Distribution network fault warning and positioning system

Abstract

This invention discloses a distribution network fault early warning and location system, belonging to the field of distribution network technology. It includes a data acquisition module for collecting traveling wave monitoring information and real-time traveling wave data of the distribution network; a data processing module for processing the real-time traveling wave data; a model training module for constructing a distribution network fault location model; a testing and optimization module for determining the optimal distribution network fault location model; and an early warning and location module for timely early warning and location of distribution network faults. This invention solves the problem that existing systems cannot provide timely early warning and location of distribution network faults based on traveling wave positioning, leading to poor operational safety and reliability of the distribution network. This invention can provide timely early warning and location of distribution network faults based on traveling wave positioning, accurately and promptly determining the fault location, providing timely and accurate data support for subsequent maintenance work, and improving the operational safety and reliability of the distribution network.

Description

Technical Field

[0001] This invention relates to the field of power distribution network technology, specifically to a power distribution network fault early warning and location system. Background Technology

[0002] The power distribution network is located at the end of the power system and has distinct characteristics such as wide geographical distribution, large power grid scale, many types of equipment, diverse network connections, and variable operation modes. With the development of urbanization and the growth of electricity demand, the power distribution network has been continuously transformed and expanded, and its scale has continued to expand.

[0003] Chinese patent application CN109738766A discloses a power distribution network fault early warning system. By incorporating a cooling fan, ventilation holes, an early warning data processing module, a comprehensive analysis and processing module, a data storage module, a data collection module, a support rod, a balance base, an adjusting nut, and rolling wheels, it solves the problems of existing power distribution network fault early warning systems, such as inconvenience in changing work locations, limited early warning effectiveness, and excessive heat generation that affects usability. However, this patent has the following drawbacks:

[0004] The existing methods cannot provide timely early warning and location of distribution network faults based on traveling wave positioning, cannot determine the location of distribution network faults in a timely and accurate manner, and cannot provide timely and accurate data support for subsequent maintenance work, resulting in poor safety and reliability of distribution network operation. Summary of the Invention

[0005] The purpose of this invention is to provide a power distribution network fault early warning and location system, which can provide timely early warning and location of power distribution network faults based on traveling wave positioning. It can determine the location of power distribution network faults in a timely and accurate manner, and provide timely and accurate data support for subsequent maintenance work. It can improve the safety and reliability of power distribution network operation and solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] The power distribution network fault early warning and location system includes:

[0008] The data acquisition module is used to collect traveling wave signals and conditions in real time during the operation of the distribution network, and to determine the traveling wave monitoring information and real-time traveling wave data based on the traveling wave location.

[0009] The data processing module is used to process real-time traveling wave data of the distribution network based on traveling wave positioning, and to determine the characteristic data of the traveling wave in the distribution network based on traveling wave positioning.

[0010] The model training module is used to construct a distribution network fault location model based on traveling wave positioning according to the needs of distribution network fault early warning and location.

[0011] The test optimization module is used to test and optimize the distribution network fault location model based on traveling wave positioning, and determine the optimal distribution network fault location model.

[0012] The early warning and location module is used to provide timely early warning and location of faults in the power distribution network.

[0013] Preferably, the data acquisition module includes:

[0014] The traveling wave monitoring unit is used to monitor and capture traveling wave signals in the distribution network in real time during operation, and to determine the traveling wave monitoring information of the distribution network.

[0015] The traveling wave acquisition unit is used to monitor and acquire the traveling wave situation of the distribution network in real time during operation, and to determine the real-time traveling wave data of the distribution network based on traveling wave positioning.

[0016] Preferably, the data processing module includes:

[0017] The data cleaning unit is used to clean the real-time traveling wave data of the distribution network based on traveling wave positioning;

[0018] Acquire real-time traveling wave data of the distribution network based on traveling wave positioning;

[0019] Cleaning of real-time traveling wave data from distribution networks based on traveling wave positioning includes:

[0020] Perform consistency checks on real-time traveling wave data of distribution networks based on traveling wave positioning;

[0021] Based on the reasonable value range and interrelationship of each parameter in the real-time traveling wave data of the distribution network based on traveling wave positioning, check whether the real-time traveling wave data of the distribution network based on traveling wave positioning meets the requirements.

[0022] Remove inconsistent data from the real-time traveling wave data of the distribution network based on traveling wave positioning that are outside the normal range, logically unreasonable, or contradictory;

[0023] Invalid and missing values ​​are processed in the real-time traveling wave data of the distribution network based on traveling wave positioning;

[0024] Remove invalid and missing data from the real-time traveling wave data of the distribution network based on traveling wave positioning, which are of no value to the early warning and location of distribution network faults;

[0025] Real-time data of traveling waves in the distribution network that are valuable for early warning and location of distribution network faults were identified.

[0026] Preferably, the data processing module further includes:

[0027] The feature extraction unit is used to extract features from the real-time traveling wave data of the cleaned distribution network.

[0028] Acquire real-time traveling wave data of the distribution network that is valuable for early warning and location of distribution network faults after cleaning;

[0029] Feature extraction is performed on real-time traveling wave data of distribution networks, which are valuable for early warning and location of distribution network faults.

[0030] Extract features that can reflect the early warning and location of faults in the distribution network;

[0031] The characteristic data of traveling wave in the distribution network based on traveling wave positioning were determined.

[0032] Preferably, the model training module includes:

[0033] The data collection unit is used to collect historical traveling wave data of the distribution network based on traveling wave positioning.

[0034] Based on the requirements for fault early warning and location in distribution networks, historical data of traveling waves in distribution networks based on traveling wave location are collected.

[0035] The model building unit is used to build a distribution network fault location model based on traveling wave positioning.

[0036] Obtain historical traveling wave data of the distribution network based on traveling wave positioning;

[0037] The historical data of traveling waves in the distribution network based on traveling wave positioning are divided;

[0038] The training dataset and the test dataset were determined;

[0039] Select a neural network model framework suitable for fault location in power distribution networks;

[0040] The selected neural network model framework is trained based on the training dataset;

[0041] A fault location model for distribution networks based on traveling wave positioning was determined.

[0042] Preferably, the test optimization module includes:

[0043] The performance testing unit is used to test the distribution network fault location model based on traveling wave positioning.

[0044] Obtain a distribution network fault location model based on traveling wave positioning;

[0045] Based on the test dataset, the performance of the distribution network fault location model based on traveling wave positioning was tested.

[0046] The performance test results based on the distribution network fault location model were determined;

[0047] An adjustment and optimization unit is used to optimize the distribution network fault location model based on traveling wave positioning;

[0048] Obtain performance test results based on the power distribution network fault location model;

[0049] Mining and analysis of the distribution network fault location model based on traveling wave positioning;

[0050] A parameter adjustment and optimization scheme based on the distribution network fault location model was determined;

[0051] The parameters of the distribution network fault location model are adjusted and optimized according to the parameter adjustment and optimization scheme based on the distribution network fault location model.

[0052] The optimal fault location model for the distribution network was determined.

[0053] Preferably, the early warning positioning module includes:

[0054] The fault early warning unit is used to provide timely early warning of faults in the distribution network;

[0055] Obtain traveling wave monitoring information from the power distribution network;

[0056] Mining and analyzing traveling wave monitoring information from the power distribution network;

[0057] When the traveling wave monitoring information of the distribution network contains traveling wave signals, it indicates that there is a fault in the distribution network, and timely fault warnings are given to the distribution network.

[0058] When the traveling wave monitoring information of the distribution network does not contain traveling wave signals, it indicates that there is no fault behavior in the distribution network, and no fault warning is given to the distribution network.

[0059] Preferably, the early warning positioning module further includes:

[0060] The fault location unit is used to locate faults in the distribution network in a timely manner.

[0061] Among them, the optimal fault location model for the distribution network is obtained;

[0062] Obtain traveling wave characteristic data of distribution network based on traveling wave positioning;

[0063] The traveling wave characteristic data of the distribution network based on traveling wave location is input into the optimal distribution network fault location model;

[0064] Based on the optimal distribution network fault location model, prediction, evaluation and fault location are performed on the traveling wave characteristic data of the distribution network based on traveling wave location.

[0065] The results of distribution network fault location based on traveling wave positioning were determined;

[0066] Among them, the fault location results of the distribution network based on traveling wave positioning include the coordinates of the fault location in the distribution network.

[0067] Preferably, the early warning positioning module includes:

[0068] The comparison module is used to calculate the location error of the fault node in the distribution network based on the optimal distribution network fault location model after locating the fault in the distribution network, and compare it with the error threshold.

[0069] The determination module is used to generate abnormal information for the current fault location when the location error is greater than a preset error threshold, and at the same time update the model parameters of the distribution network fault location model.

[0070] The comparison module includes:

[0071] The first calculation module is used to calculate the occurrence of the fault node location in the distribution network. Probability of secondary location anomalies :

[0072]

[0073] in, It is a composite symbol; The number of times the fault node is located in the distribution network; This represents the maximum classification error rate when distinguishing fault node categories during the location of fault nodes in a distribution network.

[0074] The second calculation module is used to calculate the first occurrence of fault node location in the distribution network. Probability of secondary location anomalies Calculate and determine the location error of the fault node in the distribution network. :

[0075]

[0076] in, This represents the total number of fault node categories in the distribution network. The working area of ​​the power distribution network; In order to occur the first The deviation of the positioning path when the positioning is abnormal.

[0077] Preferably, the system further includes: a component positioning module, used for:

[0078] After identifying the faulty equipment in the distribution network based on the early warning and location module, the working signals of several working components that make up the faulty equipment under the current operating conditions are obtained;

[0079] Feature extraction is performed on the aforementioned working signals to obtain the time-domain features corresponding to each working signal; the time-domain features include mean, variance, standard deviation, peak value, and valley value;

[0080] A feature vector is formed by combining the time-domain features corresponding to each working signal; the K-means clustering algorithm is used to perform cluster analysis on several feature vectors to obtain several cluster sets, and the cluster centers of the cluster sets are obtained; a distance matrix is ​​constructed based on several cluster centers; the rows and columns of the distance matrix correspond to different cluster centers, and each element in the matrix represents the distance between the corresponding row and column cluster centers;

[0081] Determine the distance matrix of all operating conditions of the faulty equipment under the fault state, and generate the first distance matrix group;

[0082] Determine the distance matrix of all operating conditions of the faulty equipment under normal conditions, and generate a second distance matrix group;

[0083] Compare the distance matrices of the first distance matrix group and the second distance matrix group under the corresponding working conditions to determine the normal working conditions and abnormal working conditions.

[0084] Determine the information of newly added work components under normal and abnormal operating conditions, and use them as work components to be screened;

[0085] Electromagnetic interference (EMI) and electromagnetic interference immunity (EMI) tests are performed on the components to be screened. Components that pass the EMI and EMI tests are discarded to obtain abnormal components.

[0086] Compared with the prior art, the beneficial effects of the present invention are:

[0087] 1. This invention monitors and captures traveling wave signals in the power distribution network in real time during operation, determines the traveling wave monitoring information of the power distribution network, and mines and analyzes the traveling wave monitoring information of the power distribution network according to the fault early warning requirements of the power distribution network. When the traveling wave monitoring information of the power distribution network contains traveling wave signals, it indicates that there is a fault behavior in the power distribution network, and timely fault early warning is given to the power distribution network.

[0088] 2. This invention monitors and collects traveling wave data of the distribution network in real time during operation, determines the real-time traveling wave data based on traveling wave location, processes the traveling wave characteristic data based on traveling wave location, and predicts, evaluates, and locates faults based on the traveling wave characteristic data of the distribution network according to the fault location requirements of the distribution network using the optimal distribution network fault location model. This determines the fault location result of the distribution network based on traveling wave location, enabling timely early warning and location of distribution network faults. It can determine the fault location of the distribution network in a timely and accurate manner, providing timely and accurate data support for subsequent maintenance work, and improving the safety and reliability of distribution network operation. Attached Figure Description

[0089] Figure 1 This is a schematic diagram of the distribution network fault early warning and location system of the present invention;

[0090] Figure 2 This is a flowchart of the algorithm for the power distribution network fault early warning and location system of the present invention. Detailed Implementation

[0091] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0092] To address the current limitations of traveling wave positioning in providing timely early warning and location of distribution network faults, the inability to accurately pinpoint fault locations, and the lack of timely and accurate data support for subsequent maintenance, which leads to poor operational safety and reliability of the distribution network, please refer to [link to relevant documentation]. Figures 1-2 This embodiment provides the following technical solution:

[0093] The power distribution network fault early warning and location system includes: a data acquisition module, a data processing module, a model training module, a testing and optimization module, and an early warning and location module.

[0094] It should be noted that the data acquisition module collects traveling wave signals and conditions of the distribution network in real time during operation, determining the traveling wave monitoring information and real-time traveling wave data based on traveling wave location. The data processing module processes the real-time traveling wave data based on traveling wave location to determine the characteristic data of the traveling wave. The model training module constructs a fault location model for the distribution network based on traveling wave location. The testing and optimization module tests and optimizes the fault location model based on traveling wave location to determine the optimal fault location model. The early warning and location module provides timely early warning and location of distribution network faults. It can provide timely and accurate early warning and location of distribution network faults based on traveling wave location, and can determine the location of distribution network faults in a timely manner and accurately. It can provide timely and accurate data support for subsequent maintenance work, and can improve the safety and reliability of distribution network operation.

[0095] The data acquisition module is used to collect traveling wave signals and conditions in real time during the operation of the distribution network, and to determine the traveling wave monitoring information and real-time traveling wave data based on the traveling wave location.

[0096] In this embodiment, the data acquisition module includes:

[0097] The traveling wave monitoring unit is used to monitor and capture traveling wave signals in the distribution network in real time during operation, and to determine the traveling wave monitoring information of the distribution network.

[0098] The traveling wave acquisition unit is used to monitor and acquire the traveling wave situation of the distribution network in real time during operation, and to determine the real-time traveling wave data of the distribution network based on traveling wave positioning.

[0099] It should be noted that traveling wave location technology is a fault location technique based on the traveling wave phenomenon in electromagnetic transient processes. When a fault occurs in a power system, such as a short circuit, grounding, or other anomaly, voltage traveling waves and current traveling waves will propagate along the power cables. These two types of traveling waves propagate along the line to both ends at near the speed of light. By deploying distributed traveling wave sensors or monitoring terminals on the distribution network lines, the traveling wave signals generated by the distribution network fault can be captured in real time. These signals contain the time information of the traveling waves arriving at each sensor. By comparing the time difference of the traveling wave signals received by sensors at different locations, the specific location of the fault point can be calculated using traveling wave ranging technology.

[0100] The data processing module is used to process real-time traveling wave data of the distribution network based on traveling wave positioning, and to determine the traveling wave characteristic data of the distribution network based on traveling wave positioning.

[0101] In this embodiment, the data processing module includes:

[0102] The data cleaning unit is used to clean the real-time traveling wave data of the distribution network based on traveling wave positioning;

[0103] Acquire real-time traveling wave data of the distribution network based on traveling wave positioning;

[0104] Cleaning of real-time traveling wave data from distribution networks based on traveling wave positioning includes:

[0105] Perform consistency checks on real-time traveling wave data of distribution networks based on traveling wave positioning;

[0106] Based on the reasonable value range and interrelationship of each parameter in the real-time traveling wave data of the distribution network based on traveling wave positioning, check whether the real-time traveling wave data of the distribution network based on traveling wave positioning meets the requirements.

[0107] Remove inconsistent data from the real-time traveling wave data of the distribution network based on traveling wave positioning that are outside the normal range, logically unreasonable, or contradictory;

[0108] Invalid and missing values ​​are processed in the real-time traveling wave data of the distribution network based on traveling wave positioning;

[0109] Remove invalid and missing data from the real-time traveling wave data of the distribution network based on traveling wave positioning, which are of no value to the early warning and location of distribution network faults;

[0110] Real-time data of traveling waves in the distribution network that are valuable for early warning and location of distribution network faults were identified;

[0111] The feature extraction unit is used to extract features from the real-time traveling wave data of the cleaned distribution network.

[0112] Acquire real-time traveling wave data of the distribution network that is valuable for early warning and location of distribution network faults after cleaning;

[0113] Feature extraction is performed on real-time traveling wave data of distribution networks, which are valuable for early warning and location of distribution network faults.

[0114] Extract features that can reflect the early warning and location of faults in the distribution network;

[0115] The characteristic data of traveling wave in the distribution network based on traveling wave positioning were determined.

[0116] Among them, the model training module is used to construct a distribution network fault location model based on traveling wave positioning according to the needs of distribution network fault early warning and location.

[0117] In this embodiment, the model training module includes:

[0118] The data collection unit is used to collect historical traveling wave data of the distribution network based on traveling wave positioning.

[0119] Based on the requirements for fault early warning and location in distribution networks, historical data of traveling waves in distribution networks based on traveling wave location are collected.

[0120] The model building unit is used to build a distribution network fault location model based on traveling wave positioning.

[0121] Obtain historical traveling wave data of the distribution network based on traveling wave positioning;

[0122] The historical data of traveling waves in the distribution network based on traveling wave positioning are divided;

[0123] The training dataset and the test dataset were determined;

[0124] Select a neural network model framework suitable for fault location in power distribution networks;

[0125] The selected neural network model framework is trained based on the training dataset;

[0126] A fault location model for distribution networks based on traveling wave positioning was determined.

[0127] The test optimization module is used to test and optimize the distribution network fault location model based on traveling wave positioning, and determine the optimal distribution network fault location model.

[0128] In this embodiment, the test optimization module includes:

[0129] The performance testing unit is used to test the distribution network fault location model based on traveling wave positioning.

[0130] Obtain a distribution network fault location model based on traveling wave positioning;

[0131] Based on the test dataset, the performance of the distribution network fault location model based on traveling wave positioning was tested.

[0132] The performance test results based on the distribution network fault location model were determined;

[0133] An adjustment and optimization unit is used to optimize the distribution network fault location model based on traveling wave positioning;

[0134] Obtain performance test results based on the power distribution network fault location model;

[0135] Mining and analysis of the distribution network fault location model based on traveling wave positioning;

[0136] A parameter adjustment and optimization scheme based on the distribution network fault location model was determined;

[0137] The parameters of the distribution network fault location model are adjusted and optimized according to the parameter adjustment and optimization scheme based on the distribution network fault location model.

[0138] The optimal fault location model for the distribution network was determined.

[0139] Among them, the early warning and location module is used to provide timely early warning and location of power distribution network faults.

[0140] In this embodiment, the early warning positioning module includes:

[0141] The fault early warning unit is used to provide timely early warning of faults in the distribution network;

[0142] Obtain traveling wave monitoring information from the power distribution network;

[0143] Mining and analyzing traveling wave monitoring information from the power distribution network;

[0144] When the traveling wave monitoring information of the distribution network contains traveling wave signals, it indicates that there is a fault in the distribution network, and timely fault warnings are given to the distribution network.

[0145] When the traveling wave monitoring information of the distribution network does not contain a traveling wave signal, it indicates that there is no fault behavior in the distribution network, and no fault warning is given to the distribution network.

[0146] The fault location unit is used to locate faults in the distribution network in a timely manner.

[0147] Among them, the optimal fault location model for the distribution network is obtained;

[0148] Obtain traveling wave characteristic data of distribution network based on traveling wave positioning;

[0149] The traveling wave characteristic data of the distribution network based on traveling wave location is input into the optimal distribution network fault location model;

[0150] Based on the optimal distribution network fault location model, prediction, evaluation and fault location are performed on the traveling wave characteristic data of the distribution network based on traveling wave location.

[0151] The results of distribution network fault location based on traveling wave positioning were determined;

[0152] Among them, the fault location results of the distribution network based on traveling wave positioning include the coordinates of the fault location in the distribution network.

[0153] Among them, the location coordinates of distribution network faults are displayed in a visual form to distribution network maintenance personnel, which facilitates timely maintenance of distribution network faults and can improve the safety and reliability of distribution network operation.

[0154] Therefore, by real-time monitoring and capturing the traveling wave signal during the operation of the distribution network, the traveling wave monitoring information of the distribution network can be determined. Based on the needs of distribution network fault early warning, the traveling wave monitoring information of the distribution network can be mined and analyzed. When the traveling wave monitoring information of the distribution network contains a traveling wave signal, it indicates that there is a fault behavior in the distribution network, and timely fault early warning can be given to the distribution network.

[0155] Therefore, by real-time monitoring and collection of traveling wave data during the operation of the distribution network, real-time traveling wave data based on traveling wave location can be determined. This data is then processed to identify the characteristic traveling wave data. Based on the fault location requirements of the distribution network, the optimal fault location model is used to predict, evaluate, and locate faults using this characteristic data. This allows for timely early warning and location of distribution network faults, providing timely and accurate data support for subsequent maintenance work and improving the safety and reliability of the distribution network operation.

[0156] Preferably, the early warning positioning module includes:

[0157] The comparison module is used to calculate the location error of the fault node in the distribution network based on the optimal distribution network fault location model after locating the fault in the distribution network, and compare it with the error threshold.

[0158] The determination module is used to generate abnormal information for the current fault location when the location error is greater than a preset error threshold, and at the same time update the model parameters of the distribution network fault location model.

[0159] The comparison module includes:

[0160] The first calculation module is used to calculate the occurrence of the fault node location in the distribution network. Probability of secondary location anomalies :

[0161]

[0162] in, It is a composite symbol; The number of times the fault node is located in the distribution network; This represents the maximum classification error rate when distinguishing fault node categories during the location of fault nodes in a distribution network.

[0163] The second calculation module is used to calculate the first occurrence of fault node location in the distribution network. Probability of secondary location anomalies Calculate and determine the location error of the fault node in the distribution network. :

[0164]

[0165] in, This represents the total number of fault node categories in the distribution network. The working area of ​​the power distribution network; In order to occur the first The deviation of the positioning path when the positioning is abnormal.

[0166] The working principle of the above technical solution is as follows: In the comparison module, after locating a fault in the distribution network based on the optimal distribution network fault location model, the positioning error of the faulty node in the distribution network is calculated. The positioning error includes the error of locating the abnormal node category. The error threshold represents a preset threshold value for the distance between categories. When the positioning error is determined to be greater than the preset error threshold, abnormal information for the current fault location is generated, i.e., an abnormal report containing fault location details, error magnitude, timestamp, etc. is generated. At the same time, the model parameters of the distribution network fault location model are updated, such as formulating a model parameter update strategy, including adjusting the value of specific parameters, introducing new parameters, or changing the parameter optimization method, etc.

[0167] The maximum classification error rate ranges from (0,1). First, the probability of the i-th location anomaly occurring during the location of a fault node in the distribution network is calculated based on the first calculation module. Second, based on the probability of the i-th location anomaly occurring during the location of a fault node in the distribution network... Probability of secondary location anomalies The location error of the fault node in the distribution network is calculated and determined. The working area of ​​the distribution network represents the area formed by the various nodes of the distribution network. When the fault occurs... The deviation of the positioning path when a positioning anomaly occurs represents the distance between the node with the positioning anomaly and the actual abnormal node.

[0168] The beneficial effects of the above technical solution are as follows: After locating a fault in the distribution network based on the early warning and positioning module, positioning detection is performed to determine the positioning error of the faulty node. When the positioning error is determined to be greater than a preset error threshold, abnormal information for the current fault location is generated, and the model parameters of the distribution network fault positioning model are updated to improve the accuracy of fault location. The positioning error of the faulty node in the distribution network is accurately calculated based on the above formula, improving the accuracy of judging the magnitude of the positioning error and the error threshold, thereby improving the reliability of the system.

[0169] Preferably, the system further includes: a component positioning module, used for:

[0170] After identifying the faulty equipment in the distribution network based on the early warning and location module, the working signals of several working components that make up the faulty equipment under the current operating conditions are obtained;

[0171] Feature extraction is performed on the aforementioned working signals to obtain the time-domain features corresponding to each working signal; the time-domain features include mean, variance, standard deviation, peak value, and valley value;

[0172] A feature vector is formed by combining the time-domain features corresponding to each working signal; the K-means clustering algorithm is used to perform cluster analysis on several feature vectors to obtain several cluster sets, and the cluster centers of the cluster sets are obtained; a distance matrix is ​​constructed based on several cluster centers; the rows and columns of the distance matrix correspond to different cluster centers, and each element in the matrix represents the distance between the corresponding row and column cluster centers;

[0173] Determine the distance matrix of all operating conditions of the faulty equipment under the fault state, and generate the first distance matrix group;

[0174] Determine the distance matrix of all operating conditions of the faulty equipment under normal conditions, and generate a second distance matrix group;

[0175] Compare the distance matrices of the first distance matrix group and the second distance matrix group under the corresponding working conditions to determine the normal working conditions and abnormal working conditions.

[0176] Determine the information of newly added work components under normal and abnormal operating conditions, and use them as work components to be screened;

[0177] Electromagnetic interference (EMI) and electromagnetic interference immunity (EMI) tests are performed on the components to be screened. Components that pass the EMI and EMI tests are discarded to obtain abnormal components.

[0178] The working principle of the above technical solution is as follows: In this embodiment, firstly, the components of the faulty device are identified. These components include sensors, actuators, and circuit boards. The operating signals of each component are acquired in real time or from historical records. These signals include various types of data such as voltage, current, temperature, and vibration.

[0179] Feature extraction is performed on each of the several working signals to obtain the time-domain features corresponding to each working signal; Mean: The average value of the signal, reflecting the central trend of the signal. Variance: The average of the squares of the deviations of the signal from its mean, measuring the degree of dispersion of the signal. Standard Deviation: The square root of the variance, also an indicator of the degree of dispersion of the signal. Peak Value: The maximum value of the signal within a given time range, reflecting the strength or extreme cases of the signal. Valley Value: The minimum value of the signal within a given time range, corresponding to the peak value, providing another extreme of the signal variation.

[0180] The time-domain features (mean, variance, standard deviation, peak value, and valley value) corresponding to each working signal are combined into a feature vector. Each feature vector represents a specific state or behavior pattern of the faulty equipment under the current operating conditions. Set the number of clusters K and initialize the cluster centers: randomly select K feature vectors as initial cluster centers; for each feature vector, calculate its distance (Euclidean distance) to all cluster centers and assign it to the nearest cluster center. For each cluster, recalculate its cluster center, which is the mean of all feature vectors in that cluster. Repeat the iteration until the cluster centers no longer change significantly or the preset number of iterations is reached. Obtain K cluster centers from the K-means clustering algorithm. Create a K×K matrix, where rows and columns correspond to different cluster centers. For each element (i,j) in the matrix, calculate the distance between the i-th cluster center and the j-th cluster center. Fill the corresponding positions in the distance matrix with the calculated distance values. The distance matrix is ​​used to assess the separation between clusters and the compactness within clusters by examining the distances between cluster centers.

[0181] In this embodiment, the distance matrix of all operating conditions of the faulty equipment under faulty conditions and the distance matrix of all operating conditions of the faulty equipment under normal conditions are determined. The distance matrix of the first distance matrix group and the distance matrix of the second distance matrix group under the corresponding operating conditions are compared to determine the normal operating conditions and abnormal operating conditions. The information of newly added working components under normal and abnormal operating conditions is determined as working components to be screened (possibly abnormal). Electromagnetic interference test and electromagnetic interference resistance test are performed on the working components to be screened. The working components to be screened that pass the electromagnetic interference test and electromagnetic interference resistance test are eliminated to obtain the abnormal working components.

[0182] The beneficial effects of the above technical solution are as follows: After the faulty equipment in the distribution network is determined by the early warning and positioning module, the abnormal working components in the faulty equipment are accurately determined by the component positioning module, which further improves the accuracy of abnormal positioning, facilitates timely maintenance and treatment, and improves the reliability of the equipment.

[0183] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0184] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A power distribution network fault early warning and location system, characterized in that, include: The data acquisition module is used to collect traveling wave signals and conditions in real time during the operation of the distribution network, and to determine the traveling wave monitoring information and real-time traveling wave data based on the traveling wave location. The data processing module is used to process real-time traveling wave data of the distribution network based on traveling wave positioning, and to determine the characteristic data of the traveling wave in the distribution network based on traveling wave positioning. The model training module is used to construct a distribution network fault location model based on traveling wave positioning according to the needs of distribution network fault early warning and location. The test optimization module is used to test and optimize the distribution network fault location model based on traveling wave positioning, and determine the optimal distribution network fault location model. The early warning and location module is used to provide timely early warning and location of faults in the power distribution network; It also includes a component location module, used for: After identifying the faulty equipment in the distribution network based on the early warning and location module, the working signals of several working components that make up the faulty equipment under the current operating conditions are obtained; Feature extraction is performed on the aforementioned working signals to obtain the time-domain features corresponding to each working signal; the time-domain features include mean, variance, standard deviation, peak value, and valley value; A feature vector is formed by combining the time-domain features corresponding to each working signal; the K-means clustering algorithm is used to perform cluster analysis on several feature vectors to obtain several cluster sets, and the cluster centers of the cluster sets are obtained; a distance matrix is ​​constructed based on several cluster centers; the rows and columns of the distance matrix correspond to different cluster centers, and each element in the matrix represents the distance between the corresponding row and column cluster centers; Determine the distance matrix of all operating conditions of the faulty equipment under the fault state, and generate the first distance matrix group; Determine the distance matrix of all operating conditions of the faulty equipment under normal conditions, and generate a second distance matrix group; Compare the distance matrices of the first distance matrix group and the second distance matrix group under the corresponding working conditions to determine the normal working conditions and abnormal working conditions. Determine the information of newly added work components under normal and abnormal operating conditions, and use them as work components to be screened; Electromagnetic interference (EMI) and electromagnetic interference immunity (EMI) tests are performed on the components to be screened. Components that pass the EMI and EMI tests are removed to obtain abnormal components. The data acquisition module includes: The traveling wave monitoring unit is used to monitor and capture traveling wave signals in the distribution network in real time during operation, and to determine the traveling wave monitoring information of the distribution network. The traveling wave acquisition unit is used to monitor and acquire the traveling wave situation of the distribution network in real time during operation, and to determine the real-time traveling wave data of the distribution network based on traveling wave positioning. The data processing module includes: The data cleaning unit is used to clean the real-time traveling wave data of the distribution network based on traveling wave positioning; Acquire real-time traveling wave data of the distribution network based on traveling wave positioning; Cleaning of real-time traveling wave data from distribution networks based on traveling wave positioning includes: Perform consistency checks on real-time traveling wave data of distribution networks based on traveling wave positioning; Based on the reasonable value range and interrelationship of each parameter in the real-time traveling wave data of the distribution network based on traveling wave positioning, check whether the real-time traveling wave data of the distribution network based on traveling wave positioning meets the requirements. Remove inconsistent data from the real-time traveling wave data of the distribution network based on traveling wave positioning that are outside the normal range, logically unreasonable, or contradictory; Invalid and missing values ​​are processed in the real-time traveling wave data of the distribution network based on traveling wave positioning; Remove invalid and missing data from the real-time traveling wave data of the distribution network based on traveling wave positioning, which are of no value to the early warning and positioning of distribution network faults; Real-time data of traveling waves in the distribution network that are valuable for early warning and location of distribution network faults were identified. The test optimization module includes: The performance testing unit is used to test the distribution network fault location model based on traveling wave positioning. Obtain a distribution network fault location model based on traveling wave positioning; Based on the test dataset, the performance of the distribution network fault location model based on traveling wave positioning was tested. The performance test results based on the distribution network fault location model were determined; An adjustment and optimization unit is used to optimize the distribution network fault location model based on traveling wave positioning; Obtain performance test results based on the power distribution network fault location model; Mining and analysis of the fault location model of distribution network based on traveling wave positioning; A parameter adjustment and optimization scheme based on the distribution network fault location model was determined; The parameters of the distribution network fault location model are adjusted and optimized according to the parameter adjustment and optimization scheme based on the distribution network fault location model. The optimal fault location model for the distribution network was determined.

2. The power distribution network fault early warning and location system according to claim 1, characterized in that, The data processing module further includes: The feature extraction unit is used to extract features from the real-time traveling wave data of the cleaned distribution network. Acquire real-time traveling wave data of the distribution network that is valuable for early warning and location of distribution network faults after cleaning; Feature extraction is performed on real-time traveling wave data of distribution networks, which is valuable for early warning and location of distribution network faults. Extract features that can reflect the early warning and location of faults in the distribution network; The characteristic data of traveling wave in the distribution network based on traveling wave positioning were determined.

3. The power distribution network fault early warning and location system according to claim 1, characterized in that, The model training module includes: The data collection unit is used to collect historical traveling wave data of the distribution network based on traveling wave positioning. Based on the requirements for fault early warning and location in distribution networks, historical data of traveling waves in distribution networks based on traveling wave location are collected. The model building unit is used to build a distribution network fault location model based on traveling wave positioning. Obtain historical traveling wave data of the distribution network based on traveling wave positioning; The historical data of traveling waves in the distribution network based on traveling wave positioning are divided; The training dataset and the test dataset were determined; Select a neural network model framework suitable for fault location in distribution networks; The selected neural network model framework is trained based on the training dataset; A fault location model for distribution networks based on traveling wave positioning was determined.

4. The power distribution network fault early warning and location system according to claim 1, characterized in that, The early warning and positioning module includes: The fault early warning unit is used to provide timely early warning of faults in the distribution network; Obtain traveling wave monitoring information from the power distribution network; Mining and analyzing traveling wave monitoring information from the power distribution network; When the traveling wave monitoring information of the distribution network contains traveling wave signals, it indicates that there is a fault in the distribution network, and timely fault warnings are given to the distribution network. When the traveling wave monitoring information of the distribution network does not contain traveling wave signals, it indicates that there is no fault behavior in the distribution network, and no fault warning is given to the distribution network.

5. The power distribution network fault early warning and location system according to claim 4, characterized in that, The early warning and positioning module also includes: The fault location unit is used to locate faults in the distribution network in a timely manner. Among them, the optimal fault location model for the distribution network is obtained; Obtain traveling wave characteristic data of distribution network based on traveling wave positioning; The traveling wave characteristic data of the distribution network based on traveling wave location is input into the optimal distribution network fault location model; Based on the optimal distribution network fault location model, prediction, evaluation and fault location are performed on the traveling wave characteristic data of the distribution network based on traveling wave location. The results of distribution network fault location based on traveling wave positioning were determined; Among them, the fault location results of the distribution network based on traveling wave positioning include the coordinates of the fault location in the distribution network.

Images