Partial discharge signal matching method and device, storage medium and electronic equipment

Abstract

The invention discloses a partial discharge signal matching method and device, a storage medium and electronic equipment. The method comprises the steps that partial discharge signals of the power equipment are collected, and the partial discharge signals comprise incident pulse signals and reflected pulse signals; constructing a feature matrix according to a local extreme point included in the partial discharge signal; dividing based on the feature matrix to obtain a minimum value feature matrix and a maximum value feature matrix; determining a matching path between the minimum value feature matrix and the maximum value feature matrix by adopting a dynamic time warping algorithm; and obtaining a matching result of the incident pulse signal and the reflected pulse signal based on the matching path. According to the invention, the technical problems of low matching precision of incident waves and reflected waves and weak anti-noise interference capability in the prior art are solved.

Description

Technical Field

[0001] This application relates to the field of power operation and maintenance. Specifically, it relates to a method, device, storage medium, and electronic device for matching partial discharge signals. Background Art

[0002] With the expansion of the scale of the power system and the complexity of power equipment, the fault diagnosis and early warning of equipment have become increasingly important. Partial Discharge (PD), as one of the precursors of power equipment faults, refers to the local discharge phenomenon caused by electrical stress when the equipment is in operation. These discharges usually manifest as high-frequency pulse signals. By monitoring and analyzing these signals, the health status of the equipment can be effectively evaluated, potential faults can be detected in a timely manner, and the stable operation of the power system can be guaranteed.

[0003] Existing partial discharge signal matching technologies mostly rely on traditional correlation analysis methods, which usually assume that there is a fixed linear relationship between signals. However, partial discharge signals in the power system are usually affected by multiple factors such as equipment aging, electrical stress, and external environmental changes, resulting in non-linear signal variations. Traditional methods show low matching accuracy when dealing with non-linear characteristics such as time delay, amplitude change, and frequency drift in signals, and it is difficult to meet the requirements of high-precision monitoring and fault early warning. The existing matching algorithms are highly sensitive to noise, which easily leads to false matching or missed detection, affecting the reliability of fault detection. At the same time, the matching methods of existing technologies are usually based on static data analysis and lack the ability to adapt to the dynamic operating state of the equipment and environmental changes. In the power system, the equipment state and environmental conditions may change at any time, and traditional methods fail to effectively respond to these changes, resulting in the inability to accurately capture faults or response delays, affecting the timeliness of fault early warning. Therefore, the existing technology has poor dynamic adaptability, complex calculations, and poor real-time performance, and cannot meet the requirements of the power system for rapid response and real-time monitoring.

[0004] In response to the above problems, no effective solution has been proposed yet. Summary of the Invention

[0005] Embodiments of this application provide a method, device, storage medium, and electronic device for matching partial discharge signals to at least solve the technical problems of low matching accuracy between incident waves and reflected waves and weak anti-noise interference ability in related technologies.

[0006] According to one aspect of the embodiments of the present application, a method for matching partial discharge signals is provided, including: collecting partial discharge signals of a power device, where the partial discharge signals include incident pulse signals and reflected pulse signals; constructing a feature matrix based on the local extreme points included in the partial discharge signals; dividing based on the feature matrix to obtain a minimum value feature matrix and a maximum value feature matrix; using the dynamic time warping algorithm to determine the matching path between the minimum value feature matrix and the maximum value feature matrix; and obtaining the matching result of the incident pulse signal and the reflected pulse signal based on the matching path.

[0007] Optionally, constructing a feature matrix based on the local extreme points included in the partial discharge signals includes: determining the extreme point magnitude and extreme point position of the local extreme points; determining the left and right slopes of the extreme points of the left and right fitting line segments of the local extreme points based on the extreme point magnitude and extreme point position; and obtaining the feature matrix based on the extreme point magnitude, extreme point position, and left and right slopes of the extreme points.

[0008] Optionally, the partial discharge signal is a time series. Obtaining the feature matrix based on the extreme point magnitude, extreme point position, and left and right slopes of the extreme points includes: converting the left and right slopes of the extreme points into circumferential angles; converting the extreme point position into a ratio between the extreme point position and the length of the time series; and obtaining the normalized feature matrix based on the extreme point magnitude, circumferential angle, and ratio.

[0009] Optionally, collecting partial discharge signals of a power device includes: collecting incident pulse signals and reflected pulse signals of partial discharge through sensors of the power device; and preprocessing based on the incident pulse signals and the reflected pulse signals to obtain partial discharge signals, where the preprocessing includes at least one of the following: denoising, filtering, smoothing, and normalization.

[0010] Optionally, there are multiple local extreme points. Using the dynamic time warping algorithm to determine the matching path between the minimum value feature matrix and the maximum value feature matrix includes: obtaining the starting trend feature based on the slope of the fitting line segment between the starting point of the partial discharge signal and the first local extreme point among the multiple local extreme points; obtaining the ending trend feature based on the slope of the fitting line segment between the ending point of the partial discharge signal and the last local extreme point among the multiple local extreme points; and using the dynamic time warping algorithm to process based on the starting trend feature, ending trend feature, minimum value feature matrix, and maximum value feature matrix to obtain the matching path.

[0011] Optionally, the dynamic time warping algorithm is adopted to determine the matching path between the minimum value feature matrix and the maximum value feature matrix, including: determining a local distance matrix according to the minimum value feature matrix and the maximum value feature matrix, wherein each element in the local distance matrix represents the distance between the minimum value included in the minimum value feature matrix and the maximum value included in the maximum value feature matrix; adopting the dynamic time warping algorithm to determine a cumulative cost matrix based on the local distance matrix; and determining the matching path based on the diagonal line of the cumulative cost matrix.

[0012] Optionally, based on the matching path, the matching result of the incident pulse signal and the reflected pulse signal is obtained, including: when the matching path is greater than a predetermined distance threshold, determining that the matching result is that the difference between the incident pulse signal and the reflected pulse signal is greater than a predetermined difference threshold; the method further includes: when the matching result is that the difference between the incident pulse signal and the reflected pulse signal is greater than a predetermined difference threshold, determining that there is an abnormality in the power equipment.

[0013] According to another aspect of the embodiments of the present application, a partial discharge signal matching device is provided, including: an acquisition module for acquiring the partial discharge signal of the power equipment, wherein the partial discharge signal includes an incident pulse signal and a reflected pulse signal; a feature construction module for constructing a feature matrix according to the local extreme points included in the partial discharge signal; a division module for dividing based on the feature matrix to obtain a minimum value feature matrix and a maximum value feature matrix; a path generation module for adopting the dynamic time warping algorithm to determine the matching path between the minimum value feature matrix and the maximum value feature matrix; and a matching module for obtaining the matching result of the incident pulse signal and the reflected pulse signal based on the matching path.

[0014] According to another aspect of the embodiments of the present application, a non-volatile storage medium is provided. The non-volatile storage medium stores multiple instructions, and the instructions are suitable for being loaded and executed by a processor to perform the partial discharge signal matching method of any one of the above.

[0015] According to another aspect of the embodiments of the present application, an electronic device is provided, including: one or more processors and a memory, where the memory is used to store one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the partial discharge signal matching method of any one of the above.

[0016] In the embodiment of the present application, a non-linear alignment method is adopted. By collecting partial discharge signals of power equipment, where the partial discharge signals include incident pulse signals and reflected pulse signals; a feature matrix is constructed based on the local extreme points included in the partial discharge signals; the feature matrix is divided to obtain a minimum value feature matrix and a maximum value feature matrix; the dynamic time warping algorithm is used to determine the matching path between the minimum value feature matrix and the maximum value feature matrix; based on the matching path, the matching result of the incident pulse signal and the reflected pulse signal is obtained. The purpose of matching the incident wave and the reflected wave is achieved, and the technical effects of improving the anti-noise interference ability and dynamic adaptability are realized, thereby solving the technical problems of low matching accuracy between the incident wave and the reflected wave and weak anti-noise interference ability in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and form a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings:

[0018] Figure 1 is a flowchart of an optional partial discharge signal matching method provided according to an embodiment of the present application;

[0019] Figure 2 is a first schematic diagram of an optional partial discharge signal matching method provided according to an embodiment of the present application;

[0020] Figure 3 is a second schematic diagram of an optional partial discharge signal matching method provided according to an embodiment of the present application;

[0021] Figure 4 is a schematic diagram of an optional partial discharge signal matching device provided according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the description, claims and the above drawings of this application are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0024] In the process of signal detection of partial discharge, the precise matching of the incident wave and the reflected wave is crucial for fault diagnosis. Due to factors such as equipment failure or aging, the incident wave and the reflected wave will change to varying degrees. Therefore, matching these waveforms and extracting the characteristic information therein is the core of improving the accuracy of fault recognition. However, when dealing with complex partial discharge signals, the existing waveform matching methods often face great technical challenges. The existing partial discharge waveform matching technologies usually rely on linear correlation algorithms or similarity measurement methods, which assume that the time and amplitude relationships between signals are fixed and linear. But in practical applications, partial discharge signals are often affected by various factors, including equipment aging, electrical stress, environmental changes, etc., which make the signals show non-linear characteristics. The traditional linear matching methods cannot effectively handle the problems of time delay, amplitude change and frequency drift in the signals, resulting in a decrease in waveform matching accuracy, and thus affecting the accuracy and reliability of fault diagnosis.

[0025] Partial discharge signals in the power system are often affected by noise interference. These noise sources include electromagnetic interference, equipment switching operations and external environmental changes. The traditional matching algorithms have weak noise processing capabilities, which easily lead to mis-matching or missed detection of signals, affecting the effect of fault detection. At the same time, most of the existing technologies are based on static data analysis and lack the dynamic adaptation ability to the operating state of power equipment and environmental changes. In the actual power system, the state of the equipment and the environmental conditions change at any time, and the traditional methods often cannot respond to these changes in time, resulting in failures not being accurately captured or delayed responses. Therefore, the existing technologies have significant deficiencies in terms of dynamic adaptability, computational complexity and real-time performance, and it is difficult to meet the requirements of modern power systems for rapid response and real-time monitoring. How to improve the waveform matching accuracy, enhance the anti-noise interference ability and improve the dynamic adaptability has become the main challenge faced by partial discharge detection technologies.

[0026] In view of the above problems, an embodiment of the present application provides an embodiment of a method for matching partial discharge signals. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0027] Figure 1 is a flowchart of an optional partial discharge signal matching method provided according to an embodiment of the present application. As Figure 1 shown, the method includes the following steps:

[0028] Step S102, collect the partial discharge signals of the power equipment, where the partial discharge signals include incident pulse signals and reflected pulse signals;

[0029] It can be understood that the partial discharge signals are collected from the power equipment through sensors, and these signals include two parts: incident pulse signals and reflected pulse signals. The collected incident pulse signals and reflected pulse signals are the basis for subsequent analysis, providing the original data for subsequent signal processing and matching, and ensuring the accuracy and reliability of the signal source.

[0030] In an optional embodiment, collecting the partial discharge signals of the power equipment includes: collecting the incident pulse signals and reflected pulse signals of the partial discharge through the sensors of the power equipment; performing preprocessing on the incident pulse signals and reflected pulse signals to obtain the partial discharge signals, where the preprocessing includes at least one of the following: denoising, filtering, smoothing, and normalization.

[0031] It can be understood that through the sensors installed on the power equipment, the incident pulse signals and reflected pulse signals generated by the partial discharge are collected in real time. These signals are the direct manifestation forms of the partial discharge phenomenon and contain the key information of the equipment health state. The collected original signals are usually affected by factors such as noise interference, equipment vibration, and electromagnetic interference, resulting in a decline in signal quality. In order to improve the accuracy and reliability of subsequent processing, the collected incident pulse signals and reflected pulse signals are preprocessed.

[0032] The specific operations of the preprocessing include at least one of the following: denoising, filtering, smoothing, and normalization. Denoising is used to remove the random noise in the signal and improve the signal-to-noise ratio of the signal. Filtering is used to remove the high-frequency or low-frequency interference components in the signal through a filter and retain the useful signal features. Smoothing is used to smooth the signal, reduce the sharp fluctuations in the signal, and make it smoother. Normalization is used to adjust the amplitude of the signal to a unified range (such as 〇 to 1) to eliminate the influence of the amplitude difference between different signals.

[0033] Step S104: Construct a feature matrix based on the local extreme points included in the partial discharge signal.

[0034] It can be understood that the collected partial discharge signal is analyzed to extract the local extreme points (including maximum points and minimum points) therein, and a feature matrix is constructed based on these extreme points. By extracting the local extreme points and constructing the feature matrix, the dimension of the signal can be significantly reduced while retaining the key feature information of the signal, reducing the complexity of subsequent calculations and improving the efficiency of signal processing.

[0035] The matching method of the incident wave and the reflected wave of partial discharge can be represented by local extreme approximation. Specifically, during the change process of the time series, the subsequence segments between adjacent extreme points show monotonic changes, so these subsequences can be fitted by the line segments connecting the extreme points. For a single extreme point, the slope change of its left and right fitting line segments reflects the morphological characteristics of the original time series. Therefore, the slope of the fitting line segment is crucial for characterizing the change trend of the signal.

[0036] For the incident wave and reflected wave time series signals , is the value of the k-th point of X, where For the following four cases:

[0037]

[0038] If meets Case 1) or 2), define the k-th data point as the local minimum point of the time series X. If meets Case 3) or 4), define the k-th data point as the local maximum point of the time series X. The local minimum points and local maximum points are collectively referred to as local extreme points.

[0039] In an optional embodiment, constructing a feature matrix based on the local extreme points included in the partial discharge signal includes: determining the extreme point magnitude and extreme point position of the local extreme points; determining the extreme point left and right slopes of the left and right fitting line segments of the local extreme points based on the extreme point magnitude and extreme point position; and obtaining the feature matrix based on the extreme point magnitude, extreme point position, and extreme point left and right slopes.

[0040] It can be understood that the preprocessed partial discharge signal is analyzed to extract the local extreme points (including maximum points and minimum points) therein. For each extreme point, record its specific value (i.e., the extreme point magnitude) and its position in the time series (i.e., the extreme point position). These information are important components of the signal morphological characteristics.

[0041] For each local extreme point, calculate the slopes of the fitting line segments on its left and right sides. The left slope is obtained by fitting a straight line to the signal points on the left side of the extreme point and calculating the slope of this line, which reflects the changing trend of the signal on the left side of the extreme point. The right slope is obtained by fitting a straight line to the signal points on the right side of the extreme point and calculating the slope of this line, which reflects the changing trend of the signal on the right side of the extreme point. These slope information can further describe the morphological changes of the signal near the extreme point.

[0042] Integrate the extreme point magnitude, extreme point position, and the left and right slopes of each extreme point into a feature vector, and combine the feature vectors of all extreme points into a feature matrix. This feature matrix not only retains the key morphological features of the signal but also enhances the ability to describe the changing trend of the signal through the slope information.

[0043] By extracting local extreme points and their related features, the time series of the original signal is greatly simplified into a feature matrix, significantly reducing the data dimension and the complexity of subsequent calculations. The feature matrix not only contains the magnitude and position of the extreme points but also introduces the left and right slope information, which can more comprehensively describe the morphological changes of the signal and improve the characterization ability of the features of partial discharge signals. In the subsequent dynamic time warping (DTW) matching process, the multi-dimensional information (magnitude, position, slope) in the feature matrix can more accurately reflect the dynamic characteristics of the signal, thereby improving the matching accuracy between the incident pulse signal and the reflected pulse signal. The extreme points and their slope information have a certain robustness to noise. Even under noise interference, these key features can still relatively accurately reflect the essential features of the signal, thereby improving the anti-interference ability of the system. The construction process of the feature matrix transforms the complex signal processing problem into the analysis of key features, reduces redundant information, and further optimizes the computational efficiency of the entire matching algorithm, making it more suitable for real-time monitoring and rapid response.

[0044] Optionally, for the extracted extreme points, obtain the extreme value sequence , which does not include the starting point and the ending point of X.

[0045] Where: , ; corresponds to the extreme point position, is the extreme point type, is the extreme point magnitude.

[0046] Convert the extreme value sequence into an extreme value feature matrix:

[0047]

[0048] Where:

[0049] , , corresponding to the size of the extreme point, corresponding to the position of the extreme point, and representing the slopes of the fitting line segments on the left and right of the extreme point, the calculation formula is as follows:

[0050]

[0051] In an alternative embodiment, the partial discharge signal is a time series. Based on the size of the extreme point, the position of the extreme point, and the slopes on the left and right of the extreme point, a feature matrix is obtained, including: converting the slopes on the left and right of the extreme point into circumferential angles; converting the position of the extreme point into a ratio between the position of the extreme point and the length of the time series; and obtaining a standardized feature matrix based on the size of the extreme point, the circumferential angle, and the ratio.

[0052] It can be understood that the slopes on the left and right of the extreme point directly reflect the change trend of the signal near the extreme point, but the numerical range of the slopes may be large and the units may not be unified. To eliminate this difference, the slope is converted into a circumferential angle (i.e., an angular value). Specifically, the slope value is mapped to an angular value (usually between 0 and 360 degrees) through the arctangent function (arctan), thereby realizing the standardization of the slope. This conversion not only unifies the dimension but also makes the change of the slope more intuitive. The position of the extreme point is absolute in the time series, but the lengths of the time series of different signals may be different. To eliminate this difference, the position of the extreme point is divided by the total length of the time series to obtain a normalized ratio. This ratio represents the relative position of the extreme point in the time series and can better reflect the distribution of the extreme point in the entire signal. Based on the size of the extreme point, the converted circumferential angle (slopes on the left and right) and the normalized ratio of the position of the extreme point, a feature matrix is constructed. Through this standardization process, each eigenvector in the feature matrix has a unified dimension and numerical range, thereby improving the comparability and consistency of the feature matrix.

[0053] By converting the slope into a circumferential angle and converting the position of the extreme point into a relative ratio, the dimensional differences between different features are eliminated, enabling the direct comparison and calculation of each feature in the feature matrix, and improving the unity and consistency of the feature matrix. The standardized feature matrix can more accurately reflect the morphological features of the signal, allowing the direct comparison and matching of features between different signals, and improving the accuracy and reliability of the matching algorithm. The standardized feature matrix after the standardization process has stronger robustness to noise and signal changes. Even when the signal is subject to a certain degree of interference or change, the standardized features can still remain relatively stable, thereby improving the anti-interference ability of the matching algorithm. By converting the position of the extreme point into a relative ratio, the standardized feature matrix can adapt to time series signals of different lengths, making the matching algorithm no longer dependent on the specific length of the signal, and thus improving the generality and flexibility of the algorithm.

[0054] Optionally, when measuring the similarity between two time series, to eliminate the dimensional differences between different features, it is necessary to perform standardization processing on , and the position of the extreme point The standardization method is as follows:

[0055]

[0056] and Convert the slope into a circumferential angle, Convert the position into the ratio of the position of the extreme point to the length of the time series. The extreme value feature matrix after the standardization process is as follows:

[0057]

[0058] Extreme value feature matrix not only retains the morphological change features of the time series, but also retains the correlation between different feature quantities.

[0059] Step S106, based on the feature matrix, perform partitioning to obtain a minimum value feature matrix and a maximum value feature matrix;

[0060] It can be understood that the constructed feature matrix is further divided into a minimum value feature matrix and a maximum value feature matrix, corresponding to the minimum value points and maximum value points in the signal respectively. This partitioning method can perform refined processing on different features of the signal, reduce redundant information, further reduce the computational complexity, and at the same time improve the ability of the feature matrix to represent the signal morphology, providing a more accurate feature basis for subsequent matching.

[0061] Optionally, to reduce the time complexity of dynamic time warping and further improve the computational efficiency, Further divided into the minimum value feature matrix and the maximum value feature matrix When corresponds to the minimum value point When corresponds to the maximum value point , and are and The number of columns of, corresponding to the number of minimum value points and maximum value points.

[0062] Step S108, using the dynamic time warping algorithm, determine the matching path between the minimum value feature matrix and the maximum value feature matrix;

[0063] It can be understood that by using the dynamic time warping (DTW) algorithm, the similarity between the minimum value feature matrix and the maximum value feature matrix is calculated, and the best matching path between them is determined. The DTW algorithm can effectively handle non-linear changes in signals, such as time delay, amplitude change, and frequency drift, etc. By finding the best matching path through dynamic programming, it significantly improves the accuracy and robustness of signal matching, especially suitable for complex signal environments.

[0064] The dynamic time warping algorithm is an algorithm for calculating the similarity between two time series, which can handle non-linear time delay, amplitude change, and frequency drift in signals. DTW finds the best matching path by non-linearly aligning the time axes of two signals and minimizing the cumulative distance between the signals.

[0065] In an optional embodiment, when there are multiple local extreme points, using the dynamic time warping algorithm to determine the matching path between the minimum value feature matrix and the maximum value feature matrix includes: obtaining the starting trend feature based on the slope of the fitting line segment between the starting point of the partial discharge signal and the first local extreme point among the multiple local extreme points; obtaining the ending trend feature based on the slope of the fitting line segment between the ending point of the partial discharge signal and the last local extreme point among the multiple local extreme points; and using the dynamic time warping algorithm for processing based on the starting trend feature, the ending trend feature, the minimum value feature matrix, and the maximum value feature matrix to obtain the matching path.

[0066] It can be understood that for the time series of partial discharge signals, the first local extreme point (maximum point or minimum point) is found. The slope of the fitted line segment between the starting point of the signal and the first local extreme point is calculated. This slope reflects the change trend of the signal from the starting point to the first extreme point and is called the starting trend feature. It can capture the initial change characteristics of the signal and provide important starting information for matching. In the time series of partial discharge signals, the last local extreme point (maximum point or minimum point) is found. The slope of the fitted line segment between the ending point of the signal and the last local extreme point is calculated. This slope reflects the change trend of the signal from the last extreme point to the ending point and is called the ending trend feature. It can capture the ending change characteristics of the signal and provide important ending information for matching. The starting trend feature and the ending trend feature are respectively added to the minimum value feature matrix and the maximum value feature matrix as the extended part of the feature matrix. The dynamic time warping (DTW) algorithm is used to process the extended minimum value feature matrix and maximum value feature matrix. The DTW algorithm calculates the optimal matching path between the two feature matrices through the dynamic programming method. In this process, the starting trend feature and the ending trend feature provide global information for matching, helping the algorithm to more accurately align the feature points in the two feature matrices, so as to obtain a high-precision matching path. Based on the above processing, the DTW algorithm outputs the matching path between the minimum value feature matrix and the maximum value feature matrix. This path reflects the best correspondence relationship between the incident pulse signal and the reflected pulse signal at the feature level.

[0067] Optionally, the starting point and the ending point of the original time series reflect the important information of the series. During the transformation of the extreme value feature matrix, and in addition to the minimum value points and the maximum value points, the first column and the last column respectively add the feature vectors of the starting point and the ending point. The feature vectors of the starting point and the ending point are represented as follows: the left slope of the starting point is 0, and the right slope is the slope of the fitted line segment between the starting point and the first extreme point; the right slope of the ending point is 0, and the left slope is the slope of the fitted line segment between the ending point and the last extreme point. The position feature and the value range feature are represented in the same way as those of the extreme points. and The feature vectors of the first column and the last column are represented as follows:

[0068]

[0069] In an alternative embodiment, the dynamic time warping algorithm is used to determine the matching path between the minimum feature matrix and the maximum feature matrix, including: determining a local distance matrix based on the minimum feature matrix and the maximum feature matrix, where each element in the local distance matrix represents the distance between the minimum value included in the minimum feature matrix and the maximum value included in the maximum feature matrix; using the dynamic time warping algorithm to determine an accumulated cost matrix based on the local distance matrix; and determining the matching path based on the diagonal of the accumulated cost matrix.

[0070] It can be understood that the local distance matrix is calculated based on the minimum feature matrix and the maximum feature matrix. The local distance matrix is a two-dimensional matrix, the rows of which correspond to the minimum value points in the minimum feature matrix, and the columns correspond to the maximum value points in the maximum feature matrix. Each element in the local distance matrix represents the distance between a minimum value point in the minimum feature matrix and a maximum value point in the maximum feature matrix. This distance can be calculated by the Euclidean distance, Manhattan distance or other appropriate distance metrics. The dynamic time warping (DTW) algorithm is used to calculate the accumulated cost matrix based on the local distance matrix. The accumulated cost matrix is a dynamic programming matrix used to record the minimum accumulated cost from the starting point to the current point. The calculation process of the accumulated cost matrix follows the rules of dynamic programming: the accumulated cost of each element is equal to its local distance plus the minimum accumulated cost path from the starting point to this point. Based on the accumulated cost matrix, starting from the lower right corner (i.e., the last element) of the matrix, backtracking along the minimum cost path to the upper left corner (starting point) to determine the matching path. The matching path usually searches along the diagonal direction of the accumulated cost matrix because the diagonal direction represents the optimal alignment relationship between two feature points. The matching path reflects the best matching relationship between the minimum feature matrix and the maximum feature matrix.

[0071] Through the dynamic programming method, the DTW algorithm can find the globally optimal matching path, rather than just the locally optimal solution. This global optimality ensures the accuracy and reliability of the matching result. The calculation of the local distance matrix can accurately measure the similarity or difference between the minimum value point and the maximum value point, providing a reliable basis for subsequent matching. The DTW algorithm dynamically aligns the feature points in the two feature matrices through the accumulated cost matrix, and can effectively handle the non-linear changes in the signal (such as time delay, amplitude change and frequency drift). This dynamic alignment method enables the algorithm to adapt to complex signal feature changes. The diagonal search based on the accumulated cost matrix can quickly determine the optimal matching path, reducing the possibility of mis-matching. At the same time, the dynamic programming characteristics of the accumulated cost matrix make the algorithm more robust to noise and signal changes.

[0072] Step S110, obtaining the matching result of the incident pulse signal and the reflected pulse signal based on the matching path.

[0073] It can be understood that according to the matching path determined by the DTW algorithm, the matching result of the incident pulse signal and the reflected pulse signal is finally obtained. In this way, the high-precision matching of the incident wave and the reflected wave is realized, the corresponding relationship between signals can be accurately identified, the reliability of fault diagnosis is improved, and at the same time, the anti-noise interference ability and dynamic adaptability of the system are enhanced, solving the problems of low matching accuracy and weak anti-interference ability of the traditional method.

[0074] In an optional embodiment, based on the matching path, obtaining the matching result of the incident pulse signal and the reflected pulse signal includes: when the matching path is greater than a predetermined distance threshold, determining that the matching result is that the difference between the incident pulse signal and the reflected pulse signal is greater than a predetermined difference threshold; the method further includes: when the matching result is that the difference between the incident pulse signal and the reflected pulse signal is greater than a predetermined difference threshold, determining that there is an abnormality in the power equipment.

[0075] It can be understood that after calculating the matching path between the minimum value feature matrix and the maximum value feature matrix, the cumulative distance (or cost) of the matching path is evaluated. This cumulative distance reflects the overall similarity or difference between the incident pulse signal and the reflected pulse signal. According to the actual application requirements or empirical data, a predetermined distance threshold (or difference threshold) is set. This threshold is used to judge whether the difference between signals is within the normal range. If the cumulative distance of the matching path is greater than the predetermined distance threshold, it is determined that the difference between the incident pulse signal and the reflected pulse signal is greater than the predetermined difference threshold. This indicates that there is a significant mismatch between the two signals at the feature level. If the cumulative distance of the matching path is less than or equal to the predetermined distance threshold, it is considered that the difference between the incident pulse signal and the reflected pulse signal is within the normal range. When the matching result indicates that the difference between the incident pulse signal and the reflected pulse signal is greater than the predetermined difference threshold, it is further determined that there is an abnormality in the power equipment. This abnormality may be related to the partial discharge phenomenon, indicating that the equipment may have faults or aging problems. If the difference is within the normal range, it is considered that the power equipment is in good operating condition and no significant abnormality is detected.

[0076] Through the cumulative distance of the matching path, the difference between the incident pulse signal and the reflected pulse signal is quantified into a specific value. This quantification method provides a clear basis for subsequent fault judgment. When the matching result shows that the signal difference is greater than the predetermined threshold, it can be timely judged that there is an abnormality in the power equipment, potential faults can be detected in advance, further damage to the equipment can be avoided, and the safe operation of the power system can be guaranteed. Through clear threshold judgment and quantitative analysis, the error of human judgment is reduced, and the reliability and stability of the entire fault diagnosis system are enhanced.

[0077] Optionally, after the original time series is transformed into a maximum value feature matrix and a minimum value feature matrix, the sequence dimension is greatly reduced, the time complexity is reduced, and the calculation efficiency is improved. The number of rows of the extreme value feature matrices is the same, representing four-dimensional features, and the variable dimensions correspond one by one. However, since the number of maximum and minimum points in the time series may be different, the number of columns of the two feature matrices of the same time series will be different. For two time series with different lengths, four extreme value feature matrices are obtained by performing extreme value feature extraction. The length of the time series, the proportion of maximum points, and the proportion of minimum points will all affect the number of columns of the extreme value feature matrix, resulting in different lengths of the number of columns although the number of rows of the feature matrices is the same. The DTW algorithm can effectively solve the matching problem of unequal lengths. Therefore, the DTW algorithm is used next to measure the similarity distance between the extreme value feature matrices. After feature extraction of two time series X and Y with lengths of n and m, four extreme value feature matrices are obtained: the minimum value feature matrix and (the number of columns are and respectively), the maximum value feature matrix and (the number of columns are and respectively). The feature matrices with the same type of extreme points are subjected to similarity measurement, and the dynamic time warping distance is calculated twice. The FLEDTW distance between X and Y is defined as follows:

[0078]

[0079] where is the warping path of the distance matrix and corresponding to the minimum value feature matrix , is the warping path of the distance matrix and corresponding to the maximum value feature matrix , and they all satisfy the three conditions of boundary, continuity, and monotonicity.

[0080] The cumulative cost matrix and is constructed using the dynamic programming method, and the above problem is transformed into the following formula for solution:

[0081]

[0082]

[0083] where , , and their definitions are as follows:

[0084]

[0085] Where: x represents the incident wave signal parameter (such as signal identification), and y represents the reflected wave signal parameter (such as signal identification).

[0086] This embodiment adds multi-dimensional extreme value features, considers the morphological features of the original sequence, reasonably matches the extreme points in the calculation of dynamic time warping, and improves the measurement accuracy of the algorithm.

[0087] Through the above steps S102, the partial discharge signals of the power equipment are collected, where the partial discharge signals include incident pulse signals and reflected pulse signals; step S104, a feature matrix is constructed based on the local extreme points included in the partial discharge signals; step S106, based on the feature matrix, division is performed to obtain a minimum value feature matrix and a maximum value feature matrix; step S108, the dynamic time warping algorithm is used to determine the matching path between the minimum value feature matrix and the maximum value feature matrix; step S110, based on the matching path, the matching results of the incident pulse signal and the reflected pulse signal are obtained. The purpose of matching the incident wave and the reflected wave can be achieved, and the technical effects of improving the anti-noise interference ability and dynamic adaptability are realized, thereby solving the technical problems of low matching accuracy between the incident wave and the reflected wave and weak anti-noise interference ability in the related technologies.

[0088] Based on the above embodiments and alternative embodiments, the present application proposes an alternative implementation manner, which is applied to the application scenario of matching the incident wave and the reflected wave of high-frequency partial discharge pulses based on dynamic time warping. By effectively non-linearly aligning the two time series of the incident pulse and the reflected pulse in the partial discharge signal by using the dynamic time warping (DTW) algorithm, problems such as time delay, amplitude change, and noise interference in the signal are overcome, and the matching accuracy and robustness of the partial discharge signal are significantly improved. The specific implementation process of this method is as follows:

[0089] 1. Signal acquisition and preprocessing, the incident pulse and the reflected pulse of the partial discharge signal are collected in real time through the sensor of the power equipment. The collected incident pulse and reflected pulse signals need to go through a series of preprocessing steps, including denoising, filtering, smoothing, normalization and other operations to remove external noise interference and improve the quality of the signal. Once the signal preprocessing is completed, more consistent and reliable data can be provided for subsequent matching analysis. Figure 2 is the first schematic diagram of an alternative partial discharge signal matching method provided according to an embodiment of the present application, as Figure 2As shown, it illustrates the trends of the incident pulse and the reflected pulse over time. The horizontal axis (X-axis) represents time, ranging from 1 to 24, representing the hours of a day (e.g., from 1 am to 12 pm). The vertical axis (Y-axis) represents the numerical magnitude of the pulse, ranging from 0 to 40. The numerical values of the "incident pulse" and the "reflected pulse" fluctuate to some extent throughout the day. The numerical value of the incident pulse is generally higher than that of the reflected pulse and reaches peaks at certain times (such as the 5th hour and the 23rd hour). The numerical value of the reflected pulse is relatively stable but also has certain fluctuations, with a slight increase at the 11th hour and the 23rd hour. It is used to analyze and compare the changes of the incident pulse and the reflected pulse throughout the day to monitor and evaluate the performance of a certain phenomenon or device.

[0090] 2. Local extreme feature extraction. By extracting the local extreme points from the incident pulse and reflected pulse signals, the dimension of the time series can be significantly reduced and the signal structure can be simplified. Specifically, the local extreme points include maximum points and minimum points, which can reflect the morphological characteristics of the signal. By performing a difference operation on the time series, the local maximum points and local minimum points are determined. These extreme points usually appear at the peaks or valleys of the signal, indicating the turning points of the signal. During the change process of the time series, the local extreme points of the incident pulse and the reflected pulse characterize the change trend of the signal through the slope change of the fitted line segment. By connecting adjacent extreme points to form subsequence segments, and then performing linear fitting on these subsequences. The slope of the fitted line segment reflects the change trend of the local time series. Figure 3 It is the second schematic diagram of an optional partial discharge signal matching method provided according to an embodiment of the present application, as Figure 3 shown. In the figure, the extreme points are marked with different circles, including local maximum points (peak points) and local minimum points (valley points). At certain time points (such as the 8th hour and the 16th hour), the positions of the extreme points of the incident pulse and the reflected pulse are close, indicating that their change trends are similar at these moments. At other time points, the positions and numerical values of the extreme points of the two are different, which may reflect different signal characteristics or system states. By comparing their change trends and extreme points, the health status of the system can be evaluated and potential faults or abnormalities can be detected in a timely manner.

[0091] 3. Determine the maximum points and minimum points. For each time series (such as the incident wave and reflected wave signals), each point is judged to determine whether it is a local maximum point or a local minimum point. The specific judgment method is as follows:

[0092] Local minimum point: When is the current point and satisfies one of the following conditions:

[0093] , .

[0094] Local maximum point: When is the current point and satisfies one of the following conditions:

[0095] , .

[0096] 4. Limit matrix calculation: For the extracted extreme points, construct an extreme feature matrix, which includes the size, position of each extreme point, and the slopes of the left and right fitting line segments. The calculation process of the feature matrix is as follows:

[0097] For the extreme value sequence , this extreme value sequence does not include the starting point and the ending point. Convert the extreme value sequence into an extreme feature matrix , and calculate the slopes of the left and right fitting line segments of the extreme points respectively, that is, the slope of the left fitting line segment of the limit point:

[0098]

[0099] The slope of the right fitting line segment of the limit point:

[0100]

[0101] 5. Standardization processing: Each extreme point has a slope of the left and right fitting line segments, which respectively represent the change rates of the line segments on the left and right sides of the extreme point. These slopes are important information reflecting the signal change trend, but due to the possible differences in their units and numerical ranges, it will affect the accuracy when directly comparing. To eliminate the dimensional problem of the slopes, each slope can be converted into the form of a circumferential angle, so that the measurements of different slopes can be standardized and converted into a unified angle value.

[0102] 6. Feature calculation: In the feature vector calculation stage, to further improve the calculation efficiency and matching accuracy of the dynamic time warping (DTW) algorithm, the present invention divides the extreme value feature matrix into a minimum value feature matrix and a maximum value feature matrix. This division strategy reduces redundant information in the calculation process by refining the local extreme values, enabling each feature matrix to contain only the parts that have a greater impact on the matching result, thereby significantly reducing the calculation complexity. To further improve the matching accuracy, considering the importance of the starting point and ending point of the signal in the time series features, the feature vectors of the starting point and ending point are added to the feature matrix. The feature vector of the starting point represents the starting trend of the signal by calculating the slope of the fitting line segment between the starting point and the first local extreme value point; the feature vector of the ending point represents the ending trend of the signal by calculating the slope of the fitting line segment between the ending point and the last local extreme value point. The introduction of these feature vectors effectively preserves the global information of the time series and further enhances the ability of the extreme value feature matrix to represent the signal form.

[0103] 7. Similarity measurement: After the extreme value feature matrix is normalized and calculated, the present invention uses the dynamic time warping (DTW) algorithm to measure the similarity of the extreme value feature matrix. The DTW algorithm is an algorithm based on dynamic programming that can effectively handle the alignment problem between time series of unequal lengths. The present invention not only considers multi-dimensional features such as position information, extreme value point type, and fitting slope in the extreme value feature matrix, but also improves the calculation accuracy and robustness of DTW through a multi-level feature matching strategy. Specifically, by calculating the matching paths between the minimum value feature matrix and the maximum value feature matrix respectively, the calculation complexity is effectively reduced while ensuring the matching accuracy. For each feature matrix, its cumulative cost matrix is calculated, and on this basis, the optimal matching path is constructed. This extended DTW algorithm not only improves the accuracy in the matching process but also can effectively adapt to partial discharge signals of different lengths and different forms, providing a more accurate measurement result in the matching process of incident waves and reflected waves, ensuring the matching accuracy and the high efficiency of the algorithm.

[0104] The above optional implementation manners achieve at least the following effects:

[0105] (1) The present application uses the dynamic time warping algorithm, which can effectively solve the accuracy problem of traditional methods in processing partial discharge signals. Different from traditional linear correlation methods, the DTW algorithm can adapt to the non-linear changes in the waveform and overcome the influence of time delay and amplitude changes on waveform matching. In a complex power environment, the partial discharge signals of cables and equipment often change due to equipment status and environmental factors. DTW can accurately correspond the incident wave and the reflected wave through optimized time series matching, thereby greatly improving the accuracy and reliability of waveform matching and ensuring the accurate identification and early warning of early faults.

[0106] (2) Partial discharge signals in the power system are usually accompanied by noise interference. Especially in the distribution network, they may be affected by factors such as electromagnetic interference and switching operations of electrical equipment, resulting in a reduction in signal quality. Traditional waveform matching methods are usually sensitive to noise and are prone to false matching or missed detection. This application can still maintain a high matching degree in the case of high noise, greatly improving the reliability of the partial discharge fault detection system and ensuring the accurate identification and location of fault signals.

[0107] (3) This application optimizes the calculation process of the DTW algorithm, making waveform matching not only more accurate but also significantly improved in real-time performance. During the operation of power equipment, the characteristics of partial discharge signals may vary significantly with changes in the environment and fluctuations in equipment status. Traditional methods have poor adaptability to these dynamic changes and are difficult to respond in a timely manner. The DTW algorithm can adjust the matching process in real-time according to the actual signal changes, adapting to the continuously changing signal characteristics during the operation of the power system. In this way, not only the timeliness of fault detection is improved, but also the requirements for real-time monitoring and fault warning of the power system are met, ensuring the reliability and timeliness of the system under different operating conditions.

[0108] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from that here.

[0109] In this embodiment, a partial discharge signal matching device is also provided. This device is used to implement the above embodiments and preferred implementation manners, and those that have been described will not be repeated. As used below, the terms "module" and "device" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0110] According to an embodiment of the present application, an apparatus embodiment for implementing the partial discharge signal matching method is also provided. Figure 4 It is a schematic diagram of an optional partial discharge signal matching device provided according to an embodiment of the present application, as Figure 4 shown. The above partial discharge signal matching device includes: an acquisition module 402, a feature construction module 404, a division module 406, a path generation module 408, and a matching module 410. The device will be described below.

[0111] The acquisition module 402 is used to acquire the partial discharge signals of power equipment, where the partial discharge signals include incident pulse signals and reflected pulse signals.

[0112] A feature construction module 404, connected to the acquisition module 402, is configured to construct a feature matrix based on local extreme points included in the partial discharge signal;

[0113] A partitioning module 406, connected to the feature construction module 404, is configured to perform partitioning based on the feature matrix to obtain a minimum value feature matrix and a maximum value feature matrix;

[0114] A path generation module 408, connected to the partitioning module 406, is configured to use the dynamic time warping algorithm to determine a matching path between the minimum value feature matrix and the maximum value feature matrix;

[0115] A matching module 410, connected to the path generation module 408, is configured to obtain a matching result of the incident pulse signal and the reflected pulse signal based on the matching path.

[0116] In a partial discharge signal matching device provided by an embodiment of the present application, by setting the acquisition module 402, the feature construction module 404, the partitioning module 406, the path generation module 408, and the matching module 410, the purpose of matching the incident wave and the reflected wave is achieved, and the technical effects of improving the anti-noise interference ability and dynamic adaptability are realized. Furthermore, the technical problems of low matching accuracy between the incident wave and the reflected wave and weak anti-noise interference ability existing in the related art are solved.

[0117] It should be noted that the above-mentioned various modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following manner: the above-mentioned various modules can be located in the same processor; or, the above-mentioned various modules are located in different processors in any combination.

[0118] It should be noted here that the above-mentioned acquisition module 402, feature construction module 404, partitioning module 406, path generation module 408, and matching module 410 correspond to steps S102 to step S110 in the embodiment. The examples and application scenarios implemented by the above-mentioned modules and the corresponding steps are the same, but are not limited to the content disclosed in the above-mentioned embodiment. It should be noted that the above-mentioned modules can run in a computer terminal as part of the device.

[0119] It should be noted that the optional or preferred implementation manners of this embodiment can be referred to the relevant descriptions in the embodiment, and will not be elaborated here.

[0120] The above-mentioned partial discharge signal matching device may further include a processor and a memory. The acquisition module 402, the feature construction module 404, the partitioning module 406, the path generation module 408, the matching module 410, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to implement corresponding functions.

[0121] The processor contains a kernel, which retrieves the corresponding program units from the memory. One or more kernels can be set. The memory may include non-permanent memory in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0122] An embodiment of the present application provides a non-volatile storage medium, on which a program is stored, and when the program is executed by a processor, a partial discharge signal matching method is implemented.

[0123] An embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program stored on the memory and executable on the processor. When the processor executes the program, the following steps are implemented: collecting partial discharge signals of a power device, where the partial discharge signals include incident pulse signals and reflected pulse signals; constructing a feature matrix based on local extreme points included in the partial discharge signals; dividing based on the feature matrix to obtain a minimum value feature matrix and a maximum value feature matrix; using a dynamic time warping algorithm to determine a matching path between the minimum value feature matrix and the maximum value feature matrix; and obtaining a matching result of the incident pulse signal and the reflected pulse signal based on the matching path. The device in this article can be a server, a PC, etc.

[0124] The present application also provides a computer program product, which, when executed on a data processing device, is adapted to execute a program initialized with the following method steps: collecting partial discharge signals of a power device, where the partial discharge signals include incident pulse signals and reflected pulse signals; constructing a feature matrix based on local extreme points included in the partial discharge signals; dividing based on the feature matrix to obtain a minimum value feature matrix and a maximum value feature matrix; using a dynamic time warping algorithm to determine a matching path between the minimum value feature matrix and the maximum value feature matrix; and obtaining a matching result of the incident pulse signal and the reflected pulse signal based on the matching path.

[0125] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0126] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and combinations of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device produce means for implementing the specified functions in the process Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0127] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the specified functions in the process Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0128] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the specified functions in the process Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0129] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0130] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0131] A computer-readable medium includes both permanent and non-permanent, removable and non-removable media and can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer-readable medium does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0132] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0133] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, system or computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0134] The above are only embodiments of the present application and are not used to limit the present application. For those skilled in the art, the present application can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for matching partial discharge signals, characterized in that, Including: Collecting partial discharge signals of power equipment, where the partial discharge signals include incident pulse signals and reflected pulse signals; Constructing a feature matrix based on local extreme points included in the partial discharge signals; Dividing based on the feature matrix to obtain a minimum value feature matrix and a maximum value feature matrix; Using the dynamic time warping algorithm to determine the matching path between the minimum value feature matrix and the maximum value feature matrix; Based on the matching path, obtaining the matching result of the incident pulse signal and the reflected pulse signal.

2. The method according to claim 1, characterized in that The constructing a feature matrix based on local extreme points included in the partial discharge signals includes: Determining the extreme point magnitude and extreme point position of the local extreme points; Based on the extreme point magnitude and extreme point position, determining the left and right slopes of the fitting line segments of the local extreme points on the left and right; Obtaining the feature matrix according to the extreme point magnitude, the extreme point position, and the left and right slopes of the extreme points.

3. The method according to claim 2, wherein The partial discharge signal is a time series, and the obtaining the feature matrix according to the extreme point magnitude, the extreme point position, and the left and right slopes of the extreme points includes: Converting the left and right slopes of the extreme points into circumferential angles; Converting the extreme point position into the ratio between the extreme point position and the length of the time series; Based on the extreme point magnitude, the circumferential angle, and the ratio, obtaining the standardized feature matrix.

4. The method according to claim 1, wherein The collecting partial discharge signals of power equipment includes: Collecting the incident pulse signal and the reflected pulse signal of partial discharge through a sensor of the power equipment; Performing preprocessing based on the incident pulse signal and the reflected pulse signal to obtain the partial discharge signal, where the preprocessing includes at least one of the following: denoising, filtering, smoothing, and normalization.

5. The method according to claim 1, wherein There are multiple local extreme points, and the using the dynamic time warping algorithm to determine the matching path between the minimum value feature matrix and the maximum value feature matrix includes: Based on the slope of the fitting line segment between the starting point of the partial discharge signal and the first local extreme point among the multiple local extreme points, obtaining the starting trend feature; Based on the slope of the fitting line segment between the ending point of the partial discharge signal and the last local extreme point among the multiple local extreme points, obtaining the ending trend feature; Based on the starting trend feature, the ending trend feature, the minimum value feature matrix, and the maximum value feature matrix, using the dynamic time warping algorithm for processing to obtain the matching path.

6. The method according to claim 1, wherein The using the dynamic time warping algorithm to determine the matching path between the minimum value feature matrix and the maximum value feature matrix includes: According to the minimum value feature matrix and the maximum value feature matrix, determining a local distance matrix, where each element in the local distance matrix represents the distance between the minimum value included in the minimum value feature matrix and the maximum value included in the maximum value feature matrix; Using the dynamic time warping algorithm to determine an accumulated cost matrix based on the local distance matrix; Based on the diagonal of the accumulated cost matrix, determining the matching path.

7. The method according to any one of claims 1 to 6, characterized in that, Obtaining a matching result of the incident pulse signal and the reflected pulse signal based on the matching path includes: When the matching path is greater than a predetermined distance threshold, determining that the matching result is that the difference between the incident pulse signal and the reflected pulse signal is greater than a predetermined difference threshold; The method further includes: when the matching result is that the difference between the incident pulse signal and the reflected pulse signal is greater than the predetermined difference threshold, determining that there is an abnormality in the power equipment.

8. A partial discharge signal matching device, characterized in that, Including: An acquisition module for acquiring partial discharge signals of a power equipment, where the partial discharge signals include incident pulse signals and reflected pulse signals; A feature construction module for constructing a feature matrix based on local extreme points included in the partial discharge signals; A division module for performing division based on the feature matrix to obtain a minimum value feature matrix and a maximum value feature matrix; A path generation module for using a dynamic time warping algorithm to determine a matching path between the minimum value feature matrix and the maximum value feature matrix; A matching module for obtaining a matching result of the incident pulse signal and the reflected pulse signal based on the matching path.

9. A non-volatile storage medium, characterized in that, The non-volatile storage medium stores multiple instructions, and the instructions are adapted to be loaded and executed by a processor to perform the partial discharge signal matching method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, Including: One or more processors and a memory, where the memory is used to store one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the partial discharge signal matching method according to any one of claims 1 to 7.

Images