A lightning arrester test detection method and system based on environmental simulation

Abstract

The present invention discloses a lightning arrester test detection method and system based on environmental simulation, including: obtaining abnormal state data of the lightning arrester, generating service environment data corresponding to high-frequency abnormal states through clustering, constructing a simulated environment data subset for environmental simulation, and obtaining the electrical parameter change characteristics of the lightning arrester during the aging process; obtaining the morphological feature sequence of the lightning arrester valve plate and matching it with the electrical parameter change characteristics, and obtaining the change of the temperature rise of the lightning arrester with the voltage amplitude; obtaining the aging status of the lightning arrester valve plate, monitoring the voltage and leakage current at both ends of the lightning arrester, and performing abnormal warning in combination with the overheating threshold corresponding to the lightning arrester under the aging status. The present invention restores the aging characteristics of the lightning arrester in the actual application process through environmental simulation, constructs a mapping relationship between the morphological characteristics of the lightning arrester valve plate, the degree of aging and the temperature rise status, and constructs a high-precision thermal threshold according to the mapping relationship, which provides a data basis for the reliability test and fault monitoring and operation and maintenance of the lightning arrester.

Description

Technical Field

[0001] The present invention relates to the technical field of lightning arrester testing, and more specifically, to a lightning arrester testing detection method and system based on environmental simulation. Background Art

[0002] Lightning arrester is one of the main equipment of power system. It can effectively limit the overvoltage amplitude of power grid, protect the substation equipment from overvoltage damage, and ensure the safe and stable operation of the system. It is also called overvoltage protector. It is suitable for overvoltage protection of transformers, transmission lines, distribution panels, switch cabinets, power meter boxes, vacuum switches, parallel compensation capacitors, rotating motors and semiconductor devices. Since power grid equipment is affected by overvoltage, bad weather, frequent vibration and other factors for a long time during operation, it is easy to cause lightning arrester to get damp and age. Therefore, determining the aging characteristic of lightning arrester has important theoretical significance and engineering practical value for the safe operation and maintenance of electrical equipment.

[0003] With the rapid development of power grid construction, the number of lightning arresters installed in various substations of the power system has also increased rapidly, and the effectiveness of lightning arrester testing has also become a focus of current attention. Before installation, lightning arresters need to undergo necessary electrical tests, such as power frequency AC withstand voltage test, DC leakage current measurement, and insulation resistance measurement. Lightning arresters that do not meet the test standards are prone to lose their lightning protection function and even cause lightning arrester explosion accidents. However, the current lightning arrester test and detection environment is single, and there is a large deviation from the diverse environment of actual application, resulting in low accuracy of test results, which is prone to high device failure rate, many system false alarms, and increased additional maintenance workload. Therefore, how to simulate application scenarios in the test and detection of lightning arresters and achieve high-precision test and detection is an urgent problem that needs to be solved. Summary of the invention

[0004] In order to solve the above technical problems, the present invention proposes a lightning arrester test detection method and system based on environmental simulation.

[0005] A first aspect of the present invention provides a lightning arrester test detection method based on environmental simulation, comprising:

[0006] Obtain abnormal state data of the arrester, extract service environment data of the abnormal state data, generate service environment data corresponding to the high-frequency abnormal state through clustering, and divide it according to different application scenarios to obtain a subset of simulated environment data;

[0007] Use different simulated environment data subsets to perform environmental simulation, analyze the aging process of the arrester in the test environment under environmental simulation, and obtain the electrical parameter change characteristics of the valve plate of the arrester during the aging process;

[0008] Acquire the morphological features of the arrester valve plate to construct a morphological feature sequence, match the electrical parameter change features with the morphological features, set sequence labels using application scenarios, and obtain the temperature rise of the arrester as a function of voltage amplitude;

[0009] The aging status is obtained according to the morphological characteristics of the valve plate of the lightning arrester to be tested, the voltage and leakage current at both ends of the lightning arrester are monitored, and abnormal warning is issued based on the overheating threshold corresponding to the lightning arrester under the aging status.

[0010] In this solution, the service environment data of abnormal state data is extracted, and the service environment data corresponding to the high-frequency abnormal state is generated by clustering. It is divided by different application scenarios to obtain the simulated environment data subset, specifically:

[0011] Obtaining basic parameter information of the arrester, extracting abnormal state data based on the basic parameter information by using multi-source data feedback, preprocessing the abnormal state data, and separating the service environment data contained in the abnormal state data after preprocessing;

[0012] Extracting application scenarios of lightning arresters according to the service environment data, generating application scenario labels, clustering abnormal state data using the service environment data, optimizing the clustering algorithm using a genetic algorithm, and selecting initial clustering centers;

[0013] Calculate the Euclidean distance of the service environment data samples, and assign each service environment data to the initial cluster center with the closest distance to generate a cluster cluster, and update the cluster center in the cluster cluster through iterative clustering;

[0014] When the end condition is reached, the final clustering result is obtained, and according to the preset screening criteria of the cluster data volume, the clusters that meet the preset screening criteria are selected for suspension, and the service environment data under the same application scenario label in the suspended clusters are aggregated to generate the service environment data change interval;

[0015] Obtain the overlap of different service environment data change intervals, merge the intervals with overlap greater than a preset threshold, obtain the updated service environment data change interval as environmental simulation data, and construct simulation environment data subsets for different application scenarios based on the environmental simulation data in the interval.

[0016] In this scheme, different simulated environment data subsets are used to perform environmental simulation, analyze the aging process of the arrester in the test environment under environmental simulation, and obtain the electrical parameter change characteristics of the valve plate of the arrester during the aging process, specifically:

[0017] Setting a time sequence for each simulated environment data subset to generate a simulated environment data sequence, constructing a lightning arrester test environment according to the simulated environment data sequence, and calculating the contribution by the ratio of the abnormal state data samples corresponding to the simulated environment data subsets of different application scenarios to all the abnormal state data samples;

[0018] Preset the detection condition base value of the arrester, weight the detection condition base value according to the contribution of different application scenarios, set exclusive detection conditions in the arrester test environment, and read the volt-ampere characteristic data of the valve plate during the aging process of the arrester in the test environment of different application scenarios;

[0019] The volt-ampere curve vector is extracted according to the volt-ampere characteristic data of the valve plate to record the electrical parameters, the volt-ampere characteristic change characteristics of the valve plate are obtained through the residual of the volt-ampere curve vector under different detection conditions, and the electrical parameter change characteristics are obtained based on the volt-ampere characteristic change characteristics.

[0020] In this solution, the morphological features of the arrester valve plate are obtained to construct a morphological feature sequence, the electrical parameter change characteristics are matched with the morphological features, and the sequence labels are set using the application scenario, specifically:

[0021] Obtaining microscopic scanning images of valve plates of lightning arresters in different test environments, preprocessing the microscopic scanning images, matching the preprocessed microscopic scanning images with valve plate templates, and obtaining similarity distribution in the matching process by similarity calculation;

[0022] The valve plate area is obtained according to the contour size of the valve plate template and the similarity distribution, the neighboring points of each contour point on the valve plate template contour are obtained in the valve plate area, and the pixel point closest to the microscopic scanning image and the valve plate template is calculated according to the contour points and the neighboring points to generate the valve plate area contour;

[0023] Sampling discrete points in the valve plate area contour, using the discrete points to obtain the surface height distribution of the valve plate, calculating the mean and standard deviation of the surface height distribution, and aggregating the surface height distribution and the mean and standard deviation of the surface height distribution to generate a morphological feature;

[0024] A morphological feature sequence is constructed according to the timing of the aging process, and the timestamp of the electrical parameter change characteristics is obtained. The morphological feature sequence is matched with the electrical parameter change characteristics according to the timestamp, and the application scenario is used to label the matched morphological feature sequence device sequence.

[0025] In this scheme, the change of the temperature rise of the lightning arrester with the voltage amplitude is obtained, specifically:

[0026] Obtain a three-dimensional model of the arrester, divide the three-dimensional model into three-dimensional grid blocks, classify the three-dimensional grid blocks according to their position information and structural information, and add internal valve plate labels and external surface labels according to the classification results;

[0027] Obtaining voltage distribution of the arrester during aging in different test environments, obtaining distribution weight information according to the voltage distribution, allocating the distribution weight information to the three-dimensional grid blocks, and setting the temperature measurement point density in combination with the three-dimensional grid block category label;

[0028] According to the temperature value sensed by the temperature measuring point, the temperature value is interpolated in the three-dimensional model to obtain the thermal distribution of the arrester, and the temperature rise condition inside and outside the arrester is analyzed by time series processing according to the thermal distribution;

[0029] According to the exclusive detection conditions of different test environments, the voltage amplitude change interval is extracted, the temperature rise condition inside and outside the arrester is obtained along with the temperature rise change characteristics of the voltage amplitude, the real-time internal and external temperature difference is obtained, and the internal and external temperature difference change characteristics are generated through the time convolution network;

[0030] The temperature rise change characteristics and the internal and external temperature difference change characteristics are matched with the electrical parameter change characteristics and morphological feature sequences according to the timestamps, and the mapping relationship between the arrester valve plate morphological characteristics, aging degree and temperature rise conditions is constructed.

[0031] In this scheme, the aging status is obtained according to the morphological characteristics of the valve plate of the lightning arrester to be tested, the voltage and leakage current at both ends of the lightning arrester are monitored, and abnormal warning is performed in combination with the overheating threshold corresponding to the lightning arrester under the aging status. Specifically:

[0032] Extracting current morphological features according to the microscopic scanning image of the valve plate of the arrester to be detected, extracting corresponding morphological feature sequences according to the application scenarios of the arrester to be detected, and performing point-by-point similarity comparison of the current morphological features in the extracted morphological feature sequences;

[0033] Based on the mapping relationship between morphological features, aging degree and temperature rise conditions, the average similarity is used to determine the aging status of the valve plate of the arrester to be tested. In addition, the current and subsequent temperature rise change characteristics and internal and external temperature difference change characteristics are obtained through the mapping relationship between aging degree and temperature rise conditions.

[0034] Calculate the characteristic distribution of the current and subsequent temperature rise change characteristics and the internal and external temperature difference change characteristics, determine whether the temperature rise exceeds the arrester's tolerance range through the relative entropy between the characteristic distributions of different timestamps, and obtain the overheating threshold corresponding to the arrester under the aging status;

[0035] The voltage and leakage current thresholds of the arrester are read according to the mapping relationship according to the overheating threshold, and the abnormal monitoring and early warning of the arrester to be detected are performed by combining the overheating threshold with the voltage threshold and the leakage current threshold.

[0036] The second aspect of the present invention further provides a lightning arrester test detection system based on environmental simulation, the system comprising: a memory, a processor, the memory comprising a lightning arrester test detection method program based on environmental simulation, the lightning arrester test detection method program based on environmental simulation when executed by the processor implements the following steps:

[0037] Obtain abnormal state data of the arrester, extract service environment data of the abnormal state data, generate service environment data corresponding to the high-frequency abnormal state through clustering, and divide it according to different application scenarios to obtain a subset of simulated environment data;

[0038] Use different simulated environment data subsets to perform environmental simulation, analyze the aging process of the arrester in the test environment under environmental simulation, and obtain the electrical parameter change characteristics of the valve plate of the arrester during the aging process;

[0039] Acquire the morphological features of the arrester valve plate to construct a morphological feature sequence, match the electrical parameter change features with the morphological features, set sequence labels using application scenarios, and obtain the temperature rise of the arrester as a function of voltage amplitude;

[0040] The aging status is obtained according to the morphological characteristics of the valve plate of the lightning arrester to be tested, the voltage and leakage current at both ends of the lightning arrester are monitored, and abnormal warning is issued based on the overheating threshold corresponding to the lightning arrester under the aging status.

[0041] The present invention discloses a lightning arrester test detection method and system based on environmental simulation, including: obtaining abnormal state data of the lightning arrester, generating service environment data corresponding to high-frequency abnormal states through clustering, constructing a simulated environment data subset for environmental simulation, and obtaining the electrical parameter change characteristics of the lightning arrester during the aging process; obtaining the morphological feature sequence of the lightning arrester valve plate and matching it with the electrical parameter change characteristics, and obtaining the change of the temperature rise of the lightning arrester with the voltage amplitude; obtaining the aging status of the lightning arrester valve plate, monitoring the voltage and leakage current at both ends of the lightning arrester, and performing abnormal warning in combination with the overheating threshold corresponding to the lightning arrester under the aging status. The present invention restores the aging characteristics of the lightning arrester in the actual application process through environmental simulation, constructs a mapping relationship between the morphological characteristics of the lightning arrester valve plate, the degree of aging and the temperature rise status, and constructs a high-precision thermal threshold according to the mapping relationship, which provides a data basis for the reliability test and fault monitoring and operation and maintenance of the lightning arrester. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A flow chart of a lightning arrester test detection method based on environmental simulation of the present invention is shown;

[0043] Figure 2 A flow chart of analyzing the aging process of a lightning arrester in a test environment according to the present invention is shown;

[0044] Figure 3 It shows a flow chart of monitoring and early warning of the arrester to be detected according to the present invention;

[0045] Figure 4 A block diagram of a lightning arrester test and detection system based on environmental simulation of the present invention is shown. DETAILED DESCRIPTION

[0046] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0048] Figure 1 The flowchart of a lightning arrester test detection method based on environmental simulation of the present invention is shown.

[0049] like Figure 1 As shown, the first aspect of the present invention provides a lightning arrester test detection method based on environmental simulation, comprising:

[0050] S102, obtaining abnormal state data of the arrester, extracting service environment data of the abnormal state data, generating service environment data corresponding to the high-frequency abnormal state by clustering, and dividing it by different application scenarios to obtain a subset of simulated environment data;

[0051] S104, performing environmental simulation using different simulated environment data subsets, analyzing the aging process of the arrester in the test environment under environmental simulation, and obtaining the electrical parameter change characteristics of the valve plate of the arrester during the aging process;

[0052] S106, acquiring the morphological features of the arrester valve plate to construct a morphological feature sequence, matching the electrical parameter change features with the morphological features, setting sequence labels according to application scenarios, and acquiring the temperature rise of the arrester as a function of the voltage amplitude;

[0053] S108, obtaining the aging status according to the morphological characteristics of the valve plate of the arrester to be tested, monitoring the voltage and leakage current at both ends of the arrester, and issuing an abnormal warning based on the overheating threshold corresponding to the arrester under the aging status.

[0054] It should be noted that the basic parameter information such as the model parameters of the lightning arrester is obtained, and based on the basic parameter information, the abnormal state data is extracted using multi-source data feedback such as operation and maintenance information and fault monitoring, and the abnormal state data is preprocessed such as data cleaning, dimensionality reduction and normalization, and the service environment data contained in the abnormal state data after preprocessing is separated, including environmental temperature and humidity, climate information, power frequency voltage, etc.; the application scenarios of the lightning arrester are extracted according to the service environment data, and application scenario labels are generated, such as power equipment scenarios, building scenarios, and transportation facilities scenarios; the abnormal state data are clustered using the service environment data, and the clustering algorithm is optimized using a genetic algorithm, the population parameters are initialized, the fitness function is defined by calculating the silhouette coefficient, the population is updated through selection, inheritance and mutation, and the optimal number of clustering clusters is output after the update iteration reaches the maximum number of iterations, and the initial clustering center is randomly selected in the service environment data according to the optimal number of clustering clusters; the service The Euclidean distance of the environmental data samples is calculated, and each service environment data is assigned to the initial clustering center with the nearest distance to generate a clustering cluster, and the clustering center is updated by iterative clustering in the clustering cluster; when the end condition is reached, the final clustering result is obtained, and the clustering cluster that meets the preset screening criteria is selected and suspended according to the preset screening criteria of the cluster data volume, and the service environment data corresponding to the cluster is the service environment corresponding to the high-frequency abnormal state. In the suspended clustering cluster, the service environment data under the same application scenario label are aggregated to generate a service environment data change interval, for example, the service environment data of the building scene is aggregated, and the service environment data change interval is constructed according to the degree of quality of the environmental data; the overlap of different service environment data change intervals is obtained, and the intervals with overlap greater than the preset threshold are merged, and the updated service environment data change interval is obtained as the environmental simulation data, and the simulated environment data subsets of different application scenarios are constructed according to the environmental simulation data in the interval.

[0055] Figure 2 A flow chart of the present invention for analyzing the aging process of a lightning arrester in a test environment is shown.

[0056] According to an embodiment of the present invention, environmental simulation is performed using different simulated environment data subsets, the aging process of the arrester in the test environment under environmental simulation is analyzed, and the electrical parameter change characteristics of the valve plate of the arrester during the aging process are obtained, specifically:

[0057] S202, setting a time sequence for each simulated environment data subset to generate a simulated environment data sequence, constructing a lightning arrester test environment according to the simulated environment data sequence, and calculating the contribution by the ratio of the abnormal state data samples corresponding to the simulated environment data subsets of different application scenarios to all the abnormal state data samples;

[0058] S204, presetting the detection condition base value of the arrester, weighting the detection condition base value according to the contribution of different application scenarios, setting exclusive detection conditions in the arrester test environment, and reading the volt-ampere characteristic data of the valve plate during the aging process of the arrester in the test environment of different application scenarios;

[0059] S206, extracting the volt-ampere curve vector to record electrical parameters according to the volt-ampere characteristic data of the valve plate, obtaining the volt-ampere characteristic change characteristics of the valve plate through the residual of the volt-ampere curve vector under different detection conditions, and obtaining the electrical parameter change characteristics based on the volt-ampere characteristic change characteristics.

[0060] It should be noted that, according to the simulated environment data sequence, the environment simulation corresponding to the high-frequency abnormal state in the application scenario is carried out to construct the arrester test environment, and the detection condition base value of the arrester is preset in the test environment. The detection conditions include pressurization time, pressurization frequency, voltage amplitude, harmonic voltage frequency, etc. In the test environment of different application scenarios, the detection condition base value is weighted by using the contribution of the abnormal state to realize adaptive detection condition setting for different application scenarios. For application scenarios with high contribution, high-intensity detection conditions such as high duration and multiple frequencies are set. The volt-ampere characteristic data of the valve piece is obtained according to the voltage and leakage current, and the valve piece aging mechanism is obtained by obtaining the change of relevant electrical parameters. The aging degree is characterized by the change of electrical parameters. With the increase of pressurization time, the increase of pressurization frequency, the increase of voltage amplitude and the increase of harmonic voltage frequency, the changes in electrical parameters are getting bigger and bigger, which proves that the electrical performance of the arrester valve piece after aging is reduced.

[0061] It should be noted that the microscopic scanning images of the valve plate of the lightning arrester in different test environments are obtained, the microscopic scanning images are preprocessed, the corresponding valve plate template is retrieved according to the basic parameters of the lightning arrester, the preprocessed microscopic scanning image is matched with the valve plate template, and the similarity calculation is used to obtain the similarity distribution in the matching process; the valve plate area is obtained according to the contour size of the valve plate template and the similarity distribution, the neighbor points of each contour point on the contour of the valve plate template are obtained in the valve plate area, and the pixel point closest to the microscopic scanning image and the valve plate template is calculated according to the contour points and the neighbor points. Generate a valve plate area contour; sample discrete points in the valve plate area contour, use the discrete points to obtain the surface height distribution of the valve plate, calculate the mean and standard deviation of the surface height distribution, and aggregate the surface height distribution and the mean and standard deviation of the surface height distribution to generate morphological features; preferably, express the morphology of the valve plate in three-dimensional space according to three-dimensional surface roughness parameters such as the surface arithmetic mean deviation, sample on the valve plate plane, obtain the arithmetic mean height in the sampling area, and process the surface arithmetic mean deviation using statistical parameters such as the mean and standardization to aggregate and generate morphological features. Construct a morphological feature sequence according to the time sequence of the aging process, obtain the timestamp of the electrical parameter change feature, match the morphological feature sequence with the electrical parameter change feature according to the timestamp, and use the application scenario to label the device sequence of the matched morphological feature sequence.

[0062] It should be noted that a three-dimensional model of the arrester is obtained, the three-dimensional model is divided into three-dimensional grid blocks, and each three-dimensional grid block is classified according to its position information and structural information, and internal valve plate labels and external surface labels are added according to the classification results; the voltage distribution of the arrester during aging in different test environments is obtained, the voltage bearing rate of the arrester in different position structures under overvoltage detection is analyzed, a voltage distribution thermogram is generated according to the voltage distribution, the voltage distribution thermal value is read to obtain the distribution weight information, the distribution weight information is assigned to the three-dimensional grid blocks, and the temperature measurement point density is set in combination with the three-dimensional grid block category label. Under the action of the power frequency voltage, the temperature of the valve plate inside the arrester rises rapidly. Due to the material differences and position differences in different parts, the temperature distribution inside and outside the arrester is uneven. Usually, the temperature of the middle internal valve plate area is higher, and the upper and lower internal valve plate areas dissipate heat faster and have lower temperatures. Therefore, the temperature measurement point density in the center area is higher.

[0063] The arrester heats up while absorbing heat, and the heat is transferred to the test environment through insulating rubber and air to maintain the thermal balance of the arrester. According to the temperature value sensed by the temperature measuring point, the temperature value is interpolated in the three-dimensional model to obtain the thermal distribution of the arrester, and the temperature rise conditions inside and outside the arrester are analyzed by time series processing according to the thermal distribution; according to the exclusive detection conditions of different test environments, the voltage amplitude change interval is extracted to obtain the temperature rise change characteristics of the temperature rise conditions inside and outside the arrester with the voltage amplitude, the real-time internal and external temperature difference is obtained, and the internal and external temperature difference change characteristics are generated through the time convolution network; the temperature rise change characteristics and the internal and external temperature difference change characteristics are matched with the electrical parameter change characteristics and the morphological feature sequence according to the timestamp, and the mapping relationship between the morphological characteristics, aging degree and temperature rise conditions of the arrester valve plate is constructed, and the internal and external temperature rise of the arrester under the action of overvoltage is used to characterize its aging condition.

[0064] Figure 3 The flowchart of the present invention for monitoring and early warning of the arrester to be detected is shown.

[0065] According to an embodiment of the present invention, the aging status is obtained based on the morphological characteristics of the valve plate of the lightning arrester to be detected, the voltage and leakage current at both ends of the lightning arrester are monitored, and an abnormal warning is performed in combination with the overheating threshold corresponding to the lightning arrester under the aging status, specifically:

[0066] S302, extracting current morphological features according to the microscopic scanning image of the valve plate of the arrester to be detected, extracting corresponding morphological feature sequences according to the application scenario of the arrester to be detected, and performing point-by-point similarity comparison of the current morphological features in the extracted morphological feature sequences;

[0067] S304, based on the mapping relationship between the morphological features, the aging degree and the temperature rise condition, the aging status of the valve plate of the arrester to be detected is determined by using the average similarity, and the current and subsequent temperature rise change characteristics and the internal and external temperature difference change characteristics are obtained by the mapping relationship between the aging degree and the temperature rise condition;

[0068] S306, calculating the characteristic distribution of the current and subsequent temperature rise change characteristics and the internal and external temperature difference change characteristics, determining whether the temperature rise exceeds the arrester's tolerance range through the relative entropy between the characteristic distributions of different timestamps, and obtaining the overheating threshold corresponding to the arrester under the aging status;

[0069] S308, reading the thresholds of the voltage and leakage current at both ends of the arrester according to the overheating threshold based on the mapping relationship, and using the overheating threshold in combination with the voltage threshold and leakage current threshold at both ends to perform abnormal monitoring and early warning of the arrester to be detected.

[0070] It should be noted that when setting the overheating threshold corresponding to the arrester under the aging status, the relative entropy between the characteristic distributions of the temperature rise change characteristics and the internal and external temperature difference change characteristics is obtained. When the relative entropy is less than the preset relative entropy threshold, it means that the temperature rise condition of the arrester has reached stability, and its corresponding maximum temperature no longer increases significantly until it stabilizes. The limit operating temperature points inside and outside the arrester are obtained according to the temperature rise condition. When the limit operating temperature point is exceeded, the arrester will lose the balance of heat absorption and heat dissipation, and a thermal collapse failure will occur. In addition, the limit operating temperature point of the arrester is adaptively adjusted according to the application scenario of the arrester to be tested. As the ambient temperature of the application scenario increases, the limit operating temperature point decreases; in actual operation, the voltage distribution of the valve plates inside the arrester is uneven, and some valve plates are subjected to high voltage for a long time and have serious heat generation. Therefore, there are differences in the degree of aging of the valve plates. Valves with different aging degrees correspond to different overheating thresholds. The average value of the overheating threshold is calculated as the overheating threshold of the arrester as a whole. The extreme operating temperature point corresponding to the overheating threshold is located in the mapping relationship corresponding to the temperature rise condition, and the thresholds of the voltage and leakage current at both ends of the lightning arrester are read. For example, the leakage current and voltage corresponding to the extreme temperature point of 110°C in the electrical parameter change mapping relationship are 1.0μA and 6kV respectively, and the read leakage current and voltage are used as threshold information.

[0071] Whether the arrester meets the production application standards is judged according to the overheating threshold of the aging status of the arrester to be tested, the theoretical stable working temperature and the extreme working temperature of the arrester to be tested during operation are stored using basic parameters, and the adaptive coefficient of temperature adjustment is calculated using the contribution of abnormal state data samples in different application scenarios to weight the stored extreme temperature working points, and the extreme working temperature point corresponding to the overheating threshold is read according to the arrester test simulated by the environment; the extreme working temperature point is compared with the theoretical extreme working temperature after coefficient weighting, and when the deviation is less than the preset deviation threshold, it is proved that the arrester to be tested meets the production application standards.

[0072] Figure 4 A block diagram of a lightning arrester test and detection system based on environmental simulation of the present invention is shown.

[0073] The second aspect of the present invention further provides a lightning arrester test detection system 4 based on environmental simulation, the system comprising: a memory 41, a processor 42, the memory comprising a lightning arrester test detection method program based on environmental simulation, the lightning arrester test detection method program based on environmental simulation being executed by the processor to implement the following steps:

[0074] Obtain abnormal state data of the arrester, extract service environment data of the abnormal state data, generate service environment data corresponding to the high-frequency abnormal state through clustering, and divide it according to different application scenarios to obtain a subset of simulated environment data;

[0075] Use different simulated environment data subsets to perform environmental simulation, analyze the aging process of the arrester in the test environment under environmental simulation, and obtain the electrical parameter change characteristics of the valve plate of the arrester during the aging process;

[0076] Acquire the morphological features of the arrester valve plate to construct a morphological feature sequence, match the electrical parameter change features with the morphological features, set sequence labels using application scenarios, and obtain the temperature rise of the arrester as a function of voltage amplitude;

[0077] The aging status is obtained according to the morphological characteristics of the valve plate of the lightning arrester to be tested, the voltage and leakage current at both ends of the lightning arrester are monitored, and abnormal warning is issued based on the overheating threshold corresponding to the lightning arrester under the aging status.

[0078] The third aspect of the present invention also provides a computer-readable storage medium, which includes a lightning arrester test and detection method program based on environmental simulation. When the lightning arrester test and detection method program based on environmental simulation is executed by a processor, the steps of the lightning arrester test and detection method based on environmental simulation as described in any one of the above items are implemented.

[0079] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. 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 can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0080] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0081] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0082] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0083] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected 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, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0084] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A lightning arrester test detection method based on environmental simulation, characterized in that: The following steps are involved: Obtain abnormal state data of the arrester, extract service environment data of the abnormal state data, generate service environment data corresponding to the high-frequency abnormal state through clustering, and divide it according to different application scenarios to obtain a subset of simulated environment data; Use different simulated environment data subsets to perform environmental simulation, analyze the aging process of the arrester in the test environment under environmental simulation, and obtain the electrical parameter change characteristics of the valve plate of the arrester during the aging process; Acquire the morphological features of the arrester valve plate to construct a morphological feature sequence, match the electrical parameter change features with the morphological features, set sequence labels using application scenarios, and obtain the temperature rise of the arrester as a function of voltage amplitude; The aging status is obtained based on the morphological characteristics of the valve plate of the lightning arrester to be tested, the voltage and leakage current at both ends of the lightning arrester are monitored, and abnormal warning is issued based on the overheating threshold corresponding to the lightning arrester under the aging status; Different simulated environment data subsets are used to perform environmental simulation, analyze the aging process of the arrester in the test environment under environmental simulation, and obtain the electrical parameter change characteristics of the valve plate of the arrester during the aging process, specifically: Setting a time sequence for each simulated environment data subset to generate a simulated environment data sequence, constructing a lightning arrester test environment according to the simulated environment data sequence, and calculating the contribution by the ratio of the abnormal state data samples corresponding to the simulated environment data subsets of different application scenarios to all the abnormal state data samples; Preset the detection condition base value of the arrester, weight the detection condition base value according to the contribution of different application scenarios, set exclusive detection conditions in the arrester test environment, and read the volt-ampere characteristic data of the valve plate during the aging process of the arrester in the test environment of different application scenarios; Extracting the volt-ampere curve vector and recording the electrical parameters according to the volt-ampere characteristic data of the valve plate, obtaining the volt-ampere characteristic change characteristics of the valve plate through the residual of the volt-ampere curve vector under different detection conditions, and obtaining the electrical parameter change characteristics based on the volt-ampere characteristic change characteristics; The morphological features of the arrester valve plate are obtained to construct a morphological feature sequence, the electrical parameter change features are matched with the morphological features, and the sequence labels are set according to the application scenario, specifically: Obtaining microscopic scanning images of valve plates of lightning arresters in different test environments, preprocessing the microscopic scanning images, matching the preprocessed microscopic scanning images with valve plate templates, and obtaining similarity distribution in the matching process by similarity calculation; The valve plate area is obtained according to the contour size of the valve plate template and the similarity distribution, the neighboring points of each contour point on the valve plate template contour are obtained in the valve plate area, and the pixel point closest to the microscopic scanning image and the valve plate template is calculated according to the contour points and the neighboring points to generate the valve plate area contour; Sampling discrete points in the valve plate area contour, using the discrete points to obtain the surface height distribution of the valve plate, calculating the mean and standard deviation of the surface height distribution, and aggregating the surface height distribution and the mean and standard deviation of the surface height distribution to generate a morphological feature; Construct a morphological feature sequence according to the time sequence of the aging process, obtain the timestamp of the electrical parameter change feature, match the morphological feature sequence with the electrical parameter change feature according to the timestamp, and use the application scenario to label the matched morphological feature sequence device sequence; Obtain the change of arrester temperature rise with voltage amplitude, specifically: Obtain a three-dimensional model of the arrester, divide the three-dimensional model into three-dimensional grid blocks, classify the three-dimensional grid blocks according to their position information and structural information, and add internal valve plate labels and external surface labels according to the classification results; Obtaining voltage distribution of the arrester during aging in different test environments, obtaining distribution weight information according to the voltage distribution, allocating the distribution weight information to the three-dimensional grid blocks, and setting the temperature measurement point density in combination with the three-dimensional grid block category label; According to the temperature value sensed by the temperature measuring point, the temperature value is interpolated in the three-dimensional model to obtain the thermal distribution of the arrester, and the temperature rise condition inside and outside the arrester is analyzed by time series processing according to the thermal distribution; According to the exclusive detection conditions of different test environments, the voltage amplitude change interval is extracted, the temperature rise condition inside and outside the arrester is obtained along with the temperature rise change characteristics of the voltage amplitude, the real-time internal and external temperature difference is obtained, and the internal and external temperature difference change characteristics are generated through the time convolution network; The temperature rise change characteristics and the internal and external temperature difference change characteristics are matched with the electrical parameter change characteristics and the morphological feature sequence according to the timestamp, and the mapping relationship between the arrester valve plate morphological characteristics, aging degree and temperature rise condition is constructed; The aging status is obtained based on the morphological characteristics of the valve plate of the lightning arrester to be tested, the voltage and leakage current at both ends of the lightning arrester are monitored, and abnormal warning is carried out in combination with the overheating threshold corresponding to the lightning arrester under the aging status, specifically: Extracting current morphological features according to the microscopic scanning image of the valve plate of the arrester to be detected, extracting corresponding morphological feature sequences according to the application scenarios of the arrester to be detected, and performing point-by-point similarity comparison of the current morphological features in the extracted morphological feature sequences; Based on the mapping relationship between morphological features, aging degree and temperature rise conditions, the average similarity is used to determine the aging status of the valve plate of the arrester to be tested. In addition, the current and subsequent temperature rise change characteristics and internal and external temperature difference change characteristics are obtained through the mapping relationship between aging degree and temperature rise conditions. Calculate the characteristic distribution of the current and subsequent temperature rise change characteristics and the internal and external temperature difference change characteristics, determine whether the temperature rise exceeds the arrester's tolerance range through the relative entropy between the characteristic distributions of different timestamps, and obtain the overheating threshold corresponding to the arrester under the aging status; The voltage and leakage current thresholds of the arrester are read according to the mapping relationship according to the overheating threshold, and the abnormal monitoring and early warning of the arrester to be detected are performed by combining the overheating threshold with the voltage threshold and the leakage current threshold.

2. The method for testing and detecting a lightning arrester based on environmental simulation according to claim 1, characterized in that: Extract the service environment data of abnormal state data, generate service environment data corresponding to high-frequency abnormal state through clustering, and divide it according to different application scenarios to obtain the simulated environment data subset, specifically: Acquire basic parameter information of the arrester, extract abnormal state data based on the basic parameter information by using multi-source data feedback, pre-process the abnormal state data, and separate the service environment data contained in the abnormal state data after pre-processing; Extracting application scenarios of lightning arresters according to the service environment data, generating application scenario labels, clustering abnormal state data using the service environment data, optimizing the clustering algorithm using a genetic algorithm, and selecting initial clustering centers; Calculate the Euclidean distance of the service environment data samples, and assign each service environment data to the initial cluster center with the closest distance to generate a cluster cluster, and update the cluster center in the cluster cluster through iterative clustering; When the end condition is reached, the final clustering result is obtained, and according to the preset screening criteria of the cluster data volume, the clusters that meet the preset screening criteria are selected for suspension, and the service environment data under the same application scenario label in the suspended clusters are aggregated to generate the service environment data change interval; Obtain the overlap of different service environment data change intervals, merge the intervals with overlap greater than a preset threshold, obtain the updated service environment data change interval as environmental simulation data, and construct simulation environment data subsets for different application scenarios based on the environmental simulation data in the interval.

3. A lightning arrester test and detection system based on environmental simulation, characterized in that: The system comprises: a memory and a processor, wherein the memory comprises a lightning arrester test detection method program based on environmental simulation, and the lightning arrester test detection method program based on environmental simulation is executed by the processor to implement the following steps: Obtain abnormal state data of the arrester, extract service environment data of the abnormal state data, generate service environment data corresponding to the high-frequency abnormal state through clustering, and divide it according to different application scenarios to obtain a subset of simulated environment data; Use different simulated environment data subsets to perform environmental simulation, analyze the aging process of the arrester in the test environment under environmental simulation, and obtain the electrical parameter change characteristics of the valve plate of the arrester during the aging process; Acquire the morphological features of the arrester valve plate to construct a morphological feature sequence, match the electrical parameter change features with the morphological features, set sequence labels using application scenarios, and obtain the temperature rise of the arrester as a function of voltage amplitude; The aging status is obtained based on the morphological characteristics of the valve plate of the lightning arrester to be tested, the voltage and leakage current at both ends of the lightning arrester are monitored, and abnormal warning is issued based on the overheating threshold corresponding to the lightning arrester under the aging status; Different simulated environment data subsets are used to perform environmental simulation, analyze the aging process of the arrester in the test environment under environmental simulation, and obtain the electrical parameter change characteristics of the valve plate of the arrester during the aging process, specifically: Setting a time sequence for each simulated environment data subset to generate a simulated environment data sequence, constructing a lightning arrester test environment according to the simulated environment data sequence, and calculating the contribution by the ratio of the abnormal state data samples corresponding to the simulated environment data subsets of different application scenarios to all the abnormal state data samples; Preset the detection condition base value of the arrester, weight the detection condition base value according to the contribution of different application scenarios, set exclusive detection conditions in the arrester test environment, and read the volt-ampere characteristic data of the valve plate during the aging process of the arrester in the test environment of different application scenarios; Extracting the volt-ampere curve vector and recording the electrical parameters according to the volt-ampere characteristic data of the valve plate, obtaining the volt-ampere characteristic change characteristics of the valve plate through the residual of the volt-ampere curve vector under different detection conditions, and obtaining the electrical parameter change characteristics based on the volt-ampere characteristic change characteristics; The morphological features of the arrester valve plate are obtained to construct a morphological feature sequence, the electrical parameter change features are matched with the morphological features, and the sequence labels are set according to the application scenario, specifically: Obtaining microscopic scanning images of valve plates of lightning arresters in different test environments, preprocessing the microscopic scanning images, matching the preprocessed microscopic scanning images with valve plate templates, and obtaining similarity distribution in the matching process by similarity calculation; The valve plate area is obtained according to the contour size of the valve plate template and the similarity distribution, the neighboring points of each contour point on the valve plate template contour are obtained in the valve plate area, and the pixel point closest to the microscopic scanning image and the valve plate template is calculated according to the contour points and the neighboring points to generate the valve plate area contour; Sampling discrete points in the valve plate area contour, using the discrete points to obtain the surface height distribution of the valve plate, calculating the mean and standard deviation of the surface height distribution, and aggregating the surface height distribution and the mean and standard deviation of the surface height distribution to generate a morphological feature; Construct a morphological feature sequence according to the time sequence of the aging process, obtain the timestamp of the electrical parameter change feature, match the morphological feature sequence with the electrical parameter change feature according to the timestamp, and use the application scenario to label the matched morphological feature sequence device sequence; Obtain the change of arrester temperature rise with voltage amplitude, specifically: Obtain a three-dimensional model of the arrester, divide the three-dimensional model into three-dimensional grid blocks, classify the three-dimensional grid blocks according to their position information and structural information, and add internal valve plate labels and external surface labels according to the classification results; Obtaining voltage distribution of the arrester during aging in different test environments, obtaining distribution weight information according to the voltage distribution, allocating the distribution weight information to the three-dimensional grid blocks, and setting the temperature measurement point density in combination with the three-dimensional grid block category label; According to the temperature value sensed by the temperature measuring point, the temperature value is interpolated in the three-dimensional model to obtain the thermal distribution of the arrester, and the temperature rise condition inside and outside the arrester is analyzed by time series processing according to the thermal distribution; According to the exclusive detection conditions of different test environments, the voltage amplitude change interval is extracted, the temperature rise condition inside and outside the arrester is obtained along with the temperature rise change characteristics of the voltage amplitude, the real-time internal and external temperature difference is obtained, and the internal and external temperature difference change characteristics are generated through the time convolution network; The temperature rise change characteristics and the internal and external temperature difference change characteristics are matched with the electrical parameter change characteristics and the morphological feature sequence according to the timestamp, and the mapping relationship between the arrester valve plate morphological characteristics, aging degree and temperature rise condition is constructed; The aging status is obtained based on the morphological characteristics of the valve plate of the lightning arrester to be tested, the voltage and leakage current at both ends of the lightning arrester are monitored, and abnormal warning is carried out in combination with the overheating threshold corresponding to the lightning arrester under the aging status, specifically: Extracting current morphological features according to the microscopic scanning image of the valve plate of the arrester to be detected, extracting corresponding morphological feature sequences according to the application scenarios of the arrester to be detected, and performing point-by-point similarity comparison of the current morphological features in the extracted morphological feature sequences; Based on the mapping relationship between morphological features, aging degree and temperature rise conditions, the average similarity is used to determine the aging status of the valve plate of the arrester to be tested. In addition, the current and subsequent temperature rise change characteristics and internal and external temperature difference change characteristics are obtained through the mapping relationship between aging degree and temperature rise conditions. Calculate the characteristic distribution of the current and subsequent temperature rise change characteristics and the internal and external temperature difference change characteristics, determine whether the temperature rise exceeds the arrester's tolerance range through the relative entropy between the characteristic distributions of different timestamps, and obtain the overheating threshold corresponding to the arrester under the aging status; The voltage and leakage current thresholds of the arrester are read according to the mapping relationship according to the overheating threshold, and the abnormal monitoring and early warning of the arrester to be detected are performed by combining the overheating threshold with the voltage threshold and the leakage current threshold.

Images