embodiment of the present invention is a four-quadrant rectifier fault diagnosis method based on energy entropy optimization and multi-feature fusion.

[0041] Simple and sensitive fault features help to reduce the computational burden of the classifier and improve the fault diagnosis results. Wavelet packets are used to perform multi-resolution decomposition of noisy, nonlinear, and non-stationary fault signals, avoiding the problem of missing fault information in high-frequency signals. The energy-information entropy criterion is proposed to select the wavelet function suitable for fault signal decomposition, thereby obtaining the optimal multi-band information and solving the problem that different fault signals are suitable for different wavelet functions.

[19] Since the change of fault mode will lead to the change of signal energy value, the entropy theory is used to evaluate the probability of energy change. The smaller the energy entropy, the greater the certainty of energy value change, that is, the greater the possibility of fault mode change. Therefore, the energy entropy feature is used to simultaneously characterize different fault modes in terms of numerical and probability distribution. Multiple energy entropy features are arranged in local tangent space in the data space.

[20] Optimization reduces outliers in multi-feature data. The data is dispersed in space, and the data distribution is approximately normal. The spatial optimization of multi-feature data enables redundant and conflicting multi-features to be optimized and fused to obtain simple and sensitive fault features.

[0042] Figure 1 An embodiment of the multi-energy entropy feature optimization fusion algorithm flow chart of the present invention is shown.

[0043] S1: Use different wavelet functions to perform wavelet packet multi-resolution decomposition on the input current signal (fault signal) of the fault mode to obtain different frequency band information. Select the wavelet function suitable for the fault signal according to the energy-information entropy ratio of each group of frequency bands. The corresponding frequency band is the optimal frequency band, and calculate the energy entropy of each frequency band coefficient; Specifically, the following steps are included: (1) Calculation of multi-band coefficients of different wavelet functions. Assume that the fault signal , using 9 Daubechies (dbN, N= 2,3,…10) wavelet functions commonly used for signal decomposition and reconstruction, the fault signal is decomposed by wavelet packet to obtain 9 groups of frequency band information.

[0044] (1) In the formula, Indicates the use of db N Wavelet function, signal passes through wavelet packet r After layer decomposition, we get m In the frequency band n The coefficients of the frequency band.

[0045] (2) Select a suitable wavelet function. Different wavelet functions have different decomposition effects on the same fault signal, which directly affects the effect of feature extraction. It is crucial to select a wavelet function suitable for the fault signal. The energy-information entropy ratio is the ratio of the energy of the frequency band coefficient to the information entropy, and takes into account the energy value changes and the size of the probability of occurrence of different fault modes, that is, the size of uncertainty.

[0046] The frequency band energy value corresponding to the wavelet function after wavelet packet decomposition: (2) After a system failure occurs, the uncertainty of each failure mode is related to the number of times the corresponding failure mode occurs. If a failure mode of the rectifier is Y i The probability of this failure mode occurring is P ( Y i ), then the information entropy of the frequency band coefficient obtained after the signal of the fault mode is decomposed is : (3) The energy-information entropy ratio of the corresponding frequency band is R : (4) The larger the energy-information entropy ratio is, the more suitable the selected wavelet function is for the fault signal, and the frequency band obtained after decomposition is the optimal frequency band.

[0047] (3) Calculate the energy entropy characteristics of the optimal frequency band. The fault signal is decomposed by wavelet packet r After layer decomposition, m frequency band coefficients, and calculate the energy entropy of each frequency band coefficient in the frequency band. n The energy value of the frequency band coefficient is E ( n ), the probability distribution is p (n), the energy entropy is T(n): (5) (6) (7) Therefore, based on the optimal wavelet function, the energy entropy characteristic of the optimal frequency band obtained by decomposing the fault signal through wavelet packets is: T ( n ): (8) (4) Construct the domain matrix of energy entropy characteristics. T for m dimensional matrix, T n is any data point in the matrix, m is the number of data points, and the number of nearest neighbors for each data point is determined as k , forming a neighborhood matrix.

[0048] (9) In the formula, For the n The data point j Neighboring points, n =1,2,…, N ; j =1,2,…, k (5) Calculate local coordinates. At the data point T n Find the orthogonal basis in the field matrix Q i To constitute g dimensional tangent space, in the neighborhood, calculate each point T nj Orthogonal projection to tangent space λ nj , then find the neighborhood matrix T mn The local coordinates of n : (10) (6) Establish global coordinates. Set global coordinates , for energy entropy characteristics T ( n ) is arranged in tangent space to obtain the global coordinate system. The global coordinates reflect the geometric structure of the local coordinate matrix and should meet the following requirements: (11) In the formula, is the mapping matrix to be determined; is the reconstruction error; yes The centralization matrix.

[0049] (7) Calculate the permutation matrix. Assume , S is a 0-1 selection matrix, is the energy entropy characteristic data point T n The weight matrix of , the permutation matrix is : (12) (8) Minimize the reconstruction error. This is to solve the minimum eigenvalue of the permutation matrix. The eigenvectors corresponding to the second to (g+1)th minimum eigenvalues ​​obtained by calculating the permutation matrix are the energy entropy features. T ( n ) is the global coordinate of each data point in the image, which is also the feature vector of the energy entropy feature after being optimized by local tangent space arrangement. .

[0050] (13) S2: Perform local tangent space arrangement optimization on multiple redundant and conflicting energy entropy features in the data space to obtain efficient fault features; In order to verify the robustness of the proposed method to the output voltage, a system simulation model is established, and the main parameters of the four-quadrant rectifier are shown in Table 2. The output voltage is set to change from 2000V to 2800V, and the rectifier input current signal under 15 fault modes is collected every 10V as the fault acquisition signal; in order to simulate the noise environment, white noise with a signal-to-noise ratio of 50dB is added to the fault acquisition signal. Each fault mode has 81 groups of samples, and 15 fault modes have 81×15=1215 samples.

[0051]

[0052] Specifically, the following steps are included: (1) Selection of optimal wavelet basis function The present invention considers the degree of fault feature mining and the computational cost, performs a five-layer wavelet packet decomposition on the fault signal, and selects the Daubechies (db N ) wavelet system, using db N(2~10) Nine wavelet basis functions are used to decompose the signal by wavelet packets, so that each sample and each fault mode has 9 frequency bands. The energy-information entropy ratio of each frequency band is calculated and compared. The maximum ratio indicates that the selected wavelet function is optimal and the frequency band obtained by decomposing the corresponding fault signal is optimal. Table 3 shows the selection results of the optimal wavelet function corresponding to different fault modes when the DC voltage on the output side is 2800V.

[0053]

[0054] (2) Extraction of energy entropy features and data analysis For 81 working conditions and 15 fault modes in each working condition, the fault signal is decomposed into 5 layers of wavelet packets using the optimal wavelet function, and 32 frequency bands are obtained. The energy entropy of each frequency band coefficient is calculated, that is, each fault mode has 32 energy entropy characteristics. Line graphs and box graphs are used to illustrate the distribution of energy entropy characteristics of each fault mode. The line graph describes the law and trend of energy entropy changes in all frequency bands. The box graph is a statistical graph used to reflect the distribution characteristics of the original data. It can provide information about the concentration trend and dispersion of the data, judge the skewness and severity of the data, and thus reveal whether the data obeys the normal distribution.

[0055] When the rectifier output voltage is 2800V, the line graphs of the energy entropy characteristics of the 15 fault modes are as follows: Figure 6 As shown in the figure, the energy entropy characteristics of different fault modes in the 1st to 5th frequency bands and the 13th frequency band are greater than those in other frequency bands, but the energy entropy of many fault modes overlaps with each other in the corresponding frequency bands, making it impossible to accurately identify the fault type.

[0056] The energy entropy characteristic data distribution of the rectifier is analyzed by box plot, such as Figure 7 As shown. There are many outliers in the energy entropy feature data, and all the outliers are on the larger side, indicating that the data distribution of the energy entropy feature is right-skewed and does not obey the normal distribution. The characteristic data box plot of each fault mode is very short, which means that many data points are distributed in a very small range, each data point is similar, and the data is relatively concentrated, which is consistent with the analysis of the line chart.

[0057] (3) Optimization of energy entropy characteristics and effect analysis During the feature extraction process, the feature data is normally distributed as much as possible, so that statistical inference and hypothesis verification can be better performed. Although the energy entropy feature obeys a skewed distribution, the dispersion and deviation of the data points are changed through fusion technology, and the difference between the data points is increased, so that the fused data can obey a normal or approximately normal distribution. Therefore, the multiple energy entropy feature data extracted are arranged in a local tangent space. In order to avoid different selections of neighboring points of different dimensions, the computational cost and data portability are taken into consideration. It is known that the number of rectifier fault types is C=15. According to the literature

[21] , its inherent dimension is defined as D=C-1, that is, the intrinsic dimension of the feature data fusion is 14 dimensions. Through multiple experiments, it is verified that the selected neighboring points of the data are 400. The line graph of the optimized energy entropy feature is as follows: Figure 8 As shown, the optimized energy entropy characteristics are numerically dispersed.

[0058] The data distribution of the optimized energy entropy characteristics is analyzed by box plot, such as Fig. 9 As shown. Compared with the characteristic data before optimization, the outliers are significantly reduced, and the characteristic data obeys an approximate normal distribution. After optimization, the energy entropy features have 1 or 2 outliers in normal, VT2VT4, and VD1, but the outliers are significantly reduced, and the optimization process eliminates the outliers of other fault modes, optimizes the characteristic data distribution of each fault mode, makes the box plot of the data longer, the standard deviation and variance increase, the deviation of the data decreases, the difference between the data increases, and changes from a concentrated state to a dispersed state. In terms of the symmetry of the characteristic data, except for the large difference in the length of the upper and lower whiskers of normal, VT1VT3, VT2VT4, VD1, and VD2, the data distribution is slightly skewed, and the length of the upper and lower whiskers of the remaining fault modes is approximately equal. It is believed that the characteristic data is a symmetrical distribution.

[0059] The optimization process improves the data distribution of energy entropy features. The improvement of data distribution is verified by the scatter plot of three principal component features, i.e., three-dimensional features, in each fault mode, such as Fig.10 As shown in the figure. The energy entropy characteristics of the 15 fault modes of the traction rectifier after optimization have indeed been improved, and the clustering effect is relatively ideal, but the energy entropy characteristics of each fault mode are very close in value, resulting in overlap of different samples in each fault mode. Since there are many fault modes and the fault samples are close, it is difficult to classify them by observation. Therefore, it is necessary to use pattern recognition technology to input the optimized energy entropy characteristics into the classifier for accurate fault diagnosis.

[0060] S3: Using Support Vector Machine (SVM) technology

[15] Perform pattern recognition to realize fault diagnosis of four-quadrant rectifier.

[0061] This application adopts a support vector machine as a classifier of fault features, in which the kernel function selects a radial basis function (RBF) that is robust to noise. A certain amount of Gaussian white noise is added to the collected original signal to maximize the simulation of the actual working environment of the rectifier. Through signal decomposition and feature extraction, the optimized energy entropy feature is used as the input of the classifier SVM, and the test results are compared with the actual results of the trained SVM classifier to give a diagnostic result.

[0062] Fault diagnosis result analysis and comparison specifically include the following steps: (1) Robustness analysis of output voltage In order to verify the robustness of the proposed method to the output voltage, the output voltage is set from 2000V to 2800V, and the input current signals of different modes are collected every 10V. At different output voltages, 50dB Gaussian white noise is added to the collected current. Each mode has 81 samples, and the total number of samples of 15 fault modes is 1215. The classifier SVM is used to randomly set 729 samples as training samples. After training, the remaining samples are used as test samples and compared with the actual output results to obtain the final diagnosis rate. The classifier was trained and tested 30 times, and the average diagnostic accuracy was used as the evaluation index. After running 30 times, the average diagnostic accuracy was 99.0625%. The average diagnostic results for each fault mode are shown in Table 4. Among the 486 random test samples, for the open-circuit fault of IGBT, except for VT2 (99.7917%), the average diagnostic accuracy of the rest was 100%, indicating that the proposed method has a good fault diagnosis effect for both the single open-circuit fault and the double open-circuit fault of IGBT. Although the fault diagnosis rate of the diode is lower than the accuracy of the IGBT, the fault diagnosis result is still high, indicating that the proposed method has a high diagnostic result for the open-circuit fault of IGBT and power diode.

[0063]

[0064] (2) Robustness analysis against noise In order to verify the diagnostic rate of the selected diagnostic method in different noise environments, white noise with signal-to-noise ratios of 30dB, 35dB, 40dB, 45dB, and 50dB was added to the original signal. According to the proposed method, feature extraction and optimization were performed to obtain simple and sensitive features. Then, the classifier SVM was used to run each group of features 30 times. The average, maximum, and minimum values ​​of the diagnostic accuracy of 15 fault modes are shown in Figure 2. Fig.11 shown.

[0065] When the preset ratio of signal-to-noise ratio is 30dB and 3:2, the average value after 30 diagnoses is 94.5903%, the maximum value is 96.6667%, and the minimum value is 93.1250%. As the signal-to-noise ratio increases, the diagnosis results are better than 30dB, indicating that the proposed method is robust to noise.

[0066] (3) Robustness analysis of training and testing ratios In order to verify the influence of the ratio of selected training samples and test samples on the diagnosis rate, the training and test ratios were set to 2:1, 3:2, 5:1, 10:1, 15:1, and 20:1. The average diagnosis rate was used as the evaluation index after running the data containing 30dB, 35dB, 40dB, 45dB, and 50dB white noise for 30 times. The diagnosis results are shown in the figure. Fig.12 As shown in the figure, when the training and test ratio is 3:2, the average diagnosis result of all data containing white noise is the lowest, but the corresponding diagnosis rate is higher. The diagnosis rates of data containing different white noises at 3:2 are 94.5903%, 97.5833%, 98.7917%, 98.8889%, and 99.0625%, respectively. Therefore, this method has good robustness to the training and test ratio.

[0067] (4) Comparison of different methods In order to illustrate the superiority of the proposed method, data with signal-to-noise ratios of 30dB, 35dB, 40dB, 45dB, and 50dB were used, and the training and testing ratios were 3:2. The average value of the diagnostic results after running the proposed method 30 times was used as the evaluation index for each group of data using energy features, energy entropy features, and optimized features. The results are shown in the figure. Fig.13 shown.

[0068] When energy and energy entropy are used as features, the accuracy of fault diagnosis is very low due to the similarity of feature data. However, since energy entropy takes into account the spectral distribution of energy, the diagnosis of faults with energy entropy as the feature is higher than that with energy. After the energy features and energy entropy features are arranged in the local tangent space, the redundancy and conflict between the features are eliminated, and the distribution of feature data changes from an approximate and overlapping state to a dispersed state, which is more inclined to a normal distribution. The dimension of feature data changes from 32 dimensions to 14 dimensions, and simple and sensitive features are obtained, which reduces the computational burden of the classifier. After the local tangent space arrangement optimization, the fault diagnosis rates of the two fault features are greatly improved. Among them, the degree of improvement of the diagnosis rate of the fault feature with energy entropy is greater than that of the fault diagnosis with energy. With the increase of signal-to-noise ratio, the average diagnostic accuracy is 94.59%, 97.58%, 98.79%, 98.89%, and 99.06%, respectively. Compared with before optimization, the diagnosis rates are increased by 39.27%, 41.95%, 44.32%, 43.97%, and 43.69%, respectively.

[0069] In terms of algorithm complexity, the evaluation indicators are feature fusion time, training time and diagnosis time, computational burden, and the average diagnostic accuracy of 30 diagnoses, as shown in Table 5. In terms of computational burden, several fusion algorithms involve the target dimension. Although PCA does not require other parameters, the fusion effect of PCA on nonlinear data is poor. Although KPCA and ISOMAP algorithms are suitable for dimensionality reduction of nonlinear data, KPCA is highly dependent on the kernel function, which affects the accuracy of diagnosis. Since the data is classified, the data is basically not embedded in a popular body, and the dimensionality reduction effect is relatively poor. Compared with the energy entropy feature before optimization, the three algorithms have shortened the training and diagnosis time. Although the training time is basically similar, the diagnosis time of local tangent space arrangement is the shortest. In terms of fusion time, although the fusion time of local tangent space arrangement is longer, it can accurately fuse fault features and make the average accuracy of fault diagnosis the highest.

[0070]

[0071] For the fault diagnosis of four-quadrant rectifier, a fault diagnosis device with energy entropy optimization and multi-feature fusion is proposed, which includes: data acquisition module 11, signal processing module 12, feature extraction module 13, feature optimization fusion module 14 and pattern recognition module 15. The diagnostic block diagram is shown in FIG. Figure 5 shown.

[0072] (1) Data acquisition module 11: Collect input current signals of 15 fault modes under different working conditions to form an original sample set.

[0073] (2) The signal processing module 12 includes wavelet packet decomposition and optimal frequency band selection. Wavelet packet decomposition selects Daubechies series wavelets suitable for signal decomposition and reconstruction. Based on 9 Daubechies (dbN, N= 2,3,…)10) wavelet functions, the wavelet packet decomposes the signals of different working conditions and different fault modes to obtain 9 sets of frequency band information for each fault mode. Optimal frequency band selection selects the optimal wavelet function according to the energy-information entropy ratio of each frequency band coefficient, and the corresponding frequency band information is the optimal frequency band suitable for the fault mode signal.

[0074] (3) Feature extraction module 13: Calculate the energy entropy features of the optimal frequency band and construct energy entropy features corresponding to different working conditions and different fault modes.

[0075] (4) Feature optimization fusion module 14: The energy entropy features are locally arranged in space and then fused to obtain the optimal energy entropy features.

[0076] (5) Pattern recognition module 15. The fault feature vector is randomly divided into training samples and test samples, and the SVM classifier is used for fault diagnosis. The training samples are used to train the SVM, and the test samples are used to verify the performance of the trained SVM classifier, thereby obtaining the diagnosis result.

[0077] References are as follows [1] Pan Pengyu, Hu Haitao, Xiao Donghua, et al. Frequency coupling interference mechanism and suppression strategy in “sweep frequency” dq impedance measurement of high-speed train converter[J]. Transactions of the Chinese Society of Electrotechnical Engineering, 2022, 37(4): 990-999. Pan Pengyu, Hu Haitao, Xiao Donghua, et al. Frequency couplinginterference mechanism and suppression strategy for frequency-sweeping-baseddq impedance measurement of high-Speed ​​train converter[J]. Transactions ofChina Electrotechnical Society, 2022, 37(4): 990-999. [2] Tian Zisi, Ge Xinglai. An on-line fault diagnostic method based on frequency-domain analysis for IGBTs in traction PWM rectifiers[C] / / 2016IEEE 8th International Power Electronics and Motion Control Conference(IPEMC-ECCE Asia), Hefei, China, 2016: 3403-3407. [3] Xu Shuiqing, Huang Wenzhan, He Yigang, et al. Open circuit fault diagnosis of neutral point clamped three-level grid-connected inverter based on adaptive sliding mode observer[J]. Transactions of the Chinese Society of Electrotechnical Engineering, 2023, 38(4): 1010-1022. Xu Shuiqing, Huang Wenzhan, He Yigang, et al. Open-circuit faultdiagnosis method of neutral point clamped three-level grid-connected inverterbased on adaptive sliding mode observer[J]. Transactions of ChinaElectrotechnical Society, 2023, 38(4): 1010-1022. [4] Xie Dong, Ge Xinglai. A state estimator-based approach for open-circuit fault diagnosis in single-phase cascaded H-bridge rectifiers[J]. IEEETransactions on Industry Applications, 2018, 55(2): 1608-1618. [5] Hu, Keting, Liu Zhigang, Francesco Iannuzzo, et al. Simple and effective open switch fault diagnosis of single-phase PWM rectifier[J]. Microelectronics Reliability, 2018, 88: 423-427. [6] Wu Hong, Wang Yue, Xue Yinglin, et al. MMC submodule open circuit fault diagnosis strategy under multi-power nearest level modulation[J]. Transactions of the Chinese Society of Electrotechnical Engineering, 2024, 39(1): 233-245. Wu Hong, Wang Yue, Xue Yinglin, et al. A diagnosis strategy for open-circuit submodule faults in MMCs under nearst level modulation suitable for different powers[J]. Transactions of China Electrotechnical Society, 2024, 39(1): 233-245. [7] Li Xueming, Xu Jiamin, Chen Zhiwen, et al. Real-time faultdiagnosis of pulse rectifier in traction system based on structural model[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 23(3): 2130-2143. [8] M. Arehpanahi, AM Entekhabi. A new technique for online openswitch fault detection and location in single-phase pulse width modulationrectifier[J]. International Journal of Engineering, 2022, 35(9): 1759-1764. [9] Wang Yanxin, Yan Jing, Wang Jianhua, et al. Intelligent diagnosis method of insulation defects in small sample GIS based on domain adversarial transfer convolutional neural network[J]. Transactions of the Chinese Society of Electrotechnical Engineering, 2022, 37(9): 2150-2160. Wang Yanxin, Yan Jing, Wang Jianhua, et al. Intelligent diagnosis for GIS with small samples using a novel adversarial transfer learning inconvolutional neural network[J]. Transactions of China ElectrotechnicalSociety, 2022, 37(9): 2150-2160.

[10] Cui Jiang, Guo Ruidong, Zhang Zhuoran, et al. Fault feature extraction technology of generator rotating rectifier based on improved DBN[J]. Proceedings of the CSEE, 2020, 40(7): 2369-2376. Cui Jiang, Guo Ruidong, Zhang Zhuoran, et al. Generator rotatingrectifier fault feature extraction technique based on improved DBN[J]. Proceedings of the CSEE, 2020, 40(7): 2369-2376.

[11] Liang Zhengqiu, Hao Liangliang, Zhou Yanzhen, et al. Fault diagnosis of rotating rectifier in nuclear power multiphase brushless excitation system based on convolutional neural network[J]. Transactions of China Electrotechnical Society, 2023, 38(20): 5458-5472. Liang Zhengqiu, Hao Liangliang, Zhou Yanzhen, et al. Fault diagnosis of rotating rectifier in nuclear multi-phase brushless excitation system based on convolutional neural network[J]. Transactions of China Electrotechnical Society, 2023, 38(20): 5458-5472.

[12] Zhang Guoheng, Gao Fengyang, Shi Yan, et al. Multi-feature fusion diagnosis method for open circuit fault of traction inverter based on Bayesian network[J]. Journal of Railway Science and Engineering, 2020, 17(3): 732-740. Zhang Guoheng, Gao Fengyang, Shi Yan, et al. Multi-feature fusiondiagnosis method of open circuit fault for traction inverter based on Bayesian network[J]. Journal of Railway Science and Engineering, 2020, 17(3):732-740.

[13] Li Bing, Cui Jiebing, He Yigang, et al. Fault diagnosis of active neutral point clamped three-level inverter based on energy spectrum entropy and wavelet neural network[J]. Transactions of the Chinese Society of Electrotechnical Engineering, 2020, 35(10): 2216-2225. Li Bing, Cui Jiebing, He Yigang, et al. Fault diagnosis of activeneutral point clamped three-level inverter based on energy spectrum entropyand wavelet neural network[J]. Transactions of China ElectrotechnicalSociety, 2020, 35(10): 2216-2225.

[14] Zhang Ruicheng, Bai Xiaoze, Dong Yan, et al. Open circuit fault diagnosis of wind power converter based on LMD energy entropy and positioning analysis[J]. Acta Energiae Solaris Sinica, 2023, 44(06): 484-494. Zhang Ruicheng, Bai Xiaoze, Dong Yan, et al. Open-circuit faultdiagnosis of wind power converter based on LMD energy entropy and location analysis[J]. Acta Energiae Solaris Sinica, 2023, 44(6): 484-494.

[15] Wu Xin, Yan Meng, Guo Yifan, et al. Non-intrusive load identification based on combined support vector machine with structured feature graph[J]. Automation of Electric Power Systems, 2022, 46(12): 210-219. Wu Xin, Yan Meng, Guo Yifan, et al. Non-intrusive load identification by combined support vector machine based on structured characteristic spectrum[J]. Automation of Electric Power Systems, 2022, 46(12):210-219.

[16] Zhang Shuguang. HXD3 electric locomotive[M]. Beijing: China Railway Publishing House, 2009. Zhang Shuguang. HXD3 electric locomotive[M]. Beijing: China RailwayPublishing House, 2009.

[17] Wen Yang, Yang Yuan, Ning Hongying, et al. Review of SiC MOSFET short-circuit protection technology[J]. Transactions of the Chinese Society of Electrotechnical Engineering, 2022, 37(10): 2538-2548. Wen Yang, Yang Yuan, Ning Hongying, et al. Review on short-circuitprotection technology of SiC MOSFET[J]. Transactions of ChinaElectrotechnical Society, 2022, 37(10): 2538-2548.

[18] Yang Heya, Xing Wenshuo, Xiang Xin, et al. MMC submodule open circuit fault diagnosis method based on multivariate Gaussian distribution anomaly detection model[J]. Transactions of the Chinese Society of Electrotechnical Engineering, 2023, 38(10): 2744-2756. Yang Heya, Xing Wenshuo, Xiang Xin, et al. A sub-module open-circuitfault detection and location strategy for modular multilevel converters based on multivariate gaussian distribution[J]. Transactions of ChinaElectrotechnical Society, 2023, 38(10): 2744-2756.

[19] He Hong, Tan Yonghong, Wang Yuexia. Optimal base wavelets selection for ECG noise reduction using a comprehensive entropy criterion[J].Entropy, 2015, 17(9): 6093-6109.

[20] Lu Na, Zhang Guangtao, Xiao Zhihuai, et al. Feature extraction based on adaptive multiwavelets and LTSA for rotating machinery faultdiagnosis[J]. Shock and Vibration, 2019(1): 1201084.

[21] He, Qingbo. Time–frequency manifold for nonlinear feature extraction in machinery fault diagnosis[J]Mechanical Systems and SignalProcessing, 2013, 35(1-2): 200-218. In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig.14 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the steps in the above method embodiment are implemented.

[0078] Those skilled in the art will understand that Fig.14The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0079] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiment when executing the computer program.

[0080] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented.

[0081] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0082] In summary, a fault diagnosis method based on energy entropy optimization and multi-feature fusion is proposed for the open circuit fault of the four-quadrant rectifier of heavy-duty trains. The results show that the proposed method can make the multi-feature data approximately normally distributed in space, reduce the outliers in the data, eliminate the redundancy and conflict between multiple features, and achieve the purpose of good clustering. Under different signal-to-noise ratios, 15 fault modes have a high diagnosis rate and have good robustness to DC side voltage, noise, and training-to-test ratio. Compared with other methods, the proposed method has better diagnostic effect than other methods.

[0083] The present invention is not limited to the structures which have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A four-quadrant rectifier fault diagnosis method based on energy entropy optimization and multi-feature fusion, characterized in that: The following steps are involved: Collect input current signals of fault modes under different working conditions to form an original sample set; Different wavelet functions are used to perform wavelet packet multi-resolution decomposition on the input current signal of the fault mode to obtain different frequency band information. The wavelet function suitable for the fault signal is selected according to the energy-information entropy ratio of each group of frequency bands. The corresponding frequency band is the optimal frequency band, and the energy entropy of each frequency band coefficient is calculated. According to the energy entropy of each frequency band coefficient, the energy entropy characteristics of the optimal frequency band are obtained, and the energy entropy characteristics corresponding to different working conditions and different fault modes are constructed; The multiple redundant and conflicting energy entropy features are optimized in local tangent space arrangement in the data space to obtain the optimal energy entropy feature; Support vector machine is used for pattern recognition to obtain the fault diagnosis results of four-quadrant rectifier.

2. The four-quadrant rectifier fault diagnosis method based on energy entropy optimization and multi-feature fusion according to claim 1 is characterized in that: The method uses different wavelet functions to perform wavelet packet multi-resolution decomposition on the input current signal of the fault mode to obtain different frequency band information, selects a wavelet function suitable for the fault signal according to the energy-information entropy ratio of each group of frequency bands, and the corresponding frequency band is the optimal frequency band. The step of calculating the energy entropy of each frequency band coefficient specifically includes: (1) Calculation of multi-band coefficients of different wavelet functions: Assuming the fault signal , using 9 Daubechies (dbN, N= 2,3,…10) wavelet functions commonly used for signal decomposition and reconstruction, the fault signal is decomposed by wavelet packet to obtain 9 groups of frequency band information; （1） In the formula, Indicates the use of db N Wavelet function, signal passes through wavelet packet r After layer decomposition, we get m In the frequency band n The coefficients of the frequency bands; (2) Select a suitable wavelet function: The frequency band energy value corresponding to the wavelet function after wavelet packet decomposition: （2） After a system failure occurs, the uncertainty of each failure mode is related to the number of times the corresponding failure mode occurs. If a failure mode of the rectifier is Y i The probability of this failure mode occurring is P ( Y i ), then the information entropy of the frequency band coefficient obtained after the signal of the fault mode is decomposed is : （3） The energy-information entropy ratio of the corresponding frequency band is R : （4） The larger the energy-information entropy ratio is, the more suitable the selected wavelet function is for the fault signal, and the frequency band obtained after decomposition is the optimal frequency band; (3) Calculate the energy entropy characteristics of the optimal frequency band: The fault signal is decomposed by wavelet packet r After layer decomposition, m frequency band coefficients, and calculate the energy entropy of each frequency band coefficient of the frequency band respectively; （5） （6） （7） In the formula, n The energy value of the frequency band coefficient is E ( n ), the probability distribution is p (n), the energy entropy is T (n); Therefore, based on the optimal wavelet function, the energy entropy characteristic of the optimal frequency band obtained by decomposing the fault signal through wavelet packets is: T ( n ): （8） (4) Constructing the domain matrix of energy entropy characteristics: Due to the energy entropy characteristics T for m dimensional matrix, T n is any data point in the matrix, m is the number of data points, and the number of nearest neighbors for each data point is determined as k , forming a neighborhood matrix; （9） In the formula, For the n The data point j Neighboring points, n =1,2,…, N ; j =1,2,…, k ; (5) Calculate local coordinates: At the data point T n Find the orthogonal basis in the field matrix Q i To constitute g dimensional tangent space, in the neighborhood, calculate each point T nj Orthogonal projection to tangent space λ nj , then find the neighborhood matrix T mn The local coordinates of n : （10） (6) Establish global coordinates: Set global coordinates , for energy entropy characteristics T ( n ) is arranged in tangent space to obtain the global coordinate system. The global coordinates reflect the geometric structure of the local coordinate matrix and should meet the following requirements: （11） In the formula, is the mapping matrix to be determined; is the reconstruction error; yes The centralization matrix; (7) Calculate the permutation matrix: Assume , S is a 0-1 selection matrix, is the energy entropy characteristic data point T n The weight matrix of , the permutation matrix is : （12） (8) Minimize reconstruction error: Solve the minimum eigenvalue of the permutation matrix. The eigenvector corresponding to the second to (g+1)th minimum eigenvalue obtained by calculating the permutation matrix is ​​the energy entropy feature T ( n ) is the global coordinate of each data point in the image, which is also the feature vector of the energy entropy feature after being optimized by local tangent space arrangement. : （13）。 3. The four-quadrant rectifier fault diagnosis method based on energy entropy optimization and multi-feature fusion according to claim 2 is characterized in that: The step of performing local tangent space arrangement optimization on multiple redundant and conflicting energy entropy features in the data space to obtain the optimal energy entropy feature specifically includes: (1) Selection of optimal wavelet basis function: Considering the degree of fault feature mining and computational cost, the fault signal is decomposed by wavelet packet. The Daubechies wavelet system, which is commonly used for signal decomposition and reconstruction, is selected. The wavelet basis functions of the Daubechies wavelet system are used to decompose the signal by wavelet packet to obtain multiple groups of frequency bands for each sample and each fault mode. The energy-information entropy ratio of each group of frequency bands is calculated and compared. The maximum ratio indicates that the selected wavelet function is optimal, and the frequency band obtained by decomposing the corresponding fault signal is optimal. (2) Extraction of energy entropy features and data analysis: For each operating condition, the multiple fault modes are decomposed into wavelet packets using their own optimal wavelet functions to obtain multiple frequency bands, and the energy entropy characteristics of each frequency band coefficient are calculated; (3) Optimization of energy entropy characteristics: In the feature extraction process, the feature data presents a normal distribution, and the extracted multiple energy entropy feature data are arranged in a local tangent space.

4. The four-quadrant rectifier fault diagnosis method based on energy entropy optimization and multi-feature fusion according to claim 1 or 3 is characterized in that: The step of using a support vector machine to perform pattern recognition to obtain a fault diagnosis result of a four-quadrant rectifier specifically includes: Support vector machine is used as the classifier of fault features, in which the kernel function selects the radial basis function which is robust to noise. Gaussian white noise is added to the collected original signal to simulate the real working environment of the four-quadrant rectifier. Through signal decomposition and feature extraction, the optimized energy entropy feature is used as the input of the classifier SVM. The test results are compared with the actual results of the trained SVM classifier to give the fault diagnosis results.

5. The four-quadrant rectifier fault diagnosis method based on energy entropy optimization and multi-feature fusion according to claim 1 is characterized in that: The step of using a support vector machine as a classifier of fault features specifically includes: The fault feature vector is randomly divided into training samples and test samples, and the support vector machine classifier is used for fault diagnosis. The training samples are used to train the support vector machine, and the test samples are used to verify the performance of the trained support vector machine classifier, so as to obtain the diagnosis result.

6. A four-quadrant rectifier fault diagnosis device based on energy entropy optimization and multi-feature fusion, characterized in that: include: A data acquisition module is used to collect input current signals of fault modes under different working conditions to form an original sample set; The signal processing module is used to use different wavelet functions to perform wavelet packet multi-resolution decomposition on the input current signal of the fault mode to obtain different frequency band information, and select the wavelet function suitable for the fault signal according to the energy-information entropy ratio of each group of frequency bands. The corresponding frequency band is the optimal frequency band, and the energy entropy of each frequency band coefficient is calculated; A feature extraction module is used to obtain the energy entropy characteristics of the optimal frequency band according to the energy entropy of each frequency band coefficient, and to construct energy entropy characteristics corresponding to different working conditions and different fault modes; The feature optimization fusion module is used to optimize the local tangent space arrangement of multiple redundant and conflicting energy entropy features in the data space to obtain the optimal energy entropy feature; The pattern recognition module is used to perform pattern recognition using a support vector machine to obtain a fault diagnosis result of a four-quadrant rectifier.

7. A computer-readable storage medium, characterized in that: Used to store a computer program, wherein when the computer program is executed by a processor, it implements the four-quadrant rectifier fault diagnosis method based on energy entropy optimization and multi-feature fusion as described in any one of claims 1 to 5.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

Images