A GIS state detection method and system, an intelligent terminal and a storage medium

Abstract

The application provides a GIS state detection method and system, an intelligent terminal and a storage medium, and relates to the field of electrical equipment detection.The method comprises the following steps: determining the leakage risk coefficient of sulfur hexafluoride gas according to a metal shell image set analysis;optimizing the gas monitoring threshold value with the maximum sulfur hexafluoride gas early warning accuracy rate as the target according to the leakage risk coefficient, the maintenance interval length, the current environmental parameters and the expected operating load to obtain the optimal monitoring threshold value; and setting an adaptive early warning strategy according to the optimal monitoring threshold value to monitor and warn the GIS equipment.The technical problem that the traditional GIS equipment gas state detection method lacks a dynamic monitoring mechanism based on the actual working condition of the equipment, which leads to misjudgment or missed judgment under complex working conditions and causes insufficient detection accuracy and reliability can be solved.The target of adaptive early warning can be achieved, the accuracy and reliability of GIS equipment gas detection can be effectively improved, and the intelligent operation and maintenance demand can be met.

Description

Technical Field

[0001] This invention relates to the field of electrical equipment testing, and more particularly to a GIS condition monitoring method, system, intelligent terminal, and storage medium. Background Technology

[0002] Gas-insulated switchgear (GIS) is widely used in high-voltage power transmission and transformation systems due to its compact structure, excellent insulation performance, and strong adaptability to harsh environments. GIS is typically filled with sulfur hexafluoride (SF6) gas, which serves as the primary insulating and arc-quenching medium. The density of SF6 gas directly affects the insulation level and operational safety of the equipment. Therefore, real-time monitoring of the SF6 gas status has become a crucial means to ensure the safe and stable operation of GIS equipment.

[0003] In existing technologies, the monitoring of sulfur hexafluoride gas typically relies on physical detection methods such as pressure, temperature, and density sensors, and alarm judgments are made based on preset static thresholds. However, such methods generally have the following shortcomings: On the one hand, the monitoring thresholds are usually fixed and lack a dynamic adjustment mechanism for multiple factors such as equipment operating environment, actual load status, and equipment aging degree, which can easily lead to misjudgments or missed judgments under complex operating conditions such as high-frequency switching, power load fluctuations, or drastic environmental changes; on the other hand, traditional detection methods ignore the actual leakage risk caused by problems such as corrosion, cracks, or aging of the equipment body (such as metal enclosure), thus limiting the accuracy and reliability of the overall detection system. Summary of the Invention

[0004] The purpose of this invention is to provide a GIS status detection method, system, intelligent terminal, and storage medium to solve the technical problem that traditional GIS equipment gas status detection methods lack a dynamic monitoring mechanism based on the actual operating conditions of the equipment, leading to misjudgments or omissions in complex operating conditions, resulting in insufficient accuracy and reliability of detection. The invention includes:

[0005] In a first aspect, the present invention provides a GIS status detection method, comprising: acquiring a set of metal casing images and maintenance interval duration based on the most recent maintenance record of the GIS equipment, and analyzing and determining a leakage risk coefficient of sulfur hexafluoride gas based on the metal casing image set; monitoring and acquiring the current environmental parameters of the area where the GIS equipment is located within a preset time zone, as well as the expected operating load of the GIS equipment; optimizing the gas monitoring threshold based on the leakage risk coefficient, maintenance interval duration, current environmental parameters, and expected operating load, with the goal of maximizing the early warning accuracy of sulfur hexafluoride gas, and obtaining an optimal monitoring threshold; setting an adaptive early warning strategy based on the optimal monitoring threshold, and monitoring and issuing early warnings for sulfur hexafluoride gas in the GIS equipment within the preset time zone.

[0006] Preferably, the GIS status detection method further includes: acquiring a metal shell image set, wherein the metal shell image set includes metal shell images of several key parts; using a convolutional neural network to perform defect identification on the metal shell images of the several key parts to obtain several defect features; and combining an empirical weight model to evaluate and determine a leakage risk coefficient based on the several defect features.

[0007] Preferably, the GIS status detection method further includes: acquiring gas monitoring indicators of sulfur hexafluoride (SF6) gas and the adjustment space of the monitoring indicators, wherein the gas monitoring indicators include gas density, gas pressure, gas temperature, moisture content, and decomposition product concentration; training an SF6 gas early warning accuracy predictor based on the leakage risk coefficient, maintenance interval, current environmental parameters, and expected operating load; and optimizing the gas monitoring threshold using the early warning accuracy predictor based on the monitoring indicator adjustment space, with the goal of maximizing the early warning accuracy of SF6 gas, and outputting the optimal monitoring threshold.

[0008] Preferably, the GIS status detection method further includes: using the leakage risk coefficient, maintenance interval duration, current environmental parameters, and expected operating load as search constraints, expanding the search constraints according to a preset tolerance range to obtain search conditions; based on the search conditions, filtering historical monitoring data of sulfur hexafluoride gas from similar GIS equipment, collecting a sample gas monitoring threshold set, and statistically analyzing the probability of false alarms and missed alarms for sulfur hexafluoride gas indicators under different sample gas monitoring thresholds, calculating the sample warning accuracy rate, and obtaining a sample warning accuracy rate set; using the sample gas monitoring threshold set and the sample warning accuracy rate set, training a generative adversarial network until convergence to obtain a warning accuracy rate predictor.

[0009] Preferably, the GIS status detection method further includes: using the sample gas monitoring threshold set and the sample early warning accuracy set as training data, and dividing them into P equal parts; selecting P times with replacement from the P sets to obtain the first training set; iterating P times to obtain P training sets, where P is an integer greater than or equal to 10; using the P training sets, training a generative adversarial network to convergence to obtain P early warning accuracy prediction branches, and combining them to obtain an early warning accuracy predictor.

[0010] Preferably, the GIS status detection method further includes: randomly selecting multiple initial monitoring thresholds within the monitoring indicator adjustment space; calculating the deviation range of the multiple initial monitoring thresholds based on the standard monitoring threshold, determining multiple deviation values ​​by weighting, and calculating multiple branch selection quantities Q, where Q is the integer value of the product of the deviation value and P, and Q is greater than or equal to 1 and less than or equal to P; based on the multiple branch selection quantities Q, using the early warning accuracy predictor to predict the multiple initial monitoring thresholds respectively, and outputting multiple predicted early warning accuracies; and optimizing the gas monitoring threshold based on the multiple predicted early warning accuracies, with the goal of maximizing the early warning accuracy of sulfur hexafluoride gas, and outputting the optimal monitoring threshold.

[0011] Preferably, the GIS status detection method further includes: setting an initial monitoring threshold as an initial solution; sorting multiple initial monitoring thresholds according to their prediction and early warning accuracy rates from highest to lowest to obtain an initial solution sequence; designating the first K solutions of the initial solution sequence as good solutions and the last M solutions as poor solutions; and performing random equal-value clustering on the M poor solutions centered on the K good solutions to obtain K solution sets, where M is N times K and N is greater than or equal to 10; within the K solution sets, adjusting the good solutions as the direction of optimization according to a preset optimization step size. The suboptimal solutions within a solution set are adjusted to obtain K updated solution sets. If the adjusted suboptimal solutions do not meet the adjustment space of the monitoring index, they are discarded, and a monitoring threshold is randomly selected to supplement them. The K updated solution sets are identified. If the prediction and warning accuracy of the updated suboptimal solutions is greater than the prediction and warning accuracy of the good solutions in the same solution set, the suboptimal solutions are used to replace the good solutions. Iterative optimization is performed until a preset number of optimizations is reached. K current solution sets are output. The solution set with the largest sum of prediction and warning accuracies is selected as the optimal solution set, and the good solutions of the optimal solution set are set as the optimal monitoring threshold.

[0012] Secondly, the present invention also provides a GIS status detection system for executing a GIS status detection method as described in the first aspect, comprising: a leakage risk coefficient determination module, used to acquire a metal casing image set and maintenance interval duration based on the most recent maintenance record of the GIS equipment, and to analyze and determine the leakage risk coefficient of sulfur hexafluoride gas based on the metal casing image set; a data monitoring and acquisition module, used to monitor and acquire the current environmental parameters of the area where the GIS equipment is located within a preset time zone, as well as the expected operating load of the GIS equipment; a gas monitoring threshold optimization module, used to optimize the gas monitoring threshold based on the leakage risk coefficient, maintenance interval duration, current environmental parameters, and expected operating load, with the goal of maximizing the early warning accuracy of sulfur hexafluoride gas, and to obtain the optimal monitoring threshold; and an equipment monitoring and early warning module, used to set an adaptive early warning strategy based on the optimal monitoring threshold, and to monitor and issue early warnings for sulfur hexafluoride gas in the GIS equipment within the preset time zone.

[0013] Thirdly, the present invention also provides a smart terminal, comprising:

[0014] At least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method described in any one of the first aspects above.

[0015] Fourthly, a computer-readable storage medium storing a computer program that, when executed, implements the steps of the method described in any one of the first aspects above.

[0016] The embodiments of the present invention have the following advantages:

[0017] By acquiring a set of metal casing images and maintenance intervals based on the most recent maintenance records of the GIS equipment, and analyzing these images to determine the leakage risk coefficient of sulfur hexafluoride (SF6) gas, the system also monitors and acquires the current environmental parameters of the area where the GIS equipment is located within a preset time zone, as well as the expected operating load of the GIS equipment. Then, based on the leakage risk coefficient, maintenance intervals, current environmental parameters, and expected operating load, and with the goal of maximizing the accuracy of SF6 gas early warning, the system optimizes the gas monitoring threshold to obtain the optimal monitoring threshold. Finally, based on the optimal monitoring threshold, an adaptive early warning strategy is set to monitor and issue early warnings for SF6 gas in the GIS equipment within the preset time zone. In other words, by integrating metal casing image recognition, environmental parameter perception, and operating load modeling, a multi-dimensional state perception and evaluation mechanism is constructed to dynamically optimize the SF6 gas monitoring threshold, achieving adaptive early warning and effectively improving the accuracy and reliability of gas detection in GIS equipment. This meets the needs of intelligent operation and maintenance and refined management. Attached Figure Description

[0018] Figure 1 This is a flowchart of the steps of a GIS status detection method according to the present invention;

[0019] Figure 2 This is a schematic diagram of the structure of a GIS status detection system according to the present invention;

[0020] Figure 3 This is a schematic diagram of the structure of the smart terminal provided by the present invention;

[0021] Figure 4 This is a schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0022] The components represented by each number in the attached diagram are explained below:

[0023] Leakage risk coefficient determination module 11, data monitoring and acquisition module 12, gas monitoring threshold optimization module 13, equipment monitoring and early warning module 14, intelligent terminal 500, memory 510, processor 520, first computer program 511, computer-readable storage medium 600, and second computer program 611. Detailed Implementation

[0024] This invention provides a GIS status detection method and system, solving the technical problem that traditional GIS equipment gas status detection methods lack a dynamic monitoring mechanism based on the actual operating conditions of the equipment, leading to misjudgments or omissions in complex operating conditions and resulting in insufficient accuracy and reliability. By integrating metal casing image recognition, environmental parameter perception, and operational load modeling, a multi-dimensional status perception and evaluation mechanism is constructed. This mechanism dynamically optimizes the monitoring threshold for sulfur hexafluoride gas, achieving adaptive early warning and effectively improving the accuracy and reliability of gas detection in GIS equipment, thereby meeting the needs of intelligent operation and maintenance and refined management.

[0025] The technical solutions of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. It should be understood that the present invention is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention. It should also be noted that, for ease of description, only the parts related to the present invention are shown in the accompanying drawings, not all of them.

[0026] Example 1, please refer to the appendix. Figure 1 This invention provides a GIS status detection method, applied to a GIS status detection system, specifically including the following steps:

[0027] S10: Based on the most recent maintenance record of the GIS equipment, obtain the metal casing image set and maintenance interval duration, and analyze and determine the leakage risk coefficient of sulfur hexafluoride gas based on the metal casing image set.

[0028] Furthermore, step S10 of the present invention further includes:

[0029] S11: Obtain a set of metal casing images, wherein the set of metal casing images includes images of several key parts of the metal casing; S12: Use a convolutional neural network to perform defect identification on the metal casing images of the several key parts and obtain several defect features; S13: Combine an empirical weight model to evaluate and determine the leakage risk coefficient based on the several defect features.

[0030] Specifically, firstly, the most recent maintenance record of the GIS equipment is retrieved. This record refers to the data and documents related to the last maintenance, repair, or inspection performed on the GIS equipment. These records typically include the maintenance date, maintenance content, problems found, and their handling results, serving as a crucial basis for assessing the current condition of the equipment. Next, based on the most recent maintenance record, an image set of the metal casing and the maintenance interval are obtained. High-definition cameras or industrial cameras are used to comprehensively photograph the metal casing of the GIS equipment, focusing on capturing images of several key areas, such as joints, sealing ring areas, and locations where corrosion or cracks may occur. This image data constitutes an image set, which is used for subsequent image processing and analysis to identify physical defects and anomalies on the equipment surface. The maintenance interval refers to the time interval from the most recent maintenance date to the current time. This duration reflects the length of time the equipment has not been maintained and is an important parameter for assessing the degree of equipment aging and potential risks. The longer the maintenance interval, the greater the likelihood of equipment aging, decreased sealing performance, or increased leakage risk.

[0031] Next, an image set of the metal casing is acquired. The image set of the metal casing includes images of several key parts of the metal casing. Key parts refer to areas in the metal casing that are prone to defects or have a high risk of leakage, such as joints, welding points, near seals, areas of surface corrosion, or locations where cracks may occur. Then, a convolutional neural network (CNN) is used to identify defects in the metal shell images of the key parts. A CNN is a deep learning model that automatically extracts spatial features from images through multiple convolutional and pooling layers, and performs classification or detection through fully connected layers. The CNN model uses its convolutional kernels to slide across the image, automatically identifying details such as edges, textures, and color changes. These features are crucial for detecting defects such as cracks, corrosion spots, and wear. The network uses trained weights and biases to distinguish between potentially defective areas and normal areas in the image, thereby locating and classifying defects and obtaining several defect features. These features include defect type (such as cracks, corrosion, pits, paint peeling, etc.), defect location (specific coordinates or area on the actual device), defect size (dimensional indicators such as the area, length, or volume of the defect), defect severity, and defect morphological features (such as the direction of cracks, the shape of corrosion spots, and other auxiliary discrimination information).

[0032] Then, an empirical weighting model is set up. The empirical weighting model is a mathematical model built based on expert experience and historical data to quantify the impact of different defect features on the risk of sulfur hexafluoride gas leakage. Different defects contribute differently to the leakage risk. For example, cracks may have a higher risk weight than slight surface corrosion. The weighting model can use weighted summation, scoring systems or machine learning methods to convert multidimensional defect features into a single risk index. Different basic weights are assigned according to the defect type (e.g., cracks have a higher weight than corrosion).

[0033] The weights are adjusted based on defect size (larger defects have higher weights); the weights are also adjusted by considering defect location and the importance of critical parts of the equipment (defects in critical parts have higher weights). Finally, all defect features are comprehensively calculated according to the weighting model to obtain a numerical leakage risk coefficient. This coefficient reflects the overall leakage risk of the metal casing. The higher the coefficient, the worse the equipment's sealing condition and the higher the leakage risk.

[0034] S20: Monitor and acquire the current environmental parameters of the area where the GIS equipment is located within the preset time zone, as well as the expected operating load of the GIS equipment.

[0035] Specifically, a preset time zone is configured. This refers to a pre-defined specific time period, such as a few hours on a particular day, a work cycle, or a maintenance cycle. Monitoring and data collection are confined to this time range to ensure the timeliness and relevance of the data. Next, the current environmental parameters of the area where the GIS equipment is located within the preset time zone, as well as the expected operating load of the GIS equipment, are monitored and acquired. The current environmental parameters refer to real-time monitoring of the geographical location of the GIS equipment and its surrounding environment, collecting environmental variables that can affect equipment operation and the state of sulfur hexafluoride (SF6) gas, including but not limited to temperature, humidity, and pressure. Ambient temperature directly affects the pressure and density of SF6 gas, thus affecting insulation performance and the accuracy of leak detection. Humidity changes may cause condensation inside the equipment, accelerating corrosion of metal components and affecting the equipment's sealing performance. Changes in ambient air pressure affect the baseline of gas state parameters and need to be used to adjust gas monitoring thresholds. These environmental parameters are typically collected in real-time by field-installed sensor devices (such as temperature and humidity sensors, and air pressure sensors) and transmitted to the monitoring system via wireless or wired networks. The expected operating load refers to the electrical load and operating status that GIS equipment may bear in a preset time zone, calculated based on the power grid dispatch plan, equipment operating history and predictive analysis. This includes the magnitude of the current load, the frequency of switching operations, etc. Among these, the greater the current and load that the equipment passes through during operation, the higher the equipment's working pressure and the higher the risk of failure. The number of operations of circuit breakers and other switching equipment, and frequent operation may exacerbate mechanical wear and the risk of gas leakage.

[0036] By collecting environmental parameters and expected load information in real time, potential problems can be identified in advance by combining environmental and load changes, providing a reliable real-time data foundation for intelligent operation and maintenance systems.

[0037] S30: Based on the aforementioned leakage risk coefficient, maintenance interval duration, current environmental parameters, and expected operating load, with the goal of maximizing the early warning accuracy of sulfur hexafluoride gas, optimize the gas monitoring threshold to obtain the optimal monitoring threshold.

[0038] Furthermore, step S30 of the present invention also includes:

[0039] S31: Obtain gas monitoring indicators for sulfur hexafluoride gas, as well as the adjustment range of the monitoring indicators, wherein the gas monitoring indicators include gas density, gas pressure, gas temperature, moisture content, and decomposition product concentration.

[0040] Specifically, firstly, gas monitoring indicators for sulfur hexafluoride (SF6) gas are obtained. These indicators include gas density, gas pressure, gas temperature, moisture content, and decomposition product concentration. Gas density reflects the mass of SF6 gas per unit volume; abnormal density changes may indicate gas leakage or abnormal compression, making it a crucial parameter for determining whether the gas meets insulation and sealing requirements. Gas pressure refers to the pressure state of the gas within the GIS equipment; decreased pressure usually indicates leakage risk, while excessively high pressure may affect the safe operation of the equipment. Pressure, density, and temperature together determine the gas state. Gas temperature affects its physical properties and pressure; abnormal temperature fluctuations may be related to abnormal equipment operation or environmental changes. Temperature serves as a reference for adjusting other monitoring indicators. Moisture (humidity) is a significant impurity in SF6 gas; excessive moisture content may lead to decreased insulation performance and equipment corrosion, accelerating equipment aging. Monitoring moisture content helps in the timely detection of internal sealing problems. SF6 decomposes under electrical faults or overheating conditions, producing harmful gases (such as SO2 and HF). Decomposition product concentration is a direct indicator of partial discharge or faults in the equipment; increased decomposition product concentration usually indicates potential safety hazards. Next, the adjustment range of the monitoring indicators for sulfur hexafluoride gas is obtained. The adjustment range of the monitoring indicators refers to the ability to dynamically adjust the warning threshold or alarm range of the above-mentioned monitoring indicators based on the current status of the equipment, environmental conditions and operating load.

[0041] S32: Based on the leakage risk coefficient, maintenance interval, current environmental parameters, and expected operating load, a predictor for the accuracy of early warning of sulfur hexafluoride gas is trained.

[0042] Furthermore, step S32 of the present invention also includes:

[0043] S321: Using the leakage risk coefficient, maintenance interval duration, current environmental parameters, and expected operating load as search constraints, the search constraints are expanded according to a preset tolerance range to obtain search conditions; S322: Based on the search conditions, historical monitoring data of sulfur hexafluoride gas from similar GIS equipment are screened, a set of sample gas monitoring thresholds is collected, and the probability of false alarms and missed alarms of sulfur hexafluoride gas indicators under different sample gas monitoring thresholds is statistically analyzed to calculate the sample warning accuracy rate and obtain a set of sample warning accuracy rates.

[0044] Specifically, firstly, the leakage risk coefficient, maintenance interval, current environmental parameters, and expected operating load are set as constraints for data retrieval. Next, a preset tolerance range is configured. This tolerance range is a reasonable variation range set by the system for each type of input parameter, used to expand the sample data matching space and avoid insufficient sample size due to overly stringent conditions, thus preventing effective threshold optimization. For example, if the leakage risk coefficient is 0.6 and the tolerance range is ±0.1, historical data matching is allowed within the range of 0.5 to 0.7. If the current ambient temperature is 35°C and the tolerance range is set to ±5°C, records with ambient temperatures ranging from 30 to 40°C are accepted when matching data. Then, the retrieval constraints are expanded according to the preset tolerance range, i.e., a reasonable upper and lower fluctuation range is set for each variable to form interval-type retrieval conditions. All expanded parameters are merged into a multi-dimensional condition vector, which serves as the standard for querying historical or simulated data, used to retrieve records or operating condition samples similar to the current equipment state in the historical database. By setting a tolerance interval to expand the matching range, we can efficiently obtain suitable historical data or model samples, providing accurate and sufficient data support for the next step of threshold optimization.

[0045] Next, based on the search criteria, historical monitoring data of sulfur hexafluoride gas from similar GIS equipment are filtered to collect a set of sample gas monitoring thresholds. Then, the probability of false alarms and missed alarms for sulfur hexafluoride gas indicators under different sample gas monitoring thresholds is calculated, and the false alarm rate and missed alarm rate are subtracted from 1 to obtain the sample warning accuracy rate, thus obtaining a set of sample warning accuracy rates.

[0046] S323: Using the sample gas monitoring threshold set and the sample early warning accuracy set, train the generative adversarial network until convergence to obtain the early warning accuracy predictor.

[0047] Furthermore, step S323 of the present invention also includes:

[0048] S3231: The sample gas monitoring threshold set and the sample early warning accuracy set are used as training data and divided into P equal parts. The first training set is obtained by selecting the P sets with replacement P times. The first training set is obtained by iteratively selecting P sets, where P is an integer greater than or equal to 10. S3232: The P training sets are used to train the generative adversarial network until convergence, resulting in P early warning accuracy prediction branches. These branches are then combined to obtain the early warning accuracy predictor.

[0049] Specifically, firstly, the sample gas monitoring threshold set and sample early warning accuracy set are used as training data, and the training data is divided into P equal parts, where P is an integer greater than or equal to 10. Next, the first training set is obtained by selecting P times with replacement from the P parts of the dataset. Using the same method, P training sets are obtained by iterative selection P times. Multiple training data subsets for model training and validation are generated through cross-validation, providing diverse and robust training samples for subsequent model training.

[0050] Then, using the sample gas monitoring threshold as input and the sample early warning accuracy as supervision, the generative adversarial network (GAN) is trained to converge using the P training sets, resulting in P early warning accuracy prediction branches. The GAN consists of a generator and a discriminator. The generator predicts an "accuracy" output based on a set of gas thresholds, simulating the real early warning accuracy. The discriminator distinguishes between the generator's predicted accuracy and the actual sample accuracy data. This adversarial structure effectively learns complex mapping relationships and performs well in nonlinear and multivariate correlation modeling. During training, the generator predicts the early warning accuracy based on the input thresholds, while the discriminator judges the difference between the predicted result and the actual accuracy. Through game optimization between the generator and discriminator, the generator's ability to predict accuracy is gradually improved until the model converges, ultimately resulting in multiple accuracy prediction branches. This training process effectively captures the complex nonlinear relationship between monitoring thresholds and early warning performance, providing reliable data support for subsequent threshold optimization and adaptive adjustment. The P early warning accuracy prediction branches are then combined to obtain an early warning accuracy predictor.

[0051] S33: Based on the adjustment space of the monitoring indicators, with the goal of maximizing the early warning accuracy of sulfur hexafluoride gas, the gas monitoring threshold is optimized using the early warning accuracy predictor, and the optimal monitoring threshold is output.

[0052] Furthermore, step S33 of the present invention also includes:

[0053] S331: Randomly select from the monitoring indicator adjustment space to obtain multiple initial monitoring thresholds; S332: Based on the standard monitoring threshold, calculate the deviation of the multiple initial monitoring thresholds respectively, determine multiple deviation values ​​by weighting, and calculate and obtain multiple branch selection numbers Q, where Q is the integer value of the product of the deviation value and P, and Q is greater than or equal to 1 and less than or equal to P; S333: Based on the multiple branch selection numbers Q, use the early warning accuracy predictor to predict the multiple initial monitoring thresholds respectively, and output multiple predicted early warning accuracy rates.

[0054] Specifically, firstly, within the adjustment space of the monitoring indicators, a set of thresholds is randomly selected using a certain strategy (such as uniform sampling or Gaussian sampling) for subsequent performance evaluation and optimization screening. The goal of this step is to form a representative and diverse initial threshold set to prepare for the subsequent selection of the optimal threshold. Next, using a standard monitoring threshold (such as the threshold set by the equipment factory or the most commonly used threshold under existing operating conditions) as a benchmark, the deviation magnitude of each of the multiple initial monitoring thresholds is calculated. The deviation magnitude is the ratio of the difference between the two to the standard value of the indicator. Simultaneously, to more reasonably evaluate the relative representativeness of different thresholds, weighting factors (such as certain parameters being more sensitive to accuracy) are introduced, and each deviation magnitude is weighted to obtain the final deviation value, resulting in multiple deviation values. Then, the deviation value of each initial threshold is multiplied by P, and the result is rounded to obtain the number of branches selected, Q. Finally, based on the number Q selected from the multiple branches, Q early warning accuracy prediction branches are randomly selected from the P early warning accuracy prediction branches of the early warning accuracy predictor, and the multiple initial monitoring thresholds are predicted respectively to obtain multiple predicted early warning accuracies, wherein the predicted early warning accuracy is the average of the output results of the Q early warning accuracy prediction branches.

[0055] By setting the number of branches to be selected based on the actual deviation of the initial monitoring threshold from the standard threshold, more prediction branches are allocated to the threshold with a large deviation to enhance the robustness of the accuracy assessment; while for the threshold with a small deviation, only a small number of branches are used for rapid assessment. This effectively saves computing resources, improves system operating efficiency and response speed, and enhances the adaptability and intelligence level of the monitoring threshold optimization process while ensuring the overall prediction accuracy.

[0056] S334: Based on the accuracy of the multiple predictions and warnings, optimize the gas monitoring threshold with the goal of maximizing the warning accuracy of sulfur hexafluoride gas, and output the optimal monitoring threshold.

[0057] Furthermore, step S334 of the present invention also includes:

[0058] S3341: Set the initial monitoring threshold as the initial solution. Sort the multiple initial monitoring thresholds according to the multiple prediction and early warning accuracy rates from largest to smallest to obtain an initial solution sequence; S3342: Set the first K solutions of the initial solution sequence as good solutions and the last M solutions as poor solutions. Using the K good solutions as the center, perform random equal-value clustering on the M poor solutions to obtain K solution sets, where M is N times K, and N is greater than or equal to 10; S3343: Within the K solution sets, using the good solutions as the adjustment direction, perform optimization on the poor solutions within the same solution set according to a preset optimization step size. S3344: Adjust the solution to obtain K updated solution sets. If the adjusted poor solution does not meet the adjustment space of the monitoring index, it is discarded and a monitoring threshold is randomly selected for supplementation. S3345: Identify the K updated solution sets. If the prediction and warning accuracy of the updated poor solution is greater than the prediction and warning accuracy of the good solution in the same solution set, the poor solution replaces the good solution. S3346: Perform iterative optimization until the preset number of optimizations is reached. Output K current solution sets. Select the solution set with the largest sum of prediction and warning accuracies as the optimal solution set, and set the good solution of the optimal solution set as the optimal monitoring threshold.

[0059] Specifically, firstly, initial monitoring thresholds are set as initial solutions. Multiple initial monitoring thresholds are sorted according to their prediction and warning accuracy rates, from highest to lowest, to obtain an initial solution sequence. Next, based on heuristics, high-performance and low-performance solutions are categorized separately to enhance search directionality. Specifically, the first K solutions in the initial solution sequence are designated as good solutions, and the last M solutions as poor solutions, where M is N times K, and N is greater than or equal to 10. Centered on the good solutions, the poor solutions are divided into K solution sets using an equal-value random clustering method. Further, within these K solution sets, adjustments are made to the poor solutions within the same solution set, using the good solutions as the adjustment direction and according to a preset optimization step size. If the adjusted poor solution does not meet the adjustment space of the monitoring index, it is discarded, and a randomly selected monitoring threshold is used to supplement it, resulting in K updated solution sets. This allows poor solutions to move closer to good solutions, improving the overall accuracy of the solution set. The replacement with randomly generated new thresholds ensures the integrity of the solution set, increases the diversity of local searches, and prevents getting trapped in local optima. Then, the K updated solution sets are identified. If the prediction and warning accuracy of the updated poor solution is greater than that of the good solution in the same solution set, the poor solution replaces the good solution. By dynamically optimizing the good solution set, new excellent solutions are introduced to improve the global search efficiency. Then, iterative optimization is continued, and the operations of solution set clustering, guided adjustment, and replacement are repeated until the preset number of iterations is reached. K current solution sets are output, and the solution set with the largest sum of prediction and warning accuracies is selected as the optimal solution set. The good solutions of the optimal solution set are set as the optimal monitoring threshold.

[0060] By constructing multiple initial monitoring threshold solutions and fusing prediction accuracy feedback information, and leveraging solution set clustering and guided differential solution adjustment strategies, a multi-solution co-evolutionary optimization framework with self-learning capabilities is realized. Through a structural design that uses good solutions as guides and poor solutions as the main search subjects, it can not only dynamically discover the optimal threshold combination, but also significantly improve the convergence speed and global optimal coverage of the threshold optimization process. In addition, through a deviation-driven branch allocation mechanism and a dynamic elimination and replacement mechanism, computational resource consumption is effectively controlled, achieving an optimal balance between accuracy improvement and computing efficiency, and meeting the actual needs of intelligent adaptive optimization of gas monitoring thresholds in GIS equipment.

[0061] S40: Set an adaptive early warning strategy based on the optimal monitoring threshold, and monitor and issue early warnings for sulfur hexafluoride gas in the GIS equipment within the preset time zone.

[0062] Specifically, firstly, an adaptive early warning strategy is set based on the optimal monitoring threshold. This strategy setting must consider the fluctuation range of the threshold adjustment and the tolerance for prediction errors to prevent oversensitivity or sluggish response. Next, sulfur hexafluoride gas in the GIS equipment is monitored and warned of within the preset time zone. Compared to traditional fixed threshold strategies, this method sets an early warning mechanism based on a "dynamic optimal threshold," which can significantly reduce false alarms and missed alarms, enhance the ability to perceive changes in equipment status under complex environments, thereby improving the timeliness and accuracy of fault warnings and achieving state-based intelligent operation and maintenance and risk management.

[0063] In summary, the GIS status detection method provided by this invention has the following technical effects:

[0064] By acquiring a set of metal casing images and maintenance intervals based on the most recent maintenance records of the GIS equipment, and analyzing these images to determine the leakage risk coefficient of sulfur hexafluoride (SF6) gas, the system also monitors and acquires the current environmental parameters of the area where the GIS equipment is located within a preset time zone, as well as the expected operating load of the GIS equipment. Then, based on the leakage risk coefficient, maintenance intervals, current environmental parameters, and expected operating load, and with the goal of maximizing the accuracy of SF6 gas early warning, the system optimizes the gas monitoring threshold to obtain the optimal monitoring threshold. Finally, based on the optimal monitoring threshold, an adaptive early warning strategy is set to monitor and issue early warnings for SF6 gas in the GIS equipment within the preset time zone. In other words, by integrating metal casing image recognition, environmental parameter perception, and operating load modeling, a multi-dimensional state perception and evaluation mechanism is constructed to dynamically optimize the SF6 gas monitoring threshold, achieving adaptive early warning and effectively improving the accuracy and reliability of gas detection in GIS equipment. This meets the needs of intelligent operation and maintenance and refined management.

[0065] Example 2: Based on the same inventive concept as the GIS status detection method in the foregoing examples, the present invention also provides a GIS status detection system. Please refer to the appendix. Figure 2 The system includes: a leakage risk coefficient determination module 11, used to acquire a set of metal casing images and maintenance interval duration based on the most recent maintenance record of the GIS equipment, and to determine the leakage risk coefficient of sulfur hexafluoride gas based on the analysis of the metal casing image set; a data monitoring and acquisition module 12, used to monitor and acquire the current environmental parameters of the area where the GIS equipment is located within a preset time zone, as well as the expected operating load of the GIS equipment; a gas monitoring threshold optimization module 13, used to optimize the gas monitoring threshold based on the leakage risk coefficient, maintenance interval duration, current environmental parameters, and expected operating load, with the goal of maximizing the early warning accuracy of sulfur hexafluoride gas, and to obtain the optimal monitoring threshold; and an equipment monitoring and early warning module 14, used to set an adaptive early warning strategy based on the optimal monitoring threshold, and to monitor and issue early warnings for sulfur hexafluoride gas in the GIS equipment within the preset time zone.

[0066] Furthermore, the GIS status detection system is also used to: acquire a metal shell image set, wherein the metal shell image set includes metal shell images of several key parts; use a convolutional neural network to perform defect identification on the metal shell images of the several key parts to acquire several defect features; and combine an empirical weight model to evaluate and determine a leakage risk coefficient based on the several defect features.

[0067] Furthermore, the GIS status detection system is also used to: acquire gas monitoring indicators of sulfur hexafluoride (SF6) gas, and the adjustment space of the monitoring indicators, wherein the gas monitoring indicators include gas density, gas pressure, gas temperature, moisture content, and decomposition product concentration; train an SF6 gas early warning accuracy predictor based on the leakage risk coefficient, maintenance interval duration, current environmental parameters, and expected operating load; and optimize the gas monitoring threshold using the early warning accuracy predictor based on the monitoring indicator adjustment space, with the goal of maximizing the early warning accuracy of SF6 gas, and output the optimal monitoring threshold.

[0068] Furthermore, the GIS status detection system is also used for: using the leakage risk coefficient, maintenance interval duration, current environmental parameters, and expected operating load as search constraints, expanding the search constraints according to a preset tolerance range to obtain search conditions; based on the search conditions, filtering historical monitoring data of sulfur hexafluoride gas from similar GIS equipment, collecting a set of sample gas monitoring thresholds, and statistically analyzing the probability of false alarms and missed alarms for sulfur hexafluoride gas indicators under different sample gas monitoring thresholds, calculating the sample warning accuracy rate, and obtaining a set of sample warning accuracy rates; using the set of sample gas monitoring thresholds and the set of sample warning accuracy rates, training a generative adversarial network until convergence to obtain a warning accuracy predictor.

[0069] Furthermore, the GIS status detection system is also used for: using the sample gas monitoring threshold set and the sample early warning accuracy set as training data, and dividing them into P equal parts; selecting P times with replacement from the P sets to obtain the first training set; iterating P times to obtain P training sets, where P is an integer greater than or equal to 10; using the P training sets, training a generative adversarial network to convergence to obtain P early warning accuracy prediction branches, and combining them to obtain an early warning accuracy predictor.

[0070] Furthermore, the GIS status detection system is also used for: randomly selecting within the monitoring indicator adjustment space to obtain multiple initial monitoring thresholds; using the standard monitoring threshold as a benchmark, calculating the deviation of the multiple initial monitoring thresholds respectively, determining multiple deviation values ​​by weighting, and calculating multiple branch selection quantities Q, where Q is the integer value of the product of the deviation value and P, and Q is greater than or equal to 1 and less than or equal to P; based on the multiple branch selection quantities Q, using the early warning accuracy predictor to predict the multiple initial monitoring thresholds respectively, and outputting multiple predicted early warning accuracies; and optimizing the gas monitoring threshold based on the multiple predicted early warning accuracies, with the goal of maximizing the early warning accuracy of sulfur hexafluoride gas, and outputting the optimal monitoring threshold.

[0071] Furthermore, the GIS status detection system is also used for: setting initial monitoring thresholds as initial solutions; sorting multiple initial monitoring thresholds according to their early warning accuracy rates from largest to smallest, based on the multiple prediction and early warning accuracy rates, to obtain an initial solution sequence; designating the first K solutions of the initial solution sequence as good solutions and the last M solutions as poor solutions; and performing random equal-value clustering on the M poor solutions centered on the K good solutions to obtain K solution sets, where M is N times K, and N is greater than or equal to 10; within the K solution sets, adjusting in the direction of good solutions according to a preset optimization step size... The suboptimal solutions within a solution set are adjusted to obtain K updated solution sets. If the adjusted suboptimal solutions do not meet the adjustment space of the monitoring index, they are discarded, and a monitoring threshold is randomly selected to supplement them. The K updated solution sets are identified. If the prediction and warning accuracy of the updated suboptimal solutions is greater than the prediction and warning accuracy of the good solutions in the same solution set, the suboptimal solutions are used to replace the good solutions. Iterative optimization is performed until a preset number of optimizations is reached. K current solution sets are output. The solution set with the largest sum of prediction and warning accuracies is selected as the optimal solution set, and the good solutions of the optimal solution set are set as the optimal monitoring threshold.

[0072] Example 3, please refer to Figure 3 , Figure 3 This is a schematic diagram of an embodiment of a smart terminal provided by the present invention. For example... Figure 3 As shown, this embodiment of the invention provides a smart terminal 500, including a memory 510, a processor 520, and a first computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the first computer program 511, it performs the following steps: based on the most recent maintenance record of the GIS equipment, it acquires a set of metal casing images and maintenance interval duration, and analyzes and determines the leakage risk coefficient of sulfur hexafluoride gas based on the metal casing image set; it monitors and acquires the current environmental parameters of the area where the GIS equipment is located within a preset time zone, as well as the expected operating load of the GIS equipment; based on the leakage risk coefficient, maintenance interval duration, current environmental parameters, and expected operating load, it optimizes the gas monitoring threshold to maximize the early warning accuracy of sulfur hexafluoride gas, and obtains the optimal monitoring threshold; based on the optimal monitoring threshold, it sets an adaptive early warning strategy to monitor and warn of sulfur hexafluoride gas in the GIS equipment within the preset time zone.

[0073] Example 4, please refer to Figure 4 , Figure 4 This is a schematic diagram illustrating an embodiment of a computer-readable storage medium provided by an embodiment of the present invention. For example... Figure 4As shown, this embodiment provides a computer-readable storage medium 600, on which a second computer program 611 is stored. When the second computer program 611 is executed by a processor, it performs the following steps: based on the most recent maintenance record of the GIS equipment, it acquires a set of metal casing images and maintenance interval duration, and analyzes and determines the leakage risk coefficient of sulfur hexafluoride gas based on the metal casing image set; it monitors and acquires the current environmental parameters of the area where the GIS equipment is located within a preset time zone, as well as the expected operating load of the GIS equipment; based on the leakage risk coefficient, maintenance interval duration, current environmental parameters, and expected operating load, it optimizes the gas monitoring threshold to maximize the early warning accuracy of sulfur hexafluoride gas, and obtains the optimal monitoring threshold; based on the optimal monitoring threshold, it sets an adaptive early warning strategy to monitor and issue early warnings for sulfur hexafluoride gas in the GIS equipment within the preset time zone.

[0074] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0075] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0076] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0077] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0078] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0079] Although preferred embodiments of the invention have been described, those skilled in the art, once they have learned the basic inventive concept, can make other changes and modifications to these embodiments.

[0080] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this invention and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. A GIS status detection method, characterized in that, The methods include: Based on the most recent maintenance record of the GIS equipment, a set of images of the metal casing and the maintenance interval are obtained, and the leakage risk coefficient of sulfur hexafluoride gas is determined by analyzing the set of images of the metal casing. Monitor and acquire the current environmental parameters of the area where the GIS equipment is located within the preset time zone, as well as the expected operating load of the GIS equipment; Based on the aforementioned leakage risk coefficient, maintenance interval duration, current environmental parameters, and expected operating load, with the goal of maximizing the early warning accuracy of sulfur hexafluoride gas, the gas monitoring threshold is optimized to obtain the optimal monitoring threshold. An adaptive early warning strategy is set according to the optimal monitoring threshold, and sulfur hexafluoride gas in the GIS equipment is monitored and warned within the preset time zone. Specifically, based on the leakage risk coefficient, maintenance interval, current environmental parameters, and expected operating load, and with the goal of maximizing the early warning accuracy of sulfur hexafluoride gas, the gas monitoring threshold is optimized to obtain the optimal monitoring threshold, including: The gas monitoring indicators of sulfur hexafluoride gas, as well as the adjustment range of the monitoring indicators, are obtained. The gas monitoring indicators include gas density, gas pressure, gas temperature, moisture content and decomposition product concentration. Based on the aforementioned leakage risk coefficient, maintenance interval duration, current environmental parameters, and expected operating load, a predictor for the accuracy of early warning of sulfur hexafluoride gas is trained. Based on the adjustment space of the monitoring indicators, with the goal of maximizing the early warning accuracy of sulfur hexafluoride gas, the gas monitoring threshold is optimized using the early warning accuracy predictor, and the optimal monitoring threshold is output, including: Multiple initial monitoring thresholds are obtained by randomly selecting from the monitoring indicator adjustment space. Based on the standard monitoring threshold, the deviation of the multiple initial monitoring thresholds is calculated respectively, multiple deviation values ​​are determined by weighting, and multiple branch selection numbers Q are calculated and obtained, where Q is the rounded value of the product of the deviation value and P, and Q is greater than or equal to 1 and less than or equal to P. Based on the number Q of the multiple branches selected, the early warning accuracy predictor is used to predict the multiple initial monitoring thresholds respectively, and outputs multiple predicted early warning accuracy rates; Based on the accuracy of the multiple predictions and early warnings, the gas monitoring threshold is optimized with the goal of maximizing the early warning accuracy of sulfur hexafluoride gas, and the optimal monitoring threshold is output.

2. The GIS status detection method according to claim 1, characterized in that, The leakage risk factor of sulfur hexafluoride gas was determined based on the analysis of the aforementioned metal casing image set, including: Acquire a set of metal shell images, which includes images of several key parts of the metal shell; Defect identification is performed on the metal shell images of the aforementioned key parts using a convolutional neural network to obtain several defect features; By combining an empirical weighting model, the leakage risk coefficient is determined based on the aforementioned defect characteristics.

3. The GIS status detection method according to claim 1, characterized in that, Based on the aforementioned leakage risk coefficient, maintenance interval duration, current environmental parameters, and expected operating load, a predictor for the accuracy of sulfur hexafluoride gas early warning is trained, including: Using the leakage risk coefficient, maintenance interval duration, current environmental parameters, and expected operating load as search constraints, the search constraints are expanded according to a preset tolerance range to obtain search conditions; Based on the search criteria, historical monitoring data of sulfur hexafluoride gas from similar GIS equipment are filtered, a set of sample gas monitoring thresholds is collected, and the probability of false alarms and missed alarms of sulfur hexafluoride gas indicators under different sample gas monitoring thresholds is statistically analyzed. The sample warning accuracy rate is calculated, and a set of sample warning accuracy rates is obtained. Using the sample gas monitoring threshold set and the sample early warning accuracy set, a generative adversarial network is trained until convergence to obtain an early warning accuracy predictor.

4. The GIS status detection method according to claim 3, characterized in that, Using the sample gas monitoring threshold set and the sample early warning accuracy set, a generative adversarial network is trained until convergence to obtain an early warning accuracy predictor, including: The sample gas monitoring threshold set and sample early warning accuracy set are used as training data and divided into P equal parts. The first training set is obtained by selecting P times with replacement from the P sets of data. The first training set is obtained by iteratively selecting P times, where P is an integer greater than or equal to 10. Using the P training sets, each generative adversarial network is trained until convergence, resulting in P branches for predicting early warning accuracy. These branches are then combined to obtain an early warning accuracy predictor.

5. The GIS status detection method according to claim 1, characterized in that, Based on the aforementioned multiple prediction and early warning accuracies, the gas monitoring threshold is optimized with the goal of maximizing the early warning accuracy of sulfur hexafluoride gas, and the optimal monitoring threshold is output, including: The initial monitoring threshold is set as the initial solution. The multiple initial monitoring thresholds are sorted according to the multiple prediction and early warning accuracy rates from large to small to obtain the initial solution sequence. The first K solutions of the initial solution sequence are set as good solutions, and the last M solutions are set as poor solutions. Then, the M poor solutions are randomly clustered with equal value centered on the K good solutions to obtain K solution sets, where M is N times K and N is greater than or equal to 10. Within the K solution sets, with good solutions as the adjustment direction, the difference solutions within the same solution set are adjusted according to the preset optimization step size to obtain K updated solution sets. If the adjusted difference solutions do not meet the adjustment space of the monitoring index, they are removed and a monitoring threshold is randomly selected for supplementation. Identify the K updated solution sets. If the prediction and warning accuracy of the updated poor solution is greater than the prediction and warning accuracy of the good solution in the same solution set, then replace the good solution with the poor solution. Perform iterative optimization until the preset number of optimizations is reached, output K current solution sets, select the solution set with the largest sum of prediction and early warning accuracy as the optimal solution set, and set the good solution of the optimal solution set as the optimal monitoring threshold.

6. A GIS status detection system, characterized in that, The steps for implementing a GIS status detection method according to any one of claims 1 to 5 include: The leakage risk coefficient determination module is used to obtain a set of metal casing images and maintenance intervals based on the most recent operation and maintenance records of the GIS equipment, and to analyze and determine the leakage risk coefficient of sulfur hexafluoride gas based on the set of metal casing images. The data monitoring and acquisition module is used to monitor and acquire the current environmental parameters of the area where the GIS equipment is located within the preset time zone, as well as the expected operating load of the GIS equipment; The gas monitoring threshold optimization module is used to optimize the gas monitoring threshold based on the leakage risk coefficient, maintenance interval, current environmental parameters and expected operating load, with the goal of maximizing the early warning accuracy of sulfur hexafluoride gas, and to obtain the optimal monitoring threshold. The equipment monitoring and early warning module is used to set an adaptive early warning strategy based on the optimal monitoring threshold and to monitor and warn of sulfur hexafluoride gas in the GIS equipment within the preset time zone. Specifically, based on the leakage risk coefficient, maintenance interval, current environmental parameters, and expected operating load, and with the goal of maximizing the early warning accuracy of sulfur hexafluoride gas, the gas monitoring threshold is optimized to obtain the optimal monitoring threshold, including: The gas monitoring indicators of sulfur hexafluoride gas, as well as the adjustment range of the monitoring indicators, are obtained. The gas monitoring indicators include gas density, gas pressure, gas temperature, moisture content and decomposition product concentration. Based on the aforementioned leakage risk coefficient, maintenance interval duration, current environmental parameters, and expected operating load, a predictor for the accuracy of early warning of sulfur hexafluoride gas is trained. Based on the adjustment space of the monitoring indicators, with the goal of maximizing the early warning accuracy of sulfur hexafluoride gas, the gas monitoring threshold is optimized using the early warning accuracy predictor, and the optimal monitoring threshold is output, including: Multiple initial monitoring thresholds are obtained by randomly selecting from the monitoring indicator adjustment space. Based on the standard monitoring threshold, the deviation of the multiple initial monitoring thresholds is calculated respectively, multiple deviation values ​​are determined by weighting, and multiple branch selection numbers Q are calculated and obtained, where Q is the rounded value of the product of the deviation value and P, and Q is greater than or equal to 1 and less than or equal to P. Based on the number Q of the multiple branches selected, the early warning accuracy predictor is used to predict the multiple initial monitoring thresholds respectively, and outputs multiple predicted early warning accuracy rates; Based on the accuracy of the multiple predictions and early warnings, the gas monitoring threshold is optimized with the goal of maximizing the early warning accuracy of sulfur hexafluoride gas, and the optimal monitoring threshold is output.

7. A smart terminal, characterized in that, include: Memory, used to store computer software programs; A processor is configured to read and execute the computer software program, thereby implementing the steps of the GIS status detection method according to any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium, characterized in that, The storage medium stores a computer software program, which, when executed by a processor, implements the steps of a GIS status detection method as described in any one of claims 1 to 5.

Images