High-voltage circuit breaker fault assessment method and device, terminal equipment and storage medium

Abstract

The invention discloses a high-voltage circuit breaker fault assessment method and device, terminal equipment and a storage medium. The method comprises the following steps: acquiring a first mechanical parameter and a first model of a to-be-assessed high-voltage circuit breaker; wherein the first mechanical parameters comprise rotating shaft damping, heights of two sides of the circuit breaker and an iron core gap; the rotating shaft damping, the heights of the two sides of the circuit breaker and the iron core gap serve as regulation variables respectively, the high-voltage circuit breaker to be evaluated is continuously regulated, and a first waveform used for representing a sound waveform and a second waveform used for representing a vibration waveform are obtained; energy entropy is calculated according to the first model, the first mechanical parameter, the first waveform and the second waveform, and a first energy entropy and a second energy entropy are obtained; inputting the first energy entropy and the second energy entropy into a preset fault category recognition model for clustering to obtain a plurality of clustering centers; and taking the final clustering center as a fault assessment result of the to-be-assessed high-voltage circuit breaker. According to the invention, the accuracy of fault assessment of the high-voltage circuit breaker is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of circuit breaker evaluation, and in particular to a high-voltage circuit breaker fault evaluation method, device, terminal equipment and storage medium. Background Art

[0002] In modern power systems, circuit breakers are one of the key devices, and their reliability directly affects the safe operation of the entire system. With the continuous development of circuit breaker fault assessment technology, high-precision sensors are used to monitor the key parameters of circuit breakers to provide real-time data for fault assessment; mathematical models and simulation technologies are used to analyze the behavior of circuit breakers under different working conditions, thereby identifying abnormal patterns.

[0003] The existing circuit breaker fault diagnosis method extracts characteristic parameters reflecting the expansion and contraction process of the energy storage spring through pressure signal data, and inputs the characteristic parameters into the optimized SVM model for state identification, thereby determining whether the energy storage spring has failed and the type of failure. Then, the influencing factors of the circuit breaker are multi-dimensional, and the existing method lacks multi-dimensional analysis of the influencing factors of the circuit breaker, and does not conduct comprehensive simulation analysis of multiple parameters, which makes the high-voltage circuit breaker fault assessment accuracy low. Summary of the invention

[0004] The embodiments of the present invention provide a high-voltage circuit breaker fault assessment method, apparatus, terminal equipment and storage medium, which can effectively solve the problem that the prior art lacks multi-dimensional analysis of factors affecting the circuit breaker and does not perform comprehensive simulation analysis on multiple parameters, resulting in low accuracy of high-voltage circuit breaker fault assessment.

[0005] An embodiment of the present invention provides a high-voltage circuit breaker fault assessment method, comprising:

[0006] Obtaining first mechanical parameters and a first model of the high-voltage circuit breaker to be evaluated; wherein the first mechanical parameters include: shaft damping, height of both sides of the circuit breaker, and core gap;

[0007] The shaft damping, the height of both sides of the circuit breaker and the core gap are respectively used as control variables to continuously control the high-voltage circuit breaker to be evaluated, so as to obtain a first waveform for representing a sound waveform and a second waveform for representing a vibration waveform;

[0008] Calculating the energy entropy of the first waveform according to the first model, the first mechanical parameter and the first waveform to obtain a first energy entropy; and calculating the energy entropy of the second waveform according to the first model, the first mechanical parameter and the second waveform to obtain a second energy entropy;

[0009] Inputting the first energy entropy and the second energy entropy into a preset fault category identification model for clustering to obtain a plurality of cluster centers;

[0010] The final cluster center is used as the fault assessment result of the high-voltage circuit breaker to be evaluated.

[0011] Furthermore, the training of the fault category identification model includes:

[0012] Obtaining second mechanical parameters, second models, and corresponding first fault categories of a plurality of high-voltage circuit breakers;

[0013] Calculating energy entropy according to the second mechanical parameter and the second model to obtain a third energy entropy for representing the energy entropy of the sound waveform and a fourth energy entropy for representing the energy entropy of the vibration waveform;

[0014] Inputting the third energy entropy and the fourth energy entropy into a fault category recognition model to be trained, and randomly generating a number of initial cluster centers;

[0015] According to the current cluster center and the energy entropy of the same group corresponding to the current cluster center, the current distance between the current cluster center and each energy entropy of the same group and the current energy entropy average value are calculated; wherein the current cluster center calculated for the first time is the initial cluster center;

[0016] Calculate the change difference based on the current energy entropy average value and the previous energy entropy average value; and update the current cluster center based on the change difference;

[0017] The current cluster center corresponding to the minimum current distance is used as the current optimal cluster center, until the change difference of the average value of the energy entropy of the current cluster center is less than the preset first threshold, and the current optimal cluster center is used as the final cluster center;

[0018] According to the second fault category corresponding to the final cluster center and the first fault category, the loss function value of the fault category identification model is calculated; when the loss function value is less than a preset second threshold, a trained fault category identification model is obtained.

[0019] Further, calculating energy entropy according to the second mechanical parameter and the second model to obtain a third energy entropy and a fourth energy entropy includes:

[0020] According to the second model and the corresponding parameter standard value, determining that the parameter standard value corresponding to the second model is the first standard value;

[0021] Compare the second mechanical parameter with the first standard value, and use the second mechanical parameter greater than the first standard value as the first target mechanical parameter;

[0022] Signal transformation is performed according to the waveform corresponding to the first target mechanical parameter to calculate and obtain the third energy entropy and the fourth energy entropy.

[0023] Furthermore, the shaft damping, the height of both sides of the circuit breaker and the core gap are respectively used as control variables, and the high-voltage circuit breaker to be evaluated is continuously controlled to obtain a first waveform for representing a sound waveform and a second waveform for representing a vibration waveform, including:

[0024] The shaft damping is used as a first control variable, and a first mechanical parameter other than the shaft damping is used as a first control quantity; and according to the first control variable and the first control quantity, the high-voltage circuit breaker to be evaluated is continuously controlled within a preset time period to obtain a shaft damping sound waveform and a shaft damping vibration waveform;

[0025] The height of both sides of the circuit breaker is used as a second control variable, and the first mechanical parameter other than the height of both sides of the circuit breaker is used as a second control quantity; and according to the second control variable and the second control quantity, the high-voltage circuit breaker to be evaluated is continuously controlled within a preset time period to obtain a sound waveform of the height of both sides of the circuit breaker and a vibration waveform of the height of both sides of the circuit breaker;

[0026] The core gap is used as a third control variable, and the first mechanical parameter other than the core gap is used as a third control quantity; and according to the third control variable and the third control quantity, the high-voltage circuit breaker to be evaluated is continuously controlled within a preset time period to obtain a core gap sound waveform and a core gap vibration waveform;

[0027] The shaft damping sound waveform, the circuit breaker two-side height sound waveform and the core gap sound waveform are used as the first waveform for representing the sound waveform;

[0028] The shaft damping vibration waveform, the circuit breaker both side height vibration waveform and the core gap vibration waveform are used as the second waveform for representing the vibration waveform.

[0029] Further, calculating the energy entropy of the first waveform according to the first model, the first mechanical parameter and the first waveform to obtain the first energy entropy; and calculating the energy entropy of the second waveform according to the first model, the first mechanical parameter and the second waveform to obtain the second energy entropy, including:

[0030] According to a first model of the high-voltage circuit breaker to be evaluated and the corresponding parameter standard value, determining that the parameter standard value corresponding to the first model is a second standard value;

[0031] Comparing the first mechanical parameter with the second standard value, and when the first mechanical parameter is greater than the second standard value, taking the first mechanical parameter greater than the second standard value as the second target mechanical parameter;

[0032] The first waveform and the second waveform corresponding to the second target mechanical parameter are used as the third waveform and the fourth waveform respectively;

[0033] A signal transformation is performed according to the third waveform to calculate the first energy entropy; and a signal transformation is performed according to the fourth waveform to calculate the second energy entropy.

[0034] Further, performing signal transformation according to the third waveform to calculate the first energy entropy; and performing signal transformation according to the fourth waveform to calculate the second energy entropy, including:

[0035] Perform denoising processing on the third waveform and the fourth waveform respectively to obtain a first fault waveform and a second fault waveform after denoising processing;

[0036] Decomposing the first fault waveform and the preset decomposition parameters to obtain a first modal function; Decomposing the second fault waveform and the preset decomposition parameters to obtain a second modal function;

[0037] Performing instantaneous frequency analysis on the first modal function and the second modal function respectively to obtain a first instantaneous frequency and a second instantaneous frequency;

[0038] An entropy value is calculated according to the first instantaneous frequency to obtain a first energy entropy; and an entropy value is calculated according to the second instantaneous frequency to obtain a second energy entropy.

[0039] Furthermore, the setting of the decomposition parameters includes:

[0040] Randomly select several initial decomposition mode numbers, initial smoothing parameters and initial bandwidth constraints;

[0041] Decomposing the first fault waveform and the second fault waveform according to the initial decomposition mode number, the initial smoothing parameter and the initial bandwidth constraint to obtain a first modal function and a second modal function;

[0042] According to the first center frequency corresponding to the first mode function and the second center frequency corresponding to the second mode function, the first center frequency and the second center frequency are sorted in descending order, and the center frequency with the largest value is used as the target center frequency;

[0043] The initial decomposition mode number, initial smoothing parameter and initial bandwidth constraint corresponding to the target center frequency are taken as the final decomposition parameters.

[0044] As an improvement of the above solution, another embodiment of the present invention provides a high-voltage circuit breaker fault assessment device, including:

[0045] A circuit breaker data acquisition module, used to acquire first mechanical parameters and a first model of the high-voltage circuit breaker to be evaluated; wherein the first mechanical parameters include: shaft damping, height of both sides of the circuit breaker, and core gap;

[0046] A waveform control module, used to use the shaft damping, the height of both sides of the circuit breaker and the core gap as control variables, to continuously control the high-voltage circuit breaker to be evaluated, and obtain a first waveform for representing a sound waveform and a second waveform for representing a vibration waveform;

[0047] an energy entropy calculation module, configured to calculate the energy entropy of the first waveform according to the first model, the first mechanical parameter and the first waveform to obtain a first energy entropy; and to calculate the energy entropy of the second waveform according to the first model, the first mechanical parameter and the second waveform to obtain a second energy entropy;

[0048] A fault category clustering module, used for inputting the first energy entropy and the second energy entropy into a preset fault category identification model for clustering to obtain a plurality of cluster centers;

[0049] The fault assessment result determination module is used to use the final cluster center as the fault assessment result of the high-voltage circuit breaker to be assessed.

[0050] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, a high-voltage circuit breaker fault assessment method as described in the above embodiment is implemented.

[0051] Another embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a high-voltage circuit breaker fault assessment method described in the above embodiment.

[0052] By implementing the present invention, at least the following beneficial effects are achieved:

[0053] The present invention provides a high-voltage circuit breaker fault assessment method, device, terminal equipment and storage medium, wherein the method can obtain a first mechanical parameter and a first model of a high-voltage circuit breaker to be assessed; wherein the first mechanical parameter includes: shaft damping, height on both sides of the circuit breaker and core gap; the shaft damping, the height on both sides of the circuit breaker and the core gap are respectively used as control variables to continuously control the high-voltage circuit breaker to be assessed, so as to obtain a first waveform for representing a sound waveform and a second waveform for representing a vibration waveform; the energy entropy of the first waveform is calculated according to the first model, the first mechanical parameter and the first waveform to obtain a first energy entropy; and the energy entropy of the second waveform is calculated according to the first model, the first mechanical parameter and the second waveform to obtain a second energy entropy; the first energy entropy and the second energy entropy are input into a preset fault category recognition model for clustering to obtain a plurality of cluster centers; and the final cluster center is used as the fault assessment result of the high-voltage circuit breaker to be assessed. Through the multi-factor analysis of the first mechanical parameter of the shaft damping, the height on both sides of the circuit breaker and the core gap, the multiple parameters are comprehensively simulated and analyzed to obtain a first waveform for representing the sound waveform and a second waveform for representing the vibration waveform, and the first energy entropy of the first waveform and the second energy entropy of the second waveform are input into a preset fault category recognition model to cluster the fault assessment result. The combination of multi-parameter influences can accurately identify the high-voltage circuit breaker fault assessment result, avoid the low accuracy of the assessment result due to the influence of a single factor, and multi-parameter analysis improves the accuracy of high-voltage circuit breaker fault assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a flow chart of a high-voltage circuit breaker fault assessment method provided by one embodiment of the present invention;

[0055] Figure 2 It is a structural schematic diagram of a high-voltage circuit breaker fault assessment device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] See also Figure 1 , is a flow chart of a high-voltage circuit breaker fault assessment method provided by an embodiment of the present invention, comprising:

[0058] S1. Obtaining first mechanical parameters and a first model of a high-voltage circuit breaker to be evaluated; wherein the first mechanical parameters include: shaft damping, height of both sides of the circuit breaker, and core gap;

[0059] S2, taking the shaft damping, the height of both sides of the circuit breaker and the core gap as control variables, respectively, and continuously controlling the high-voltage circuit breaker to be evaluated to obtain a first waveform for representing a sound waveform and a second waveform for representing a vibration waveform;

[0060] S3, calculating the energy entropy of the first waveform according to the first model, the first mechanical parameter and the first waveform to obtain a first energy entropy; and calculating the energy entropy of the second waveform according to the first model, the first mechanical parameter and the second waveform to obtain a second energy entropy;

[0061] S4, inputting the first energy entropy and the second energy entropy into a preset fault category identification model for clustering to obtain a plurality of cluster centers;

[0062] S5. Taking the final cluster center as the fault assessment result of the high-voltage circuit breaker to be assessed.

[0063] Specifically, the first mechanical parameter represents the mechanical parameter of the high-voltage circuit breaker to be evaluated; the first model represents the model of the high-voltage circuit breaker to be evaluated; the first waveform represents the sound waveform obtained by continuously regulating the high-voltage circuit breaker to be evaluated; the second waveform represents the vibration waveform obtained by continuously regulating the high-voltage circuit breaker to be evaluated; the first energy entropy represents the energy entropy of the first waveform; the second energy entropy represents the energy entropy of the second waveform. The fault evaluation results include normal circuit breaker, stuck circuit breaker, loose circuit breaker and circuit breaker refusal to operate.

[0064] In a preferred embodiment of the present invention, the first mechanical parameter and the first model of the high-voltage circuit breaker to be evaluated are first obtained; wherein the first mechanical parameter includes: shaft damping, height on both sides of the circuit breaker and core gap; then the shaft damping, height on both sides of the circuit breaker and the core gap are respectively used as control variables to continuously control the high-voltage circuit breaker to be evaluated, and a first waveform for representing a sound waveform and a second waveform for representing a vibration waveform are obtained; then the energy entropy of the first waveform and the second waveform are respectively calculated according to the first model, the first mechanical parameter, the first waveform and the second waveform to obtain a first energy entropy and a second energy entropy; then the first energy entropy and the second energy entropy are input into a preset fault category recognition model for clustering to obtain several cluster centers; finally, the final cluster center is used as the fault evaluation result of the high-voltage circuit breaker to be evaluated. By setting and regulating multiple parameters, the state of the high-voltage circuit breaker can be systematically analyzed and monitored, and the comprehensiveness of fault evaluation can be improved; through the calculation of energy entropy and cluster analysis, different fault modes can be clearly classified, which is helpful to accurately identify the fault type.

[0065] Preferably, the training of the fault category identification model includes:

[0066] Obtaining second mechanical parameters, second models, and corresponding first fault categories of a plurality of high-voltage circuit breakers;

[0067] Calculating energy entropy according to the second mechanical parameter and the second model to obtain a third energy entropy for representing the energy entropy of the sound waveform and a fourth energy entropy for representing the energy entropy of the vibration waveform;

[0068] Inputting the third energy entropy and the fourth energy entropy into a fault category recognition model to be trained, and randomly generating a number of initial cluster centers;

[0069] According to the current cluster center and the energy entropy of the same group corresponding to the current cluster center, the current distance between the current cluster center and each energy entropy of the same group and the current energy entropy average value are calculated; wherein the current cluster center calculated for the first time is the initial cluster center;

[0070] Calculate the change difference based on the current energy entropy average value and the previous energy entropy average value; and update the current cluster center based on the change difference;

[0071] The current cluster center corresponding to the minimum current distance is used as the current optimal cluster center, until the change difference of the average value of the energy entropy of the current cluster center is less than the preset first threshold, and the current optimal cluster center is used as the final cluster center;

[0072] According to the second fault category corresponding to the final cluster center and the first fault category, the loss function value of the fault category identification model is calculated; when the loss function value is less than a preset second threshold, a trained fault category identification model is obtained.

[0073] Specifically, the second mechanical parameters represent the mechanical parameters of several high-voltage circuit breakers used to train the model, and the second mechanical parameters include shaft damping, height on both sides of the circuit breaker, and core gap; the second model represents the model corresponding to several high-voltage circuit breakers; the first fault category represents the fault category corresponding to several high-voltage circuit breakers; the third energy entropy represents the energy entropy corresponding to the sound waveform obtained by controlling the second mechanical parameter; the fourth energy entropy represents the energy entropy corresponding to the vibration waveform obtained by controlling the second mechanical parameter; the preset first threshold is used to evaluate the threshold of the difference in change of the energy entropy average value; the preset second threshold is used to evaluate the loss function value.

[0074] In a preferred embodiment of the present invention, the corresponding sound waveform and vibration waveform are determined according to the second mechanical parameter and the second model, and then the energy entropy is calculated according to the determined sound waveform and vibration waveform to obtain the third energy entropy and the fourth energy entropy; the third energy entropy and the fourth energy entropy corresponding to the same second model are numbered as the energy entropies corresponding to the same number, and the same group of energy entropies and the first fault category are used as a sample set, and the sample set is divided into a test set and a training set to train the fault category recognition model to be trained; the fault category recognition model to be trained takes the predicted second fault category as the output and the actual first fault category as the prediction target, so that the predicted second fault category and the actual first fault category are the same as the training target, and the fault category recognition model to be trained is tested according to the test set until the loss function value of the fault category recognition model to be trained is less than the preset second threshold, and the test training is stopped to obtain the trained fault category recognition model.

[0075] The clustering logic of the fault category recognition model to be trained includes: randomly generating several initial cluster centers, for example, setting the number of clusters to 3, randomly selecting 3 initial cluster centers, and then calculating the distance between the energy entropy of the same group and the initial cluster center according to the current cluster center and the energy entropy of the same group corresponding to the current cluster center, sorting the distance between the energy entropy of the same group and the initial cluster center in descending order, selecting the distance with the smallest value, setting the initial cluster center corresponding to the distance with the smallest value as the optimal cluster center, calculating the average value of the energy entropy of the same group included in each initial cluster center, assigning the initial cluster center to the energy entropy average value, until the change difference of the initial cluster center assignment is less than the preset first threshold, stopping the iteration, and taking the current optimal cluster center as the final cluster center. By clustering the energy entropy, the fault category can be accurately separated, which is helpful to identify and distinguish different fault types and improve the accuracy of fault assessment. The energy entropy and fault category are used as sample sets and divided into training sets and test sets, and the fault category recognition model to be trained is trained according to actual faults, which can learn from actual fault data, thereby improving the actual application effect of the fault category recognition model.

[0076] Specifically, calculating the energy entropy according to the second mechanical parameter and the second model to obtain the third energy entropy and the fourth energy entropy includes:

[0077] According to the second model and the corresponding parameter standard value, determining that the parameter standard value corresponding to the second model is the first standard value;

[0078] Compare the second mechanical parameter with the first standard value, and use the second mechanical parameter greater than the first standard value as the first target mechanical parameter;

[0079] Signal transformation is performed according to the waveform corresponding to the first target mechanical parameter to calculate and obtain the third energy entropy and the fourth energy entropy.

[0080] Preferably, the shaft damping, the height of both sides of the circuit breaker and the core gap are respectively used as control variables, and the high-voltage circuit breaker to be evaluated is continuously controlled to obtain a first waveform for representing a sound waveform and a second waveform for representing a vibration waveform, including:

[0081] The shaft damping is used as a first control variable, and a first mechanical parameter other than the shaft damping is used as a first control quantity; and according to the first control variable and the first control quantity, the high-voltage circuit breaker to be evaluated is continuously controlled within a preset time period to obtain a shaft damping sound waveform and a shaft damping vibration waveform;

[0082] The height of both sides of the circuit breaker is used as a second control variable, and the first mechanical parameter other than the height of both sides of the circuit breaker is used as a second control quantity; and according to the second control variable and the second control quantity, the high-voltage circuit breaker to be evaluated is continuously controlled within a preset time period to obtain a sound waveform of the height of both sides of the circuit breaker and a vibration waveform of the height of both sides of the circuit breaker;

[0083] The core gap is used as a third control variable, and the first mechanical parameter other than the core gap is used as a third control quantity; and according to the third control variable and the third control quantity, the high-voltage circuit breaker to be evaluated is continuously controlled within a preset time period to obtain a core gap sound waveform and a core gap vibration waveform;

[0084] The shaft damping sound waveform, the circuit breaker two-side height sound waveform and the core gap sound waveform are used as the first waveform for representing the sound waveform;

[0085] The shaft damping vibration waveform, the circuit breaker both side height vibration waveform and the core gap vibration waveform are used as the second waveform for representing the vibration waveform.

[0086] In a preferred embodiment of the present invention, any simulation parameter is set as a variable, and the remaining simulation parameters are set as a quantitative, such as: setting the shaft damping as a variable, setting the height difference on both sides of the circuit breaker and the core gap as a quantitative; setting the height difference on both sides of the circuit breaker as a variable, setting the shaft damping and the core gap as a quantitative, setting the core gap as a variable, and setting the shaft damping and the height difference on both sides of the circuit breaker as a quantitative. The shaft damping is used to simulate the jamming fault factor, the height difference on both sides of the circuit breaker is used to simulate the loose fault factor, and the core gap is used to simulate the refusal fault factor. The preset time period is divided into Q sub-time periods, and the sub-time periods are numbered T1, T2, ..., TQ. Different variables and quantitatives are set in the preset time period, such as the variable is the shaft damping, the quantitative is the height difference on both sides of the circuit breaker and the core gap, the first gradient is set as the increment of the shaft damping or the decrement of the shaft damping, the shaft damping is continuously increased or continuously reduced according to the current shaft damping and the first gradient, and the shaft damping sound waveform X1 and the shaft damping vibration waveform Y1 are recorded. The shaft damping sound waveform X1, the height difference sound waveform X2 of the circuit breaker, and the core gap sound waveform X3 are used as the first waveform for representing the sound waveform; the shaft damping vibration waveform Y1, the height difference vibration waveform Y2 of the circuit breaker, and the core gap vibration waveform Y3 are used as the second waveform for representing the vibration waveform. When the variables are the height difference on both sides of the circuit breaker and the core gap, the corresponding control steps are the same as the control steps of the shaft damping.

[0087] By setting different simulation parameters and using them as variables and quantities, the impact of different fault factors on circuit breaker performance can be fully simulated, and multiple fault modes can be fully considered to improve the comprehensiveness of the evaluation; the preset time period is subdivided into multiple sub-time periods, so that the behavior of the high-voltage circuit breaker to be tested can be analyzed on a finer time scale, which helps to capture fault characteristics in a short period of time and improve sensitivity to dynamic changes; sound waveform and vibration waveform data are collected at the same time, and their corresponding relationships at the same time point are associated, providing a multi-dimensional data source. The comprehensive analysis of sound and vibration signals can more comprehensively reflect the operating status of the circuit breaker and improve the accuracy of fault assessment.

[0088] Specifically, calculating the energy entropy of the first waveform according to the first model, the first mechanical parameter and the first waveform to obtain the first energy entropy; and calculating the energy entropy of the second waveform according to the first model, the first mechanical parameter and the second waveform to obtain the second energy entropy, including:

[0089] According to a first model of the high-voltage circuit breaker to be evaluated and the corresponding parameter standard value, determining that the parameter standard value corresponding to the first model is a second standard value;

[0090] Comparing the first mechanical parameter with the second standard value, and when the first mechanical parameter is greater than the second standard value, taking the first mechanical parameter greater than the second standard value as the second target mechanical parameter;

[0091] The first waveform and the second waveform corresponding to the second target mechanical parameter are used as the third waveform and the fourth waveform respectively;

[0092] A signal transformation is performed according to the third waveform to calculate the first energy entropy; and a signal transformation is performed according to the fourth waveform to calculate the second energy entropy.

[0093] In a preferred embodiment of the present invention, the preset simulation database records the model of the high-voltage circuit breaker and the standard value of the corresponding mechanical parameter. According to the first model of the high-voltage circuit breaker to be evaluated and the parameter standard value corresponding to the first mechanical parameter, the parameter standard value corresponding to the first model is determined to be the second standard value, and the first mechanical parameter and the second standard value are compared, and the first mechanical parameter greater than the second standard value is used as the second target mechanical parameter; the first waveform and the second waveform corresponding to the second target mechanical parameter are used as the third waveform and the fourth waveform respectively (the first waveform and the second waveform corresponding to the first mechanical parameter less than or equal to the second standard value are deleted); finally, the signal transformation is performed according to the third waveform and the fourth waveform, and the first energy entropy and the second energy entropy are calculated.

[0094] In another preferred embodiment of the present invention, the third waveform and the corresponding fourth waveform are set as waveforms in the same group, and the waveforms in the same group are numbered, and the number of the third waveform is represented by X. P B n , the corresponding fourth waveform number is represented by Y P B nm , where n and m are both natural numbers, P∈[1,3] and P is an integer. The waveforms are grouped according to the standard value comparison results and numbered to systematically manage the test data, which is convenient for tracking and analyzing the test results of different waveforms, and is helpful for data collation and subsequent analysis. The waveform numbers are set to facilitate waveform management. The corresponding waveform can be queried by entering the number, which improves the data management effect. The first mechanical parameter is set as a variable and quantitative in order to observe the impact of a single mechanical parameter on the circuit breaker fault by changing a single mechanical parameter, and to compare the variables set in different orders with the corresponding standard values, so as to facilitate the screening of fault waveforms corresponding to different variables. By deleting invalid waveforms, the amount of data is simplified and the amount of subsequent calculations is reduced.

[0095] Preferably, performing signal transformation according to the third waveform to calculate the first energy entropy; and performing signal transformation according to the fourth waveform to calculate the second energy entropy, including:

[0096] Perform denoising processing on the third waveform and the fourth waveform respectively to obtain a first fault waveform and a second fault waveform after denoising processing;

[0097] Decomposing the first fault waveform and the preset decomposition parameters to obtain a first modal function; Decomposing the second fault waveform and the preset decomposition parameters to obtain a second modal function;

[0098] Performing instantaneous frequency analysis on the first modal function and the second modal function respectively to obtain a first instantaneous frequency and a second instantaneous frequency;

[0099] An entropy value is calculated according to the first instantaneous frequency to obtain a first energy entropy; and an entropy value is calculated according to the second instantaneous frequency to obtain a second energy entropy.

[0100] In a preferred embodiment of the present invention, denoising is performed on the third waveform and the fourth waveform respectively to obtain the first fault waveform and the second fault waveform after denoising, and the denoising adopts wavelet packet soft threshold denoising. The modal function is obtained by the method of empirical mode decomposition (EMD), and the implementation steps are as follows: (1) Parameter setting: set the number of decomposed modes (N), the number of modal functions extracted from the waveform; set the smoothing parameter (S) to control the smoothness in the decomposition process to reduce the influence of noise; set the bandwidth constraint (B) to limit the frequency range of the modal function to better capture the fault characteristics; (2) Denoising: denoising the first fault waveform and the second fault waveform, wavelet transform or filter technology can be used to reduce the influence of noise on subsequent decomposition; (3) Modal decomposition: adopt empirical mode decomposition (EMD), take the denoised first fault waveform and the second fault waveform as input; extract the intrinsic modal function (I) by repeatedly extracting local extreme points and calculating the envelope. MF); set conditions to check whether the number of extracted modal functions reaches the preset number of decomposed modes (N); (4) smoothing and constraints: apply smoothing parameters (S) to the extracted modal functions for post-processing to reduce high-frequency noise; perform frequency domain analysis on the modal functions according to the bandwidth constraint (B) to ensure that the extracted modal functions are within the specified bandwidth range; (5) result output: output the modal function of the first fault waveform and the modal function of the second fault waveform, that is, the first modal function and the second modal function.

[0101] The first modal function and the second modal function are subjected to instantaneous frequency analysis respectively to obtain the first instantaneous frequency and the second instantaneous frequency, that is, the first instantaneous frequency and the corresponding second instantaneous frequency are obtained by H i bert transform (Hilbert transform). Then, the entropy values ​​are calculated according to the first instantaneous frequency and the second instantaneous frequency respectively to obtain the first energy entropy and the second energy entropy. In mechanical and electrical equipment, the sudden change of frequency may be closely related to the occurrence of faults. Analyzing the change of instantaneous frequency can provide a basis for fault identification, capture the frequency change of the signal in time, and help understand the dynamic characteristics of the signal; the change of energy entropy indicates the change of the system state. When the entropy value changes significantly, it indicates that the system has a fault or abnormal state; the instantaneous frequency extracted by applying Hilbert transform is combined with energy entropy to provide more abundant information for signal analysis, which helps to identify and quantify important features in the signal to support fault detection and early warning. The same group of energy entropies can set the first energy entropy and the corresponding second energy entropy as the same group of energy entropies, and compare the energy characteristics of different signals in the same time period, so as to perform more effective fault analysis and pattern recognition. The energy entropies in the same group are numbered, and the number of the first energy entropy is represented as EX P B n , the corresponding second energy entropy second number is represented by EYP B nm , where E represents the sign of energy entropy, and energy entropy is calculated using Hilbert marginal energy entropy formula.

[0102] Schematically, the setting of the decomposition parameters includes:

[0103] Randomly select several initial decomposition mode numbers, initial smoothing parameters and initial bandwidth constraints;

[0104] Decomposing the first fault waveform and the second fault waveform according to the initial decomposition mode number, the initial smoothing parameter and the initial bandwidth constraint to obtain a first modal function and a second modal function;

[0105] According to the first center frequency corresponding to the first mode function and the second center frequency corresponding to the second mode function, the first center frequency and the second center frequency are sorted in descending order, and the center frequency with the largest value is used as the target center frequency;

[0106] The initial decomposition mode number, initial smoothing parameter and initial bandwidth constraint corresponding to the target center frequency are taken as the final decomposition parameters.

[0107] In a preferred embodiment of the present invention, an initial number of decomposed modes, an initial smoothing parameter and an initial bandwidth constraint are preset, and according to the center frequencies of the first mode function and the second mode function, the center frequencies are traversed and sorted in descending order; the center frequency with the largest value is selected, and the number of decomposed modes, the smoothing parameter and the bandwidth constraint corresponding to the center frequency with the largest value are set as the target number of decomposed modes, the target smoothing parameter and the target bandwidth constraint, respectively; the value of the target number of decomposed modes is a first value, the value of the target smoothing parameter is a second value, and the value of the target bandwidth constraint is a third value, and the initial number of decomposed modes, the initial smoothing parameter and the initial bandwidth constraint corresponding to the target center frequency are used as the final decomposition parameters.

[0108] Wavelet packet soft threshold denoising can effectively reduce the noise in the signal and improve the signal quality of the data, thereby improving the accuracy of the analysis results; by decomposing the modal function, the waveform data is decomposed into multiple levels of detail, which helps to analyze and understand the waveform characteristics more deeply; Hibert transform provides instantaneous frequency calculation, which helps to capture the frequency changes of the waveform at different time points and enhance the understanding of the dynamic behavior of the signal.

[0109] By implementing this embodiment, the first mechanical parameters and the first model of the high-voltage circuit breaker to be evaluated are obtained; wherein the first mechanical parameters include: shaft damping, height on both sides of the circuit breaker and core gap; the shaft damping, the height on both sides of the circuit breaker and the core gap are respectively used as control variables, and the high-voltage circuit breaker to be evaluated is continuously controlled to obtain a first waveform for representing a sound waveform and a second waveform for representing a vibration waveform; the energy entropy of the first waveform and the second waveform are respectively calculated according to the first model, the first mechanical parameters, the first waveform and the second waveform to obtain a first energy entropy and a second energy entropy; the first energy entropy and the second energy entropy are input into a preset fault category identification model for clustering to obtain a plurality of cluster centers; the final cluster center is used as the fault evaluation result of the high-voltage circuit breaker to be evaluated. Through the multi-factor analysis of the first mechanical parameter of the shaft damping, the height on both sides of the circuit breaker and the core gap, the multiple parameters are comprehensively simulated and analyzed to obtain a first waveform for representing the sound waveform and a second waveform for representing the vibration waveform, and the first energy entropy of the first waveform and the second energy entropy of the second waveform are input into a preset fault category recognition model to cluster the fault assessment result. The combination of multi-parameter influences can accurately identify the high-voltage circuit breaker fault assessment result, avoid the low accuracy of the assessment result due to the influence of a single factor, and multi-parameter analysis improves the accuracy of high-voltage circuit breaker fault assessment.

[0110] See also Figure 2 , is a schematic structural diagram of a high-voltage circuit breaker fault assessment device provided by an embodiment of the present invention, comprising:

[0111] A circuit breaker data acquisition module, used to acquire first mechanical parameters and a first model of the high-voltage circuit breaker to be evaluated; wherein the first mechanical parameters include: shaft damping, height of both sides of the circuit breaker, and core gap;

[0112] A waveform control module, used to use the shaft damping, the height of both sides of the circuit breaker and the core gap as control variables, to continuously control the high-voltage circuit breaker to be evaluated, and obtain a first waveform for representing a sound waveform and a second waveform for representing a vibration waveform;

[0113] an energy entropy calculation module, configured to calculate the energy entropy of the first waveform according to the first model, the first mechanical parameter and the first waveform to obtain a first energy entropy; and to calculate the energy entropy of the second waveform according to the first model, the first mechanical parameter and the second waveform to obtain a second energy entropy;

[0114] A fault category clustering module, used for inputting the first energy entropy and the second energy entropy into a preset fault category identification model for clustering to obtain a plurality of cluster centers;

[0115] The fault assessment result determination module is used to use the final cluster center as the fault assessment result of the high-voltage circuit breaker to be assessed.

[0116] The present invention provides a high-voltage circuit breaker fault assessment device. According to a circuit breaker data acquisition module, a first mechanical parameter and a first model of a high-voltage circuit breaker to be assessed are obtained; wherein the first mechanical parameter includes: shaft damping, height of both sides of the circuit breaker and core gap; through a waveform control module, the shaft damping, the height of both sides of the circuit breaker and the core gap are respectively used as control variables to continuously control the high-voltage circuit breaker to be assessed, so as to obtain a first waveform for representing a sound waveform and a second waveform for representing a vibration waveform; in an energy entropy calculation module, the energy entropies of the first waveform and the second waveform are respectively calculated according to the first model, the first mechanical parameter, the first waveform and the second waveform, so as to obtain a first energy entropy and a second energy entropy; through a fault category clustering module, the first energy entropy and the second energy entropy are input into a preset fault category recognition model for clustering, so as to obtain a plurality of cluster centers; finally, according to a fault assessment result determination module, the final cluster center is used as the fault assessment result of the high-voltage circuit breaker to be assessed. Through the multi-factor analysis of the first mechanical parameter of the shaft damping, the height on both sides of the circuit breaker and the core gap, the multiple parameters are comprehensively simulated and analyzed to obtain a first waveform for representing the sound waveform and a second waveform for representing the vibration waveform, and the first energy entropy of the first waveform and the second energy entropy of the second waveform are input into a preset fault category recognition model to cluster the fault assessment result. The combination of multi-parameter influences can accurately identify the high-voltage circuit breaker fault assessment result, avoid the low accuracy of the assessment result due to the influence of a single factor, and multi-parameter analysis improves the accuracy of high-voltage circuit breaker fault assessment.

[0117] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0118] Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0119] Another embodiment of the present invention further provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements a high-voltage circuit breaker fault assessment method as described in the above embodiment when executing the computer program. The terminal device may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory.

[0120] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0121] The memory can be used to store the computer program, and the processor realizes various functions of the terminal device by running or executing the computer program stored in the memory and calling the data 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 application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Med i aCard, SMC), a secure digital (Secure Digital, SD) card, a flash card (F l ash Card), at least one disk storage device, a flash memory device or other volatile solid-state storage device.

[0122] Another embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a high-voltage circuit breaker fault assessment method described in the above embodiment.

[0123] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium.

[0124] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A high voltage circuit breaker fault assessment method, characterized in that: include: Obtaining first mechanical parameters and a first model of the high-voltage circuit breaker to be evaluated; wherein the first mechanical parameters include: shaft damping, height of both sides of the circuit breaker, and core gap; The shaft damping, the height of both sides of the circuit breaker and the core gap are respectively used as control variables to continuously control the high-voltage circuit breaker to be evaluated, so as to obtain a first waveform for representing a sound waveform and a second waveform for representing a vibration waveform; Calculating the energy entropy of the first waveform according to the first model, the first mechanical parameter and the first waveform to obtain a first energy entropy; and calculating the energy entropy of the second waveform according to the first model, the first mechanical parameter and the second waveform to obtain a second energy entropy; Inputting the first energy entropy and the second energy entropy into a preset fault category identification model for clustering to obtain a plurality of cluster centers; The final cluster center is used as the fault assessment result of the high-voltage circuit breaker to be evaluated.

2. A high voltage circuit breaker fault assessment method according to claim 1, characterized in that: The training of the fault category identification model includes: Obtaining second mechanical parameters, second models, and corresponding first fault categories of a plurality of high-voltage circuit breakers; Calculating energy entropy according to the second mechanical parameter and the second model to obtain a third energy entropy for representing the energy entropy of the sound waveform and a fourth energy entropy for representing the energy entropy of the vibration waveform; Inputting the third energy entropy and the fourth energy entropy into a fault category recognition model to be trained, and randomly generating a number of initial cluster centers; According to the current cluster center and the energy entropy of the same group corresponding to the current cluster center, the current distance between the current cluster center and each energy entropy of the same group and the current energy entropy average value are calculated; wherein the current cluster center calculated for the first time is the initial cluster center; Calculate the change difference based on the current energy entropy average value and the previous energy entropy average value; and update the current cluster center based on the change difference; The current cluster center corresponding to the minimum current distance is used as the current optimal cluster center, until the change difference of the average value of the energy entropy of the current cluster center is less than the preset first threshold, and the current optimal cluster center is used as the final cluster center; According to the second fault category corresponding to the final cluster center and the first fault category, the loss function value of the fault category identification model is calculated; when the loss function value is less than a preset second threshold, a trained fault category identification model is obtained.

3. A high voltage circuit breaker fault assessment method as claimed in claim 2, characterized in that: Calculating energy entropy according to the second mechanical parameter and the second model to obtain a third energy entropy and a fourth energy entropy includes: According to the second model and the corresponding parameter standard value, determining that the parameter standard value corresponding to the second model is the first standard value; Compare the second mechanical parameter with the first standard value, and use the second mechanical parameter greater than the first standard value as the first target mechanical parameter; Signal transformation is performed according to the waveform corresponding to the first target mechanical parameter to calculate and obtain the third energy entropy and the fourth energy entropy.

4. A high voltage circuit breaker fault assessment method according to claim 1, characterized in that: The shaft damping, the height of both sides of the circuit breaker and the core gap are respectively used as control variables, and the high-voltage circuit breaker to be evaluated is continuously controlled to obtain a first waveform for representing a sound waveform and a second waveform for representing a vibration waveform, including: The shaft damping is used as a first control variable, and a first mechanical parameter other than the shaft damping is used as a first control quantity; and according to the first control variable and the first control quantity, the high-voltage circuit breaker to be evaluated is continuously controlled within a preset time period to obtain a shaft damping sound waveform and a shaft damping vibration waveform; The height of both sides of the circuit breaker is used as a second control variable, and the first mechanical parameter other than the height of both sides of the circuit breaker is used as a second control quantity; and according to the second control variable and the second control quantity, the high-voltage circuit breaker to be evaluated is continuously controlled within a preset time period to obtain a sound waveform of the height of both sides of the circuit breaker and a vibration waveform of the height of both sides of the circuit breaker; The core gap is used as a third control variable, and the first mechanical parameter other than the core gap is used as a third control quantity; and according to the third control variable and the third control quantity, the high-voltage circuit breaker to be evaluated is continuously controlled within a preset time period to obtain a core gap sound waveform and a core gap vibration waveform; The shaft damping sound waveform, the circuit breaker two-side height sound waveform and the core gap sound waveform are used as the first waveform for representing the sound waveform; The shaft damping vibration waveform, the circuit breaker both side height vibration waveform and the core gap vibration waveform are used as the second waveform for representing the vibration waveform.

5. A high voltage circuit breaker fault assessment method according to claim 1, characterized in that: Calculate the energy entropy of the first waveform according to the first model, the first mechanical parameter and the first waveform to obtain a first energy entropy; and calculating the energy entropy of the second waveform according to the first model, the first mechanical parameter and the second waveform to obtain the second energy entropy, including: According to a first model of the high-voltage circuit breaker to be evaluated and the corresponding parameter standard value, determining that the parameter standard value corresponding to the first model is a second standard value; Comparing the first mechanical parameter with the second standard value, and when the first mechanical parameter is greater than the second standard value, taking the first mechanical parameter greater than the second standard value as the second target mechanical parameter; The first waveform and the second waveform corresponding to the second target mechanical parameter are used as the third waveform and the fourth waveform respectively; A signal transformation is performed according to the third waveform to calculate the first energy entropy; and a signal transformation is performed according to the fourth waveform to calculate the second energy entropy.

6. A high voltage circuit breaker fault assessment method as claimed in claim 5, characterized in that: Performing signal transformation according to the third waveform to calculate and obtain a first energy entropy; And performing signal transformation according to the fourth waveform to calculate and obtain a second energy entropy, including: Perform denoising processing on the third waveform and the fourth waveform respectively to obtain a first fault waveform and a second fault waveform after denoising processing; Decomposing the first fault waveform and the preset decomposition parameters to obtain a first modal function; Decomposing the second fault waveform and the preset decomposition parameters to obtain a second modal function; Performing instantaneous frequency analysis on the first modal function and the second modal function respectively to obtain a first instantaneous frequency and a second instantaneous frequency; An entropy value is calculated according to the first instantaneous frequency to obtain a first energy entropy; and an entropy value is calculated according to the second instantaneous frequency to obtain a second energy entropy.

7. A high voltage circuit breaker fault assessment method as claimed in claim 6, characterized in that: The setting of the decomposition parameters includes: Randomly select several initial decomposition mode numbers, initial smoothing parameters and initial bandwidth constraints; Decomposing the first fault waveform and the second fault waveform according to the initial decomposition mode number, the initial smoothing parameter and the initial bandwidth constraint to obtain a first modal function and a second modal function; According to the first center frequency corresponding to the first mode function and the second center frequency corresponding to the second mode function, the first center frequency and the second center frequency are sorted in descending order, and the center frequency with the largest value is used as the target center frequency; The initial decomposition mode number, initial smoothing parameter and initial bandwidth constraint corresponding to the target center frequency are taken as the final decomposition parameters.

8. A high voltage circuit breaker fault assessment device, characterized in that: include: A circuit breaker data acquisition module, used to acquire first mechanical parameters and a first model of the high-voltage circuit breaker to be evaluated; wherein the first mechanical parameters include: shaft damping, height of both sides of the circuit breaker, and core gap; A waveform control module, used to use the shaft damping, the height of both sides of the circuit breaker and the core gap as control variables, to continuously control the high-voltage circuit breaker to be evaluated, and obtain a first waveform for representing a sound waveform and a second waveform for representing a vibration waveform; an energy entropy calculation module, configured to calculate the energy entropy of the first waveform according to the first model, the first mechanical parameter and the first waveform to obtain a first energy entropy; and to calculate the energy entropy of the second waveform according to the first model, the first mechanical parameter and the second waveform to obtain a second energy entropy; A fault category clustering module, used for inputting the first energy entropy and the second energy entropy into a preset fault category identification model for clustering to obtain a plurality of cluster centers; The fault assessment result determination module is used to use the final cluster center as the fault assessment result of the high-voltage circuit breaker to be assessed.

9. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, a high-voltage circuit breaker fault assessment method as claimed in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute a high-voltage circuit breaker fault assessment method as claimed in any one of claims 1 to 7.

Images