A lightning protection intelligent monitoring method and system in distribution network

Abstract

The present application provides a method and system for intelligent monitoring of lightning protection in a distribution network, which extracts the transient energy of polarity current from the lightning current of each lightning monitoring node, and then determines the mutual correlation between all transient energies. Based on the fuzzy evaluation mechanism, the state response evaluation of the lightning current of the lightning monitoring node is performed according to the mutual correlation to obtain the monitoring confidence of the lightning monitoring node; the timing dependency of the lightning current between adjacent lightning monitoring nodes is determined according to the historical lightning current, and the response characteristics of the lightning current attenuation between adjacent lightning monitoring nodes are determined through all the timing dependencies and the topological structure of the target distribution network; the lightning current of the lightning monitoring node is confidence corrected according to the monitoring confidence and all the response characteristics to obtain the corrected lightning current, and then the lightning strike location is located. The scheme of the present application can realize the associated confidence correction of the lightning current between the monitoring nodes, thereby improving the positioning accuracy of the lightning strike location.

Description

Technical Field

[0001] The present application relates to the field of electric power measurement technology, and more specifically, to an intelligent lightning protection monitoring method and system in a distribution network. Background Art

[0002] The application of power measurement in lightning protection monitoring is mainly to monitor the changes in lightning current in the distribution network in real time, identify and locate lightning events in time, and effectively ensure the safety of power equipment. The impact of lightning on the power system is mainly reflected in the current and voltage fluctuations caused by lightning. These fluctuations may cause damage to transformers, switchgear, wires, etc., and even cause power grid failures. Through high-precision sensors and acquisition equipment, it is possible to obtain current, voltage, frequency and other data of each node in the distribution network in real time, and identify the occurrence of lightning events through data analysis technology. Especially in the high-incidence season of lightning, power measurement equipment can provide key current change information to assist the lightning protection system in judging the impact of lightning on power equipment and carry out corresponding early warning and protection.

[0003] In the prior art, the lightning protection monitoring system of the distribution network mainly relies on a single monitoring node to collect and analyze the lightning current in real time. However, the lightning current has strong temporal and spatial variability, and it is difficult for a single monitoring node to fully capture the entire process of the lightning event. The lightning current not only has different distributions in space, but also has transient changes on different time scales, and it is difficult for a single monitoring node to simultaneously reflect these multi-dimensional characteristics. For the complex topological structure in the distribution network, the propagation of the lightning current between the monitoring nodes also has a certain timing dependence. The monitoring of a single monitoring node cannot provide important information about the current transmission characteristics between the monitoring nodes, resulting in the inability to accurately analyze the propagation path and fluctuation characteristics of the lightning current. Secondly, a single monitoring node is susceptible to external interference, such as equipment failure, sensor sensitivity differences and other factors, which will cause errors in data collection, thereby affecting the reliability of the lightning current. Therefore, how to achieve the correlation confidence correction of the lightning current between the monitoring nodes, thereby improving the positioning accuracy of the lightning strike location has become a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a method and system for intelligent lightning protection monitoring in a distribution network, which can realize the correlation confidence correction of lightning current between monitoring nodes, thereby improving the positioning accuracy of the lightning strike location.

[0005] In a first aspect, the present application provides a method for intelligent monitoring of lightning protection in a distribution network, comprising the following steps:

[0006] Perform distributed sensing and monitoring on the lightning current in the target distribution network to obtain the lightning current of each lightning monitoring node in the target distribution network;

[0007] Extracting the transient energy of the polarity current from the lightning current of each lightning monitoring node, and then determining the cross-correlation between all transient energies, and based on the fuzzy evaluation mechanism, performing a state response evaluation on the lightning current of each lightning monitoring node according to the cross-correlation, and obtaining the monitoring confidence of the lightning current of each lightning monitoring node;

[0008] Obtain the historical lightning current of each lightning monitoring node in the target distribution network, and then determine the timing dependency of the lightning current between every two adjacent lightning monitoring nodes based on all the historical lightning currents, and determine the response characteristics of the lightning current attenuation between every two adjacent lightning monitoring nodes through all the timing dependencies and the topological structure of the target distribution network;

[0009] According to the monitoring confidence of the lightning current of each lightning monitoring node and all the response characteristics, the lightning current of each lightning monitoring node is confidence corrected to obtain the corrected lightning current, and the lightning strike location is located based on all the corrected lightning currents.

[0010] Preferably, extracting the transient energy of the polarity current from the lightning current of each lightning monitoring node specifically includes:

[0011] For each lightning monitoring node, a positive polarity current and a negative polarity current are extracted from the lightning strike current of the lightning monitoring node;

[0012] Performing short-time Fourier transform on the positive polarity current and the negative polarity current respectively to extract energy distribution of the lightning current in the frequency domain;

[0013] The transient energy of the polarity current at the lightning monitoring node is determined by the energy distribution, and then the transient energy of the polarity current at each lightning monitoring node is obtained.

[0014] Preferably, determining the cross-correlation between all transient energies specifically includes:

[0015] For every two lightning monitoring nodes, the Pearson correlation coefficient of the transient energy between the two lightning monitoring nodes is determined according to the transient energy of the polarity current at the two lightning monitoring nodes, and then the Pearson correlation coefficient of the transient energy between every two lightning monitoring nodes is obtained;

[0016] The cross-correlations between all transient energies were determined by all Pearson correlation coefficients.

[0017] Preferably, based on the fuzzy evaluation mechanism, the state response evaluation of the lightning current of each lightning monitoring node is performed according to the mutual correlation, and the monitoring confidence of the lightning current of each lightning monitoring node is obtained, which specifically includes:

[0018] Initialize the membership of each lightning monitoring node's monitoring behavior;

[0019] Constructing a mutual correlation matrix of monitoring behaviors among all lightning monitoring nodes according to the mutual correlation;

[0020] Mapping the values ​​in the mutual correlation matrix into fuzzy sets through fuzzy membership functions;

[0021] Constructing a fuzzy evaluation matrix according to all initialized membership degrees and the fuzzy set;

[0022] Based on the fuzzy evaluation matrix, a fuzzy evaluation is performed on the response behavior state of each lightning monitoring node in monitoring the lightning current, so as to obtain the monitoring confidence of the lightning current of each lightning monitoring node.

[0023] Preferably, determining the time sequence dependency of the lightning currents between every two adjacent lightning monitoring nodes based on all historical lightning currents specifically includes:

[0024] Performing time alignment on all historical lightning currents to obtain all aligned historical lightning currents;

[0025] Convert all aligned historical lightning currents into lightning current sequences of each lightning monitoring node;

[0026] Based on the cross-correlation function, the time sequence dependency of the lightning currents between every two adjacent lightning monitoring nodes is determined through the lightning current sequences of every two adjacent lightning monitoring nodes.

[0027] Preferably, determining the response characteristics of the lightning current attenuation between every two adjacent lightning monitoring nodes through all the timing dependencies and the topological structure of the target distribution network specifically includes:

[0028] The topological structure of the target distribution network is determined through the location information of each lightning monitoring node and the electrical connection relationship between each lightning monitoring node;

[0029] Construct an exponential decay model of lightning current based on all timing dependencies;

[0030] Setting the topology of the target distribution network as a constraint parameter of the exponential decay model;

[0031] The exponential decay model is used to simulate the attenuation process of the lightning current between every two adjacent lightning monitoring nodes, and then the response characteristics of the lightning current attenuation between every two adjacent lightning monitoring nodes are extracted from the simulation results.

[0032] Preferably, the lightning current of the lightning monitoring node is collected using Rogowski coil current.

[0033] In a second aspect, the present application provides an intelligent lightning protection monitoring system in a distribution network, comprising:

[0034] A monitoring module is used to perform distributed sensing monitoring of lightning current in the target distribution network to obtain the lightning current of each lightning monitoring node in the target distribution network;

[0035] A processing module, used to extract the transient energy of the polarity current from the lightning current of each lightning monitoring node, and then determine the cross-correlation between all transient energies, and based on the fuzzy evaluation mechanism, perform a state response evaluation on the lightning current of each lightning monitoring node according to the cross-correlation to obtain the monitoring confidence of the lightning current of each lightning monitoring node;

[0036] The processing module is further used to obtain the historical lightning current of each lightning monitoring node in the target distribution network, and then determine the timing dependency of the lightning current between every two adjacent lightning monitoring nodes based on all the historical lightning currents, and determine the response characteristics of the lightning current attenuation between every two adjacent lightning monitoring nodes through all the timing dependencies and the topological structure of the target distribution network;

[0037] The positioning module is used to perform confidence correction on the lightning current of each lightning monitoring node according to the monitoring confidence of the lightning current of each lightning monitoring node and all response characteristics to obtain the corrected lightning current, and locate the lightning strike location based on all the corrected lightning currents.

[0038] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned intelligent lightning protection monitoring method in the distribution network.

[0039] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned intelligent lightning protection monitoring method in the distribution network is implemented.

[0040] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0041] In an embodiment of the present application, distributed sensing monitoring is performed on the lightning current in the target distribution network to obtain the lightning current of each lightning monitoring node in the target distribution network; the transient energy of the polarity current is extracted from the lightning current of each lightning monitoring node, and then the correlation between all transient energies is determined, and based on the fuzzy evaluation mechanism, the state response evaluation of the lightning current of each lightning monitoring node is performed according to the correlation to obtain the monitoring confidence of the lightning current of each lightning monitoring node; the historical lightning current of each lightning monitoring node in the target distribution network is obtained, and then the timing dependency of the lightning current between every two adjacent lightning monitoring nodes is determined according to all the historical lightning currents, and the response characteristics of the lightning current attenuation between every two adjacent lightning monitoring nodes are determined through all the timing dependencies and the topological structure of the target distribution network; the lightning current of each lightning monitoring node is confidence corrected according to the monitoring confidence of the lightning current of each lightning monitoring node and all the response characteristics to obtain the corrected lightning current, and the lightning strike location is located based on all the corrected lightning currents.

[0042] It can be seen that the present application performs confidence correction on the lightning current of each lightning monitoring node through the monitoring confidence and all response characteristics of the lightning current of each lightning monitoring node, and obtains the corrected lightning current; wherein, firstly, by analyzing the cross-correlation between the transient energy of the lightning current, the state response evaluation of each lightning monitoring node is performed based on the fuzzy evaluation mechanism, and the monitoring confidence of the lightning current of each lightning monitoring node is obtained. The reliability of the lightning monitoring node in monitoring the lightning current can be evaluated through the monitoring confidence. At the same time, the fuzzy evaluation mechanism can handle uncertainty and ambiguity in a complex environment, and then effectively distinguish between high-quality current data and current data affected by interference, thereby ensuring that the evaluation of the lightning current is more accurate; then, the response characteristics of the lightning current attenuation between adjacent lightning monitoring nodes are determined through the timing dependency and the topological structure of the target distribution network, and the corresponding Based on the response characteristics of the attenuation of lightning current between adjacent lightning monitoring nodes, the system can identify inconsistent lightning currents in lightning events and make corrections, which helps to improve the correlation between lightning currents between different lightning monitoring nodes, and can provide key spatiotemporal feature support for the associated confidence correction of lightning currents, thereby ensuring the coordinated correction of lightning currents between lightning monitoring nodes, thereby improving the reliability of the corrected lightning currents of lightning monitoring nodes; finally, confidence correction of lightning currents is performed based on the monitoring confidence and response characteristics of each lightning monitoring node, ensuring that the lightning current data of each node is more accurate and consistent. Through the corrected lightning current, the system can more accurately locate the location where the lightning strike occurs, thereby improving the accuracy of lightning strike positioning; in summary, the present application scheme can realize the associated confidence correction of lightning currents between monitoring nodes, thereby improving the positioning accuracy of the location where the lightning strike occurs. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is an exemplary flow chart of a method for intelligent monitoring of lightning protection in a distribution network according to some embodiments of the present application;

[0044] Figure 2 is a schematic diagram of the structure of the lightning monitoring node distribution according to some embodiments of the present application;

[0045] Figure 3 is a schematic diagram of a process for determining timing dependencies according to some embodiments of the present application;

[0046] Figure 4 is a structural schematic diagram of an intelligent lightning protection monitoring system in a distribution network according to some embodiments of the present application;

[0047] Figure 5 It is a structural schematic diagram of a computer device for implementing an intelligent monitoring method for lightning protection in a distribution network according to some embodiments of the present application. DETAILED DESCRIPTION

[0048] In order to better understand the technical solution of the present application, the technical solution of the present application will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0049] refer to Figure 1 , which is an exemplary flow chart of a method for intelligent monitoring of lightning protection in a distribution network according to some embodiments of the present application. The method 100 for intelligent monitoring of lightning protection in a distribution network mainly includes the following steps:

[0050] In step 101, distributed sensing monitoring is performed on the lightning current in the target distribution network to obtain the lightning current of each lightning monitoring node in the target distribution network.

[0051] It should be noted that the reference Figure 2 As shown, the figure is a structural schematic diagram of the distribution of lightning monitoring nodes in some embodiments of the present application, wherein the power station is the source of electricity, the substation is responsible for converting the electricity generated by the power station into a voltage level suitable for transmission and distribution, and the lightning detection nodes 1, 2, 3, 4, 5, 6, 7, 8, and 9 are distributed in different locations of the distribution network for monitoring lightning current.

[0052] In the specific implementation, first, multiple lightning monitoring nodes are set in the target distribution network, and a high-sensitivity Rogowski coil current sensor is installed at each lightning monitoring node, and the sampling frequency of the Rogowski coil current sensor is set between 10 and 50 Hz. The Rogowski coil current sensor is further used to collect the lightning current of each lightning monitoring node in the target distribution network, wherein the lightning current is numerical data, and the specific numerical value represents the current amplitude; then, the real-time collected lightning current data is transmitted to the monitoring center through wireless communication (such as LoRaT) or wired method (such as optical fiber), and the lightning current of each lightning monitoring node in the target distribution network is further obtained from the database of the monitoring center.

[0053] It should be noted that in the present application, the lightning current can be collected by a Rogowski coil current sensor. In other embodiments, other current sensors can also be used to collect the lightning current, which is not limited here.

[0054] In step 102, the transient energy of the polarity current is extracted from the lightning strike current of each lightning monitoring node, and then the cross-correlation between all transient energies is determined. Based on the fuzzy evaluation mechanism, the state response evaluation of the lightning strike current of each lightning monitoring node is performed according to the cross-correlation to obtain the monitoring confidence of the lightning strike current of each lightning monitoring node.

[0055] In some embodiments, extracting the transient energy of the polarity current from the lightning current of each lightning monitoring node may be achieved by using the following steps:

[0056] For each lightning monitoring node, a positive polarity current and a negative polarity current are extracted from the lightning strike current of the lightning monitoring node;

[0057] Performing short-time Fourier transform on the positive polarity current and the negative polarity current respectively to extract energy distribution of the lightning current in the frequency domain;

[0058] The transient energy of the polarity current at the lightning monitoring node is determined by the energy distribution, and then the transient energy of the polarity current at each lightning monitoring node is obtained.

[0059] It should be noted that the polarity current in this application refers to positive polarity current and negative polarity current.

[0060] In specific implementation, for each lightning monitoring node, firstly, the positive polarity current and the negative polarity current can be separated from the lightning current of the lightning monitoring node by the threshold detection or waveform analysis method in the prior art; secondly, the separated positive polarity current and negative polarity current are respectively subjected to short-time Fourier transform (Short-Time Fourier The specific steps of short-time Fourier transform (STFT) include: selecting an appropriate window function (such as a Gaussian window function) and setting the time window width and sliding step size to smooth the current (i.e., positive polarity current and negative polarity current) segments and reduce frequency leakage, and then calculating the Fourier transform of the current in each time window to obtain the amplitude spectrum in the time-frequency domain, and then squaring the amplitude spectrum through the power spectrum density formula to obtain the energy distribution in the frequency domain, so as to obtain the energy distribution of the lightning current in the frequency domain in each time window; then, performing amplitude integration operation on the energy distribution of the lightning current in the frequency domain, calculating the total energy value in each time window, and taking the total energy value as the transient energy in the time window, and then taking the transient energy of all time windows as the transient energy of the positive and negative polarity currents at the lightning monitoring node, and then obtaining the transient energy of the positive and negative polarity currents at each lightning monitoring node; it should be noted that, through the above method, both the time local characteristics of the current can be retained and the frequency domain energy characteristics of the lightning current can be accurately described, which can provide high-precision input data for subsequent analysis.

[0061] It should be noted that positive and negative lightning currents have different amplitudes, durations and waveform characteristics. By separating the positive and negative currents, the transient energy characteristics of the two polarity currents can be analyzed separately, which helps to more comprehensively capture the essential characteristics of lightning currents and improve monitoring accuracy.

[0062] In some embodiments, determining the cross-correlation between all transient energies may be achieved by using the following steps:

[0063] For every two lightning monitoring nodes, the Pearson correlation coefficient of the transient energy between the two lightning monitoring nodes is determined according to the transient energy of the polarity current at the two lightning monitoring nodes, and then the Pearson correlation coefficient of the transient energy between every two lightning monitoring nodes is obtained;

[0064] The cross-correlations between all transient energies were determined by all Pearson correlation coefficients.

[0065] In the specific implementation, for every two lightning monitoring nodes, first, all transient energies of positive and negative polarity currents at the two lightning monitoring nodes are arranged into transient energy sequences of two polarity currents according to the time sequence of the time window, and then the two transient energy sequences are substituted into the Pearson correlation coefficient formula to obtain the Pearson correlation coefficient of the transient energy between the two lightning monitoring nodes. It should be noted that in this application, in order to ensure the stability of the calculation, the transient energy sequence can be normalized (such as subtracting the mean and dividing by the standard deviation) to eliminate the dimension effect, which is not repeated here; then, for all pairs of lightning monitoring nodes, a correlation coefficient matrix is ​​constructed, and each element in the matrix represents the mutual correlation value between the lightning monitoring nodes. Finally, a global analysis is performed through the correlation coefficient matrix to extract the mutual correlation characteristics of all nodes in the system, which can provide input for subsequent fuzzy evaluation analysis. The method of this application improves the calculation accuracy of the mutual correlation through standardization and statistical analysis, and at the same time ensures that the correlation between lightning monitoring nodes can be accurately characterized in complex distribution network lightning strike monitoring.

[0066] It should be noted that the Pearson correlation coefficient in the present application reflects the linear correlation strength of the transient energy between two lightning monitoring nodes; it should also be noted that the cross-correlation between transient energies in the present application reflects the similarity of the lightning current energy change patterns between different lightning monitoring nodes, which can reveal whether there is a similar trend in the energy fluctuations of lightning currents at two or more lightning monitoring nodes at the same time or in a similar time period.

[0067] In some embodiments, based on the fuzzy evaluation mechanism, the state response evaluation of the lightning current of each lightning monitoring node is performed according to the mutual correlation, and the monitoring confidence of the lightning current of each lightning monitoring node is obtained by the following steps:

[0068] Initialize the membership of each lightning monitoring node's monitoring behavior;

[0069] Constructing a mutual correlation matrix of monitoring behaviors among all lightning monitoring nodes according to the mutual correlation;

[0070] Mapping the values ​​in the mutual correlation matrix into fuzzy sets through fuzzy membership functions;

[0071] Constructing a fuzzy evaluation matrix according to all initialized membership degrees and the fuzzy set;

[0072] Based on the fuzzy evaluation matrix, a fuzzy evaluation is performed on the response behavior state of each lightning monitoring node in monitoring the lightning current, so as to obtain the monitoring confidence of the lightning current of each lightning monitoring node.

[0073] In the specific implementation, first, the membership of the monitoring behavior of each lightning monitoring node is initialized. The membership reflects the degree of belonging of the node monitoring behavior under different states. It is usually defined using a fuzzy membership function based on experience or prior knowledge (such as a triangular membership function or a trapezoidal membership function). For example, the monitoring behavior of a lightning monitoring node can be evaluated based on the quality of historical monitoring current data to obtain a preliminary membership value; secondly, the correlation coefficient matrix in the above embodiment is used as the mutual correlation matrix of the monitoring behavior of all lightning monitoring nodes. The mutual correlation matrix is ​​used to describe the correlation of the monitoring behaviors between lightning monitoring nodes, wherein the higher the mutual correlation value, the stronger the correlation of the monitoring behaviors between lightning monitoring nodes; then, the fuzzy membership function is used to map the values ​​in the mutual correlation matrix into fuzzy The numerical values ​​of these correlation coefficients are converted into fuzzy levels (such as "low", "medium" and "high" correlation); further, all the initialized memberships are fuzzy weighted according to the mutual correlation matrix to obtain the evaluation factor of each lightning monitoring node, and then all the evaluation factors are constructed into a matrix according to the location information of the lightning monitoring node, and the matrix is ​​used as the fuzzy evaluation matrix; finally, the fuzzy evaluation matrix is ​​set as the evaluation parameter of the fuzzy model, and the lightning current of each lightning monitoring node is used as the input of the fuzzy model, and then the monitoring confidence of each lightning monitoring node is analyzed through the fuzzy model. The monitoring confidence reflects the detection reliability of the lightning monitoring node for the lightning current, and the monitoring confidence of each lightning monitoring node is used as the monitoring confidence of the lightning current of the corresponding lightning monitoring node.

[0074] It should be noted that the monitoring confidence in the present application is a metric to measure the reliability of the monitoring node's lightning current monitoring results; it should also be noted that the fuzzy evaluation matrix in the present application reflects the response state of the lightning monitoring node in the monitoring behavior.

[0075] In step 103, the historical lightning currents of each lightning monitoring node in the target distribution network are obtained, and then the timing dependency of the lightning currents between every two adjacent lightning monitoring nodes is determined based on all the historical lightning currents, and the response characteristics of the lightning current attenuation between every two adjacent lightning monitoring nodes are determined through all the timing dependencies and the topological structure of the target distribution network.

[0076] It should be noted that in the present application, obtaining the historical lightning current of each lightning monitoring node in the target distribution network can be specifically implemented in the following manner, namely: the lightning current of each lightning monitoring node in the target distribution network can be collected using a Rogowski coil current sensor within a specified time period as the historical lightning current of the corresponding lightning monitoring node. It should be noted that the specified time period in the present application can be set to the past year to the current moment. In other embodiments, the specified time period can also be set to other time periods, which are not limited here.

[0077] In some embodiments, reference Figure 3 As shown, this figure is a schematic diagram of the process of determining the timing dependency in some embodiments of the present application. In this embodiment, the timing dependency of the lightning current between every two adjacent lightning monitoring nodes is determined based on all historical lightning currents, which can be implemented by the following steps:

[0078] In step 1031, all historical lightning currents are time-aligned to obtain all aligned historical lightning currents;

[0079] In step 1032, all aligned historical lightning currents are converted into lightning current sequences of each lightning monitoring node;

[0080] In step 1033, based on the cross-correlation function, the time sequence dependency of the lightning current between every two adjacent lightning monitoring nodes is determined through the lightning current sequences of every two adjacent lightning monitoring nodes.

[0081] In the specific implementation, first, linear interpolation method can be used to time-align all historical lightning current data to ensure that the monitoring data of different nodes are synchronized in time. It should be noted that time alignment can also be achieved by spline interpolation method; then, the aligned historical lightning current is converted into lightning current sequences of each lightning monitoring node according to the acquisition time. These lightning current sequences represent the changes of lightning current of each lightning monitoring node at different time points; finally, in order to accurately evaluate the temporal correlation of lightning current between adjacent nodes, the cross-correlation function (CCF) can be used to analyze the temporal dependency between lightning current sequences of each two adjacent lightning monitoring nodes. The cross-correlation function can reveal their temporal similarity and synchronization by calculating the correlation coefficient of two lightning current sequences at different time delays. Specifically, the calculation steps of the cross-correlation function include: for each pair of lightning current sequences, their point-to-point products at different time delays are calculated, and then their maximum correlation values ​​at each delay are obtained by statistical methods. The maximum correlation value can be used as the temporal dependency between the two lightning current sequences.

[0082] It should be noted that the timing dependency in the present application is an indicator for measuring the correlation of lightning currents between adjacent lightning monitoring nodes on the time axis, which reflects the dynamic correlation between adjacent lightning monitoring nodes in lightning current changes.

[0083] In some embodiments, determining the response characteristics of the lightning current attenuation between every two adjacent lightning monitoring nodes through all the timing dependencies and the topological structure of the target distribution network can be implemented by the following steps:

[0084] The topological structure of the target distribution network is determined through the location information of each lightning monitoring node and the electrical connection relationship between each lightning monitoring node;

[0085] Construct an exponential decay model of lightning current based on all timing dependencies;

[0086] Setting the topology of the target distribution network as a constraint parameter of the exponential decay model;

[0087] The exponential decay model is used to simulate the attenuation process of the lightning current between every two adjacent lightning monitoring nodes, and then the response characteristics of the lightning current attenuation between every two adjacent lightning monitoring nodes are extracted from the simulation results.

[0088] In the specific implementation, first, the topological structure of the target distribution network is constructed through the location information of each lightning monitoring node (such as GPS coordinates or distribution network layout diagram) and the electrical connection relationship (such as the power line between lightning monitoring nodes). This topological structure provides a basis for further analysis of the propagation path of lightning current and the interaction between nodes; secondly, based on the physical characteristics of lightning current propagation in the power system, it is assumed that the lightning current follows the exponential decay law during the propagation process, that is, the current intensity decays exponentially with the increase of propagation distance, and then an exponential decay model is initialized, and then all the timing dependencies are set as the objective function in the exponential decay model. The exponential decay model is constructed by taking the topological structure of the target distribution network as the constraint parameter of the exponential decay model, combining the location information and electrical connection relationship of every two adjacent lightning monitoring nodes with the exponential decay model and setting them as the input parameters of the model; finally, based on the exponential decay model, the propagation characteristics of the lightning current between adjacent lightning monitoring nodes in the distribution network are simulated through the known timing dependency, the current decay process is simulated and calculated, and the lightning current decay response characteristics between every two adjacent lightning monitoring nodes are extracted through the simulation results. Specifically, the response characteristics include the decay rate and the delay effect.

[0089] It should be noted that the response characteristic of lightning current attenuation in the present application is an indicator reflecting the attenuation response law of lightning current intensity in space and time.

[0090] In step 104, confidence correction is performed on the lightning current of each lightning monitoring node according to the monitoring confidence of the lightning current of each lightning monitoring node and all response characteristics to obtain a corrected lightning current, and the lightning strike location is located based on all the corrected lightning currents.

[0091] In some embodiments, confidence correction is performed on the lightning strike current of each lightning monitoring node according to the monitoring confidence of the lightning strike current of each lightning monitoring node and all response characteristics, and the corrected lightning strike current can be obtained by the following steps:

[0092] Selecting a lightning monitoring node as a selected lightning monitoring node;

[0093] When the monitoring confidence of the lightning current of the selected lightning monitoring node is less than a preset monitoring threshold, all adjacent lightning monitoring nodes adjacent to the selected lightning monitoring node are screened;

[0094] The constraint parameters of the pre-trained correction model are updated by selecting the monitoring confidence of the lightning current of the lightning monitoring node and the response characteristics of the lightning current attenuation between all adjacent lightning monitoring nodes;

[0095] Correcting the lightning strike current of the selected lightning monitoring node according to the pre-trained correction model after parameter update to obtain the corrected lightning strike current of the selected lightning monitoring node;

[0096] Continue to determine the corrected lightning currents of the remaining lightning monitoring nodes.

[0097] In the specific implementation, first, by selecting a lightning monitoring node as a reference node, the monitoring confidence of its lightning current is preliminarily determined. If the confidence is lower than the preset threshold, it is necessary to correct it through the lightning current data of the adjacent lightning monitoring nodes; secondly, the monitoring nodes adjacent to the selected node are screened, and the constraint parameters of a pre-trained correction model are updated according to the lightning current attenuation response characteristics of these nodes. The pre-trained correction model can be a regression model or a deep learning model established based on historical lightning current data and attenuation characteristics. The model can effectively correct the measurement results of low-confidence nodes. The parameter updating process can use the gradient descent algorithm in supervised learning to optimize the parameters in the correction model to ensure that it better adapts to the actual situation; then, the updated model is used to correct the lightning current of the selected lightning monitoring node to obtain the corrected lightning current of the node. This process can be performed on the remaining lightning monitoring nodes one by one to gradually improve the credibility of the lightning current data of all monitoring nodes; it should be noted that the present application scheme effectively combines the adjacent relationship and attenuation response characteristics of multiple nodes, improves the measurement accuracy of lightning current through model correction, and is particularly suitable for effective correction when the data of some nodes are unreliable.

[0098] It should be noted that the method for determining the monitoring threshold in the present application can be implemented through the following steps: first, analyze the statistical characteristics of historical lightning current data (such as mean, standard deviation, etc.) to identify the normal range and abnormal data boundaries, and use the boundary value as the initial threshold; then, combine empirical rules or expert systems to adjust the initial threshold according to sensor characteristics and environmental factors; finally, use the adjusted initial threshold as the monitoring threshold of the present application scheme. In other embodiments, the method for determining the monitoring threshold can also be implemented in other ways, which are not limited here.

[0099] On the other hand, in some embodiments, the present application provides a lightning protection intelligent monitoring system in a distribution network, referring to Figure 4 , which is a structural schematic diagram of a lightning protection intelligent monitoring system in a distribution network according to some embodiments of the present application, the lightning protection intelligent monitoring system 400 in the distribution network includes: a monitoring module 401, a processing module 402 and a positioning module 403, which are respectively described as follows:

[0100] Monitoring module 401, in this application, the monitoring module 401 is mainly used to perform distributed sensing monitoring of lightning current in the target distribution network, and obtain the lightning current of each lightning monitoring node in the target distribution network;

[0101] Processing module 402, in the present application, the processing module 402 is used to extract the transient energy of the polarity current from the lightning current of each lightning monitoring node, and then determine the cross-correlation between all transient energies, and based on the fuzzy evaluation mechanism, perform state response evaluation on the lightning current of each lightning monitoring node according to the cross-correlation to obtain the monitoring confidence of the lightning current of each lightning monitoring node;

[0102] The processing module 402 in the present application is also used to obtain the historical lightning current of each lightning monitoring node in the target distribution network, and then determine the timing dependency of the lightning current between every two adjacent lightning monitoring nodes based on all the historical lightning currents, and determine the response characteristics of the lightning current attenuation between every two adjacent lightning monitoring nodes through all the timing dependencies and the topological structure of the target distribution network;

[0103] Positioning module 403. In the present application, positioning module 403 is mainly used to perform confidence correction on the lightning strike current of each lightning monitoring node according to the monitoring confidence of the lightning strike current of each lightning monitoring node and all response characteristics, obtain the corrected lightning strike current, and locate the lightning strike location based on all the corrected lightning strike currents.

[0104] In addition, the present application also provides a computer device, which includes a memory and a processor, the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned intelligent lightning protection monitoring method in the distribution network.

[0105] In some embodiments, reference Figure 5 , which is a schematic diagram of the structure of a computer device for implementing a lightning protection intelligent monitoring method in a distribution network according to some embodiments of the present application. The lightning protection intelligent monitoring method in a distribution network in the above embodiment can be Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503 and at least one communication interface 504.

[0106] The processor 501 may be a general-purpose central processing unit (CPU) or an application-specific integrated circuit (ASIC).

[0107] The communication bus 502 may be used to transmit information between the above-mentioned components.

[0108] The memory 503 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 503 may exist independently and be connected to the processor 501 via the communication bus 502. The memory 503 may also be integrated with the processor 501.

[0109] The memory 503 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the program code stored in the memory 503. The program code may include one or more software modules. The intelligent monitoring method for lightning protection in the distribution network in the above embodiment can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0110] The communication interface 504 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0111] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-CPU processor or a multi-CPU processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0112] The above-mentioned computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.

[0113] In addition, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned intelligent lightning protection monitoring method in the distribution network is implemented.

[0114] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0115] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A lightning protection intelligent monitoring method in a distribution network, characterized in that: The steps include: Perform distributed sensing and monitoring on the lightning current in the target distribution network to obtain the lightning current of each lightning monitoring node in the target distribution network; Extracting the transient energy of the polarity current from the lightning current of each lightning monitoring node, and then determining the cross-correlation between all transient energies, and based on the fuzzy evaluation mechanism, performing a state response evaluation on the lightning current of each lightning monitoring node according to the cross-correlation, and obtaining the monitoring confidence of the lightning current of each lightning monitoring node; Obtain the historical lightning current of each lightning monitoring node in the target distribution network, and then determine the timing dependency of the lightning current between every two adjacent lightning monitoring nodes based on all the historical lightning currents, and determine the response characteristics of the lightning current attenuation between every two adjacent lightning monitoring nodes through all the timing dependencies and the topological structure of the target distribution network; According to the monitoring confidence of the lightning current of each lightning monitoring node and all the response characteristics, the lightning current of each lightning monitoring node is confidence corrected to obtain the corrected lightning current, and the lightning strike location is located based on all the corrected lightning currents.

2. The method according to claim 1, characterized in that The transient energy of polarity current extracted from the lightning current of each lightning monitoring node specifically includes: For each lightning monitoring node, a positive polarity current and a negative polarity current are extracted from the lightning strike current of the lightning monitoring node; Performing short-time Fourier transform on the positive polarity current and the negative polarity current respectively to extract energy distribution of the lightning current in the frequency domain; The transient energy of the polarity current at the lightning monitoring node is determined by the energy distribution, and then the transient energy of the polarity current at each lightning monitoring node is obtained.

3. The method according to claim 1, characterized in that Determining the cross-correlation between all transient energies specifically includes: For every two lightning monitoring nodes, the Pearson correlation coefficient of the transient energy between the two lightning monitoring nodes is determined according to the transient energy of the polarity current at the two lightning monitoring nodes, and then the Pearson correlation coefficient of the transient energy between every two lightning monitoring nodes is obtained; The cross-correlations between all transient energies were determined by all Pearson correlation coefficients.

4. The method according to claim 1, characterized in that Based on the fuzzy evaluation mechanism, the state response evaluation of the lightning current of each lightning monitoring node is performed according to the mutual correlation, and the monitoring confidence of the lightning current of each lightning monitoring node is obtained, which specifically includes: Initialize the membership of each lightning monitoring node's monitoring behavior; Constructing a mutual correlation matrix of monitoring behaviors among all lightning monitoring nodes according to the mutual correlation; Mapping the values ​​in the mutual correlation matrix into fuzzy sets through fuzzy membership functions; Constructing a fuzzy evaluation matrix according to all initialized membership degrees and the fuzzy set; Based on the fuzzy evaluation matrix, a fuzzy evaluation is performed on the response behavior state of each lightning monitoring node in monitoring the lightning current, so as to obtain the monitoring confidence of the lightning current of each lightning monitoring node.

5. The method according to claim 1, characterized in that The timing dependency relationship of the lightning current between each two adjacent lightning monitoring nodes is determined based on all historical lightning currents, specifically including: Performing time alignment on all historical lightning currents to obtain all aligned historical lightning currents; Convert all aligned historical lightning currents into lightning current sequences of each lightning monitoring node; Based on the cross-correlation function, the time sequence dependency of the lightning currents between every two adjacent lightning monitoring nodes is determined through the lightning current sequences of every two adjacent lightning monitoring nodes.

6. The method according to claim 1, characterized in that The response characteristics of the lightning current attenuation between each two adjacent lightning monitoring nodes are determined through all the timing dependencies and the topological structure of the target distribution network, including: The topological structure of the target distribution network is determined through the location information of each lightning monitoring node and the electrical connection relationship between each lightning monitoring node; Construct an exponential decay model of lightning current based on all timing dependencies; Setting the topology of the target distribution network as a constraint parameter of the exponential decay model; The exponential decay model is used to simulate the attenuation process of the lightning current between every two adjacent lightning monitoring nodes, and then the response characteristics of the lightning current attenuation between every two adjacent lightning monitoring nodes are extracted from the simulation results.

7. The method according to claim 1, characterized in that The lightning current of the lightning monitoring node is collected using the Rogowski coil current.

8. An intelligent lightning protection monitoring system in a distribution network, characterized in that: include: A monitoring module is used to perform distributed sensing monitoring of lightning current in the target distribution network to obtain the lightning current of each lightning monitoring node in the target distribution network; A processing module, used to extract the transient energy of the polarity current from the lightning current of each lightning monitoring node, and then determine the cross-correlation between all transient energies, and based on the fuzzy evaluation mechanism, perform a state response evaluation on the lightning current of each lightning monitoring node according to the cross-correlation to obtain the monitoring confidence of the lightning current of each lightning monitoring node; The processing module is further used to obtain the historical lightning current of each lightning monitoring node in the target distribution network, and then determine the timing dependency of the lightning current between every two adjacent lightning monitoring nodes based on all the historical lightning currents, and determine the response characteristics of the lightning current attenuation between every two adjacent lightning monitoring nodes through all the timing dependencies and the topological structure of the target distribution network; The positioning module is used to perform confidence correction on the lightning current of each lightning monitoring node according to the monitoring confidence of the lightning current of each lightning monitoring node and all response characteristics to obtain the corrected lightning current, and locate the lightning strike location based on all the corrected lightning currents.

9. A computer device, comprising a memory and a processor, wherein the memory stores a code, characterized in that: The processor is configured to obtain the code and execute the intelligent monitoring method for lightning protection in a distribution network according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the intelligent monitoring method for lightning protection in a distribution network as described in any one of claims 1 to 7 is implemented.

Images