A switch cabinet defect diagnosis method based on multi-information fusion and related products

Abstract

The application belongs to the field of electrical equipment fault diagnosis, and particularly relates to a switch cabinet defect diagnosis method based on multi-information fusion and related products, which comprises the following steps: establishing detection of the switch cabinet by using multiple detection methods, and extracting feature vectors from the detection signals; constructing different defect diagnosis models for different detection methods by using the dimension-reduced feature set; obtaining the to-be-tested sample of the to-be-tested switch cabinet by using multiple detection methods, and inputting the to-be-tested sample into the corresponding defect diagnosis model; obtaining the basic allocation probability, fusing to obtain the final comprehensive allocation probability, and determining the final prediction result; the combination of multiple detection methods can make up for the limitations of a single detection method, can more comprehensively and accurately identify multiple defect types in the switch cabinet, and can fuse the outputs of different defect detection models, thereby significantly improving the robustness and accuracy of diagnosis.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of electrical equipment fault diagnosis, in particular to a switch cabinet defect diagnosis method based on multi-information fusion and related products. BACKGROUND

[0002] As an important device in the power system, switch cabinets are widely used in power transmission and distribution, substations and other places. The reliability of their operating state is crucial to the stability of the entire power system. However, switch cabinets are susceptible to environmental factors, operational errors, and equipment aging during long-term operation, leading to various defects. These defects can cause electrical faults, even damage to equipment, power outages, and other serious consequences. Therefore, it is of great significance to effectively detect and diagnose defects in switch cabinets.

[0003] In the prior art, defect detection methods for switch cabinets are mostly based on a single detection technology. However, due to the complexity of electrical equipment faults, a single detection method often fails to comprehensively and accurately identify and diagnose various defect types. Even though there are some fusion technologies at present, how to effectively fuse the signal information of different detection methods to obtain a unified and reliable diagnosis result is still a technical problem.

[0004] Therefore, there is an urgent need for a new method that can integrate the features of multiple detection methods and use more intelligent fusion technology to improve the accuracy and reliability of switch cabinet defect diagnosis. SUMMARY

[0005] To solve the above technical problems, the present application provides a switch cabinet defect diagnosis method based on multi-information fusion and related products. Through comprehensive analysis of multiple detection methods (such as transient ground voltage detection, ultrasonic detection, and ultra-high frequency detection), advanced dimensionality reduction algorithms and D-S evidence theory fusion technology are used to effectively improve the accuracy, robustness, and reliability of switch cabinet defect diagnosis.

[0006] The present application is realized by the following technical solutions:

[0007] A switch cabinet defect diagnosis method based on multi-information fusion, comprising:

[0008] Establishing a switch cabinet test platform to simulate various typical defects;

[0009] Using multiple detection methods to detect the switch cabinet and extracting feature vectors from the detection signals;

[0010] Dimensionality reduction is performed on the feature vectors to obtain a reduced feature set;

[0011] Using the reduced feature set, different defect diagnosis models are constructed for different detection methods;

[0012] Obtain the to-be-tested sample of the to-be-tested switch cabinet through various detection methods, and input the to-be-tested sample into a corresponding defect diagnosis model;

[0013] Obtain the basic allocation probability of the to-be-tested sample through different defect diagnosis models, fuse the basic allocation probability to obtain a final comprehensive allocation probability, and determine the final prediction result through the maximum support principle.

[0014] Specifically, the switch cabinet test platform is installed with a TEV sensor, an ultrasonic sensor, a UHF sensor, a data acquisition card, a preamplifier and a synchronous collector.

[0015] The detection methods include transient earth voltage detection, ultrasonic detection and ultra-high frequency detection; the transient earth voltage detection is performed through the TEV sensor, the data acquisition card and the synchronous collector, the ultrasonic detection is performed through the ultrasonic sensor, the data acquisition card, the preamplifier and the synchronous collector, and the ultra-high frequency detection is performed through the UHF sensor, the data acquisition card, the preamplifier and the synchronous collector.

[0016] Obtain the original transient earth voltage signal, filter and denoise the original transient earth voltage signal, calculate the maximum amplitude A of the processed transient earth voltage signal max , the amplitude mean μ A , the amplitude standard deviation σ A , the phase mean μ φ , the phase standard deviation σ φ , the total energy E total , the frequency mean μ f and the frequency standard deviation σ f ; and construct a feature vector F TEV =[A max , μ A , σ A , μ φ , σ φ μ φ , E total , μ f , σ f ] T ;

[0017] Obtain the original ultrasonic signal, filter and remove high-frequency noise and low-frequency interference; calculate the peak amplitude U peak , the effective value μ U , the amplitude standard deviation σ U , the instantaneous limit mean , the instantaneous phase standard deviation δ U , the total signal energy E U , the spectral center frequency f U and the spectral bandwidth B U ; and construct a feature vector

[0018] Get the original UHF signal and perform bandpass filtering on it; extract the maximum signal amplitude P of the processed signal max , mean amplitude μ P , amplitude standard deviation σ P , Phase Center Phase standard deviation Total energy E P , main frequency f max and frequency extension bandwidth W P ; Construct feature vector

[0019]

[0020] Specifically, the method of obtaining the feature set after dimensionality reduction includes:

[0021] Calculate the mean of the eigenvectors F for F TEV 、F US or F UHF , F (i) For the first i characteristic components;

[0022] Calculate the standard deviation of the eigenvector Where N is N TEV 、N US or N UHF ;

[0023] Normalize the eigenvector to obtain the standardized eigenvector

[0024] Determine the Gaussian kernel function Among them, x p and x q is the first feature vector in the original p The characteristic components and q feature components, σ The kernel width parameter is automatically selected based on cross-validation;

[0025] Constructing the kernel matrix K , the element K in the kernel matrix pq =k(x p , x q ), and centralize the kernel matrix K′=K-1 N K-K1 N +1 N K1 N , where 1 N Each element is N×N matrix;

[0026] Perform eigenvalue decomposition on the centralized kernel matrix K′, K′v k =λ k v k , and obtain the eigenvalue λ k and its corresponding eigenvector v k ;

[0027] Sort the eigenvalues ​​by size, determine the dimension M of the vector after dimensionality reduction, select the first M eigenvectors to form the feature matrix V, and project the original eigenvector to obtain the eigenvector F1=V after dimensionality reduction. T K′;

[0028] Reduce the dimension of multiple feature vectors to construct a feature vector set.

[0029] Furthermore, the method for obtaining the feature set after dimensionality reduction also includes:

[0030] After obtaining the eigenvector F1 after dimensionality reduction, the independent components are obtained by ICA separation. in, For the r Separation matrix of independent components;

[0031] Evaluate each independent component s based on mutual information r (n) contribution to the recognition task, and set the contribution threshold, select the independent components greater than the contribution threshold, and construct the secondary dimensionality reduction feature vector F2 = [s1(n), s2(n), ..., s K (n)] T , where K is the number of independent components retained after adaptive selection;

[0032] Reduce the dimension of multiple eigenvectors to construct a set of secondary eigenvectors.

[0033] Optionally, a feature vector set corresponding to transient ground voltage detection and a corresponding defect type label are constructed as a data set, and the data set is divided into a training set and a validation set;

[0034] The support vector machine is trained using the training set, and the model is evaluated using the validation set. The parameters are adjusted to obtain a defect detection model based on transient ground voltage.

[0035] The feature vector set corresponding to ultrasonic testing and the corresponding defect type label are constructed into a dataset, and the dataset is divided into a training set and a validation set;

[0036] The random forest model is trained using the training set, and the model is evaluated using the validation set. The parameters are adjusted to obtain an ultrasonic-based defect detection model.

[0037] The feature vector set and the corresponding defect type label corresponding to the UHF detection are constructed into a dataset, and the dataset is divided into a training set and a validation set;

[0038] The naive Bayes classifier is trained using the training set, and the model is evaluated using the validation set. The parameters are adjusted to obtain a defect detection model based on UHF.

[0039] Specifically, the method of fusing the outputs of multiple defect diagnosis models includes:

[0040] Based on the number of types of simulated typical defects, a defect type set Θ = {θ1, θ2, ..., θ M}, where M is the total number of defect types;

[0041] Input the test sample u of the switch cabinet to be tested into the defect detection model and obtain the defect type prediction probability distribution of the test sample u in, For the vth model, the sample u belongs to defect θ M The probability of ; v = 1, 2, 3, and corresponds to the defect detection model based on transient ground voltage detection, the defect detection model based on ultrasonic detection, and the defect detection model based on ultra-high frequency detection, respectively;

[0042] Order v Defect detection model for the sample to be tested u Give defects t The basic distribution probability and

[0043] Obtaining the basic distribution probability of the defect detection model based on transient ground voltage detection Obtaining the basic distribution probability of the defect detection model based on ultrasonic testing Obtaining the basic distribution probability of the defect detection model based on UHF detection

[0044] right and Perform fusion to obtain the basic distribution probability after fusion

[0045] right and Perform fusion to obtain the basic distribution probability after fusion

[0046] right and Perform fusion to obtain the basic distribution probability after fusion

[0047] right and Perform fusion to obtain the basic distribution probability after fusion

[0048] right and Perform fusion to obtain the final comprehensive distribution probability

[0049] Normalize the final comprehensive allocation probability

[0050] Circularly obtain samples to be tested u The final combined assigned probability relative to all defect types;

[0051] Determine the output sample through the maximum support principle u Predicted defect types

[0052] Optionally, and Methods for performing fusion include:

[0053] Determine the conflict coefficient in, A and B is the set of defect types Θ Different subsets of For subset A The basic distribution probability of the defect detection model based on transient ground voltage detection, is the basic distribution probability of subset B in the defect detection model based on ultrasonic testing, Indicates no intersection;

[0054] Calculate the basic distribution probability after fusion

[0055] The basic distribution probability of the output fusion after normalization

[0056] right and Methods for performing fusion include:

[0057] Determine the conflict coefficient Among them, A and B are different subsets of the defect type set Θ, For subset A The basic distribution probability of the defect detection model based on transient ground voltage detection, is the basic distribution probability of subset B in the defect detection model based on ultrasonic testing, Indicates no intersection;

[0058] Calculate the basic distribution probability after fusion

[0059] output the fused basic assignment probability after normalization

[0060] fusing and The method of fusing comprises:

[0061] determining a conflict coefficient wherein, A and B is a different subset of the set of defect types Θ , is a basic assignment probability of the subset B A in a defect detection model based on transient ground voltage detection, is a basic assignment probability of the subset B in a defect detection model based on ultrasonic wave detection, denotes no intersection;

[0062] calculating a fused basic assignment probability

[0063] output the fused basic assignment probability after normalization

[0064] A switch cabinet defect diagnosis terminal based on multi-information fusion comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements a switch cabinet defect diagnosis method based on multi-information fusion as described above when executing the computer program.

[0065] A computer readable storage medium stores a computer program, and the computer program implements a switch cabinet defect diagnosis method based on multi-information fusion as described above when executed by a processor.

[0066] A computer program product comprises a computer program / instruction, and the computer program / instruction implements a switch cabinet defect diagnosis method based on multi-information fusion as described above when executed by a processor.

[0067] Compared with the prior art, the present application has the following advantages and beneficial effects:

[0068] The present application builds an experimental platform, simulates various typical defects, adopts various detection methods such as transient ground voltage, ultrasonic wave, and ultra-high frequency, extracts feature vectors from detection signals, and performs dimension reduction processing to obtain a reduced feature set. Based on the reduced feature set, different defect diagnosis models are constructed, feature vectors of a switch cabinet to be tested are obtained and input into corresponding models, outputs of the models are fused, and finally a comprehensive diagnosis result is obtained.

[0069] The application can more comprehensively and accurately identify various defect types in the switch cabinet by combining various detection means, and fuses the outputs of different defect detection models, thereby significantly improving the robustness and accuracy of diagnosis. BRIEF DESCRIPTION OF DRAWINGS

[0070] The accompanying drawings illustrate exemplary embodiments of the present application and together with the general description of the application given above and the detailed description of the embodiments below, serve to explain the principles of the present application. In such drawings:

[0071] Figure 1 FIG. 1 is a structural schematic diagram of a switch cabinet defect diagnosis method based on multi-information fusion according to the present application. DETAILED DESCRIPTION

[0072] In order to make the objectives, technical solutions and advantages of the present application clearer, further detailed description will be made to the present application in combination with the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the related content, and are not a limitation on the present application.

[0073] In addition, it should be further noted that only parts related to the present application are shown in the drawings for ease of description.

[0074] The embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0075] Embodiment One

[0076] As shown in FIG. 1, a switch cabinet defect diagnosis method based on multi-information fusion includes: Figure 1

[0077] A switch cabinet test platform is established to simulate various typical defects. A switch cabinet test platform is built to meet the actual working conditions, which can simulate the running state of the switch cabinet and introduce artificial defects in the test platform, including typical defect types such as metal protrusions, air gaps, metal suspensions and internal insulation discharge.

[0078] Various detection methods are used to detect the switch cabinet, and feature vectors are extracted from the detection signals. The methods include transient earth voltage detection (TEV detection), ultrasonic detection and ultra-high frequency detection (UHF detection). After the data collected by each detection method is processed, the feature vectors are extracted, which can reflect the physical characteristics of various defects in the switch cabinet, such as signal amplitude, frequency, phase and other information.

[0079] ​The feature vectors are reduced in dimension to obtain a reduced feature set; a simplified feature set that effectively preserves information is obtained after dimension reduction, providing efficient input for subsequent diagnosis.

[0080] Different defect diagnosis models are constructed for different detection methods using the reduced feature set; the data of each detection method (such as TEV, ultrasonic wave, UHF) corresponds to an independent model.

[0081] The test sample of the switch cabinet to be tested is obtained by multiple detection methods, and the test sample is input into the corresponding defect diagnosis model; the signal data is obtained from the detection platform, and the feature vector is extracted, and then the feature vector of the sample is input into the corresponding defect diagnosis model.

[0082] The basic allocation probability of the test sample is obtained by different defect diagnosis models, and the model outputs the basic allocation probability of the sample for each defect type. The basic allocation probability reflects the possibility of the sample belonging to a certain defect type.

[0083] The final comprehensive allocation probability is obtained by fusing the basic allocation probability of each model, and the final prediction result is determined by the maximum support principle. That is, the defect type with the maximum comprehensive allocation probability is selected as the final prediction result.

[0084] The switch cabinet test platform is installed with TEV sensor, ultrasonic wave sensor, UHF sensor, data acquisition card, preamplifier and synchronous collector. The detection methods include: transient earth voltage detection, ultrasonic wave detection and ultra-high frequency detection; the transient earth voltage detection is performed by the TEV sensor, data acquisition card and synchronous collector, the ultrasonic wave detection is performed by the ultrasonic wave sensor, data acquisition card, preamplifier and synchronous collector, and the ultra-high frequency detection is performed by the UHF sensor, data acquisition card, preamplifier and synchronous collector.

[0085] The TEV sensor is used to detect the transient earth voltage (TEV), which mainly captures the voltage fluctuations caused by partial discharge in the switch cabinet. The fluctuations reflect the partial insulation performance of electrical equipment and can reveal potential discharge defects. During the detection process, the sensor collects signals, which are converted by the data acquisition card and synchronized by the synchronous collector to ensure the consistency of the signal timing.

[0086] The ultrasonic wave sensor is used to detect the ultrasonic wave signals generated by partial discharge. This signal can penetrate the insulating medium and reflect the location and intensity of internal defects. The signals collected by the ultrasonic wave sensor are enhanced by the preamplifier, transmitted to the data acquisition card for sampling, and finally synchronized by the synchronous collector for signal timing.

[0087] UHF sensor is used to capture the ultra-high frequency electromagnetic wave signal generated by partial discharge, especially suitable for detection of partial discharge in gas insulated equipment. The signal collected by the sensor is processed by band-pass filter and preamplifier, then sampled by data acquisition card and synchronized by synchronous collector.

[0088] Obtain the original transient earth voltage signal, filter and denoise it; that is, the signal usually contains noise components after collection, and filter technology (such as low-pass filter or high-pass filter) is used to preprocess the signal to remove irrelevant noise and retain effective signal.

[0089] Calculate the maximum amplitude A of the processed transient earth voltage signal max , the amplitude mean μ A , the amplitude standard deviation σ A , the phase mean μ φ , the phase standard deviation σ φ , the total energy E total , the frequency mean μ f and the frequency standard deviation σ f ; construct the feature vector F TEV = [A max , μ A , σ A , μ φ , σ φ , E total , μ f , σ f ] T ;

[0090] Obtain the original ultrasonic signal, remove high-frequency noise and low-frequency interference by filtering; use a filter to remove high-frequency noise and low-frequency interference in the ultrasonic signal, and retain the core information of the signal.

[0091] Calculate the peak amplitude U of the processed ultrasonic signal peak , the effective value μ U , the amplitude standard deviation σ U , the instantaneous limit mean the instantaneous phase standard deviation δ U , the total energy E of the signal U , the spectral center frequency f U and the spectral bandwidth B U ; construct the feature vector

[0092] Obtain the original ultra-high frequency signal, and perform band-pass filtering on it; band-pass filter the UHF signal to remove irrelevant frequency components and retain the effective frequency band.

[0093] Extract the maximum signal amplitude P of the processed signal max, mean amplitude μ P , amplitude standard deviation σ P , phase center phase standard deviation total energy E P , dominant frequency f max and frequency spread bandwidth W P ; construct a feature vector

[0094] After obtaining the above feature vector, the method for obtaining the reduced dimension feature set includes:

[0095] Calculate the mean of the feature vector F is F TEV , F US or F UHF , F (i) is the first i feature component in F; by summing each component in the feature vector and dividing by the number of components, the average level of the overall feature can be obtained, which can reflect the concentration trend of the feature vector, that is, describe the center position of the overall feature vector.

[0096] To measure the distribution width of the feature value, the standard deviation of the feature vector is calculated where N is N TEV , N US or N UHF ; by calculating the difference between each feature component and the mean, then squaring these differences, and finally taking the square root, the dispersion of the feature component can be obtained. A larger standard deviation indicates that the feature component fluctuates greatly, and a smaller standard deviation indicates that the fluctuation is smaller.

[0097] Standardize the feature vector to eliminate the scale difference between different feature components, and obtain the standardized feature vector Through standardization, each component of the feature vector will have zero mean and unit variance. Standardization is to scale each feature component according to its mean and standard deviation, ensuring that the mean of the feature component is zero and the standard deviation is one.

[0098] Measure the similarity between different feature components in the feature vector through the Gaussian kernel function, the Gaussian kernel function where x p and x q are the pth and q feature components in the original feature vector, σ is the kernel width parameter automatically selected based on cross-validation; based on Euclidean distance, the difference between two feature components is measured. The Gaussian kernel function decays exponentially, so that feature components with smaller distances have higher similarity, and components with larger distances have rapidly decreasing similarity.

[0099] Construct the kernel matrix K, the element K in the kernel matrix pq =k(x p , x q ), and centralize the kernel matrix K′=K-1 N K-K1 N +1 N K1 N , among which 1 N Each element is N×N matrix; each element K of the kernel matrix pq =k(x p , x q ) represents the pth eigenvalue and the pth eigenvalue of the eigenvector q The similarity between the feature components is calculated by centering the entire kernel matrix (removing the mean).

[0100] Perform eigenvalue decomposition on the centralized kernel matrix K′, K′v k =λ k v k , and obtain the eigenvalues λ k and its corresponding eigenvector v k ; The eigenvalue represents the importance of the eigenvector, and the eigenvector is the new feature axis after dimensionality reduction.

[0101] Sort the eigenvalues ​​by size, determine the dimension M of the vector after dimensionality reduction, select the first M eigenvectors to form the feature matrix V, and project the original eigenvector into the new space to obtain the eigenvector F1=V after dimensionality reduction. T K′;

[0102] Reduce the dimensionality of multiple feature vectors to obtain a feature set with reduced dimensionality.

[0103] In order to further reduce the complexity of the data, after obtaining the eigenvector F1 after dimensionality reduction, the independent components are obtained by ICA separation. in, For the r The separation matrix of the independent components can be optimized iteratively to maximize the non-Gaussianity, and independent signals can be obtained. Independent component analysis (ICA) is a signal separation technique used to decompose a linear combination signal into independent source signals.

[0104] Evaluate each independent component s based on mutual information r (n) Contribution to the recognition task. The higher the mutual information value, the greater the contribution of the component to the task. Based on the set contribution threshold, independent components above the threshold are selected to form the feature vector set after secondary dimensionality reduction.

[0105] and set a contribution threshold, select independent components greater than the contribution threshold, and construct a secondary dimension reduction feature vector F2=[s1(n), s2(n),..., s K (n)] T where K is the number of independent components reserved after adaptive selection;

[0106] Finally, the multiple feature vectors after dimension reduction construct a feature vector set.

[0107] Example Three

[0108] The feature vector set (such as maximum amplitude, amplitude mean, total energy, etc.) corresponding to the transient voltage detection and the corresponding defect type label (such as partial discharge, insulation damage, etc.) are constructed into a data set, and the data set is divided into a training set and a validation set; the training set is used to train the model, and the validation set is used to evaluate the performance of the model during the training process to avoid model overfitting. A common division method is to use 80% of the data for training and 20% of the data for validation.

[0109] The support vector machine is trained through the training set, and the model is evaluated through the validation set to adjust the parameters to obtain a defect detection model based on transient voltage. The support vector machine (SVM) classifies by finding a hyperplane that maximizes the class interval. Using the feature vectors and labels in the training set, the SVM model learns how to distinguish different defect types.

[0110] The feature vector set (such as peak amplitude, effective value, spectral center frequency, etc.) corresponding to the ultrasonic detection and the corresponding defect type label are constructed into a data set, and the data set is divided into a training set and a validation set;

[0111] The random forest model is trained through the training set, and the model is evaluated through the validation set to adjust the parameters to obtain a defect detection model based on ultrasonic waves; random forest is a classification method by constructing multiple decision trees. Each tree is trained by randomly sampling from the training set, and the final prediction result is determined by majority voting. Random forest reduces overfitting and improves generalization performance through this "multiple tree" method.

[0112] The feature vector set corresponding to the ultra-high frequency detection and the corresponding defect type label are constructed into a data set, and the data set is divided into a training set and a validation set;

[0113] The Naive Bayes classifier is trained through the training set, and the model is evaluated through the validation set to adjust the parameters to obtain a defect detection model based on ultra-high frequency. Naive Bayes classifier calculates the posterior probability of each class by assuming that the features are independent, and selects the class with the maximum posterior probability as the prediction result. The Naive Bayes classifier is trained using the ultra-high frequency detection feature vectors and label data in the training set.

[0114] In this embodiment, three different training models, namely Support Vector Machine (SVM), Random Forest (RF) and Naive Bayes (NB), are used for transient earth voltage (TEV) detection, ultrasonic detection and ultra-high frequency (UHF) detection respectively. The reason is that the signal characteristics and data characteristics of each detection method are considered.

[0115] Transient earth voltage signals have high complexity and high-dimensional characteristics, especially the transient signals generated during partial discharge. The data characteristics of these signals are usually distributed in high-dimensional space. Support Vector Machine (SVM) is good at processing high-dimensional data and can effectively find the optimal classification hyperplane in complex data sets. By using kernel functions, SVM can also handle linearly inseparable cases, which is consistent with the nonlinear characteristics of transient earth voltage signals.

[0116] Ultrasonic signals are affected by environmental noise, equipment state and other factors during detection, and the signal characteristics often show high randomness and nonlinearity. Random Forest (RF) classifies by integrating multiple decision trees, and each tree is randomly sampled from the data set during training. RF can effectively handle noise in ultrasonic signals through this "randomness", and RF model has strong adaptability to non-linear and complex feature distribution.

[0117] Ultra-high frequency signals in partial discharge detection often show clear statistical distribution characteristics, such as signal amplitude, frequency, phase, etc. Naive Bayes (NB) is a classification algorithm based on Bayes theorem, which assumes that features are independent of each other and is suitable for processing data sets with clear probability distribution. The dimensions of the features of the ultra-high frequency detection signal often have high independence, so using NB classifier can quickly and accurately infer the defect type to which the signal belongs.

[0118] Embodiment Four

[0119] The method for fusing the outputs of multiple defect diagnosis models includes:

[0120] Based on the number of types of simulated typical defects, a defect type set Θ = {θ1, θ2,..., θM} is constructed, where M is the total number of defect types; the set contains all possible defect types that may occur in the system, ensuring that each detection model is based on the same defect type for output. M

[0121] The to-be-tested sample u of the to-be-tested switch cabinet is input into the defect detection model, and the defect type prediction probability distribution of the to-be-tested sample u is obtained. u u is the probability that the vth model predicts that the sample u belongs to the defect θv. M ​​​​probability; v = 1, 2, 3, and respectively correspond to the defect detection model based on transient ground voltage detection, the defect detection model based on ultrasonic wave detection, and the defect detection model based on ultra-high frequency detection; obtaining the defect prediction probability distribution of each model provides the preliminary result of classifying the sample. Through the prediction probability, the possibility that the sample may belong to each defect type can be obtained.

[0122] Let the first v defect detection model be assigned a basic allocation probability of defect u to the sample to be tested t . and convert the prediction probability distribution of each detection model into a basic allocation probability. The basic allocation probability is an important concept in the D-S evidence theory, which represents the support degree of the model for each defect type, and the sum of the basic allocation probabilities of all defect types is equal to 1.

[0123] Obtain the basic allocation probability of the defect detection model based on transient ground voltage detection Obtain the basic allocation probability of the defect detection model based on ultrasonic wave detection Obtain the basic allocation probability of the defect detection model based on ultra-high frequency detection

[0124] Fuse and to obtain the fused basic allocation probability

[0125] Fuse and to obtain the fused basic allocation probability

[0126] Fuse and to obtain the fused basic allocation probability

[0127] Fuse and to obtain the fused basic allocation probability

[0128] Fuse and to obtain the final comprehensive allocation probability

[0129] Through step-by-step fusion of the outputs of all models, the final comprehensive basic allocation probability is obtained, and the final comprehensive allocation probability is normalized

[0130] Loop to obtain the sample to be testedu The final combined assigned probability relative to all defect types;

[0131] Determine the output sample through the maximum support principle u Predicted defect types

[0132] The three preliminary fusion methods are the same.

[0133] right and Methods for performing fusion include:

[0134] The conflict coefficient is used to measure the inconsistency between the outputs of the two models, reflecting the degree of conflict between the results of the transient ground voltage detection model and the ultrasonic detection model. in, A and B are different subsets of the defect type set Θ, For subset A The basic distribution probability of the defect detection model based on transient ground voltage detection, For subset B In the basic distribution probability of the defect detection model based on ultrasonic testing, Indicates no intersection; that is, a conflict occurs only when two models make inconsistent judgments about different subsets (i.e., no intersection).

[0135] Calculate the basic distribution probability after fusion A∩B=θ t It means that both the transient voltage detection model and the ultrasonic detection model believe that the sample may belong to the defect type θ t situation.

[0136] The basic distribution probability of the output fusion after normalization

[0137] right and Methods for performing fusion include:

[0138] Determine the conflict coefficient in, A and B is the set of defect types Θ Different subsets of For subset A The basic distribution probability of the defect detection model based on transient ground voltage detection, is the basic distribution probability of subset B in the defect detection model based on ultrasonic testing, Indicates no intersection;

[0139] Calculate the basic distribution probability after fusion

[0140] outputting the fused basic assignment probability after normalization

[0141] to and The method of fusing comprises:

[0142] determining a conflict coefficient wherein, A and B are different subsets of the set of defect types Θ, is a basic assignment probability of the subset A of the defect detection model based on transient ground voltage detection, is a basic assignment probability of the subset B of the defect detection model based on ultrasonic wave detection, denotes no intersection;

[0143] calculating a fused basic assignment probability

[0144] outputting the fused basic assignment probability after normalization

[0145] Embodiment five

[0146] A switchgear defect diagnosis terminal based on multi-information fusion comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements a switchgear defect diagnosis method based on multi-information fusion as described above when executing the computer program.

[0147] The memory can be used to store software programs and modules, and the processor executes various functional applications and data processing of the terminal by running the software programs and modules stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one execution program required by a function, etc.

[0148] The data storage area can store data created according to the use of the terminal, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state memory device.

[0149] A computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement a switchgear defect diagnosis method based on multi-information fusion as described above.

[0150] Without loss of generality, computer-readable media can include computer storage media and communication media. Computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, RAM, ROM, EPROM, EEPROM, flash memory or other solid state memory technology, CD-ROM, DVD, or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices. It should be understood by those skilled in the art that computer storage media does not limit the computer-readable media to the foregoing examples. The system memory and the mass storage device can be collectively referred to as memory.

[0151] A computer program product includes computer programs / instructions that, when executed by a processor, implement a switch cabinet defect diagnosis method based on multi-information fusion as described above.

[0152] A computer program product includes computer programs or instruction sets for performing specific tasks or implementing specific functions. These programs or instructions are designed to be executed by a processor, thereby implementing a series of predefined steps or operations. The program product can be stored in various forms of computer storage media, such as memory, hard disk, solid state drive, optical disk or other forms of digital storage devices. It can exist in the form of compiled binary code, or in the form of scripts or bytecodes executable by an interpreter. The program product, through carefully designed algorithms and logical instructions, enables the processor to process data in a specific order and manner, complete various functions such as data analysis, user interaction, device control, etc.

[0153] In the description of the present specification, the description of the terms "one embodiment / way", "some embodiments / ways", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment / way or example are included in at least one embodiment / way or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment / way or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments / ways or examples. In addition, the skilled in the art can combine and combine the different embodiments / ways or examples described in the present specification and the features of the different embodiments / ways or examples without contradiction.

[0154] Furthermore, the terms "first", "second", etc. are used herein for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly pointing to the number of technical features indicated. Thus, features defined with "first", "second" etc. can explicitly or implicitly include at least one of such features. In the description of the application, the meaning of "plurality" is at least two, for example two, three, etc., unless explicitly and specifically defined otherwise.

[0155] Those skilled in the art will understand that the above-mentioned embodiments are merely intended to clearly illustrate the present application, and are not intended to limit the scope of the present application. Other changes or modifications can be made to the above-mentioned embodiments by those skilled in the art, and these changes or modifications are still within the scope of the present application.

Claims

1. A switch cabinet defect diagnosis method based on multi-information fusion, characterized in that: include: Establish a switchgear test platform to simulate various typical defects; Use multiple detection methods to detect switchgear and extract feature vectors from detection signals; Reduce the dimension of the feature vector to obtain the reduced dimension feature set; Using the reduced feature set, different defect diagnosis models were constructed for different detection methods. A support vector machine was trained using the training set to obtain a defect detection model based on transient ground voltage. A random forest model was trained using the training set to obtain a defect detection model based on ultrasonic waves. A naive Bayes classifier was trained using the training set to obtain a defect detection model based on ultra-high frequency. Obtain test samples of the switchgear to be tested through various detection methods, and input the test samples into the corresponding defect diagnosis model; The basic distribution probabilities of the samples to be tested are obtained through different defect diagnosis models, and the basic distribution probabilities are fused to obtain the final comprehensive distribution probability. The final prediction result is determined by the maximum support principle. The fusion method includes: Obtaining the basic distribution probability of the defect detection model based on transient ground voltage detection Obtaining the basic distribution probability of the defect detection model based on ultrasonic testing Obtaining the basic distribution probability of the defect detection model based on UHF detection respectively and and as well as and Perform pairwise fusion to obtain the first intermediate distribution probability Second intermediate distribution probability and the third intermediate distribution probability The first intermediate distribution probability and the second intermediate distribution probability Perform fusion to obtain the fourth intermediate distribution probability The fourth intermediate distribution probability and the third intermediate distribution probability Fusion is performed to obtain the final comprehensive distribution probability 2. The switch cabinet defect diagnosis method based on multi-information fusion according to claim 1 is characterized in that: The switchgear test platform is equipped with TEV sensors, ultrasonic sensors, UHF sensors, data acquisition cards, preamplifiers, and synchronous collectors; Detection methods include: transient ground voltage detection, ultrasonic detection and UHF detection; transient ground voltage detection is performed using TEV sensors, data acquisition cards and synchronous collectors; ultrasonic detection is performed using ultrasonic sensors, data acquisition cards, preamplifiers and synchronous collectors; and UHF detection is performed using UHF sensors, data acquisition cards, preamplifiers and synchronous collectors. Obtain the original transient ground voltage signal, filter and denoise it; calculate the maximum amplitude A of the processed transient ground voltage signal max , amplitude mean μ A , amplitude standard deviation σ A , phase mean μ φ , phase standard deviation σ φ , total energy E total , frequency mean μ f and the frequency standard deviation σ f ; Construct feature vector F TEV =[A max , μ A , σ A , μ φ , σ φ , E total , μ f , σ f ] T ; Obtain the original ultrasonic signal, remove high-frequency noise and low-frequency interference by filtering; calculate the peak amplitude U of the processed ultrasonic signal peak , effective value μ U , amplitude standard deviation σ U , Instantaneous limit mean Instantaneous phase standard deviation δ U , total signal energy E U , spectrum center frequency f U and spectrum bandwidth B U ; Construct feature vector Get the original UHF signal and perform bandpass filtering on it; extract the maximum signal amplitude P of the processed signal max , mean amplitude μ P , amplitude standard deviation σ P , Phase Center Phase standard deviation Total energy E P , main frequency f max and frequency extension bandwidth W P ; Construct feature vector 3. The switch cabinet defect diagnosis method based on multi-information fusion according to claim 2 is characterized in that: Methods for obtaining the feature set after dimensionality reduction include: Calculate the mean of the eigenvectors F for F TEV 、F US or F UHF , F (i) is the i-th characteristic component in F; Calculate the standard deviation of the eigenvector Where N is N TEV 、N US or N UHT ; Normalize the eigenvector to obtain the standardized eigenvector Determine the Gaussian kernel function Among them, x p and x q are the p-th and q-th feature components in the original feature vector, and σ is the kernel width parameter automatically selected based on cross-validation; Construct the kernel matrix K, the element K in the kernel matrix pq =k(x p , x q ), and centralize the kernel matrix K′=K-1 N K-K1 N +1NK1 N , where 1 N Each element is N×N matrix; Perform eigenvalue decomposition on the centralized kernel matrix K′, K′v k =λ k v k , and obtain the eigenvalue λ k and its corresponding eigenvector v k ; Sort the eigenvalues ​​by size, determine the dimension H of the vector after dimensionality reduction, select the first H eigenvectors to form the feature matrix V, and project the original eigenvector to obtain the eigenvector F1=V after dimensionality reduction. T K′; Reduce the dimension of multiple feature vectors to construct a feature vector set.

4. The switch cabinet defect diagnosis method based on multi-information fusion according to claim 3 is characterized in that: Methods for obtaining the feature set after dimensionality reduction also include: After obtaining the eigenvector F1 after dimensionality reduction, the independent components are obtained by ICA separation. in, is the separation matrix of the rth independent component; Evaluate each independent component s based on mutual information r (n) contribution to the recognition task, and set the contribution threshold, select the independent components greater than the contribution threshold, and construct the secondary dimensionality reduction feature vector F2 = [s1(n), s2(n), ..., s K (n)] T , where K is the number of independent components retained after adaptive selection; Reduce the dimension of multiple eigenvectors to construct a set of secondary eigenvectors.

5. The switch cabinet defect diagnosis method based on multi-information fusion according to claim 2 is characterized in that: The feature vector set corresponding to transient ground voltage detection and the corresponding defect type label are constructed into a dataset, and the dataset is divided into a training set and a validation set; The support vector machine is trained using the training set, and the model is evaluated using the validation set. The parameters are adjusted to obtain a defect detection model based on transient ground voltage. The feature vector set corresponding to ultrasonic testing and the corresponding defect type label are constructed into a dataset, and the dataset is divided into a training set and a validation set; The random forest model is trained using the training set, and the model is evaluated using the validation set. The parameters are adjusted to obtain an ultrasonic-based defect detection model. The feature vector set and the corresponding defect type label corresponding to the UHF detection are constructed into a dataset, and the dataset is divided into a training set and a validation set; The naive Bayes classifier is trained using the training set, and the model is evaluated using the validation set. The parameters are adjusted to obtain a defect detection model based on UHF.

6. The switch cabinet defect diagnosis method based on multi-information fusion according to claim 5 is characterized in that: Methods for fusing the outputs of multiple defect diagnosis models include: Based on the number of types of simulated typical defects, a defect type set Θ = {θ1, θ2, ..., θ M }, where M is the total number of defect types; Input the test sample u of the switch cabinet to be tested into the defect detection model and obtain the defect type prediction probability distribution of the test sample u in, For the vth model, the sample u belongs to defect θ M The probability of ; v = 1, 2, 3, and corresponds to the defect detection model based on transient ground voltage detection, the defect detection model based on ultrasonic detection, and the defect detection model based on ultra-high frequency detection, respectively; Let the vth defect detection model assign the basic distribution probability of defect t to the test sample u and Obtaining the basic distribution probability of the defect detection model based on transient ground voltage detection Obtaining the basic distribution probability of the defect detection model based on ultrasonic testing Obtaining the basic distribution probability of the defect detection model based on UHF detection right and Perform fusion to obtain the basic distribution probability after fusion right and Perform fusion to obtain the basic distribution probability after fusion right and Perform fusion to obtain the basic distribution probability after fusion right and Perform fusion to obtain the basic distribution probability after fusion right and Perform fusion to obtain the final comprehensive distribution probability Normalize the final comprehensive allocation probability Circularly obtain the final comprehensive distribution probability of the sample u to be tested relative to all defect types; Determine the predicted defect type of the output sample u through the maximum support principle 7. The switch cabinet defect diagnosis method based on multi-information fusion according to claim 5 is characterized in that: right and Methods for performing fusion include: Determine the conflict coefficient Among them, A and B are different subsets of the defect type set Θ, is the basic distribution probability of subset A in the defect detection model based on transient ground voltage detection, is the basic distribution probability of subset B in the defect detection model based on ultrasonic testing, Indicates no intersection; Calculate the basic distribution probability after fusion The basic distribution probability of the output fusion after normalization right and Methods for performing fusion include: Determine the conflict coefficient in, is the basic distribution probability of subset A in the defect detection model based on transient ground voltage detection, is the basic assignment probability of B in the defect detection model based on ultrasonic testing; Calculate the basic distribution probability after fusion The basic distribution probability of the output fusion after normalization right and Methods for performing fusion include: Determine the conflict coefficient in, is the basic allocation probability of subset A in the defect detection model based on transient ground voltage detection; Calculate the basic distribution probability after fusion The basic distribution probability of the output fusion after normalization 8. A switch cabinet defect diagnosis terminal based on multi-information fusion, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for diagnosing switch cabinet defects based on multi-information fusion according to any one of claims 1 to 7 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, a switch cabinet defect diagnosis method based on multi-information fusion according to any one of claims 1 to 7 is implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the switch cabinet defect diagnosis method based on multi-information fusion as described in any one of claims 1 to 7 is implemented.

Images