Intelligent leakage current real-time monitoring and diagnosis system and method

Abstract

The invention relates to the technical field of electrical variable measurement, in particular to an intelligent leakage current real-time monitoring and diagnosis system and method, and the method comprises the steps: obtaining a real-time current signal of a target regional power grid and a corresponding current signal timestamp, and carrying out the intelligent processing of a real-time electric signal, and obtaining a corresponding current signal sequence; performing wavelet packet transformation and intelligent processing on the current signal sequence to obtain a current signal sub-sequence; for each current signal sub-sequence dynamic window sequence set, intelligent feature analysis is carried out on the dynamic window sequence set, and steady-state features and transient-state features of the current signals are obtained; and establishing a current diagnosis model, and performing diagnosis and early warning on the real-time current based on the current diagnosis model. According to the method, the problem of missing detection or false alarm caused by decomposition of a single frequency band, difficulty in accurately distinguishing high-frequency transient noise and low-frequency steady-state abnormity is solved, the threshold value is adjusted according to the actual risk duration, real-time dynamic prediction is realized, and the health management level of a regional power grid is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of measuring electrical variables, and particularly relates to an intelligent leakage current real-time monitoring and diagnosis system and method. Background Art

[0002] With the accelerating development of electrification, the number of electrical equipment connected to the industrial regional power grid has increased sharply, resulting in an increase in the risk of leakage. Therefore, it is necessary to monitor and diagnose the current of the power grid to prevent leakage. At the same time, leakage monitoring and diagnosis is the "first line of defense" for the safe operation of the industrial regional power grid, and it is also a key technology to improve energy efficiency, reduce operation and maintenance costs, and promote the healthy management level of the industrial regional power grid.

[0003] In the existing technology, traditional methods mostly use single-band decomposition, which is difficult to accurately distinguish high-frequency transient noise from low-frequency steady-state abnormalities, resulting in missed detections or false alarms. Moreover, traditional systems rely on fixed thresholds or static models and cannot capture the dynamic changes of current signals in real time, with early warning delays or poor adaptability. It is difficult for traditional methods to distinguish the environmental noise caused by the start and stop of electrical equipment from leakage signals, and the healthy management level of the regional power grid is poor. Summary of the Invention

[0004] The purpose of the present invention is to propose an intelligent leakage current real-time monitoring and diagnosis system and method for the problems existing in the background art.

[0005] The technical solution of the present invention: An intelligent leakage current real-time monitoring and diagnosis method includes the following steps:

[0006] Obtain the real-time current signal of the target regional power grid and the corresponding current signal timestamp, and perform intelligent processing on the real-time electrical signal to obtain the corresponding current signal sequence;

[0007] Perform wavelet packet transform processing on the current signal sequence, decompose the current signal processing sequence into current signal subsequences of different frequency bands, and perform intelligent processing on the current signal subsequences to obtain the current signal subsequences;

[0008] Establish a dynamic window for each current signal subsequence, mark the current signal subsequence located at the center of the dynamic window as the central sequence C, use the current signal subsequences included in the dynamic window as the dynamic sequence of the central sequence C, establish a dynamic window sequence set, and perform intelligent feature analysis on the dynamic window sequence set to obtain the steady-state feature Sav and transient feature Tsv of the current signal;

[0009] Establish a current diagnosis model based on the steady-state analysis value Sav and transient risk value Tsv, and diagnose and give early warnings to the real-time current based on the current diagnosis model.

[0010] Preferably, the wavelet packet transform processing of the current signal processing sequence includes:

[0011] Select a first decomposition level, and decompose the current signal processing sequence into a number of first current signal subsequences with a first frequency band width based on the first decomposition level;

[0012] Select a second decomposition level, and decompose the current signal processing sequence into a number of second current signal subsequences with a second frequency band width based on the second decomposition level;

[0013] The first decomposition level is less than the second decomposition level.

[0014] Preferably, the method for intelligent feature analysis of the dynamic window sequence set is:

[0015] Obtain the rated current of the historical electrical equipment of the intervention current signal and the corresponding historical current signal sequence, perform intelligent analysis on the historical electrical equipment information and the historical current signal sequence, and determine the fitting degree of the electrical equipment information to the current signal sequence;

[0016] The method for intelligent analysis of the historical electrical equipment information and the historical current signal sequence is:

[0017] Decompose the historical current signal sequence based on the first decomposition level to obtain historical subsequences, obtain the average current of the acquisition points of each historical subsequence, and calculate the current standard deviation of each historical subsequence based on the current values of the sampling points of each historical subsequence, and obtain the degree of dispersion of the current at the acquisition points of each historical subsequence.

[0018] Preferably, calculate the difference between the current standard deviations of adjacent historical subsequences, establish a sequence of the differences between the current standard deviations of historical subsequences, traverse the sequence of the differences between the current standard deviations of historical subsequences, mark the elements in the sequence of the differences between the current standard deviations of historical subsequences that are less than the standard deviation threshold as target elements, and identify the continuity of a number of target elements;

[0019] Number the elements of the sequence of the differences between the current standard deviations. If there are at least m consecutive numbers of target elements, it is determined that the consecutive target elements have continuity, and the target element with the smallest number is marked as the selected element;

[0020] Mark the historical subsequence corresponding to the current standard deviation with the calculated selected element as the subtractor as the target sequence. For the historical current signal sequence, perform segmentation at the starting sequence of the target sequence to obtain two segmented sequences, delete the segmented sequence to which the target sequence belongs, and use the remaining segmented sequence as the noise sequence N.

[0021] Preferably, process the noise sequence N:

[0022] Obtain the extreme values of each historical subsequence in the noise sequence N, and calculate the absolute value and mean of the extreme values of each historical subsequence to obtain the average energy value of the subsequence;

[0023] Through the formula Calculate the goodness of fit Gof between the noise sequence N and the rated current of the electrical equipment;

[0024] In the formula, |E i | is the average energy value of each historical subsequence; i is the historical subsequence number, i = [1, 2,..., n], and n is the total number of historical subsequences; represents the standard deviation of the average energy value of the noise sequence N; Pc is the rated current of the electrical equipment; t is the sequence duration of the noise sequence N; λ1 and λ2 are the weight coefficients of the standard deviation of the average energy value and the sequence duration, respectively, obtained based on historical big data testing.

[0025] Preferably, the method for intelligent feature analysis of the dynamic window sequence set further includes intelligent processing of the first current signal subsequence, and the method is as follows:

[0026] Obtain the average current and average electrical signal frequency of the central sequence C respectively, as well as the average current and average electrical signal frequency of the first k acquisition periods and the last k acquisition periods before and after the central sequence C, and perform normalization processing on the average current, rated current, and average electrical signal frequency, and calculate the steady-state analysis value of the dynamic window based on the steady-state analysis model. The expression of the steady-state analysis model is:

[0027]

[0028] In the formula, Sav is the steady-state analysis value of the dynamic window; If j and Ff j are the average current and average electrical signal frequency of the first j acquisition periods of the central sequence C respectively, Ib (k-j) and Fb (k-j) are the average current and average electrical signal frequency of the last k - j acquisition periods of the central sequence C respectively; j is the acquisition period number, j = [1, 2,..., k]; Im and Fm are the average current and average electrical signal frequency of the central sequence C respectively.

[0029] Preferably, the method for intelligent feature analysis of the dynamic window sequence set further includes intelligent processing of the second current signal subsequence, and the method is as follows:

[0030] Obtain the risk sequence of the previous risk period when leakage protection occurs in the historical current signal sequence, determine a number of risk sequences, and use the instantaneous frequency and instantaneous current as the first transient parameter and the second transient parameter of the risk sequence; obtain the first transient parameter and the second transient parameter corresponding to all acquisition points in the risk sequence to obtain the first transient parameter set and the second transient parameter set;

[0031] Perform parameter analysis on the same transient parameter set, and the method is as follows:

[0032] Calculate the mean value of the transient parameters of the last acquisition point of several risk sequences as the risk parameter of the transient parameter set;

[0033] Sort the transient parameters in the same transient parameter set in ascending order to obtain a parameter sorting sequence, and based on the second decomposition layer number, split the parameter sorting sequence to obtain several parameter sorting subsequences with the same number as the second decomposition layer number, and obtain the values in the parameter sorting subsequences;

[0034] Count the number of transient parameters included in each parameter sorting subsequence to obtain the total number of transient parameters in the subsequence. Based on the values in the parameter sorting subsequence and the total number of transient parameters in the subsequence, use the weighted average algorithm to calculate the weighted average parameter in the transient parameter set and use it as the abnormal parameter;

[0035] Use the interpolation algorithm to obtain the time point corresponding to the weighted average parameter in the risk sequence and mark it as the target acquisition point, obtain the rated power of the electrical equipment corresponding to the target acquisition point and mark it as the corrected power, and the interval duration from the time point corresponding to the target acquisition point to the end time point of the risk period, and use it as the risk duration corresponding to the abnormal parameter of the risk sequence;

[0036] Based on the above method of performing parameter analysis on the same transient parameter set, respectively obtain the abnormal parameters and risk durations corresponding to the first transient parameter set and the second parameter set, and mark them as the first risk parameter, the second risk parameter, the first abnormal parameter, the second abnormal parameter, the first risk duration, and the second risk duration respectively.

[0037] Preferably, determine the real-time current and real-time electrical signal frequency based on the second current signal subsequence and use them as the first real-time parameter and the second real-time parameter, and obtain the corresponding real-time electrical equipment power; if any real-time parameter reaches the corresponding risk parameter, then count the actual risk duration of the corresponding real-time parameter, and respectively obtain the first actual risk duration corresponding to the first transient parameter set and the second actual risk duration corresponding to the second transient parameter set;

[0038] Through the formula Calculate the transient risk value Tsv of the second current signal subsequence;

[0039] In the formula, I tis the real-time current; F t is the real-time frequency; I1 is the first abnormal parameter; F1 is the second abnormal parameter; T I is the first actual risk duration; T F is the second actual risk duration; T t is the actual risk duration; min() is the minimum comparison function; P t is the real-time electrical equipment power; P1 is the corrected power.

[0040] Preferably, the method for establishing a current diagnosis model based on the steady-state analysis value Sav and the transient risk value Tsv is as follows:

[0041] Compare the steady-state analysis value Sav of the current first current signal subsequence with the preset steady-state threshold S0;

[0042] If Sav > S0, it is determined that the steady-state characteristic of the real-time current is abnormal and a first abnormal label is generated; otherwise, no operation is performed;

[0043] And compare the transient risk value Tsv of the current second current signal subsequence with the preset transient threshold T0;

[0044] If Tsv ≤ 0.8T0, no operation is performed; if 0.8T0 < Tsv ≤ T0, the current second current signal subsequence is marked as an abnormal subsequence, and it is judged whether there are at least z consecutive abnormal subsequences; if there are at least z consecutive abnormal subsequences, it is judged that the transient characteristic of the real-time current is first abnormal and a second abnormal label is generated; if there are not at least z consecutive abnormal subsequences, no operation is performed;

[0045] If T0 < Tsv, it is judged that the transient characteristic of the real-time current is second abnormal and a third abnormal label is generated;

[0046] According to the first abnormal label, the second abnormal label and the third abnormal label, it is determined that there is a leakage phenomenon, and the technical personnel are notified for maintenance.

[0047] The present invention also discloses an intelligent leakage current real-time monitoring and diagnosis system, which applies the above-mentioned intelligent leakage current real-time monitoring and diagnosis method, and specifically includes:

[0048] A data acquisition module, configured to obtain the real-time current signal of the power grid in the target area and the corresponding current signal timestamp, and perform intelligent processing on the real-time electrical signal to obtain the corresponding current signal sequence;

[0049] A data preprocessing module, configured to perform wavelet packet transform processing on the current signal sequence, decompose the current signal processing sequence into current signal subsequences of different frequency bands, and perform intelligent processing on the current signal subsequences to obtain the current signal subsequences;

[0050] A data analysis module is used to establish a dynamic window for each current signal subsequence, mark the current signal subsequence located at the center of the dynamic window as the central sequence C, use the current signal subsequences included in the dynamic window as the dynamic sequences of the central sequence C to establish a dynamic window sequence set, perform intelligent feature analysis on the dynamic window sequence set, and obtain the steady-state feature Sav and transient feature Tsv of the current signal;

[0051] An intelligent monitoring and diagnosis module is used to establish a current diagnosis model based on the steady-state analysis value Sav and transient risk value Tsv, and diagnose and give early warnings to the real-time current based on the current diagnosis model.

[0052] Compared with the prior art, the above technical solution of the present invention has the following beneficial technical effects:

[0053] (1) By combining the first decomposition layer number and the second decomposition layer number, the current signal is decomposed into subsequences of different frequency bands, significantly improving the frequency band resolution. Based on the dynamic window sequence analysis, a dynamic window is established for each subsequence, and by combining the steady-state feature and transient risk value of the central sequence, accurate separation of high-frequency transients and low-frequency steady-state signals is achieved, solving the problem of difficult accurate distinction between high-frequency transient noise and low-frequency steady-state anomalies in single-band decomposition, resulting in missed detections or false alarms, and improving the health management level of the regional power grid;

[0054] (2) Through the real-time update and analysis of the dynamic window sequence set, combined with the average current and frequency of the previous and next k acquisition periods, current fluctuations are quickly identified: based on the transient parameters of the historical risk sequence and the weighted average algorithm, the transient risk value is dynamically generated, and the threshold is adjusted according to the actual risk duration to achieve real-time dynamic prediction, solving the problems of early warning delay or poor adaptability caused by relying on fixed thresholds and static models;

[0055] (3) According to the threshold comparison of the steady-state analysis value and the transient risk value, a hierarchical anomaly label is generated, and combined with the judgment of continuous z abnormal subsequences, the false alarm rate is reduced, and multi-dimensional accurate diagnosis of the leakage phenomenon is achieved. Description of the Drawings

[0056] Figure 1 It is a flowchart of the first embodiment proposed by the present invention. Detailed Embodiments

[0057] Embodiment 1, as Figure 1 shown, an intelligent real-time monitoring and diagnosis method for leakage current proposed by the present invention includes the following methods:

[0058] Obtain the real-time current signal of the target regional power grid and the corresponding current signal timestamp, and perform intelligent processing on the real-time electrical signal to obtain the corresponding current signal sequence;

[0059] Perform wavelet packet transform processing on the current signal sequence, decompose the current signal processing sequence into current signal subsequences in different frequency bands, and perform intelligent processing on the current signal subsequences to obtain the current signal subsequences;

[0060] Establish a dynamic window for each current signal subsequence, mark the current signal subsequence located at the center of the dynamic window as the central sequence C, use the current signal subsequences included in the dynamic window as the dynamic sequence of the central sequence C, establish a dynamic window sequence set, and perform intelligent feature analysis on the dynamic window sequence set to obtain the steady-state and transient features of the current signal;

[0061] Performing wavelet packet transform processing on the current signal processing sequence includes:

[0062] Select the first decomposition level, and decompose the current signal processing sequence into several first current signal subsequences with a frequency band width of the first frequency band based on the first decomposition level;

[0063] Select the second decomposition level, and decompose the current signal processing sequence into several second current signal subsequences with a frequency band width of the second frequency band based on the second decomposition level;

[0064] The first decomposition level is less than the second decomposition level;

[0065] The method for performing intelligent feature analysis on the dynamic window sequence set is:

[0066] Obtain the rated current of the historical electrical equipment of the intervention current signal and the corresponding historical current signal sequence, perform intelligent analysis on the historical electrical equipment information and the historical current signal sequence, and determine the fitting degree of the electrical equipment information to the current signal sequence;

[0067] The method for performing intelligent analysis on the historical electrical equipment information and the historical current signal sequence is:

[0068] Decompose the historical current signal sequence based on the first decomposition level to obtain historical subsequences, obtain the average current at the acquisition points of each historical subsequence, and calculate the current standard deviation of the historical subsequence based on the current values at the sampling points of each historical subsequence to obtain the degree of dispersion of the current at the acquisition points of each historical subsequence;

[0069] Calculate the difference in current standard deviation between adjacent historical subsequences, establish a sequence of differences in current standard deviation of historical subsequences, traverse the sequence of differences in current standard deviation of historical subsequences, mark the elements in the sequence of differences in current standard deviation of historical subsequences that are less than the standard deviation threshold as target elements, and identify the continuity of several target elements;

[0070] Number the elements of the current standard deviation difference sequence. If there are at least m consecutive numbers of target elements, it is determined that the consecutive target elements have continuity, and the target element with the smallest number is marked as the selected element;

[0071] Mark the historical subsequence corresponding to the current standard deviation with the calculated selected element as the minuend as the target sequence. Split the historical current signal sequence at the starting sequence of the target sequence to obtain two split sequences. Delete the split sequence to which the target sequence belongs, and use the remaining split sequence as the noise sequence N;

[0072] Process the noise sequence N:

[0073] Obtain the extreme values of each historical subsequence in the noise sequence N, and calculate the absolute value and mean of the extreme values of each historical subsequence to obtain the average energy value of the historical subsequence; It should be noted that the extreme values of the historical subsequence are the maximum and minimum values within a short sequence length, and there can be multiple extreme values of the historical subsequence;

[0074] Through the formula Calculate the goodness of fit Gof between the noise sequence N and the rated current of the electrical equipment;

[0075] In the formula, |E i | is the average energy value of each historical subsequence; i is the historical subsequence number, i = [1, 2,..., n], and n is the total number of historical subsequences; Represents the standard deviation of the average energy value of the noise sequence N; Pc is the rated current of the electrical equipment; t is the sequence duration of the noise sequence N; λ1 and λ2 are the weight coefficients of the standard deviation of the average energy value and the sequence duration, respectively, obtained based on historical big data testing;

[0076] The method for intelligent feature analysis of the dynamic window sequence set also includes intelligent processing of the first current signal subsequence. The method is as follows:

[0077] Obtain the average current and average electrical signal frequency of the center sequence C, respectively, as well as the average current and average electrical signal frequency of the first k acquisition periods and the last k acquisition periods before and after the center sequence C, and perform normalization processing on the average current, rated current, and average electrical signal frequency. Calculate the steady-state analysis value of the dynamic window based on the steady-state analysis model. The expression of the steady-state analysis model is:

[0078]

[0079] In the formula, Sav is the steady-state analysis value of the dynamic window; If j and Ff j Are the average current and average electrical signal frequency of the first j acquisition periods of the center sequence C, respectively, Ib (k-j)and Fb (k-j) are respectively the average current and the average electrical signal frequency of the last k - j acquisition periods of the central sequence C; j is the number of the acquisition period, j = [1, 2, ……, k]; Im and Fm are respectively the average current and the average electrical signal frequency of the central sequence C;

[0080] The method for intelligent feature analysis of the dynamic window sequence set also includes intelligent processing of the second current signal subsequence, and the method is as follows:

[0081] Obtain the risk sequence of the previous risk period that generates leakage protection in the historical current signal sequence, determine a number of risk sequences, and use the instantaneous frequency and the instantaneous current as the first transient parameter and the second transient parameter of the risk sequence; obtain the first transient parameter and the second transient parameter corresponding to all acquisition points in the risk sequence to obtain the first transient parameter set and the second transient parameter set;

[0082] Perform parameter analysis on the same transient parameter set, and the method is as follows:

[0083] Calculate the mean value of the transient parameters of the last acquisition point of a number of risk sequences as the risk parameter of the transient parameter set;

[0084] Sort the transient parameters in the same transient parameter set in ascending order to obtain a parameter sorting sequence, perform sequence splitting on the parameter sorting sequence based on the second decomposition level to obtain a number of parameter sorting subsequences with the same number as the second decomposition level, and obtain the values in the parameter sorting subsequences;

[0085] Count the number of transient parameters included in each parameter sorting subsequence to obtain the total number of transient parameters in the subsequence. Based on the value in the parameter sorting subsequence and the total number of transient parameters in the subsequence, use the weighted average algorithm to calculate the weighted average parameter in the transient parameter set and use it as the abnormal parameter;

[0086] Use the interpolation algorithm to obtain the time point corresponding to the weighted average parameter in the risk sequence and mark it as the target acquisition point, obtain the rated power of the electrical equipment corresponding to the target acquisition point and mark it as the corrected power, and obtain the interval duration from the time point corresponding to the target acquisition point to the end time point of the risk period and use it as the risk duration corresponding to the abnormal parameter of the risk sequence;

[0087] Based on the above method for parameter analysis of the same transient parameter set, obtain the abnormal parameters and risk durations corresponding to the first transient parameter set and the second parameter set respectively, and mark them as the first risk parameter, the second risk parameter, the first abnormal parameter, the second abnormal parameter, the first risk duration, and the second risk duration respectively;

[0088] Determine the real-time current and the real-time electrical signal frequency based on the second current signal subsequence and use them as the first real-time parameter and the second real-time parameter, and obtain the corresponding real-time electrical equipment power; if any real-time parameter reaches the corresponding risk parameter, then count the actual risk duration of the corresponding real-time parameter, and respectively obtain the first actual risk duration corresponding to the first transient parameter set and the second actual risk duration corresponding to the second transient parameter set;

[0089] Through the formula Calculate the transient risk value Tsv of the second current signal subsequence;

[0090] In the formula, I t Is the real-time current; F t Is the real-time frequency; I1 is the first abnormal parameter; F1 is the second abnormal parameter; T I Is the first actual risk duration; T F Is the second actual risk duration; T t Is the actual risk duration; min() is the minimum value comparison function; P t Is the real-time electrical equipment power; P1 is the corrected power;

[0091] Establish a current diagnosis model based on the steady-state analysis value Sav and the transient risk value Tsv, and diagnose and give an early warning for the real-time current based on the current diagnosis model;

[0092] The method for establishing a current diagnosis model based on the steady-state analysis value Sav and the transient risk value Tsv is as follows:

[0093] Compare the steady-state analysis value Sav of the current first current signal subsequence with the preset steady-state threshold S0;

[0094] If Sav > S0, it is determined that the steady-state characteristic of the real-time current is abnormal and a first abnormal label is generated; otherwise, no operation is performed;

[0095] And compare the transient risk value Tsv of the current second current signal subsequence with the preset transient threshold T0;

[0096] If Tsv ≤ 0.8T0, no operation is performed; if 0.8T0 < Tsv ≤ T0, mark the current second current signal subsequence as an abnormal subsequence, and determine whether there is at least a continuous number z of abnormal subsequences; if there is at least a continuous number z of abnormal subsequences, then determine that the transient characteristic of the real-time current is first abnormal and generate a second abnormal label; if there is no at least a continuous number z of abnormal subsequences, no operation is performed; it should be noted that z is specifically obtained according to the big data analysis situation; for example, if z takes the value of 2, it means that if there is at least a continuous number of 2 abnormal subsequences, it is determined that the transient characteristic of the real-time current is first abnormal;

[0097] If T0 < Tsv, then determine that the second anomaly of the real-time current transient feature occurs and generate a third anomaly label.

[0098] Based on the first anomaly label, the second anomaly label, and the third anomaly label, determine that there is a leakage phenomenon and notify the technical personnel for maintenance.

[0099] Embodiment 2. An intelligent leakage current real-time monitoring and diagnosis system proposed by the present invention is applied to an intelligent leakage current real-time monitoring and diagnosis method proposed in Embodiment 1, and specifically includes:

[0100] A data acquisition module, configured to obtain the real-time current signal of the power grid in the target area and the corresponding current signal timestamp, and perform intelligent processing on the real-time electrical signal to obtain the corresponding current signal sequence.

[0101] A data preprocessing module, configured to perform wavelet packet transform processing on the current signal sequence, decompose the current signal processing sequence into current signal subsequences in different frequency bands, and perform intelligent processing on the current signal subsequences to obtain the current signal subsequences.

[0102] A data analysis module, configured to establish a dynamic window for each current signal subsequence, and mark the current signal subsequence located at the center of the dynamic window as the center sequence C. Use the current signal subsequences included in the dynamic window as the dynamic sequence of the center sequence C to establish a dynamic window sequence set, and perform intelligent feature analysis on the dynamic window sequence set to obtain the steady-state feature Sav and transient feature Tsv of the current signal.

[0103] An intelligent monitoring and diagnosis module, configured to establish a current diagnosis model based on the steady-state analysis value Sav and the transient risk value Tsv, and diagnose and give an early warning for the real-time current based on the current diagnosis model.

[0104] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited thereto. Within the knowledge scope of those skilled in the art to which the present invention pertains, various changes can be made without departing from the purpose of the present invention.

Claims

1. An intelligent leakage current real-time monitoring and diagnosis method, characterized in that: include Obtain the real-time current signal of the target area power grid and the corresponding current signal timestamp, and perform intelligent processing on the real-time electrical signal to obtain the corresponding current signal sequence; Performing wavelet packet transform processing on the current signal sequence, decomposing the current signal sequence into current signal subsequences of different frequency bands, and performing intelligent processing on the current signal subsequences to obtain current signal subsequences; A dynamic window is established for each current signal subsequence, and the current signal subsequence located at the center of the dynamic window is marked as the center sequence C. The current signal subsequence contained in the dynamic window is taken as the center sequence C dynamic sequence, and a dynamic window sequence set is established. The dynamic window sequence set is subjected to intelligent feature analysis to obtain the steady-state feature Sav and transient feature Tsv of the current signal. A current diagnosis model is established based on the steady-state analysis value Sav and the transient risk value Tsv, and the real-time current is diagnosed and warned based on the current diagnosis model.

2. The intelligent real-time monitoring and diagnosis method for leakage current according to claim 1 is characterized in that: The wavelet packet transform processing of the current signal processing sequence includes: Selecting a first decomposition layer number, and decomposing the current signal processing sequence into a plurality of first current signal subsequences having a frequency band width of a first frequency band based on the first decomposition layer number; Selecting a second decomposition layer number, and decomposing the current signal processing sequence into a plurality of second current signal subsequences having a frequency band width of a second frequency band based on the second decomposition layer number; The first decomposition level is smaller than the second decomposition level.

3. The intelligent real-time monitoring and diagnosis method for leakage current according to claim 2 is characterized in that: The method for intelligent feature analysis of dynamic window sequence set is: Obtain the rated current of the historical electrical equipment intervening the current signal and the corresponding historical current signal sequence, perform intelligent analysis on the historical electrical equipment information and the historical current signal sequence, and determine the fitting degree of the electrical equipment information to the current signal sequence; The method for intelligent analysis of historical electrical equipment information and historical current signal sequences is: The historical current signal sequence is decomposed based on the first decomposition layer to obtain historical subsequences, the current mean of the sampling point of each historical subsequence is obtained, and the current standard deviation is calculated based on the current value of the sampling point of each historical subsequence to obtain the discrete degree of the current of the sampling point of each historical subsequence.

4. The intelligent real-time monitoring and diagnosis method for leakage current according to claim 3 is characterized in that: Calculate the current standard deviation difference of adjacent historical subsequences, establish the current standard deviation difference sequence of historical subsequences, traverse the current standard deviation difference sequence of historical subsequences, mark the elements in the current standard deviation difference sequence of historical subsequences that are less than the standard deviation threshold as target elements, and identify the continuity of several target elements; Numbering the elements of the current standard deviation difference sequence, if there are at least m target elements with consecutive numbers, it is determined that several target elements with consecutive numbers are continuous, and the target element with the smallest number is marked as the selected element; The historical subsequence corresponding to the current standard deviation of the selected element calculated and used as the subtrahend is marked as the target sequence. The historical current signal sequence is segmented at the starting sequence of the target sequence to obtain two segmented sequences. The segmented sequence to which the target sequence belongs is deleted, and the remaining segmented sequence is used as the noise sequence N.

5. The intelligent real-time monitoring and diagnosis method for leakage current according to claim 4 is characterized in that: Process the noise sequence N: Obtain the extreme value of each historical subsequence in the noise sequence N, and calculate the absolute value and mean of the extreme value of each historical subsequence to obtain the average energy value of the historical subsequence; By formula The fitting degree Gof between the noise sequence N and the rated current of the electrical equipment is calculated; In the formula, |E i |The average energy value for each historical subsequence; i is the historical subsequence number, i = [1, 2, ..., n], n is the total number of historical subsequences; represents the standard deviation of the average energy value of the noise sequence N; Pc is the rated current of the electrical equipment; t is the sequence length of the noise sequence N; λ1 and λ2 are the weight coefficients of the standard deviation of the average energy value and the sequence length, respectively, which are obtained based on historical big data testing.

6. The intelligent real-time monitoring and diagnosis method for leakage current according to claim 5 is characterized in that: The method for performing intelligent feature analysis on the dynamic window sequence set also includes performing intelligent processing on the first current signal subsequence, as follows: The average current and average electrical signal frequency of the central sequence C, as well as the average current and average electrical signal frequency of the first k acquisition periods and the last k acquisition periods of the central sequence C are obtained respectively, and the average current, rated current and average electrical signal frequency are normalized. The steady-state analysis value of the dynamic window is calculated based on the steady-state analysis model. The expression of the steady-state analysis model is: Where Sav is the steady-state analysis value of the dynamic window; If j and Ff j are the average current and average electrical signal frequency of the first j acquisition periods of the central sequence C, Ib (k-j) and Facebook (k-j) are the average current and average electrical signal frequency of the last kj acquisition periods of the central sequence C respectively; j is the number of the acquisition period, j=[1, 2, ..., k]; Im and Fm are the average current and average electrical signal frequency of the central sequence C respectively.

7. The intelligent real-time monitoring and diagnosis method for leakage current according to claim 5, characterized in that: The method for performing intelligent feature analysis on the dynamic window sequence set also includes performing intelligent processing on the second current signal subsequence, as follows: Obtaining a risk sequence of a previous risk period in which leakage protection is generated in a historical current signal sequence, determining a number of risk sequences, and using an instantaneous frequency and an instantaneous current as a first transient parameter and a second transient parameter of the risk sequence; Acquire the first transient parameters and the second transient parameters corresponding to all acquisition points in the risk sequence to obtain a first transient parameter set and a second transient parameter set; Perform parameter analysis on the same transient parameter set as follows: Calculate the mean value of the transient parameters of the last acquisition point of several risk sequences as the risk parameter of the transient parameter set; Sort the transient parameters in the same transient parameter set in ascending order to obtain a parameter sorting sequence, split the parameter sorting sequence based on the second decomposition level to obtain a number of parameter sorting subsequences whose number is the same as the second decomposition level, and obtain the median of the parameter sorting subsequences; Count the number of transient parameters contained in each parameter sorting subsequence to obtain the total number of transient parameters in the subsequence. Based on the median of the parameter sorting subsequence and the total number of transient parameters in the subsequence, use the weighted average algorithm to calculate the weighted average parameters in the transient parameter set and use them as the abnormal parameters. Use the interpolation algorithm to obtain the time point corresponding to the weighted average parameter in the risk sequence and mark it as the target collection point, obtain the rated power of the electrical equipment corresponding to the target collection point and mark it as the corrected power, and the interval time from the time point corresponding to the target collection point to the end time point of the risk period, and use it as the risk duration of the abnormal parameter corresponding to the risk sequence; Based on the above method of performing parameter analysis on the same transient parameter set, the abnormal parameters and risk durations corresponding to the first transient parameter set and the second parameter set are obtained respectively, and are marked as the first risk parameter, the second risk parameter, the first abnormal parameter, the second abnormal parameter, the first risk duration and the second risk duration respectively.

8. The intelligent real-time monitoring and diagnosis method for leakage current according to claim 7 is characterized in that: Based on the second current signal subsequence, the real-time current and the real-time electrical signal frequency are determined as the first real-time parameter and the second real-time parameter, and the corresponding real-time electrical equipment power is obtained; if any real-time parameter reaches the corresponding risk parameter, the actual risk duration of the corresponding real-time parameter is counted to obtain the first actual risk duration corresponding to the first transient parameter set and the second actual risk duration corresponding to the second transient parameter set, respectively; By formula Calculate and obtain a transient risk value Tsv of the second current signal subsequence; In the formula, I t is the real-time current; F t is the real-time frequency; I1 is the first abnormal parameter; F1 is the second abnormal parameter; T I is the first actual risk duration; T F is the second actual risk duration; T t is the actual duration of risk; min() is the minimum value comparison function; P t is the real-time power of electrical equipment; P1 is the corrected power.

9. The intelligent real-time monitoring and diagnosis method for leakage current according to claim 8, characterized in that: The method of establishing a current diagnosis model based on the steady-state analysis value Sav and the transient risk value Tsv is: Compare the steady-state analysis value Sav of the current first current signal subsequence with the preset steady-state threshold S0; If Sav > S0, determine that the real-time current steady-state feature is abnormal and generate a first abnormal label; Otherwise, do nothing; And compare the transient risk value Tsv of the current second current signal subsequence with the preset transient threshold T0; If Tsv ≤ 0.8T0, do nothing; if 0.8T0 < Tsv ≤ T0, mark the current second current signal subsequence as an abnormal subsequence, and determine whether there is at least a continuous number z of abnormal subsequences; if there is at least a continuous number z of abnormal subsequences, then determine that the real-time current transient feature is the first abnormal and generate a second abnormal label; if there is no at least a continuous number z of abnormal subsequences, do nothing; If T0 < Tsv, determine that the real-time current transient feature is the second abnormal and generate a third abnormal label; Based on the first abnormal label, the second abnormal label and the third abnormal label, determine that there is a leakage phenomenon and notify the technical personnel for maintenance.

10. The intelligent real-time monitoring and diagnosis system for leakage current according to claim 1, which uses the intelligent real-time monitoring and diagnosis method for leakage current according to any one of claims 1 to 9, characterized in that: Specifically include: A data acquisition module, which is used to obtain the real-time current signal of the target area power grid and the corresponding current signal timestamp, and perform intelligent processing on the real-time electrical signal to obtain the corresponding current signal sequence; A data preprocessing module, which is used to perform wavelet packet transform processing on the current signal sequence, decompose the current signal processing sequence into current signal subsequences of different frequency bands, and perform intelligent processing on the current signal subsequences to obtain the current signal subsequences; A data analysis module, which is used to establish a dynamic window for each current signal subsequence, mark the current signal subsequence located at the center of the dynamic window as the center sequence C, use the current signal subsequences included in the dynamic window as the dynamic sequence of the center sequence C, establish a dynamic window sequence set, and perform intelligent feature analysis on the dynamic window sequence set to obtain the steady-state feature Sav and transient feature Tsv of the current signal; An intelligent monitoring and diagnosis module, which is used to establish a current diagnosis model based on the steady-state analysis value Sav and the transient risk value Tsv, and diagnose and give early warning to the real-time current based on the current diagnosis model.

Images