A method for identifying the operating status of a lightning arrester based on online monitoring data

Abstract

The invention discloses a method for identifying the operating state of a lightning arrester based on online monitoring data, and relates to the technical field of lightning arrester monitoring. The system discloses the following steps: Step 1: setting a state monitoring cycle, and obtaining a preliminary state analysis value of the lightning arrester after each state monitoring cycle; Step 2: judging whether the operating state of the lightning arrester is an abnormal operating state or a normal operating state based on a comparison result between the preliminary state analysis value and a preliminary state analysis threshold; through Step 1 and Step 2, various basic monitoring data of the lightning arrester are deeply processed and analyzed from multiple angles by means of online monitoring, the operating state of the lightning arrester in the current cycle is comprehensively judged, and the lightning arrester in the abnormal operating state is marked in time.

Description

Technical Field

[0001] The invention relates to the technical field of arrester monitoring, and more specifically, to a method for identifying the operating state of an arrester based on online monitoring data. Background Art

[0002] In the power system, lightning arresters, as key overvoltage protection devices, are crucial to ensure the stable operation of the power system and the safety of equipment. Traditional lightning arrester monitoring methods mostly rely on regular manual inspections and offline tests, which is not only time-consuming and labor-intensive, but also difficult to achieve real-time and comprehensive monitoring of the operating status of lightning arresters. With the expansion of the scale of power systems and the development of intelligent technology, higher requirements are placed on the accuracy and real-time performance of lightning arrester monitoring.

[0003] Although the existing online monitoring system of lightning arresters can collect the operating data of lightning arresters in real time, it often lacks in-depth processing and analysis of the data, resulting in inaccurate and incomplete judgment of the operating status of the lightning arrester. For example, some systems only use simple threshold comparison to determine whether the lightning arrester is in an abnormal state. This method ignores the diversity and complexity of the operating status of the lightning arrester, which is prone to misjudgment or missed judgment, making it difficult for monitoring personnel to understand the abnormal operating status of the lightning arrester and its severity. Summary of the invention

[0004] In view of the deficiencies in the prior art, an object of the present invention is to provide a method for identifying the operating status of a lightning arrester based on online monitoring data.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for identifying the operating status of a lightning arrester based on online monitoring data comprises the following steps:

[0007] Step 1: Set the status monitoring cycle, and obtain the initial status value of the arrester after each status monitoring cycle;

[0008] Step 2: Based on the comparison result between the state preliminary analysis value and the state preliminary analysis threshold value, determine whether the operating state of the arrester is an abnormal operating state or a normal operating state;

[0009] Step 3: When the state of the lightning arrester is marked as an abnormal state, obtaining the abnormal state identification level value of the lightning arrester;

[0010] Step 4: Obtain the abnormal state recognition level of the arrester according to the abnormal state recognition level value.

[0011] Furthermore, the state initial analysis value of the arrester is obtained in the following way: divide the state monitoring period into i state initial analysis periods of equal length, obtain the initial analysis period value of each state initial analysis period, obtain the initial analysis basic value RAj, set the initial analysis period boundary value, when the initial analysis period value of the state initial analysis period is greater than or equal to the initial analysis period boundary value, mark the state initial analysis period as a prominent state period, compare all prominent state periods in pairs, when two prominent state periods are adjacent periods, increase the number of continuation of the prominent state by one, when two prominent state periods are not adjacent periods, increase the number of single prominent states by one, mark the number of continuation of the prominent state as FAh, mark the number of single prominent states as LDt, and use the formula The initial state analysis value VTp of the lightning arrester is obtained, where ha is the protrusion continuation coefficient and hb is the protrusion single coefficient.

[0012] Furthermore, the preliminary analysis basic value RAj is obtained in the following way: a rectangular coordinate system is constructed with the state monitoring period as the X-axis and the preliminary analysis time period value as the Y-axis, the preliminary analysis time period value of each state preliminary analysis time period is marked in the rectangular coordinate system in the form of coordinate points, adjacent coordinate points in the rectangular coordinate system are connected to obtain the state preliminary analysis curve, the two end points of the state preliminary analysis curve are drawn perpendicular to the X-axis, and the total area of ​​the closed figure formed by the state preliminary analysis curve, the two perpendicular line segments and the X-axis is marked as the preliminary analysis basic value RAj.

[0013] Furthermore, the initial analysis period value of the state initial analysis period is obtained in the following way: collect the operating data of various basic monitoring data of the arrester in the state initial analysis period, and then obtain the basic monitoring values ​​of various basic monitoring data, set the basic monitoring critical value, when the basic monitoring value of the basic monitoring data is greater than or equal to the basic monitoring critical value, mark the basic monitoring value as prominent basic data, when the basic monitoring value of the basic monitoring data is less than the basic monitoring critical value, mark the basic monitoring value as ordinary basic data, sum up and average the basic monitoring values ​​of all prominent basic data to obtain the prominent benchmark value, sum up and average the basic monitoring values ​​of all ordinary basic data to obtain the ordinary benchmark value, calculate the difference between the prominent benchmark value and the ordinary benchmark value and take the absolute value to obtain the benchmark distance value Ksy, obtain the total number of abnormal linkage groups BEG, and use the formula The initial analysis period value CVB of the state initial analysis period is obtained.

[0014] Furthermore, the total number of abnormal linkage groups BEG is obtained in the following way: all the prominent basic data are matched in pairs into a prominent linkage group, the basic monitoring values ​​of the two prominent basic data in the prominent linkage group are summed to obtain the prominent linkage value, and the prominent linkage threshold is set. When the prominent linkage value is greater than or equal to the prominent linkage threshold, the corresponding prominent linkage group is marked as an abnormal linkage group, and the total number of abnormal linkage groups is marked as BEG.

[0015] Furthermore, the basic monitoring values ​​of various basic monitoring data are obtained in the following manner: obtaining the basic monitoring models corresponding to the various basic monitoring data, preprocessing the operating data of the various basic monitoring data, and inputting the preprocessed operating data of the various basic monitoring data into the corresponding basic monitoring models respectively, each basic monitoring model outputs a basic monitoring value of a basic monitoring data, and then obtaining the basic monitoring values ​​of various basic monitoring data.

[0016] Furthermore, the abnormal state recognition level value of the lightning arrester is obtained in the following way: collecting the operating data of various basic monitoring data of the lightning arrester during the state monitoring period, and obtaining the target data of various basic monitoring data of the lightning arrester during the state monitoring period, constructing a lightning arrester operation optimization simulation model based on the operating data and target data of various basic monitoring data, performing N simulation operation optimizations on the lightning arrester operation optimization simulation model, and obtaining the operation state optimization value BCn of each simulation operation optimization, where n=1, 2, ..., N, N is the total number of simulation operation optimizations, and n is the number of simulation operation optimizations. The operation state optimization coefficient is set to Ds, and the formula is used Obtain the abnormal state recognition level value Lmx of the lightning arrester.

[0017] Furthermore, the running state optimization value of the simulation operation optimization is obtained by the following method: after the simulation operation optimization is completed, the optimization cost cb and optimization time st of the entire simulation operation optimization are obtained, and the formula is used The optimized running state value BCn of the simulation running optimization is obtained, where m1 is the optimization cost coefficient and m2 is the optimization duration coefficient.

[0018] Furthermore, the abnormal state identification level of the lightning arrester is obtained according to the abnormal state identification level value, specifically: the value range of the abnormal state identification level value includes (0, Lm1], (Lm1, Lm2], …, (Lmx-1, Lmx], the abnormal state identification level includes abnormal state identification level 1, abnormal state identification level 2, …, abnormal state identification level x-1, abnormal state identification level x, the operation abnormality degree of abnormal state identification level 1 is less than the operation abnormality degree of abnormal state identification level 2 is less than … the operation abnormality degree of abnormal state identification level x.

[0019] Compared with the prior art, the present invention has the following beneficial effects:

[0020] The method of the present invention performs in-depth processing and analysis of various basic monitoring data of the lightning arrester from multiple angles through online monitoring through steps one and two, comprehensively determines the operating status of the lightning arrester in the current cycle, and promptly marks the lightning arrester in the abnormal operating status, and comprehensively determines the abnormal state recognition level of the lightning arrester through steps three and four by combining data analysis and simulation analysis, so as to facilitate monitoring personnel to understand the abnormal operating status of the lightning arrester more intuitively and accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A method flow chart of a method for identifying the operating status of a lightning arrester based on online monitoring data;

[0022] Figure 2 A flowchart for obtaining the initial analysis period value of the state initial analysis period;

[0023] Figure 3 The present invention is a flow chart for obtaining the abnormal state recognition level value of the lightning arrester. DETAILED DESCRIPTION

[0024] Reference Figure 1-Figure 3 , a method for identifying the operating status of a lightning arrester based on online monitoring data, comprising the following steps:

[0025] Step 1: Set the status monitoring cycle, and obtain the initial status value of the arrester after each status monitoring cycle.

[0026] The state initial analysis value of the arrester is obtained in the following way: divide the state monitoring period into i state initial analysis periods of equal length, obtain the initial analysis period value of each state initial analysis period, construct a rectangular coordinate system with the state monitoring period as the X-axis and the initial analysis period value as the Y-axis, mark the initial analysis period value of each state initial analysis period in the form of coordinate points in the rectangular coordinate system, connect adjacent coordinate points in the rectangular coordinate system to obtain the state initial analysis curve, draw perpendicular lines from the two end points of the state initial analysis curve to the X-axis, mark the total area of ​​the closed figure formed by the state initial analysis curve, the two perpendicular lines and the X-axis as the initial analysis basic value RAj, set the initial analysis period boundary value ( The boundary value of the initial analysis period is a preset value, which is adjusted according to the needs). When the initial analysis period value of the state initial analysis period is greater than or equal to the boundary value of the initial analysis period, the state initial analysis period is marked as a prominent state period. When the initial analysis period value of the state initial analysis period is less than the boundary value of the initial analysis period, no further processing is performed. All prominent state periods are compared in pairs. When two prominent state periods are adjacent periods, the number of continuation of the prominent state is increased by one. When two prominent state periods are not adjacent periods, the number of single prominent states is increased by one. The number of continuation of the prominent state is marked as FAh, and the number of single prominent states is marked as LDt. The formula is used. The initial state analysis value VTp of the lightning arrester is obtained, where ha is the protrusion continuation coefficient, hb is the protrusion single coefficient, the value of ha is 0.88, and the value of hb is 0.76.

[0027] The initial analysis period value of the status initial analysis period is obtained in the following way: collect the operating data of various basic monitoring data of the lightning arrester during the status initial analysis period (the combination of various basic monitoring data can comprehensively reflect the operating status of the lightning arrester. The types of basic monitoring data are not limited to leakage current data, insulation resistance data, reference voltage data, discharge counter action data, and temperature data. The leakage current data is collected by a leakage current sensor, the insulation resistance data is collected by a zero-residual-pressure passive electronic sensor, the reference voltage data is collected by a voltage sensor, the discharge counter action data is collected by a Hall effect sensor or a discharge coil sensor, and the temperature data is collected by a temperature sensor), and then obtain the basic monitoring values ​​of various basic monitoring data, set the basic monitoring critical value (the basic monitoring critical value is a preset value, which is adjusted according to demand), and when the basic monitoring value of the basic monitoring data is greater than or equal to the basic monitoring critical value, mark the basic monitoring value as a prominent basic value. Basic data, when the basic monitoring value of the basic monitoring data is less than the basic monitoring critical value, the basic monitoring value is marked as ordinary basic data, the basic monitoring values ​​of all prominent basic data are summed and averaged to obtain the prominent benchmark value, the basic monitoring values ​​of all ordinary basic data are summed and averaged to obtain the ordinary benchmark value, the difference between the prominent benchmark value and the ordinary benchmark value is calculated and the absolute value is taken to obtain the benchmark distance value Ksy, all prominent basic data are matched into a prominent linkage group, the basic monitoring values ​​of the two prominent basic data in the prominent linkage group are summed to obtain the prominent linkage value, and the prominent linkage threshold is set (the prominent linkage threshold is a preset value, which is adjusted according to needs), when the prominent linkage value is greater than or equal to the prominent linkage threshold, the corresponding prominent linkage group is marked as an abnormal linkage group, when the prominent linkage value is less than the prominent linkage threshold, no further processing is performed, and the total number of abnormal linkage groups is marked as BEG, using the formula The initial analysis period value CVB of the state initial analysis period is obtained.

[0028] The basic monitoring values ​​of various basic monitoring data are obtained in the following ways: obtaining the basic monitoring models corresponding to the various basic monitoring data, preprocessing the operating data of various basic monitoring data (the preprocessing methods include but are not limited to data cleaning and data formatting), and inputting the preprocessed operating data of various basic monitoring data into the corresponding basic monitoring models respectively, each basic monitoring model outputs a basic monitoring value of a basic monitoring data, and then obtaining the basic monitoring values ​​of various basic monitoring data.

[0029] Each basic monitoring data corresponds to a basic monitoring model, and the basic monitoring model is built based on the deep learning model. The construction method of each basic monitoring model only differs in the training data. The following example introduces the construction steps of the basic monitoring model of leakage current data: collect the operating data of multiple leakage current data, and the operating data of each leakage current data includes full current data, resistive current data, leakage current peak data, leakage current change trend data, etc. Preprocess the operating data of each leakage current data, build a deep learning model, and use the preprocessed operating data as the training data of the deep learning model (if it is insulation resistance The basic monitoring model for data is used, and the operating data of the insulation resistance data is used as the training data of the deep learning model). A basic monitoring value is assigned to each training data. The value range of the basic monitoring value is (1.1~1.9). The larger the value of the basic monitoring value, the more abnormal the leakage current data is (if it is the basic monitoring model of insulation resistance data, it means that the insulation resistance data is more abnormal). The smaller the value of the basic monitoring value, the more normal the leakage current data is. The training data is divided into 70% training set, 15% validation set and 15% test set, and the deep learning model is trained. After the training, the basic monitoring model for leakage current data is obtained.

[0030] Step 2: Set the initial status analysis threshold (the initial status analysis threshold is a preset value, which can be adjusted according to needs). When the initial status analysis value of the arrester is greater than or equal to the initial status analysis threshold, the operating status of the arrester is marked as an abnormal operating status. When the initial status analysis value of the arrester is less than the initial status analysis threshold, the operating status of the arrester is marked as a normal operating status.

[0031] Through steps one and two, various basic monitoring data of the arrester are deeply processed and analyzed from multiple angles through online monitoring, the operating status of the arrester in the current cycle is comprehensively determined, and the arrester in abnormal operating status is marked in time.

[0032] Step 3: When the state of the arrester is marked as abnormal, collect the operating data of various basic monitoring data of the arrester during the state monitoring period, and obtain the target data of various basic monitoring data of the arrester during the state monitoring period (the target data is the operating data that the arrester should reach or maintain under the normal operation of the arrester under various basic monitoring data, which are all pre-set data), build an arrester operation optimization simulation model based on the operating data and target data of various basic monitoring data, and perform N simulation operation optimizations on the arrester operation optimization simulation model (each simulation operation optimization optimizes and adjusts the parameters in the model to improve the performance and stability of the arrester, including adjusting the resistor capacitance value, Dielectric constant and other parameters to optimize voltage distribution and energy absorption capacity, etc.), and obtain the operating state optimization value BCn for each simulation run optimization, n=1, 2, …, N, N is the total number of simulation run optimizations, n is the number of simulation run optimizations, set the operating state optimization coefficient to Ds, s=1, 2, 3, …s; D1<D2<D3<…<Ds, set each operating state optimization coefficient to correspond to a range of operating state optimization values, including (0, BC1], (BC1, BC2], …, (BCN-1, BCN], when the operating state optimization value BCn∈(BC1, BC2], the corresponding operating state optimization coefficient is D2, using the formula Obtain the abnormal state recognition level value Lmx of the lightning arrester.

[0033] A lightning arrester operation optimization simulation model is constructed based on the operation data and target data of various basic monitoring data. Specifically, the operation data and target data of the basic monitoring data are preprocessed, including data cleaning, denoising, outlier processing, etc., and simulation software such as ANSYS, MATLAB, and PSCAD are selected. The preprocessed operation data and target data are input into the simulation software to complete the construction of the lightning arrester operation optimization simulation model.

[0034] The running state optimization value of the simulation operation optimization is obtained in the following way: After the simulation operation optimization is completed, the optimization cost cb and optimization time st of the entire simulation operation optimization are obtained, and the formula is used The optimized running state value BCn of the simulation operation optimization is obtained, where m1 is the optimization cost coefficient, m2 is the optimization duration coefficient, the value of m1 is 0.95, and the value of m2 is 0.62.

[0035] Step 4: Obtain the abnormal state identification level of the arrester according to the abnormal state identification level value. The monitoring personnel can intuitively understand the current abnormal operation state of the arrester according to the abnormal state identification level.

[0036] The abnormal state identification level of the lightning arrester is obtained according to the abnormal state identification level value, specifically: the value range of the abnormal state identification level value includes (0, Lm1], (Lm1, Lm2], ..., (Lmx-1, Lmx], the abnormal state identification level includes abnormal state identification level 1, abnormal state identification level 2, ..., abnormal state identification level x-1, abnormal state identification level x, when the abnormal state identification level value ∈ (0, Lm1], the lightning arrester is abnormal state identification level 1, the operation abnormality degree of abnormal state identification level 1 is < the operation abnormality degree of abnormal state identification level 2 < ... the operation abnormality degree of abnormal state identification level x.

[0037] Through step three and step four, the abnormal state recognition level of the lightning arrester is comprehensively determined by combining data analysis and simulation analysis, which makes it convenient for monitoring personnel to understand the abnormal operating state of the lightning arrester more intuitively and accurately.

[0038] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0039] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0040] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0041] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0042] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0043] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0044] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0045] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for identifying the operating status of a lightning arrester based on online monitoring data, characterized in that: The steps include: Step 1: Set the state monitoring cycle. After each state monitoring cycle, divide the state monitoring cycle into i state preliminary analysis periods of equal length, and then obtain the state preliminary analysis value VTp of the arrester; Step 2: Set the state initial analysis threshold. When the state initial analysis value of the arrester is greater than or equal to the state initial analysis threshold, the operation state of the arrester is marked as an abnormal operation state. When the state initial analysis value of the arrester is less than the state initial analysis threshold, the operation state of the arrester is marked as a normal operation state. Step 3: When the state of the arrester is marked as an abnormal state, collect the operating data of various basic monitoring data of the arrester during the state monitoring period, and obtain the target data of various basic monitoring data of the arrester during the state monitoring period, build an arrester operation optimization simulation model based on the operating data and target data of various basic monitoring data, perform N simulation operation optimizations on the arrester operation optimization simulation model, and obtain the abnormal state recognition level value Lmx of the arrester; Step 4: Obtain the abnormal state recognition level of the arrester according to the abnormal state recognition level value; The state initial analysis value of the arrester is obtained in the following way: obtain the initial analysis period value of each state initial analysis period, obtain the initial analysis basic value RAj, set the initial analysis period boundary value, when the initial analysis period value of the state initial analysis period is greater than or equal to the initial analysis period boundary value, mark the state initial analysis period as a prominent state period, compare all prominent state periods in pairs, when two prominent state periods are adjacent periods, increase the number of continuation of the prominent state by one, when two prominent state periods are not adjacent periods, increase the number of single prominent states by one, mark the number of continuation of the prominent state as FAh, mark the number of single prominent states as LDt, and use the formula The initial state analysis value VTp of the arrester is obtained, where ha is the protrusion continuation coefficient and hb is the protrusion single coefficient; The abnormal state recognition level value of the arrester is obtained by the following method: obtain the operation state optimization value BCn of each simulation operation optimization, n = 1, 2, ..., N, N is the total number of simulation operation optimizations, n is the number of simulation operation optimizations, set the operation state optimization coefficient to Ds, and use the formula Obtain the abnormal state recognition level value Lmx of the lightning arrester.

2. A method for identifying the operating status of a lightning arrester based on online monitoring data according to claim 1, characterized in that: The initial analysis basic value RAj is obtained in the following way: a rectangular coordinate system is constructed with the state monitoring period as the X-axis and the initial analysis time period value as the Y-axis, the initial analysis time period value of each state initial analysis time period is marked in the rectangular coordinate system in the form of coordinate points, adjacent coordinate points in the rectangular coordinate system are connected to obtain the state initial analysis curve, the two end points of the state initial analysis curve are drawn perpendicular to the X-axis, and the total area of ​​the closed figure formed by the state initial analysis curve, the two perpendicular line segments and the X-axis is marked as the initial analysis basic value RAj.

3. The method for identifying the operating status of a lightning arrester based on online monitoring data according to claim 1, characterized in that: The initial analysis period value of the state initial analysis period is obtained in the following way: collect the operating data of various basic monitoring data of the arrester in the state initial analysis period, and then obtain the basic monitoring values ​​of various basic monitoring data, set the basic monitoring critical value, when the basic monitoring value of the basic monitoring data is greater than or equal to the basic monitoring critical value, mark the basic monitoring value as outstanding basic data, when the basic monitoring value of the basic monitoring data is less than the basic monitoring critical value, mark the basic monitoring value as ordinary basic data, sum up and average the basic monitoring values ​​of all outstanding basic data to obtain the outstanding benchmark value, sum up and average the basic monitoring values ​​of all ordinary basic data to obtain the ordinary benchmark value, calculate the difference between the outstanding benchmark value and the ordinary benchmark value and take the absolute value to obtain the benchmark distance value Ksy, obtain the total number of abnormal linkage groups BEG, and use the formula The initial analysis period value CVB of the state initial analysis period is obtained.

4. The method for identifying the operating status of a lightning arrester based on online monitoring data according to claim 3 is characterized in that: The total number of abnormal linkage groups BEG is obtained in the following way: all the prominent basic data are matched in pairs into a prominent linkage group, the basic monitoring values ​​of the two prominent basic data in the prominent linkage group are summed to obtain the prominent linkage value, and the prominent linkage threshold is set. When the prominent linkage value is greater than or equal to the prominent linkage threshold, the corresponding prominent linkage group is marked as an abnormal linkage group, and the total number of abnormal linkage groups is marked as BEG.

5. The method for identifying the operating status of a lightning arrester based on online monitoring data according to claim 3 is characterized in that: The basic monitoring values ​​of various basic monitoring data are obtained in the following way: obtain the basic monitoring models corresponding to the various basic monitoring data, preprocess the operating data of the various basic monitoring data, input the preprocessed operating data of the various basic monitoring data into the corresponding basic monitoring models respectively, each basic monitoring model outputs a basic monitoring value of a basic monitoring data, and then obtains the basic monitoring values ​​of various basic monitoring data.

6. The method for identifying the operating status of a lightning arrester based on online monitoring data according to claim 1, characterized in that: The running state optimization value of the simulation operation optimization is obtained in the following way: After the simulation operation optimization is completed, the optimization cost cb and optimization time st of the entire simulation operation optimization are obtained, and the formula is used The optimized running state value BCn of the simulation running optimization is obtained, where m1 is the optimization cost coefficient and m2 is the optimization duration coefficient.

7. The method for identifying the operating status of a lightning arrester based on online monitoring data according to claim 1, characterized in that: The abnormal state identification level of the lightning arrester is obtained according to the abnormal state identification level value, specifically: the value range of the abnormal state identification level value includes (0, Lm1], (Lm1, Lm2], ..., (Lmx-1, Lmx], the abnormal state identification level includes abnormal state identification level 1, abnormal state identification level 2, ..., abnormal state identification level x-1, abnormal state identification level x, the operation abnormality degree of abnormal state identification level 1 is less than the operation abnormality degree of abnormal state identification level 2 < ... the operation abnormality degree of abnormal state identification level x.

Images