A high-voltage switch cabinet contact composite monitoring method and device

Abstract

This application provides a method and apparatus for composite monitoring of high-voltage switchgear contacts, belonging to the field of power equipment monitoring. The method includes: acquiring various types of parameter data of the high-voltage switchgear contacts to be measured; preprocessing the parameter data; determining the fault type corresponding to each type of parameter data based on a fault database and the preprocessed parameter data, wherein the fault database stores the mapping relationship between fault types and intervals of each type of parameter data; determining a comprehensive deviation based on the deviation corresponding to each type of parameter data after preprocessing, and then determining a target interval for the comprehensive deviation to characterize the fault degree of the high-voltage switchgear contacts; and monitoring the state of the high-voltage switchgear contacts based on the fault type and the target interval. The high-voltage switchgear contact composite monitoring method and apparatus provided in this application can accurately monitor the fault type and fault degree of high-voltage switchgear contacts, improving the monitoring efficiency and accuracy of high-voltage switchgear contacts.

Description

Technical Field

[0001] This application belongs to the field of power equipment monitoring technology, and more specifically, relates to a composite monitoring method and device for high-voltage switchgear contacts. Background Technology

[0002] High-voltage switchgear, as a key component of power equipment, undertakes the functions of receiving, distributing, controlling, and protecting electrical energy, ensuring the stable operation of the power grid. Traditional methods for monitoring the contacts of high-voltage switchgear often rely on the deviation of a single parameter from a static threshold to trigger an alarm, ignoring the combined influence of multiple parameters. This results in a high false alarm rate and makes it difficult to meet the reliability and safety requirements of high-voltage switchgear contacts. Summary of the Invention

[0003] The purpose of this application is to provide a composite monitoring method and device for high-voltage switchgear contacts, so as to improve the monitoring efficiency and accuracy of high-voltage switchgear contacts.

[0004] A first aspect of this application provides a method for composite monitoring of contacts in a high-voltage switchgear, comprising:

[0005] Acquire the test data of the contacts of the high-voltage switchgear. The test data includes various types of parameter data. Preprocess the test data to obtain the preprocessed parameter data of various types, including temperature data, pressure data and environmental data.

[0006] Based on the fault database and various types of parameter data, the fault type corresponding to each type of parameter data is determined. The fault database stores the mapping relationship between fault types and the intervals of each type of parameter data.

[0007] The comprehensive deviation is determined based on the deviation of each type of parameter data after preprocessing. The target range of the comprehensive deviation is then determined based on the comprehensive deviation. The target range is used to characterize the fault degree of the contacts in the high-voltage switchgear.

[0008] Based on the target range of fault type and comprehensive deviation, monitor the status of high-voltage switchgear contacts;

[0009] The fault database was determined in the following way:

[0010] Acquire historical data of the contacts of the high-voltage switchgear. The historical data includes various types of historical parameter data, such as historical temperature data, historical pressure data, and historical environmental data.

[0011] Historical data is preprocessed, and a fault database is determined based on the preprocessed historical data and the digital twin model.

[0012] A second aspect of this application provides a composite monitoring device for high-voltage switchgear contacts, comprising:

[0013] The data acquisition module is used to acquire the test data of the contacts of the high-voltage switchgear. The test data includes various types of parameter data, including temperature data, pressure data and environmental data. The test data is preprocessed to obtain the preprocessed parameter data of each type.

[0014] The fault type determination module is used to determine the fault type corresponding to each type of parameter data based on the fault database and the parameter data of each type. The fault database stores the mapping relationship between the fault type and the interval of each type of parameter data.

[0015] The fault severity determination module is used to determine the comprehensive deviation based on the deviation of each type of parameter data after preprocessing, and to determine the target range of the comprehensive deviation based on the comprehensive deviation. The target range is used to characterize the fault severity of the contacts of the high-voltage switchgear.

[0016] The status monitoring module is used to monitor the status of the contacts of the high-voltage switchgear based on the target range of fault type and comprehensive deviation.

[0017] Among them, the fault type determination module is specifically used to obtain historical data of the contacts of the high-voltage switchgear. The historical data includes various types of historical parameter data, including historical temperature data, historical pressure data, and historical environmental data.

[0018] Historical data is preprocessed, and a fault database is determined based on the preprocessed historical data and the digital twin model.

[0019] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the above-described high-voltage switchgear contact composite monitoring method.

[0020] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described high-voltage switchgear contact composite monitoring method.

[0021] The beneficial effects of the composite monitoring method and device for high-voltage switchgear contacts provided in this application are as follows: This application determines the fault type based on preprocessed parameter data of various types and the fault database, determines the corresponding comprehensive deviation based on preprocessed parameter data of various types, and then determines the target range of the comprehensive deviation. Based on the target range of the comprehensive deviation, the fault degree of the high-voltage switchgear contacts is determined, forming a systematic monitoring method for the state of high-voltage switchgear contacts, improving the comprehensiveness and accuracy of fault judgment; This application considers the complex working conditions of the contacts by using temperature, pressure and environmental data, avoiding the limitations of single parameter monitoring, ensuring the accuracy of monitoring results, and improving the reliability of high-voltage switchgear contacts. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 A flowchart illustrating a composite monitoring method for contacts in a high-voltage switchgear, provided as an embodiment of this application;

[0024] Figure 2 A structural block diagram of a composite monitoring device for high-voltage switchgear contacts provided in an embodiment of this application;

[0025] Figure 3 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0026] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0027] To make the objectives, technical solutions, and advantages of this application clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0028] Please refer to Figure 1 , Figure 1 This application provides a flowchart illustrating a composite monitoring method for contacts in a high-voltage switchgear, which may include:

[0029] S101: Acquire the test data of the contacts of the high-voltage switchgear. The test data includes various types of parameter data. Preprocess the test data to obtain the preprocessed parameter data of various types, including temperature data, pressure data and environmental data.

[0030] In this embodiment, the measured data of the high-voltage switchgear contacts are acquired from various sensors near the contacts. These sensors include temperature sensors, pressure sensors, and environmental sensors. The measured data includes various types of parameter data, such as temperature data, pressure data, and environmental data. Data preprocessing is performed on each type of parameter data using a 3D model. The principle is to determine whether each collected data point is abnormal. For abnormal data, interpolation is used to correct it. Normalization is performed on all types of parameter data.

[0031] S102: Based on the fault database and various types of parameter data, determine the fault type corresponding to each type of parameter data. The fault database stores the mapping relationship between fault types and the intervals of various types of parameter data.

[0032] This embodiment determines the fault type corresponding to each type of parameter data based on the fault database and various types of parameter data (e.g., temperature data, pressure data, environmental data). Specifically, it obtains historical fault records from the fault database, which include fault types (e.g., initial poor contact of contacts, damp environment, short circuit, etc.) and the corresponding parameter data for each type of fault when it occurred.

[0033] The fault database was determined in the following way:

[0034] Acquire historical data of the contacts of the high-voltage switchgear. The historical data includes various types of historical parameter data, such as historical temperature data, historical pressure data, and historical environmental data.

[0035] Historical data is preprocessed, and a fault database is determined based on the preprocessed historical data and the digital twin model.

[0036] In this embodiment, historical data of the high-voltage switchgear contacts is acquired. This historical data is multi-type data, including various parameter data such as temperature, pressure, and environmental data. Specifically, surface temperature data of the high-voltage switchgear contacts is collected using an infrared thermometer, pressure data is recorded using a pressure sensor, and environmental data (e.g., temperature and humidity data) of the high-voltage switchgear's interior is acquired using sensors. The historical data undergoes preprocessing, including handling missing and outlier values, and unifying the frequency of the various data types to a time series of 1 occurrence per 15 minutes. All historical data is converted to a unified format; for example, temperature data can be converted to the temperature difference between the contact and ambient temperatures to eliminate interference from ambient temperature; pressure data is converted to a pressure deviation rate. Statistical characteristic parameters and trend characteristics of each type of parameter data are extracted from the historical data.

[0037] A digital twin model consistent with the physical contacts is constructed to simulate the fault scenarios corresponding to each fault type. Based on the three-dimensional structure of the switchgear and the physical characteristics of the contacts, a digital twin model is constructed. The input parameters are pre-processed parameter data of various types, including temperature difference, pressure deviation rate and ambient humidity. The output is the simulation results of the contact operation status.

[0038] In this embodiment, fault types can include poor contact of the contacts, failure of the contact spring, and dampness in the environment. Normal parameter data from historical data (e.g., temperature difference < 25℃, pressure deviation rate between -5% and +5%, ambient humidity ≤ 85%) is input, and the model outputs the normal operating state of the contacts. Abnormal samples from historical data (e.g., a set of data showing a temperature difference > 30℃ for 3 consecutive hours, a pressure deviation rate of -10%, and ambient humidity of 90%) are input, and the model simulates the poor contact state of the contacts.

[0039] Based on the output of the digital twin model, the faults are categorized according to fault type, operating status, and parameter values ​​of each type. The equipment operating status at the time of the fault is recorded, and the parameter data of each type corresponding to the same fault type under different operating states are associated and archived. A fault database is determined based on the correspondence between fault types and parameter data of each type.

[0040] S103: Determine the comprehensive deviation based on the deviation of each type of parameter data after preprocessing, and determine the target range of the comprehensive deviation based on the comprehensive deviation. This target range is used to characterize the fault degree of the high-voltage switchgear contacts.

[0041] In this embodiment, a preset temperature difference threshold is set, and the temperature deviation is determined based on the contact temperature and the ambient temperature; the pressure deviation rate is used as the pressure deviation; a preset ambient humidity range threshold is set, and the ambient humidity deviation is determined based on the actual humidity.

[0042] The overall deviation can be determined by matching the weights of temperature deviation, pressure deviation, and environmental deviation according to a preset weighting ratio, and then determining these weights for each of the temperature deviation, pressure deviation, and environmental humidity deviation. Alternatively, the weights for the deviations of each type of parameter data can be determined based on the information entropy corresponding to the deviations of each type of parameter data and the first formula. The first formula is... ,in, For the first i The weights corresponding to the deviation of each type of parameter data n For the number of types, For the first i The information entropy corresponding to the deviation of each type of parameter data.

[0043] This embodiment can determine the comprehensive deviation degree corresponding to each time period based on temperature data, pressure data, and environmental data for each time period. An initial interval for the comprehensive deviation degree is then defined based on this comprehensive deviation degree, and an initial risk level is determined. Furthermore, a target interval for the comprehensive deviation degree is determined based on this initial interval; this target interval is used to characterize the degree of failure of the fault type.

[0044] The severity of a fault type is determined based on the target range of each comprehensive deviation and the initial fault type.

[0045] For example, the preset temperature threshold can be 25℃, and the temperature deviation is... ,in, T This represents the temperature difference between the contact point and the ambient temperature. t 0 represents the preset temperature threshold; if T ≤ t0, then ΔT is zero. The pressure deviation rate is... ,in, P To measure the actual pressure, P 0 represents the rated pressure. The preset ambient humidity range threshold can be 30%-70%, with 70% as the upper limit. The ambient humidity deviation is... ,in, H To measure the ambient humidity, when the ambient humidity is... H When ≤70%, ΔH is zero.

[0046] In this embodiment, the overall deviation can be determined based on the weight of the deviation corresponding to each type of parameter data. A weight is assigned to the deviation corresponding to each type of parameter data based on its impact on equipment failure, with the total weight being 1. In this embodiment, contact pressure and temperature have a significant impact on the contact state, and are assigned relatively high weights. For example, the weight of pressure deviation is set to 0.4, the weight of temperature deviation is set to 0.4, and the weight of ambient humidity deviation is set to 0.2. The overall deviation is determined based on each deviation and its corresponding weight. An initial range for the overall deviation is then determined based on this initial range, and a target range for the overall deviation is determined based on this initial range. The risk level is determined based on the initial range of the overall deviation. The initial range of the overall deviation S and its corresponding risk level can be: if the overall deviation is in the first initial range (0 < S < 5%), the equipment is in a safe range with no significant failure risk; if the overall deviation is in the second initial range (5% ≤ S ≤ 15%), the equipment is in a warning range and requires enhanced monitoring; if the overall deviation is in the third initial range (S > 15%), the equipment is in a risk range and requires immediate investigation. In this embodiment, the initial interval division can be dynamically adjusted according to the equipment model and operating environment. For example, the threshold of the high-risk interval can be appropriately reduced for older equipment.

[0047] S104: Monitor the status of high-voltage switchgear contacts based on the target range of fault type and comprehensive deviation.

[0048] In this embodiment, the severity of a fault type is determined based on the fault types in the fault database and the target range of the comprehensive deviation. The target range of the comprehensive deviation includes a first target range, a second target range, and a third target range. Specifically, the severity of the fault type is determined based on the following method:

[0049] For each fault type, the corresponding parameter data is determined based on the fault database. Then, the corresponding comprehensive deviation is determined based on the determined parameter data. If the comprehensive deviation value is within the first target range, the fault type is classified as a Level 1 fault; if it is within the second target range, it is classified as a Level 2 fault; and if it is within the third target range, it is classified as a Level 3 fault. The severity of the fault increases sequentially from Level 1 to Level 3.

[0050] Based on the fault type and the corresponding range, determine the monitoring results of the high-voltage switchgear contacts, clarify the contact status, and present the monitoring results in a visual form.

[0051] For example, the corresponding fault type is determined based on the test data of the contact of the high-voltage switchgear under test. If the comprehensive deviation determined based on the test data is 8% (within the second target range), then the comprehensive deviation corresponding to the test data belongs to the second level fault, and the monitoring of the high-voltage switch contact needs to be strengthened.

[0052] As can be seen from the above, the embodiments of this application acquire the test data of the high-voltage switchgear, preprocess the test data, determine the corresponding fault type based on the fault database and the preprocessed test data, determine the comprehensive deviation based on the deviation of the preprocessed test data, determine the target range of the comprehensive deviation, and then determine the fault severity of the fault type based on the fault type and the target range of the comprehensive deviation, thus forming a systematic management mechanism for monitoring the contact status of the high-voltage switchgear. The embodiments of this application integrate temperature data, pressure data and environmental data, comprehensively consider the complex working conditions of the contacts, avoid the limitations of single parameter monitoring, and ensure the accuracy of monitoring results.

[0053] In one embodiment of this application, a comprehensive deviation is determined based on the deviation corresponding to each type of preprocessed parameter data, and a target range for the comprehensive deviation is determined based on the comprehensive deviation, including:

[0054] The weights corresponding to the deviations of each type of parameter data are determined based on the entropy method and the deviations of the preprocessed parameter data. The comprehensive deviation of each type of parameter data is determined based on the weights corresponding to the deviations of the preprocessed parameter data. The initial range of the comprehensive deviation is determined based on the comprehensive deviation.

[0055] The sliding range of the overall deviation is determined based on the sliding window.

[0056] Determine the target range for the overall deviation based on the initial range and the sliding range;

[0057] Before determining the weights corresponding to the deviations of each type of parameter data after preprocessing based on the entropy method, the process also includes:

[0058] Based on the deviation of each type of parameter data after preprocessing, the standardized value proportion of the deviation of each type of parameter data is determined. The standardized value proportion is the proportion of the deviation value of each type of parameter data in the total standardized deviation value of all types of parameter data.

[0059] The weights corresponding to the deviations of each type of parameter data are determined based on the entropy method and the deviations of the preprocessed parameter data, including:

[0060] Based on the standardized value proportion of the deviation of each type of parameter data and the entropy method formula, the information entropy corresponding to the deviation of each type of parameter data after preprocessing is determined. Based on the information entropy and the first formula, the weights corresponding to the deviation of each type of parameter data are determined respectively.

[0061] The entropy method formula is as follows: ,in, For the first i The information entropy corresponding to the difference in the data bias of each type of parameter. m For the first i The total number of data points collected for each type of parameter. p ij For the first i The first type parameter data j The proportion of standardized values ​​for each parameter data;

[0062] The first formula is: ,in, For the first i The weights corresponding to the deviation of each type of parameter data For the first i The information entropy corresponding to the deviation of each type of parameter data n Number of types.

[0063] In this embodiment, the standardized percentage of the deviation of each type of parameter data is first determined based on the deviation of the preprocessed parameter data. The standardized value percentage is the proportion of the deviation value of each type of parameter data in the total standardized deviation value of all types of parameter data.

[0064] For example, data for each type of parameter was collected three times, and the standardized deviation values ​​of the three types of parameter data were obtained after three sets of preprocessing, as shown in Table 1 below. For each type of parameter, the standardized value proportion of the deviation of the parameter type was determined based on the sum of the standardized values ​​of that type of parameter in the three sets of parameter data. For example, ρ 11 This represents the percentage of the standardized value of the first parameter data in the first parameter type (contact pressure). ρ 11 =0.8 / (0.8+0.9+0.7)≈0.33.

[0065] Table 1 Standardized deviation values ​​for each type of parameter data

[0066]

[0067] Based on the standardized value proportion of the deviation of each type of parameter data and the entropy method, the information entropy corresponding to the deviation of each type of parameter data after preprocessing is determined. Based on the information entropy and the first formula, the weights corresponding to the deviation of each type of parameter data are determined.

[0068] The entropy method formula is: ,in, For the first i The information entropy corresponding to the deviation of each type of parameter data m For the first i The total number of data points collected for each type of parameter. p ij For the first i The first type parameter data j The percentage of standardized values ​​for each parameter.

[0069] The first formula is: ,in, For the first i The weights corresponding to the deviation of each type of parameter data n The number of data types is [number], and the sum of the weights corresponding to the deviation of each data type is 1. The overall deviation is determined based on the parameter data of each type and its corresponding weight. The overall deviation is [value]. ,in, For the first i The deviation of the parameter data of each type.

[0070] The initial range of the overall deviation is determined based on the overall deviation of all the data to be measured. In this embodiment, three initial ranges for the overall deviation are set as [0, 5%], [5%, 15%], and [15%, 1%]. If 0 ≤ overall deviation S < 5%, the equipment is in the safe range, and there is no obvious risk of failure of the contacts of the high-voltage switchgear. If 5% ≤ overall deviation S ≤ 15%, the equipment is in the warning range, and the monitoring of the contacts of the high-voltage switchgear needs to be strengthened. If the overall deviation S > 15%, the equipment is in the risk range, and the contacts of the high-voltage switchgear need to be checked immediately.

[0071] Set the size of the sliding window to continuous. k With a sliding step size of 1, the sliding window includes comprehensive deviation data corresponding to k time points. The mean comprehensive deviation of the sliding window is determined based on the comprehensive deviation data. and range R The formula for calculating the range is: The sliding interval is determined based on the mean and range of the overall deviation of the sliding window. The sliding interval is... .

[0072] Based on the initial interval of the comprehensive deviation, if the mean of the comprehensive deviation of the sliding window is... If the value falls within a certain initial interval, then that initial interval is taken as the target interval; if the average comprehensive deviation of the sliding window is... If two consecutive windows cross the boundary of the initial interval, then the interval is updated, and the target interval for the overall deviation is determined based on the updated interval.

[0073] If the average comprehensive deviation of the sliding window If two consecutive windows cross the boundary of the initial interval, the specific steps to update the interval are as follows: Set the initial interval to [ L 初始 , U 初始 If two consecutive means , If both are below the lower boundary of the initial interval, then the lower boundary of the new interval is the lower boundary of the sliding interval corresponding to the minimum value of the two consecutive average comprehensive deviations. The upper boundary remains unchanged, meaning the target interval for the comprehensive deviation is [ , U 初始 ], The lower boundary of the sliding interval corresponds to the minimum of two consecutive mean comprehensive deviations; if both consecutive mean values ​​are higher than the upper boundary of the initial interval, then the upper boundary of the new interval is the upper boundary of the sliding interval corresponding to the maximum of the two mean values, while the lower boundary remains unchanged. That is, the target interval for the comprehensive deviation is […]. L 初始 , ], The maximum value of two consecutive mean comprehensive deviations corresponds to the upper boundary of the sliding interval; if two consecutive means cross the upper and lower boundaries of the initial interval respectively (for example, < L 初始 and > U 初始 Then, based on the two means, the upper and lower boundaries are determined, that is, the target range for the overall deviation is... ,in, This represents the average overall deviation of the first sliding window. This represents the average overall deviation of the second sliding window. This represents the extreme value of the overall deviation for the first sliding window. This represents the range of the overall deviation of the second sliding window.

[0074] For example, the sliding window size is 5. The mean of the overall deviation of the first sliding window is 3% (lower than the lower boundary of the second initial interval), the range is 0.4%, and the corresponding sliding interval is [2.8%, 3.2%]; the mean of the overall deviation of the second sliding window is 6% (higher than the upper boundary of the first initial interval), the range is 0.5%, and the corresponding sliding interval is [5.75%, 6.25%].

[0075] Since the combined mean deviation of the two sliding windows crosses the boundaries of [0, 5%] and [5%, 15%], the steps for updating the target interval based on the initial interval and the sliding interval are as follows: the lower boundary of the target interval is 2.8%, and the upper boundary of the target interval is... =6.25%, the updated target interval is [2.8%, 6.25%]. This target interval merges part of the first initial interval and part of the second initial interval. This target interval is taken as the first target interval, and the remaining interval of the second initial interval is determined as the second target interval. The second target interval is [6.25%, 15%], and the third target interval is [15%, 1].

[0076] This application embodiment sets a sliding window to dynamically expand the initial range of the comprehensive deviation to determine the target range of the comprehensive deviation, thereby adapting to continuous abnormal fluctuations (e.g., the moving average going out of bounds). This ensures that the target range of the comprehensive deviation can retain the baseline characteristics of the initial range while covering the trend of short-term significant deviations, avoiding erroneous updates due to occasional fluctuations.

[0077] In one embodiment of this application, for each type of fault, the number of times that fault type occurs is obtained based on historical fault records;

[0078] The service life of high-voltage switchgear contacts can be predicted based on the number of times the fault type occurs and the target range corresponding to each fault occurrence.

[0079] This embodiment correlates the fault severity and service life of high-voltage switchgear contacts based on the target range of the comprehensive deviation. This embodiment sets the service life loss weight of high-voltage switchgear contacts to be positively correlated with the fault severity. The initial fault loss weight for high-voltage switchgear contacts corresponding to the first target range is set to 0.1, the initial fault loss weight for high-voltage switchgear contacts corresponding to the second target range is set to 0.3, and the initial fault loss weight for high-voltage switchgear contacts corresponding to the third target range is set to 0.6. A weight correction coefficient of k is set, so the fault loss weights corresponding to the first, second, and third target ranges are 0.1k, 0.3k, and 0.6k, respectively.

[0080] For each fault type, the total number of occurrences of that fault type is obtained from historical fault records, along with the fault loss weight corresponding to each fault, to determine the cumulative fault loss value L1. The formula for determining the cumulative fault loss value is: ,in, n 1 represents the total number of times this type of fault occurred. For the first The failure loss weight corresponding to each failure. For the first Next and first The duration between failures.

[0081] Obtain the rated service life and initial use time of the high-voltage switchgear contacts. Determine the cumulative service life of the high-voltage switchgear contacts based on the current time and initial use time. Determine the life loss value L2 of the high-voltage switchgear contacts based on the total duration corresponding to the cumulative service life and the rated service life.

[0082] The total life loss rate of the high-voltage switchgear contacts is determined based on the cumulative fault loss value L1 and the life loss value L2 of the high-voltage switchgear contacts. The remaining lifespan of the high-voltage switchgear contacts is determined based on the total life loss rate of the high-voltage switchgear contacts and the rated lifespan of the high-voltage switchgear contacts.

[0083] The total lifespan loss rate of the contacts in the high-voltage switchgear is: , where L 1max This represents the theoretical maximum failure loss value.

[0084] The remaining useful life is calculated as follows: ,in, This refers to the cumulative service life of the contacts in the high-voltage switchgear. This refers to the rated service life of the contacts in the high-voltage switchgear. The operating time of high-voltage switchgear contacts that are additionally consumed due to faults.

[0085] In one embodiment of this application, determining the target range of the comprehensive deviation based on the comprehensive deviation includes:

[0086] Determine the range of values ​​for the comprehensive deviation based on the comprehensive deviation corresponding to the data to be tested;

[0087] The risk entropy is determined based on the range of values ​​for the comprehensive deviation degree and the risk entropy formula.

[0088] The formula for risk entropy is: ,in, For risk entropy, q This represents the number of intervals after dividing the range of values ​​for the comprehensive deviation by equal distances. r For the first r Each intervalp r For the first r The probability of the overall deviation occurring within each interval;

[0089] Two-dimensional data pairs are determined based on the comprehensive deviation degree and risk entropy. These two-dimensional data pairs are paired data composed of the comprehensive deviation degree and risk entropy.

[0090] The target range for the comprehensive deviation is determined based on this two-dimensional data.

[0091] In this embodiment, risk entropy reflects the dispersion and uncertainty of the overall deviation. The higher the entropy value of risk entropy, the more dispersed the distribution of the deviation, and the greater the uncertainty of the failure risk; the lower the entropy value of risk entropy, the more concentrated the dispersion of the deviation, and the more controllable the risk.

[0092] Acquire the measured data of the high-voltage switchgear contacts at various times, determine the comprehensive deviation corresponding to each measured data point, and identify the maximum and minimum values ​​of each comprehensive deviation. Then, determine the range of values ​​for the comprehensive deviation based on these maximum and minimum values. Divide the determined range of values ​​for the comprehensive deviation into several intervals using an equidistant method. For each interval, determine the probability of a specific comprehensive deviation occurring within that interval based on the number of comprehensive deviations within that interval and the total number of comprehensive deviations at all times. Finally, determine the risk entropy based on the range of values ​​for the comprehensive deviation and the risk entropy formula, which is: ,in, For risk entropy, q This represents the number of intervals after dividing the range of values ​​for the comprehensive deviation by equal distances. r For the first r Each interval p r For the first r The probability of the overall deviation occurring within each interval.

[0093] Set risk entropy The threshold range, for example, if risk entropy If the risk entropy is less than 0.3, the overall deviation is considered to be within a safe range; if 0.3 ≤ risk entropy... If the risk entropy is ≤0.6, it is determined that the comprehensive deviation corresponding to this risk entropy range is in the warning interval; if the risk entropy If the value is greater than 0.6, then the comprehensive deviation corresponding to the risk entropy range is determined to be within the risk range.

[0094] Based on all the data to be tested, calculate the corresponding comprehensive deviation and risk entropy to form a two-dimensional data pair. Based on historical fault records, the overall deviation S and risk entropy are determined respectively. The safe zone, warning zone, and risk zone are defined, and the corresponding two-dimensional data pairs for each zone are determined. If S < 5% and If the deviation is less than 0.3, it is considered that the overall deviation is concentrated and the value is small, belonging to the safe range, and the risk level is low; if 5%≤S≤15% or 0.3≤ If S ≤ 0.6, it is judged as a dispersion or moderate value of the overall deviation, falling within the warning range, with a risk level of medium risk, requiring enhanced monitoring; if S > 15% or If the value is greater than 0.6, it is judged as having a large and dispersed overall deviation, high uncertainty, and a high risk level.

[0095] The comprehensive deviation range is determined based on the comprehensive deviation degree and risk entropy. The range division uses comprehensive deviation degree as the primary indicator and risk entropy as a secondary indicator. When the comprehensive deviation degree is within a critical range (e.g., close to the initial threshold), the risk entropy is used to determine the range assignment: if S falls within a certain initial range, and If the entropy value meets the threshold of the interval, it is directly assigned to that interval; if S is close to the interval boundary (e.g., S=14.5%, close to the high-risk threshold of 15%), and If the value is ≥0.6 (high-risk entropy value), it is considered a high-risk interval; if S is at the boundary but... Lower (e.g., S=15.2%, but) If the deviation is 0.2, then although the deviation is high, it is relatively concentrated (which may be occasional fluctuations), and can be temporarily classified as a medium-risk range, and should be continuously monitored.

[0096] Output the target range for the final overall deviation, combined with the numerical range of S and Identify the risk range to which the current data belongs.

[0097] This embodiment combines the comprehensive deviation degree and the entropy value of risk entropy to determine the target range of comprehensive deviation degree, and classifies the risk level through the dual dimensions of deviation degree and uncertainty.

[0098] For example, the weights of temperature deviation (0.4), pressure deviation (0.3), and contact resistance deviation (0.3) are determined using the entropy method formula. Based on the deviations of each parameter type and their corresponding weights, the overall deviation is determined to be 9.8%. The range of the overall deviation is determined by its maximum and minimum values, and then divided into five equally spaced intervals. This sample falls within interval 3 (e.g., a percentage of 0.3), with the other intervals having percentages of 0.1, 0.2, 0.2, and 0.2 respectively. Therefore, the risk entropy value is 1.56. Since the overall deviation of this sample is 9.8%, falling within the range of 5% ≤ S ≤ 15%, and the risk entropy value is 1.56, it is considered a high-risk entropy value. Therefore, this sample is determined to be an abnormal sample with a medium-risk level.

[0099] In one embodiment of this application, a fault database is determined based on preprocessed historical data and a digital twin model, including:

[0100] Data characterizing contact failures in high-voltage switchgear were selected from various types of preprocessed historical parameter data.

[0101] Data characterizing faults in high-voltage switchgear contacts are used as real fault samples, and virtual fault samples for edge scenarios are determined based on the real fault samples and the digital twin model.

[0102] The fault database is determined based on real fault samples and virtual fault samples.

[0103] In this embodiment, data representing the failure of high-voltage switchgear contacts are selected from the preprocessed parameter data of various types. This data representing the failure of high-voltage switchgear contacts is used as the real fault sample. That is, the data that clearly corresponds to the actual fault is used as the real fault sample. The selection criteria are: the real fault sample must include the complete fault occurrence and development process and the fault type that has been verified by on-site inspection.

[0104] Edge scenarios refer to extreme operating conditions or rare fault combinations not covered in real-world fault samples (e.g., high temperature and humidity combined with a sudden pressure drop, or compound faults in the later stages of equipment aging). These scenarios need to be determined by considering the equipment's operating years and extreme weather records. Characteristic parameters of real-world fault samples are determined; these parameters can be the upper limit of temperature difference or the lower limit of pressure deviation rate. These characteristic parameters are used as the model input boundaries, and combinations of various parameter data are adjusted to simulate edge scenarios. Through iterative simulation of the digital twin model, potential fault data in edge scenarios are output, including characteristic parameter change curves (e.g., hourly rate of increase in temperature difference, pressure decay trend) and fault trigger time, forming virtual fault samples.

[0105] The data format of the virtual fault samples is aligned with that of the real fault samples, and the feature parameters are then normalized. The fault database is determined based on the real and virtual fault samples.

[0106] The fault database set up in this embodiment not only retains the actual characteristics of real fault samples, but also fills the gaps in edge scenarios with virtual fault samples, thereby improving the ability to identify fault types under complex working conditions.

[0107] For example, 50 sets of real fault samples are selected from historical data, including 15 sets of samples of poor contact. For the edge scenario of "poor contact" (high temperature and humidity + sudden pressure drop), a digital twin model is used to simulate and generate 10 sets of virtual fault samples. The 15 sets of real fault samples and the 10 sets of virtual fault samples are then fused. The fault parameters of the real fault samples are: ambient humidity 60%~85%, pressure deviation rate -8%~-15%, temperature difference 30℃~45℃, and the evolution trend is "triggering an alarm within 72 hours". The fault parameters of the virtual fault samples are: ambient humidity 85%~95%, pressure deviation rate -15%~-28%, temperature difference 45℃~60℃, and the evolution trend is "triggering an alarm within 24~48 hours". Based on the fault types corresponding to different humidity, pressure, and environmental data of the real and virtual fault samples, the samples are fused to form a fault database.

[0108] In one embodiment of this application, there are multiple real fault samples and multiple virtual fault samples. A fault database is determined based on the real fault samples and the virtual fault samples, including:

[0109] For each real fault sample, determine the overlap between the real fault sample and each virtual fault sample, and take the virtual fault samples with an overlap of less than a preset overlap threshold as complementary samples.

[0110] The fault database is determined based on each real fault sample and complementary sample.

[0111] In this embodiment, core parameters characterizing the fault type are extracted from preprocessed historical parameter data of various types, including temperature difference range, pressure deviation rate range, ambient humidity threshold, and fault evolution duration, as dimensions for overlap calculation. For each type of historical parameter data, the similarity of overlapping parameter data in real fault samples and virtual fault samples is determined.

[0112] For each core parameter, the feature vector of the real fault sample is set as A= ,in, a i For the first i The values ​​of each real fault feature vector, and the range corresponding to the core parameters of the real fault sample are []. a i_min , a i_max (For example, for the actual temperature difference range,) a i_min To minimize the temperature difference, a i_max (For the maximum temperature difference), the feature vector of the virtual fault sample is B= ,in,b i For the first i The values ​​of each virtual fault vector, and the range corresponding to the core parameters of the virtual fault sample are [ b i_min , b i_max ].

[0113] The overlap of each core parameter range is ,in, D The degree of overlap for each core parameter range, d 1 represents the length of the overlapping portion of the core parameter intervals corresponding to the real fault sample and the virtual fault sample. d 2 represents the total length of the core parameter intervals corresponding to the real fault samples and the virtual fault samples. The overlap of the overall fault parameters is determined based on the overlap of each core parameter interval; the overall overlap of the fault parameters is... ,in, For the first a The degree of overlap of the core parameters w This represents the total number of core parameters.

[0114] Complementary samples are determined based on the overlap of overall fault parameters. If the overlap of overall fault parameters between the real fault sample and the virtual fault sample is less than or equal to a preset overlap threshold (which can be 40%), and the parameter range of the virtual fault sample includes scenarios not covered by the real fault sample (e.g., higher temperature differences, more extreme humidity), then the virtual fault sample is determined to be a complementary sample. If the overlap of overall fault parameters between the real fault sample and the virtual fault sample is greater than the preset overlap threshold, or the parameter range of the virtual fault sample does not include scenarios not covered by the real fault sample, then the virtual fault sample is determined to be a redundant sample. The overlap is calculated for each real fault sample and virtual fault sample of the same fault type. Samples with an overall fault parameter overlap of ≤40% are selected as complementary samples, and redundant samples with an overlap of >40% are discarded. Based on the selected complementary samples, the normal scenario parameters of the real fault sample and the extreme scenario parameters of the virtual fault sample are merged to form a parameter range with more comprehensive coverage. Based on the merged parameter ranges, the range of fault parameters corresponding to the fault type is determined. Combined with time-series data from real and virtual fault samples, the fault evolution trend is identified (e.g., a 5°C increase in temperature difference every 12 hours). The data is then organized according to the format "Fault Type - Fault Parameter Range - Evolution Trend - Sample Source" to form a fault database.

[0115] A composite monitoring method for high-voltage switchgear contacts corresponding to the above embodiment, Figure 2This is a structural block diagram of a composite monitoring device for contacts in a high-voltage switchgear, provided as an embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 2 The high-voltage switchgear contact composite monitoring device 20 includes: a data acquisition module 21, a fault type determination module 22, a fault severity determination module 23, and a status monitoring module 24.

[0116] Among them, the data acquisition module 21 is used to acquire the test data of the contacts of the high-voltage switchgear. The test data includes various types of parameter data. The test data is preprocessed to obtain the preprocessed parameter data of various types, including temperature data, pressure data and environmental data.

[0117] The fault type determination module 22 is used to determine the fault type corresponding to each type of parameter data based on the fault database and the parameter data of each type. The fault database stores the mapping relationship between the fault type and the interval of each type of parameter data.

[0118] The fault severity determination module 23 is used to determine the comprehensive deviation based on the deviation corresponding to each type of parameter data after preprocessing, and to determine the target range of the comprehensive deviation based on the comprehensive deviation. The target range is used to characterize the fault severity of the contacts of the high-voltage switchgear.

[0119] The status monitoring module 24 is used to monitor the status of the contacts of the high-voltage switchgear based on the target range of fault type and comprehensive deviation.

[0120] The high-voltage switchgear contact composite monitoring device 20 also includes a fault database determination module, which is used to acquire historical data of the high-voltage switchgear contacts. The historical data includes various types of historical parameter data, including historical temperature data, historical pressure data, and historical environmental data.

[0121] Historical data is preprocessed, and a fault database is determined based on the preprocessed historical data and the digital twin model.

[0122] In one embodiment of this application, when the fault severity determination module 23 determines the comprehensive deviation based on the deviation corresponding to each type of preprocessed parameter data, and determines the target range of the comprehensive deviation based on the comprehensive deviation, it is specifically used for:

[0123] The weights corresponding to the deviations of each type of parameter data are determined based on the entropy method and the deviations of the preprocessed parameter data. The comprehensive deviation of each type of parameter data is determined based on the weights corresponding to the deviations of the preprocessed parameter data. The initial range of the comprehensive deviation is determined based on the comprehensive deviation.

[0124] The sliding range of the overall deviation is determined based on the sliding window.

[0125] The target range for the overall deviation is determined based on the initial range and the sliding range.

[0126] In one embodiment of this application, before determining the weights corresponding to the deviations of each type of parameter data based on the entropy method and the deviations of the preprocessed parameter data, the fault severity determination module 23 is further configured to:

[0127] Based on the deviation of each type of parameter data after preprocessing, the standardized value proportion of the deviation of each type of parameter data is determined. The standardized value proportion is the proportion of the deviation value of each type of parameter data in the total standardized deviation value of all types of parameter data.

[0128] The fault severity determination module 23, when determining the weights corresponding to the deviations of each type of parameter data based on the entropy method and the deviations of the preprocessed parameter data, is specifically used for:

[0129] Based on the standardized value proportion of the deviation of each type of parameter data and the entropy method formula, the information entropy corresponding to the deviation of each type of parameter data after preprocessing is determined. Based on the information entropy and the first formula, the weights corresponding to the deviation of each type of parameter data are determined respectively.

[0130] The entropy method formula is: ,in, For the first i The information entropy corresponding to the deviation of each type of parameter data m For the first i The total number of data points collected for each type of parameter. p ij For the first i The first type parameter data j The proportion of standardized values ​​for each parameter data;

[0131] The first formula is: ,in, For the first i The weights corresponding to the deviation of each type of parameter data n Number of types.

[0132] In one embodiment of this application, the fault severity determination module 23 is further configured to:

[0133] Risk entropy is determined based on the overall deviation.

[0134] Two-dimensional data pairs are determined based on the comprehensive deviation degree and risk entropy. The two-dimensional data pairs are pairs of data composed of comprehensive deviation degree and risk entropy.

[0135] The target range for the comprehensive deviation is determined based on the two-dimensional data.

[0136] In one embodiment of this application, the fault severity determination module 23, when determining the risk entropy based on the comprehensive deviation, is further specifically used for:

[0137] Determine the range of values ​​for the comprehensive deviation based on the comprehensive deviation corresponding to the data to be tested;

[0138] The risk entropy is determined based on the range of values ​​for the comprehensive deviation degree and the risk entropy formula.

[0139] The formula for risk entropy is: ,in, For risk entropy, q The number of intervals into which the range of values ​​for the comprehensive deviation is divided at equal intervals. r For the first r Each interval p r Let be the probability of the overall deviation occurring within the r-th interval.

[0140] In one embodiment of this application, the fault database determination module is further configured to filter data characterizing the failure of the contacts of the high-voltage switchgear from preprocessed historical parameter data of various types;

[0141] Data characterizing faults in high-voltage switchgear contacts are used as real fault samples, and virtual fault samples for edge scenarios are determined based on the real fault samples and the digital twin model.

[0142] The fault database is determined based on real fault samples and virtual fault samples.

[0143] In one embodiment of this application, there are multiple real fault samples and multiple virtual fault samples. The fault database determination module is further specifically used to determine the overlap between each real fault sample and each virtual fault sample, and to take the virtual fault samples with an overlap less than a preset overlap threshold as complementary samples.

[0144] The fault database is determined based on each real fault sample and complementary sample.

[0145] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 3The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of each module / unit in the above-described device embodiments, for example... Figure 2 The functions of the data acquisition module 21, fault type determination module 22, fault severity determination module 23, and status monitoring module 24 are shown.

[0146] It should be understood that, in the embodiments of this application, the processor 301 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0147] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0148] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store fault type information, comprehensive deviation information, target range of comprehensive deviation, and fault severity information of high-voltage switchgear contacts.

[0149] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this application can execute the implementation method described in the high-voltage switchgear contact composite monitoring method provided in the embodiments of this application, or they can execute the implementation method of the electronic device described in the embodiments of this application, which will not be repeated here.

[0150] In another embodiment of this application, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0151] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., provided on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0152] Those skilled in the art will recognize that the modules / units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0153] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0154] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules, units, or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces or modules, or it may be an electrical, mechanical, or other form of connection.

[0155] The modules described as separate components may or may not be physically separate. Similarly, the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0156] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0157] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and such modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A composite monitoring method for contacts in a high-voltage switchgear, characterized in that, include: Acquire the test data of the contacts of the high-voltage switchgear, the test data includes various types of parameter data, preprocess the test data to obtain preprocessed parameter data of various types, the various types of parameter data include: temperature data, pressure data and environmental data; Based on the fault database and the parameter data of each type, the fault type corresponding to each type of parameter data is determined. The fault database stores the mapping relationship between the fault type and the interval of each type of parameter data. The weights corresponding to the deviations of each type of parameter data are determined based on the entropy method and the deviations of each type of parameter data after preprocessing. The comprehensive deviation is determined based on the weights corresponding to the deviations of each type of parameter data after preprocessing. The initial range of the comprehensive deviation is determined based on the comprehensive deviation. The sliding range of the overall deviation is determined based on the sliding window. The target range of the comprehensive deviation is determined based on the initial range and the sliding range. The target range is used to characterize the fault degree of the contacts of the high-voltage switchgear. Based on the fault type and the target range of the comprehensive deviation, monitor the status of the high-voltage switchgear contacts; The fault database is determined in the following way: Acquire historical data of the contacts of the high-voltage switchgear. The historical data includes various types of historical parameter data, including historical temperature data, historical pressure data, and historical environmental data. The historical data is preprocessed, and the fault database is determined based on the preprocessed historical data and the digital twin model.

2. The composite monitoring method for high-voltage switchgear contacts as described in claim 1, characterized in that, Before determining the weights corresponding to the deviations of each type of parameter data based on the entropy method and the deviations corresponding to the preprocessed parameter data, the method further includes: Based on the deviation of each type of parameter data after preprocessing, the standardized value proportion of the deviation of each type of parameter data is determined, and the standardized value proportion is the proportion of the deviation value of each type of parameter data in the total standardized deviation value of all types of parameter data. The determination of the weights corresponding to the deviations of each type of parameter data based on the entropy method and the deviations of the preprocessed parameter data includes: Based on the standardized value proportion of the deviation of each type of parameter data and the entropy method formula, the information entropy corresponding to the deviation of each type of parameter data after preprocessing is determined, and the weight corresponding to the deviation of each type of parameter data is determined based on the information entropy and the first formula. The entropy method formula is as follows: ,in, For the first i The information entropy corresponding to the deviation of each type of parameter data m For the first i The total number of data points collected for each type of parameter. p ij For the first i The first type parameter data j The proportion of standardized values ​​for each parameter data; The first formula is: ,in, For the first i The weights corresponding to the deviation of each type of parameter data n Number of types.

3. The composite monitoring method for high-voltage switchgear contacts as described in claim 1, characterized in that, Determining the target range of the comprehensive deviation based on the comprehensive deviation includes: The risk entropy is determined based on the comprehensive deviation. Two-dimensional data pairs are determined based on the comprehensive deviation degree and the risk entropy, wherein the two-dimensional data pairs are paired data composed of the comprehensive deviation degree and the risk entropy; The target range of the comprehensive deviation is determined based on the two-dimensional data.

4. The composite monitoring method for high-voltage switchgear contacts as described in claim 3, characterized in that, The step of determining the risk entropy based on the comprehensive deviation includes: Based on the comprehensive deviation corresponding to the data to be tested, determine the range of values ​​for the comprehensive deviation. The risk entropy is determined based on the range of values ​​for the comprehensive deviation and the risk entropy formula. The risk entropy formula is: ,in, For risk entropy, q This represents the number of intervals after dividing the range of values ​​for the comprehensive deviation by equal distances. r For the first r Each interval p r For the first r The probability of the overall deviation occurring within each interval.

5. The composite monitoring method for high-voltage switchgear contacts as described in claim 1, characterized in that, The process of determining the fault database based on preprocessed historical data and a digital twin model includes: Data characterizing the contact failures of the high-voltage switchgear are selected from various types of preprocessed historical parameter data. The data characterizing the faults in the contacts of the high-voltage switchgear are used as real fault samples, and virtual fault samples for edge scenarios are determined based on the real fault samples and the digital twin model. A fault database is determined based on the real fault samples and the virtual fault samples.

6. The composite monitoring method for high-voltage switchgear contacts as described in claim 5, characterized in that, There are multiple real fault samples and multiple virtual fault samples. The step of determining the fault database based on the real fault samples and the virtual fault samples includes: For each real fault sample, the overlap between the real fault sample and each virtual fault sample is determined, and virtual fault samples with an overlap of less than a preset overlap threshold are taken as complementary samples. A fault database is determined based on each of the real fault samples and the complementary samples.

7. A composite monitoring device for contacts of a high-voltage switchgear, characterized in that, include: The data acquisition module is used to acquire the test data of the contacts of the high-voltage switchgear. The test data includes various types of parameter data. The test data is preprocessed to obtain preprocessed parameter data of various types, including temperature data, pressure data and environmental data. The fault type determination module is used to determine the fault type corresponding to each type of parameter data based on the fault database and the parameter data of each type. The fault database stores the mapping relationship between fault types and the intervals of each type of parameter data. The fault severity determination module is used to determine the weights corresponding to the deviations of each type of parameter data based on the entropy method and the deviations corresponding to the preprocessed parameter data of each type; to determine the comprehensive deviation based on the weights corresponding to the deviations of the preprocessed parameter data of each type; to determine the initial range of the comprehensive deviation based on the comprehensive deviation; to determine the sliding range of the comprehensive deviation based on the sliding window; and to determine the target range of the comprehensive deviation based on the initial range and the sliding range. The target range is used to characterize the fault severity of the contacts of the high-voltage switchgear. The status monitoring module is used to monitor the status of the contacts of the high-voltage switchgear based on the target range of the fault type and the comprehensive deviation degree. The fault database determination module is used for: Acquire historical data of the contacts of the high-voltage switchgear. The historical data includes various types of historical parameter data, including historical temperature data, historical pressure data, and historical environmental data. The historical data is preprocessed, and the fault database is determined based on the preprocessed historical data and the digital twin model.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 6.

Images