Circuit breaker fault detection method based on electrical parameter analysis

Abstract

The invention relates to the technical field of digital data processing, in particular to a circuit breaker fault detection method based on electrical parameter analysis, and the method comprises the steps: obtaining monitoring data, and constructing a parameter matrix; screening suspicious elements based on prediction deviation of elements in the parameter matrix and a mutation point detection result, and determining a first characteristic value according to a starting moment determined by the suspicious elements and a rule degree of data fluctuation in a fluctuation duration of the suspicious elements, and determining a fault interval by combining a consistency analysis result of irregular data fluctuation in parameter matrixes of different types of monitoring data, screening target data from residual terms, obtaining a plurality of clustering trees based on the target data by using an agglomerated hierarchical clustering algorithm, and determining a fault detection result of the circuit breaker based on differences among different clustering trees. According to the method, the residual component is used for replacing the initial data, so that the clustering effect of the clustering number on the monitoring data with different fault sensitivity degrees is improved while the clustering data size is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of digital data processing, and in particular to a circuit breaker fault detection method based on electrical parameter analysis. Background Art

[0002] Circuit breakers are widely used in high-voltage and low-voltage power systems. They can automatically cut off power when overload, short circuit or other faults occur. Circuit breakers use electromagnetic mechanisms to drive the switch to quickly cut off the circuit and protect equipment from damage caused by faults. Therefore, the safe operation of the circuit breaker itself is a prerequisite for the normal operation of the power system.

[0003] At present, the fault diagnosis technology of circuit breakers has made significant progress in data-driven methods, and the data analysis results of vibration signals, electrical signals, or electrical parameters are used to diagnose whether the circuit breaker has a fault and the type of fault. Among them, the method based on data clustering is one of the common methods for fault diagnosis using the electrical parameters of the circuit breaker. This type of method has good robustness when facing a large amount of electrical parameter data collected on the circuit breaker. However, when processing large-scale electrical parameters, the time overhead is large, the timeliness of the fault diagnosis of the circuit breaker is poor, and it will cause a large memory consumption. Summary of the invention

[0004] In order to solve the technical problems that when using data clustering to perform fault diagnosis on the electrical parameters of a circuit breaker, a large amount of parameters leads to poor detection timeliness and high computing memory consumption, the present application provides a circuit breaker fault detection method based on electrical parameter analysis, and the technical solution adopted is as follows: The present application provides a circuit breaker fault detection method based on electrical parameter analysis, the method comprising the following steps: Obtain monitoring data of circuit breakers and construct parameter matrix for each monitoring data; Screen suspicious elements based on the prediction deviation of the elements in the parameter matrix and the mutation point detection results, and determine the first eigenvalue of the suspicious element according to the starting time determined by the suspicious elements in different rows of the parameter matrix and the regularity of the data fluctuation within the fluctuation time of the suspicious element; Based on the first eigenvalue of the suspicious element in each row of the parameter matrix, combined with the consistency analysis results of irregular data fluctuations in the parameter matrix of different types of monitoring data, the fault interval of circuit breaker fault detection is determined; The target data is screened from the residual items according to the fault interval of circuit breaker fault detection, and several clustering trees are obtained based on the target data using an agglomerative hierarchical clustering algorithm. The fault detection result of the circuit breaker is determined based on the difference between different clustering trees.

[0005] Preferably, the screening of suspicious elements includes: Using a data prediction algorithm to obtain a predicted value of each element based on a number of elements in the parameter matrix that are in the same row as each element and are located before each element, the absolute value of the difference between the predicted value and each element is used as the predicted deviation of each element; The mutation point in each row of the parameter matrix is ​​obtained by using the mutation point detection method; For any non-mutation point in each row of elements, the sum of the time intervals between each non-mutation point and its adjacent left and right mutation points is calculated as the fluctuation duration of each non-mutation point; The non-mutation point with the largest prediction deviation and the shortest fluctuation duration in each row of elements is regarded as the suspicious element in each row of elements.

[0006] Preferably, determining the first characteristic value of the suspicious element includes: Taking the acquisition time of the suspicious element as the starting time, calculating the cumulative result of the time interval between the starting time determined by the suspicious element in each row of elements in the parameter matrix and the starting time determined by the suspicious elements in the remaining rows of elements on the parameter matrix; The ratio of the accumulated result to the fluctuation duration of the suspicious element in each row of elements is used as the fault characteristic value of the suspicious element in each row of elements; The first characteristic value of the suspicious element is obtained according to the prediction deviations of all elements within the fluctuation duration of the suspicious element, the discrete characteristic values ​​of all elements, and the fault characteristic value.

[0007] Preferably, obtaining the first characteristic value of the suspicious element includes: The sum of the discrete eigenvalues ​​of all elements within the fluctuation duration of the suspicious element and the parameter adjustment constant is used as the denominator; The ratio of the product of the mean of the predicted deviations of all elements within the fluctuation time of the suspicious element and the fault characteristic value of the suspicious element to the denominator is taken as the first characteristic value of the suspicious element.

[0008] Preferably, the determining of the fault interval for circuit breaker fault detection includes: Performing difference measurement on the fluctuation duration of the suspicious elements determined in all parameter matrices of each circuit breaker to obtain the measurement result; The correlation analysis method is used to obtain the correlation analysis results between the characteristic sequences of each circuit breaker on two different monitoring data; Determine the second eigenvalue of the suspicious element by using the correlation analysis result between the feature sequences, the measurement result, and the first eigenvalue of the suspicious element; Obtain the second eigenvalue of the suspicious element of each circuit breaker in all parameter matrices, obtain the mode of all the second eigenvalues, and use the union of the fluctuation durations of the suspicious elements corresponding to the modes as the suspected fault interval of each circuit breaker; The union of the suspected fault intervals of all circuit breakers is taken as the fault interval for circuit breaker fault detection.

[0009] Preferably, the characteristic sequence is acquired by taking a sequence composed of elements within a fluctuation duration of a suspicious element corresponding to each circuit breaker in the parameter matrix as a characteristic sequence of each circuit breaker on the monitoring data corresponding to the parameter matrix.

[0010] Preferably, determining the second characteristic value of the suspicious element includes: Calculate the mean of the correlation analysis results between the characteristic sequences of each circuit breaker on any two different monitoring data; The second eigenvalue of the suspicious element consists of the first eigenvalue of the suspicious element, the measurement result, and the mean; wherein the second eigenvalue is positively correlated with the first eigenvalue and the mean, respectively; and the second eigenvalue is negatively correlated with the measurement result.

[0011] Preferably, the screening target data includes: Take each row element in the parameter matrix as input and use the time series decomposition STL algorithm to obtain the residual term of each row element; A set of residual components belonging to the fault interval of circuit breaker fault detection in each residual item obtained by decomposing each parameter matrix is ​​recorded as target data of each residual item; The set consisting of the target data of the residual items of the corresponding row elements of each circuit breaker from all the parameter matrices is taken as the target data set of each circuit breaker.

[0012] Preferably, determining the fault detection result of the circuit breaker includes: A clustering tree of each circuit breaker is obtained based on the target data set of each circuit breaker using a hierarchical clustering algorithm; Determine the status difference of each circuit breaker based on the height difference between the clustering trees of different circuit breakers and the difference between the number of nodes at the same height; An abnormal value in the state difference of all circuit breakers is detected by using an abnormal detection algorithm, and the circuit breaker corresponding to the abnormal value is regarded as a faulty circuit breaker.

[0013] Preferably, determining the fault status of each circuit breaker includes: The clustering tree of each circuit breaker is used as the target clustering tree; Calculate the height difference between the target clustering tree and the clustering tree of any other circuit breaker; Calculate the cumulative result of the difference between the number of nodes at the same height between the target clustering tree and the clustering tree of any other circuit breaker at the same height; The product of the height difference value and the accumulation result is accumulated on the clustering trees of all circuit breakers as the state difference of the circuit breaker corresponding to the target clustering tree.

[0014] This application has at least the following beneficial effects: First, the present application performs time series decomposition on the initial data of the circuit breaker voltage to obtain the residual component, and obtains the residual term by performing time series decomposition on each row element in each parameter matrix. Compared with abnormality detection through monitoring data, the use of residual terms can better reflect the irregular data fluctuations caused by the circuit breaker's own failure; secondly, by analyzing the difference between the data fluctuations caused by the power system where the circuit breaker is located to the monitoring data and the irregular data fluctuations caused by the circuit breaker failure, the suspicious elements that may be in the fault interval and the first eigenvalues ​​of the suspicious elements are obtained, so as to achieve a preliminary evaluation of the monitoring data under the circuit breaker fault state; then, the second eigenvalue of the suspicious element is determined by using the correlation between the data fluctuations of different types of monitoring data when the circuit breaker itself fails, and then the suspected fault of the circuit breaker is determined. Interval, considering that when a circuit breaker fails, different types of monitoring data will have certain differences in sensitivity to the fault, so that the subsequent clustering tree can process monitoring data of various sensitivity levels; then, the union of all the suspected fault intervals is obtained as the fault interval for circuit breaker fault detection. The acquisition of the fault interval takes into account that on the one hand, different sensors have different noise sensitivities; on the other hand, the circuit breakers at various locations in the power system are affected differently. Taking the union can use more data for subsequent detection, eliminate the impact of noise data, and improve the accuracy of subsequent fault detection; then, the fault interval of circuit breaker fault detection is used to obtain the target data set for each circuit breaker, and use it as the input data of the agglomerative hierarchical clustering algorithm to generate a clustering tree, reducing the amount of clustering data while maintaining the clustering tree pair. In this application, the residual component caused by the fault is used to replace the initial data, which not only reduces the amount of data and improves the operating efficiency of the algorithm, but also improves the clustering effect of the number of clusters on monitoring data with different fault sensitivities, making the final fault detection result more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 A flow chart of a circuit breaker fault detection method based on electrical parameter analysis provided in this application. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of the circuit breaker fault detection method based on electrical parameter analysis proposed in the present application, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0019] The specific scheme of the circuit breaker fault detection method based on electrical parameter analysis provided by the present application is described in detail below with reference to the accompanying drawings.

[0020] An embodiment of the present application provides a circuit breaker fault detection method based on electrical parameter analysis. Specifically, the following circuit breaker fault detection method based on electrical parameter analysis is provided. Figure 1 , the method comprises the following steps: Step S001, obtaining real-time monitoring data of the circuit breaker and preprocessing the obtained data.

[0021] The online monitoring system of the circuit breaker usually consists of three parts: the monitoring front end, the monitoring host computer, and the background system. The monitoring front end monitors the electrical parameters of the circuit breaker online through the data acquisition equipment, analyzes and calculates the collected monitoring data through the monitoring host computer, provides data support for the diagnosis of circuit breaker faults, and uses the background system to record the monitoring data and fault diagnosis results. Among them, the data acquisition equipment includes but is not limited to the opening current sensor, the closing current sensor, the Hall sensor, and the voltage sensor, and the monitoring data that can be collected include but are not limited to the opening current, the closing current, the operating voltage, the opening speed, the closing speed, and the voltage.

[0022] Specifically, each type of monitoring data of the circuit breaker collected by the monitoring front end is expressed in the form of a parameter matrix to facilitate subsequent data analysis and recording. First, for each type of monitoring data, in order to avoid missing data during the collection process, the collection results are cleaned by data filling to ensure that all types of monitoring data have specific collection results at the same collection time. Secondly, a parameter matrix is ​​constructed using the processed monitoring data: each column in the parameter matrix is ​​composed of the same type of monitoring data of several circuit breakers at the same collection time, and each row in the parameter matrix is ​​composed of monitoring data of a circuit breaker at different collection times. And the constructed parameter matrices are respectively denoted as , , respectively represent the parameter matrices of the first, second, and nth monitoring data.

[0023] Among them, data filling is a well-known technology in the field of data processing, and this application will not go into details. Commonly used data filling methods include but are not limited to mean filling, nearest neighbor filling, and interpolation filling. This application does not impose any special restrictions on the specific method of data filling. Preferably, as an embodiment of this application, the collection results are cleaned by using the nearest neighbor filling method.

[0024] At this point, the parameter matrix of the circuit breaker is obtained for analyzing the circuit breaker status.

[0025] Step S002: Comprehensively analyze the fluctuation degree of the circuit breaker on different types of monitoring data and the predictability of the data fluctuation period, screen suspicious elements in the parameter matrix, and determine the first eigenvalue of the suspicious element.

[0026] Agglomerative Hierarchical Clustering is a data processing method that constructs a clustering hierarchy by gradually merging similar samples or clusters. The basic idea of ​​agglomerative hierarchical clustering is to start from each sample or cluster and gradually merge the most similar samples or clusters until all samples or clusters are merged into a large cluster or a predetermined stop condition is reached. The algorithm is relatively robust, but due to its high computational complexity, agglomerative hierarchical clustering has large space and time overhead when processing large-scale data sets, resulting in long computing time and large memory consumption. Therefore, in this application, the parameter matrix collected by the circuit breaker is optimized to obtain less data that can reflect whether the circuit breaker is processing a fault state as the input data of the agglomerative hierarchical clustering algorithm, thereby reducing the running time and complexity of the algorithm while being able to detect circuit breaker faults.

[0027] First, the monitoring data of all circuit breakers in the entire power system are analyzed in time series, using the monitoring matrix of the nth electrical parameter For example, Each row element of is used as the input of the time series decomposition algorithm STL, and each row element is decomposed into trend term, residual term and seasonal term. The seasonal smoothing parameter, trend smoothing parameter and estimation window length in the algorithm are set to empirical values ​​of 11, 17 and 25 respectively. Among them, time series decomposition is a well-known technology in the field of data processing, and this application will not go into details.

[0028] Secondly, for each row of elements in the parameter matrix, the residual term represents the data features that cannot be explained by the trend and seasonal terms. The residual term includes the outliers, noise, and irregular data changes that appear in the time series of the circuit breaker monitoring data. Therefore, when a circuit breaker fails, the data changes in the monitoring data at the time of the failure are clearly different from the data trends of the monitoring data when the circuit breaker is normal, which cannot be reflected by the trend term and the seasonal term, but can be represented by the residual term.

[0029] Due to the existence of various power conditions in the power system, such as power dispatching and harmonic oscillation, the monitoring data on the circuit breaker has certain fluctuations, which also exist in the residual term after decomposition. For example, the inrush current and overvoltage generated when the circuit breaker is closed will directly cause current and voltage fluctuations; when there is a pre-potential fault in the power system where the circuit breaker is located, there will be contact problems caused by short-circuit current, which may also cause current fluctuations.

[0030] In summary, the decomposed residual term not only includes the data changes caused by the circuit breaker failure, but also may contain data fluctuations caused by various factors in the power system where the circuit breaker is located. Therefore, it is necessary to conduct an in-depth analysis of the residual term.

[0031] Specifically, when a circuit breaker fails, various monitoring data of the circuit breaker will change synchronously, and within a short period of time after the failure, that is, the same monitoring data at several adjacent collection moments will experience irregular data fluctuations, which are unpredictable; and when the above-mentioned power conditions in the power system cause data fluctuations in the parameter matrix, they are usually predictable, and generally there will only be mutations in a few or even one type of monitoring data.

[0032] First, for the parameter matrix For each element in , the K elements in the same row as each element and located before each element are used as the input of the prediction algorithm, the prediction model is used to output the predicted value of each element, and the absolute value of the difference between the predicted value and each element is used as the prediction deviation of each element. The larger the prediction deviation, the greater the data change amplitude of the element, and the more likely it is caused by a circuit breaker failure.

[0033] It should be noted that data prediction is a well-known technology in the field of data processing, and this application will not go into details. Commonly used data predictions include, but are not limited to, prediction methods based on support vector machines, exponential smoothing methods, autoregressive moving average model ARIMA, and prediction models based on neural networks. This application does not impose any special restrictions on data prediction methods. Preferably, as an embodiment of the present application, the prediction results of each element are obtained using the autoregressive moving average model ARIMA.

[0034] Secondly, the parameter matrix is ​​obtained by using mutation point detection The mutation points in each row of elements in , these mutation points correspond to the elements where the monitoring data has changed, after obtaining all the mutation points in each row of elements. For any non-mutation point in each row of elements, the sum of the time intervals between each non-mutation point element and its adjacent left and right mutation points is calculated as the fluctuation duration of each non-mutation point. The smaller the fluctuation duration, the more severe the short-term data fluctuation of the element may be. It may be a short-term data fluctuation caused by transient faults such as partial discharge and overvoltage. If the data fluctuation is caused by factors in the power system, the duration of the data change is relatively long.

[0035] In particular, the elements on the left side of the first mutation point and the elements on the right side of the last mutation point in each row of elements do not participate in the calculation of the time interval. This is because if an element is monitoring data during a circuit breaker failure, then the mutation point corresponding to the moment when the circuit breaker failure returns to normal must be located on the right side of the element.

[0036] Furthermore, the non-mutation point with the largest prediction deviation and the shortest fluctuation duration in each row of elements is regarded as a suspicious element with a high probability of being in the circuit breaker failure period, and the acquisition time of the suspicious element is regarded as the starting time of the irregular data fluctuation. The starting time of each row of elements in the above process is determined. If the starting times of multiple rows of elements belong to the same time, it means that there is a high probability that a composite fault such as short circuit and phase failure has occurred in the power system where the circuit breaker is located, causing the linkage protection mechanism in the power system, resulting in synchronous action of circuit breakers at different locations, and the irregular data fluctuation is not caused by the fault of the circuit breaker itself.

[0037] Here, the first characteristic value of the suspicious element is calculated to evaluate the irregular data fluctuation caused by the circuit breaker failure that continues to occur at several consecutive acquisition moments after the starting moment. The specific calculation formula is as follows: In the formula, is the fault characteristic value of the suspicious element in the first row, M is the number of rows in the parameter matrix, , are the starting time of determining the suspicious elements in the first row and the mth row of the parameter matrix, respectively. is the fluctuation duration of the suspicious elements in the first row of elements.

[0038] Based on the fault characteristic value and the regularity of the data fluctuation within the fluctuation time of the suspicious element, the first characteristic value of the suspicious element is comprehensively determined: In the formula, is the first eigenvalue of the suspicious element in the first row of elements, is the mean of the prediction deviations of all elements within the fluctuation period of the suspicious elements in the first row, It is the discrete eigenvalue of all elements within the fluctuation duration of the suspicious elements in the first row. is a tuning constant used to avoid the influence of denominator 0 on calculation. The value of is a positive number less than 0.01. Preferably, in one embodiment of the present application, the empirical value is 0.001.

[0039] It should be noted that the discrete eigenvalue is used to evaluate the irregular data fluctuation of all elements within the fluctuation duration of the suspicious element. The calculation method of the discrete eigenvalue includes but is not limited to the distribution variance and the coefficient of variation. The present application does not impose any special restrictions on the specific calculation method. Preferably, in one embodiment of the present application, the coefficient of variation of all elements within the fluctuation duration of the suspicious element is calculated as the discrete eigenvalue.

[0040] It should be further explained that the greater the time deviation of the starting moment of the data change determined by the monitoring data of different circuit breakers in the parameter matrix, the lower the possibility of the residual term caused by the composite fault in the power system; at the same time, the higher the irregularity of the data, the greater the predictability, the higher the irregularity of the data change, and the greater the correlation between the data characteristics expressed in the residual term and the circuit breaker fault. The larger the value of , the greater the possibility that the suspicious elements in the first row are abnormal data caused by circuit breaker failures, and the more likely the residual items of the elements within the fluctuation duration of the suspicious elements in the first row reflect the irregular data fluctuation characteristics caused by circuit breaker failures.

[0041] At this point, the first characteristic value of the suspicious element is determined, and the possibility of the irregular data fluctuation of the suspicious element caused by the circuit breaker fault is preliminarily evaluated.

[0042] S003, determining a fault interval for circuit breaker fault detection based on a first eigenvalue of a suspicious element in each row of elements in the parameter matrix and combining a consistency analysis result of irregular data fluctuations in the parameter matrix of different types of monitoring data.

[0043] In the above steps, the first eigenvalue of the suspicious element in each row of the parameter matrix is ​​determined based on the fluctuation duration of the same monitoring data of the sensor and the synchronization characteristics of the fluctuation of the circuit breaker, and a preliminary evaluation is made on whether the different data in the residual term is caused by the circuit breaker failure. However, only a single parameter is still not enough to obtain data that can be used for circuit breaker fault detection. Therefore, in this application, the parameter matrix of different types of monitoring data at the starting time determined by each suspicious element in the parameter matrix is ​​further analyzed to determine the fault interval of circuit breaker fault detection.

[0044] Specifically, according to the above process, the suspicious elements in each row of elements in the parameter matrix of each monitoring data are obtained respectively. For any circuit breaker, the ath circuit breaker is taken as an example for description. After the suspicious elements in the monitoring data of the ath circuit breaker are determined in all parameter matrices, the fluctuation duration and starting time of each suspicious element are obtained respectively.

[0045] On the one hand, when the ath circuit breaker fails, during the time period from the ath circuit breaker failure to the restoration of normal state, the duration of data changes of different types of monitoring data on the ath circuit breaker should be relatively consistent, that is, the fluctuation duration of suspicious elements in different parameter matrices is basically close. On the other hand, if the data fluctuation is caused by the circuit breaker failure, for different types of monitoring data of the same circuit breaker, for example, when the closing current of the circuit breaker increases, it will cause difficulty in closing, and the closing speed will change significantly; when the closing resistance of the circuit breaker fails, the closing current will increase, resulting in failure of inrush current suppression, which may be accompanied by voltage fluctuations. That is, the failure of the circuit breaker itself will inevitably lead to a certain degree of correlation between different types of monitoring data. Therefore, it is possible to perform correlation analysis on the elements of different types of monitoring data within the fluctuation duration, and further screen the time range of the circuit breaker failure based on the correlation analysis results.

[0046] Specifically, the suspicious elements of the corresponding rows of the a-th circuit breaker in all parameter matrices are obtained respectively, and the sequence composed of the elements in the fluctuation time of each suspicious element is used as the characteristic sequence of the corresponding monitoring data of the parameter matrix. The correlation analysis method is used to analyze the correlation between different characteristic sequences of the a-th circuit breaker, and the correlation between the characteristic sequences of the a-th circuit breaker in the i-th monitoring data and the j-th monitoring data is recorded as , the mean value of the correlation between the characteristic sequences of the a-th circuit breaker on all monitoring data is recorded as .

[0047] Embodiment 1: The characteristic sequence of any one of the n types of monitoring data of the a-th circuit breaker is taken as the dependent variable, and the characteristic sequences of the other types of monitoring data are taken as independent variables. The correlation analysis algorithm is used to perform the correlation analysis between the independent variable and the dependent variable to determine the correlation between different characteristic sequences.

[0048] Embodiment 2: The characteristic sequences of any two types of monitoring data of the a-th circuit breaker in n types of monitoring data are taken as independent variables, and the characteristic sequences of the remaining types of monitoring data are taken as dependent variables. The correlation analysis algorithm is used to perform correlation analysis between the independent variables and the dependent variables to determine the correlation between different characteristic sequences.

[0049] It should be noted that correlation analysis is a well-known technology in the field of data processing. Common correlation analysis algorithms include but are not limited to grey correlation analysis, response surface analysis, and multi-factor analysis. This application does not place any special restrictions on specific methods. Preferably, as an embodiment of this application, the correlation between the different feature sequences is obtained using a grey correlation analysis method.

[0050] Here, the second eigenvalue of the suspicious element is calculated to evaluate whether there is a certain correlation between the irregular data fluctuations occurring in the circuit breaker within the fluctuation duration. First, the difference between the fluctuation durations determined by the a-th circuit breaker in all parameter matrices is evaluated. The greater the difference between the lengths of all the fluctuation durations, the greater the difference in the fluctuations of different types of monitoring data, and the greater the impact of other factors in the power system. Among them, the purpose of performing the difference evaluation is to measure the difference between different fluctuation durations. Therefore, under the premise of being able to achieve this purpose, the difference between the fluctuation durations can be measured by methods including but not limited to distribution variance and coefficient of variation.

[0051] Secondly, the second eigenvalue of the suspicious element is obtained by measuring the difference between the first eigenvalue of the suspicious element and the fluctuation duration. The second eigenvalue is respectively related to the first eigenvalue, There is a positive correlation between the second eigenvalue and the difference measurement result of the fluctuation duration, and there is a negative correlation between the second eigenvalue and the fluctuation duration.

[0052] It should be noted that positive correlation means that when one variable increases, the other variable also increases, and the two variables change in the same direction. When one variable changes from large to small or from small to large, the other variable also changes from large to small or from small to large. The specific relationship is determined by actual application and this application does not impose any special restrictions.

[0053] It should be noted that negative correlation means that when one variable increases, the other variable decreases accordingly, and the two variables change in opposite directions. When one variable changes from large to small or from small to large, the other variable also changes from small to large or from large to small. The specific relationship is determined by actual application and this application does not impose any special restrictions.

[0054] Preferably, in one embodiment of the present application, the specific calculation formula of the second characteristic value of the suspicious element is as follows: In the formula, is the second eigenvalue of the suspicious element in the jth parameter matrix of the ath circuit breaker, is the first eigenvalue of the suspicious element in the jth parameter matrix of the ath circuit breaker, is the mean value of the correlation between the corresponding feature sequences of the a-th circuit breaker in all parameter matrices, It is the mean of the differences between the corresponding fluctuation durations of the a-th circuit breaker in all parameter matrices.

[0055] Further, according to the above steps, the second eigenvalues ​​of the suspicious elements of the a-th circuit breaker in all parameter matrices are obtained respectively, the mode of all the second eigenvalues ​​is obtained, and the union of the fluctuation durations of the suspicious elements corresponding to the mode is used as the suspected fault interval when the a-th circuit breaker fails. The reason for taking the mode here is that when a circuit breaker fails, the sensitivity of different types of monitoring data to the fault will vary to a certain extent. If you want to train a detection model with excellent detection performance, you should be able to process monitoring data of various sensitivity levels.

[0056] According to the above steps, the suspected fault intervals of all circuit breakers are determined respectively, and the union of all the suspected fault intervals is obtained as the fault interval for circuit breaker fault detection. The reason for taking the union is that on the one hand, different sensors have different noise sensitivities; on the other hand, circuit breakers at different locations in the power system are affected differently. Taking the union can use more data for subsequent detection, eliminate the influence of noise data, and improve the accuracy of subsequent fault detection.

[0057] S004, selecting target data from the residual items according to the fault interval of the circuit breaker fault detection, obtaining a plurality of clustering trees based on the target data using an agglomerative hierarchical clustering algorithm, and determining the fault detection result of the circuit breaker based on the difference between different clustering trees.

[0058] After the fault interval of circuit breaker fault detection is obtained through the above steps, a set of residual components belonging to the fault interval in each residual item is extracted from each parameter matrix, which is recorded as the target data of each residual item; a set of target data of residual items of corresponding row elements of each circuit breaker from all parameter matrices is taken as the target data set of each circuit breaker.

[0059] Furthermore, after obtaining the target data sets of all circuit breakers according to the above process, the target data sets of each circuit breaker are respectively used as input data of the agglomerative hierarchical clustering algorithm. The similarity calculation between clusters during clustering uses the even-link algorithm, and no clustering threshold is set. The clustering tree of each target data set is obtained in turn, and the number of nodes of each clustering tree at each height is counted respectively. The more the number of nodes, the worse the clustering effect at the corresponding height.

[0060] Secondly, the abnormal data in the target data set of all parameter matrices are evaluated based on the height difference between different clustering trees and the difference in the number of nodes at the same height. The greater the change in the monitoring data when the circuit breaker itself fails, the more the residual component of the monitoring data collected in the fault interval after decomposition can reflect the characteristics of the monitoring data when the circuit breaker fails, and the higher the irregularity of the residual component. Therefore, the clustering tree of the target data trip of the parameter matrix of the faulty circuit breaker has a higher degree of irregularity at the same height compared with the other clustering trees, and the clustering in the clustering process is worse.

[0061] In the formula, is the state difference of the ath circuit breaker, M is the number of circuit breakers, is the height difference between the clustering trees obtained from the target data of the a-th circuit breaker and the b-th circuit breaker, It is the cumulative result of the difference between the number of nodes at all the same heights of the clustering tree obtained from the target data of the a-th circuit breaker and the b-th circuit breaker.

[0062] In particular, if the heights of two clustering trees are inconsistent, when calculating the difference between the number of nodes of the two clustering trees at the same height, the clustering tree with the largest height is used as the standard, and the number of nodes of the clustering tree with the lowest height at the height difference between the two clustering trees is recorded as 0. For example, if the heights of the two clustering trees are 10 and 8 respectively, the number of nodes of the clustering tree with a height of 8 at heights of 9 and 10 are both recorded as 0.

[0063] According to the above steps, the state differences of all circuit breakers are obtained respectively, anomaly detection algorithms are used to detect abnormal values, and the circuit breaker corresponding to each abnormal value is regarded as a faulty circuit breaker.

[0064] It should be noted that anomaly detection is a well-known technology in the field of data processing, and the specific process will not be repeated here. Common anomaly detection methods include but are not limited to LOF anomaly detection and isolation forest detection. This application does not impose any special restrictions on anomaly detection algorithms. Preferably, as an embodiment of the present application, the LOF anomaly detection algorithm is used to obtain the outliers in all the state differences.

[0065] It should be noted that the above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

[0066] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A circuit breaker fault detection method based on electrical parameter analysis, characterized in that: The method comprises the following steps: Obtain monitoring data of circuit breakers and construct parameter matrix for each monitoring data; Screen suspicious elements based on the prediction deviation of the elements in the parameter matrix and the mutation point detection results, and determine the first eigenvalue of the suspicious element according to the starting time determined by the suspicious elements in different rows of the parameter matrix and the regularity of the data fluctuation within the fluctuation time of the suspicious element; Based on the first eigenvalue of the suspicious element in each row of the parameter matrix, combined with the consistency analysis results of irregular data fluctuations in the parameter matrix of different types of monitoring data, the fault interval of circuit breaker fault detection is determined; The target data is screened from the residual items according to the fault interval of circuit breaker fault detection, and several clustering trees are obtained based on the target data using an agglomerative hierarchical clustering algorithm. The fault detection result of the circuit breaker is determined based on the difference between different clustering trees.

2. The circuit breaker fault detection method based on electrical parameter analysis according to claim 1, characterized in that: The screening of suspicious elements includes: Using a data prediction algorithm to obtain a predicted value for each element based on a number of elements in the parameter matrix that are in the same row as each element and are located before each element, the absolute value of the difference between the predicted value and each element is used as the predicted deviation of each element; The mutation point in each row of the parameter matrix is ​​obtained by using the mutation point detection method; For any non-mutation point in each row of elements, the sum of the time intervals between each non-mutation point and its adjacent left and right mutation points is calculated as the fluctuation duration of each non-mutation point; The non-mutation point with the largest prediction deviation and the shortest fluctuation duration in each row of elements is regarded as the suspicious element in each row of elements.

3. The circuit breaker fault detection method based on electrical parameter analysis according to claim 1, characterized in that: The determining of the first characteristic value of the suspicious element includes: Taking the acquisition time of the suspicious element as the starting time, calculating the cumulative result of the time interval between the starting time determined by the suspicious element in each row of elements in the parameter matrix and the starting time determined by the suspicious elements in the remaining rows of elements on the parameter matrix; The ratio of the accumulated result to the fluctuation duration of the suspicious element in each row of elements is used as the fault characteristic value of the suspicious element in each row of elements; The first characteristic value of the suspicious element is obtained according to the prediction deviations of all elements within the fluctuation duration of the suspicious element, the discrete characteristic values ​​of all elements, and the fault characteristic value.

4. The circuit breaker fault detection method based on electrical parameter analysis according to claim 3, characterized in that: The obtaining of the first characteristic value of the suspicious element includes: The sum of the discrete eigenvalues ​​of all elements within the fluctuation duration of the suspicious element and the parameter adjustment constant is used as the denominator; The ratio of the product of the mean of the predicted deviations of all elements within the fluctuation time of the suspicious element and the fault characteristic value of the suspicious element to the denominator is taken as the first characteristic value of the suspicious element.

5. The circuit breaker fault detection method based on electrical parameter analysis according to claim 1, characterized in that: The determining of the fault interval for circuit breaker fault detection comprises: Performing difference measurement on the fluctuation duration of the suspicious elements determined in all parameter matrices of each circuit breaker to obtain the measurement result; The correlation analysis method is used to obtain the correlation analysis results between the characteristic sequences of each circuit breaker on two different monitoring data; Determine the second eigenvalue of the suspicious element by using the correlation analysis result between the feature sequences, the measurement result, and the first eigenvalue of the suspicious element; Obtain the second eigenvalue of the suspicious element of each circuit breaker in all parameter matrices, obtain the mode of all the second eigenvalues, and use the union of the fluctuation durations of the suspicious elements corresponding to the modes as the suspected fault interval of each circuit breaker; The union of the suspected fault intervals of all circuit breakers is taken as the fault interval for circuit breaker fault detection.

6. The circuit breaker fault detection method based on electrical parameter analysis according to claim 5, characterized in that: The characteristic sequence is obtained by taking a sequence composed of elements within the fluctuation duration of the suspicious element corresponding to each circuit breaker in the parameter matrix as a characteristic sequence of each circuit breaker on the monitoring data corresponding to the parameter matrix.

7. The circuit breaker fault detection method based on electrical parameter analysis according to claim 5, characterized in that: The determining the second characteristic value of the suspicious element comprises: Calculate the mean of the correlation analysis results between the characteristic sequences of each circuit breaker on any two different monitoring data; The second eigenvalue of the suspicious element consists of the first eigenvalue of the suspicious element, the measurement result, and the mean; wherein the second eigenvalue is positively correlated with the first eigenvalue and the mean, respectively; and the second eigenvalue is negatively correlated with the measurement result.

8. The circuit breaker fault detection method based on electrical parameter analysis according to claim 1, characterized in that: The screening target data includes: Take each row element in the parameter matrix as input and use the time series decomposition STL algorithm to obtain the residual term of each row element; A set of residual components belonging to the fault interval of circuit breaker fault detection in each residual item obtained by decomposing each parameter matrix is ​​recorded as target data of each residual item; The set consisting of the target data of the residual items of the corresponding row elements of each circuit breaker from all the parameter matrices is taken as the target data set of each circuit breaker.

9. The circuit breaker fault detection method based on electrical parameter analysis according to claim 1, characterized in that: The determining of the fault detection result of the circuit breaker comprises: A clustering tree of each circuit breaker is obtained based on the target data set of each circuit breaker using a hierarchical clustering algorithm; Determine the status difference of each circuit breaker based on the height difference between the clustering trees of different circuit breakers and the difference between the number of nodes at the same height; An abnormal value in the state difference of all circuit breakers is detected by using an abnormal detection algorithm, and the circuit breaker corresponding to the abnormal value is regarded as a faulty circuit breaker.

10. The circuit breaker fault detection method based on electrical parameter analysis according to claim 9, characterized in that: Determining the fault status of each circuit breaker includes: The clustering tree of each circuit breaker is used as the target clustering tree; Calculate the height difference between the target clustering tree and the clustering tree of any other circuit breaker; Calculate the cumulative result of the difference between the number of nodes at the same height between the target clustering tree and the clustering tree of any other circuit breaker at the same height; The product of the height difference value and the accumulation result is accumulated on the clustering trees of all circuit breakers as the state difference of the circuit breaker corresponding to the target clustering tree.

Images