High-voltage circuit breaker and heating fault prediction method and system for isolating switch of high-voltage circuit breaker

Abstract

The invention relates to the technical field of machine learning, in particular to a heating fault prediction method and system for a high-voltage circuit breaker and an isolating switch of the high-voltage circuit breaker. The method comprises the following steps: carrying out multi-source data acquisition on a high-voltage isolation switch and an associated high-voltage circuit breaker through an SCADA system, and carrying out data preprocessing to obtain a preprocessed data set; performing operation feature correlation analysis on the preprocessed data set to obtain a correlation operation feature set; performing dynamic association network construction on the association operation feature set to obtain a dynamic association network graph; acquiring historical fault data; performing propagation risk path search according to the historical fault data and the dynamic association network diagram to obtain a candidate risk path set; and performing path propagation probability calculation on the candidate risk path set to obtain a path probability data set. According to the method, the influence of the associated high-voltage circuit breaker on the heating risk of the isolating switch is effectively identified, so that the accuracy of fault prediction and the timeliness of early warning are improved, and a more reliable guarantee is provided for safe and stable operation of a power system.

Description

Technical Field

[0001] The present invention relates to the field of machine learning technology, and in particular to a method and system for predicting heating faults of a high-voltage circuit breaker and an isolating switch thereof. Background Art

[0002] High-voltage circuit breakers are an important type of protection and control equipment in power systems. They are mainly used in high-voltage transmission lines and substations to perform on-load switching operations on circuits and quickly cut off fault currents when a system fault occurs, protecting power equipment and limiting the expansion of accidents. High-voltage circuit breakers are closely related to high-voltage disconnectors. Disconnectors are usually used in conjunction with circuit breakers to reliably isolate the live parts of circuit breakers during maintenance or overhaul of circuit breakers. At the same time, frequent operation of circuit breakers will aggravate the wear of disconnectors and cause heating failures of disconnectors. Therefore, in the prediction of disconnector failures, the influence of the associated high-voltage circuit breakers must be fully considered. The traditional method for predicting heating failures of disconnectors of high-voltage circuit breakers mainly relies on manual inspections and regular maintenance, which has problems such as low prediction accuracy, strong hysteresis, and low efficiency. In recent years, with the rapid development of sensor technology, data analysis technology, and artificial intelligence technology, some new prediction methods have emerged, as follows:

[0003] 1. Prediction method based on temperature monitoring: By monitoring the contact temperature, terminal temperature and other parameters of the isolating switch, the temperature change trend is used to predict the occurrence of faults.

[0004] 2. Prediction method based on vibration analysis: By analyzing the vibration signal of the disconnector, abnormal vibration patterns are identified and the occurrence of faults is predicted.

[0005] 3. Prediction method based on infrared thermal imaging: Use infrared thermal imaging technology to detect the temperature distribution of the disconnector, identify abnormal hot spots, and predict the occurrence of faults.

[0006] However, most of these methods only focus on the status of the disconnector itself and lack consideration of the impact of associated high-voltage circuit breakers, resulting in limited prediction accuracy and warning timeliness.

[0007] The disconnector of a high-voltage circuit breaker does not operate in isolation, and its failure is often closely related to one or more associated high-voltage circuit breakers. For example, frequent operation of a high-voltage circuit breaker will cause the disconnector contacts to wear more severely, increasing the risk of thermal failure; a high-voltage circuit breaker tripping will cause the disconnector to withstand overcurrent shocks, causing thermal failures.

[0008] Traditional methods lack analysis of the impact of associated high-voltage circuit breakers. The main reasons are:

[0009] 1. Incomplete data collection: Traditional methods mainly collect the operating data of the disconnector itself, but lack the collection and analysis of the associated high-voltage circuit breaker data.

[0010] 2. Difficulty in modeling association relationships: The association relationships between multiple high-voltage circuit breakers and high-voltage disconnectors are complex and diverse, and it is difficult to describe them using a simple mathematical model.

[0011] 3. Lack of effective analysis methods: Even if data on related high-voltage circuit breakers is collected, there is a lack of effective analysis methods to identify failure risks. Summary of the invention

[0012] Based on this, it is necessary to provide a method and system for predicting heating faults of high-voltage circuit breakers and their isolating switches to solve at least one of the above technical problems.

[0013] To achieve the above object, a method for predicting thermal faults of isolating switches of high-voltage circuit breakers comprises the following steps:

[0014] Step S1: performing multi-source data acquisition on the high-voltage disconnector and its associated high-voltage circuit breaker through the SCADA system, and performing data preprocessing to obtain a preprocessed data set; performing operation feature correlation analysis on the preprocessed data set to obtain a correlated operation feature set;

[0015] Step S2: constructing a dynamic association network for the associated operation feature set to obtain a dynamic association network graph;

[0016] Step S3: Acquire historical fault data; search for propagation risk paths based on historical fault data and the dynamic association network diagram to obtain a candidate risk path set; calculate the path propagation probability of the candidate risk path set to obtain a path probability data set; extract key risk propagation paths based on the path probability data set and the candidate risk path set to obtain key risk propagation paths;

[0017] Step S4: Calculate the path propagation probability according to the key risk propagation path to obtain a path probability matrix; perform a dynamic analysis of the fault probability according to the path probability matrix to obtain a dynamic fault probability matrix;

[0018] Step S5: constructing a fever risk prediction model according to the associated operation feature set and the dynamic fault probability matrix to obtain a fever risk prediction model; using the fever risk prediction model to predict the fever risk, and calculating a comprehensive risk index to obtain a comprehensive fever risk index;

[0019] Step S6: Acquire historical warning data; construct an adaptive warning model based on the historical warning data to obtain an adaptive warning model; perform adaptive warning of heating faults of high-voltage disconnectors based on the comprehensive heating risk index and the adaptive warning model to realize the prediction of heating faults of high-voltage disconnectors.

[0020] The present invention not only ensures data quality by collecting multi-source data and performing preprocessing, but also extracts key operating characteristics of associated high-voltage circuit breakers, laying a data foundation for subsequent analysis of mutual influence between devices and construction of prediction models. By constructing a dynamic association network, the association relationship between devices and their trend over time are intuitively displayed, providing intuitive visual guidance for identifying key risk propagation paths. By analyzing historical fault data and dynamic association networks, potential risk propagation paths are found, and the propagation probability of each path is evaluated, providing a basis for accurately locating key risk paths. By constructing a fault propagation model and combining real-time monitoring data for dynamic analysis, real-time risk assessment of key risk propagation paths is achieved, providing a dynamic probability basis for predicting heat failures of disconnectors. By constructing a prediction model based on association characteristics and dynamic fault probabilities, the future heat risk of disconnectors can be predicted more accurately, and a more intuitive reference basis for risk warning can be provided through a comprehensive risk index. By constructing an adaptive warning model and dynamically adjusting the warning threshold according to the comprehensive risk index, a more accurate and flexible warning mechanism is achieved, which effectively reduces the risk of false alarms and missed alarms and improves the efficiency and accuracy of warnings. Therefore, the present invention provides a method for predicting the heating fault of the disconnector of a high-voltage circuit breaker, which effectively solves the problem that the existing method lacks consideration of the impact of the associated high-voltage circuit breaker by introducing the technology of multi-source data association analysis, dynamic association network construction and risk propagation path identification. The method can effectively identify the impact of the associated high-voltage circuit breaker on the heating risk of the disconnector, thereby improving the accuracy of fault prediction and the timeliness of early warning, and providing more reliable protection for the safe and stable operation of the power system.

[0021] Preferably, step S1 comprises the following steps:

[0022] Step S11: performing multi-source data acquisition on the high-voltage disconnector and its associated high-voltage circuit breaker through the SCADA system to obtain an original data set; performing data preprocessing on the original data set to obtain a preprocessed data set;

[0023] Step S12: performing data time alignment on the preprocessed data set to obtain a time-aligned data set;

[0024] Step S13: establishing an association relationship between the high-voltage disconnector and its associated high-voltage circuit breaker to obtain association relationship data;

[0025] Step S14: performing feature matching of the same time window on the time-aligned data set according to the association relationship data to obtain a feature matching data set;

[0026] Step S15: Generate an associated operation feature set according to the feature matching data set to obtain an associated operation feature set.

[0027] The present invention collects multi-source data through the SCADA system and performs preprocessing, which can eliminate noise and redundant information in the original data, improve the quality and consistency of the data, and lay the foundation for subsequent feature analysis and model construction. The preprocessing data set is aligned in time to ensure that the data of different devices are synchronously corresponding in time, eliminate the influence of time difference on association analysis, and ensure the accuracy of subsequent feature matching and association analysis. The association relationship data between the high-voltage disconnector and its associated high-voltage circuit breaker is established, the topological relationship between the devices is clarified, and the necessary information basis is provided for the subsequent analysis of the influence of the associated high-voltage circuit breaker and the risk propagation path. According to the association relationship data, feature matching of the same time window is performed, and the operating data of the associated high-voltage circuit breaker is associated in the same time dimension, forming multi-dimensional association feature information, which provides a richer data basis for the subsequent extraction of the associated operation feature set. According to the feature matching data set, the associated operation feature set is generated, and the main features that can characterize the operating status of the high-voltage disconnector and the associated high-voltage circuit breaker are extracted, which reduces the data dimension and reduces the calculation complexity, while retaining the key information, and provides a more refined data representation for the subsequent dynamic association network construction and fault prediction.

[0028] Preferably, step S2 comprises the following steps:

[0029] Step S21: performing time series segmentation of the associated operation feature set to obtain a time series feature data set;

[0030] Step S22: Calculate the dynamic correlation relationship of the time series feature data set to obtain a correlation relationship matrix;

[0031] Step S23: dynamically evolving the correlation relationship matrix to obtain a dynamic correlation matrix sequence;

[0032] Step S24: setting the association strength threshold according to the dynamic association matrix sequence, and drawing a network diagram to obtain a dynamic association network diagram.

[0033] The present invention divides the associated operation feature set into associated feature time series, converts the time series data into multiple time segment samples, so that each sample can more completely reflect the operating status of the equipment in a specific time period, and provides a more refined data basis for the calculation of dynamic association relationships. The dynamic association relationship calculation is performed on the time series feature data set, the degree of association between different features is quantified, and an association relationship matrix is ​​constructed, which provides a quantitative basis for the subsequent analysis of the mutual influence and risk propagation between devices. By constructing a dynamic association matrix sequence, the changing trend of the association relationship over time is captured, overcoming the limitations of traditional static analysis methods, and being able to more accurately reflect the dynamic changes in the operating status of the power system, providing a more reliable basis for risk warning. According to the dynamic association matrix sequence, the association strength threshold is set, strong association relationships are screened out, and a dynamic association network diagram is drawn to present complex association relationships in an intuitive way, which helps to more clearly understand the mutual influence between devices and provide direct visual guidance for identifying key risk propagation paths.

[0034] Preferably, step S3 comprises the following steps:

[0035] Step S31: performing network topology structure analysis on the dynamic association network graph to obtain a network topology data set;

[0036] Step S32: Acquire historical fault data, wherein the historical fault data includes historical high-voltage circuit breaker fault state data, historical disconnector heating state data, and equipment operation and maintenance data;

[0037] Step S33: searching for a propagation risk path on the network topology data set according to the historical fault data to obtain a candidate risk path set;

[0038] Step S34: Calculate the path propagation probability of the candidate risk path set to obtain a path probability data set;

[0039] Step S35: sorting the candidate risk path set by path importance according to the path probability data set to obtain a sorted path probability data set;

[0040] Step S36: Use the preset sorting path threshold to perform key path screening on the sorting path probability data set to obtain the key risk propagation path.

[0041] The present invention extracts key information characterizing the network structure, such as node degree, centrality, clustering coefficient, etc., as well as network connectivity, shortest path, etc., by performing network topology structure analysis on the dynamic association network graph, and provides a structured data basis for subsequent risk propagation path search. Historical fault data is obtained, including historical high-voltage circuit breaker fault state data, historical disconnector heating state data, and equipment operation and maintenance data, to provide historical experience and data support for subsequent analysis of fault propagation laws, calculation of path propagation probability, and identification of key risk paths. According to the historical fault data, the network topology data set is searched for propagation risk paths, all possible propagation paths from the fault source node to the target node are found, and a candidate risk path set is constructed, providing candidates for subsequent risk assessment and prediction. By calculating the path propagation probability of the candidate risk path set, the possibility of fault propagation on each path is quantified, providing a quantitative basis for evaluating the risk level of different paths. The candidate risk path set is sorted by path importance according to the path probability data set, and high-risk paths are placed in front, which is convenient for key attention and improves the efficiency of risk identification. The preset sorting path threshold is used to screen the critical paths of the sorting path probability data set, eliminating the interference of low-risk paths and accurately locating the key risk propagation paths that cause thermal failures of disconnect switches, providing a more accurate target for subsequent fault prediction and early warning.

[0042] Preferably, step S33 includes the following steps:

[0043] Step S331: marking fault nodes of the network topology data set according to known high-voltage circuit breaker fault status data to obtain a fault-marked network data set;

[0044] Step S332: marking heating nodes of the fault marking network data set according to the historical isolating switch heating state data to obtain the heating marking network data set;

[0045] Step S333: Screening the fever mark network data set for potential risk edges to obtain a risk edge data set;

[0046] Step S334: determining the risk propagation direction of the risk edge data set to obtain a directed risk edge data set;

[0047] Step S335: Perform a temporal path search on the directed risk edge data set to obtain a candidate risk path set.

[0048] The present invention marks the fault nodes of the network topology data set according to the known high-voltage circuit breaker fault status data, clarifies the starting point of fault propagation, and provides a starting point for the subsequent risk path search. The heating nodes of the fault-marked network data set are marked according to the historical disconnector heating status data, and the end point of risk propagation is clarified, providing a target for the subsequent risk path search. The heating-marked network data set is screened for potential risk edges, and edges that are not related to fault propagation are removed, thereby narrowing the search range and improving the efficiency of path search. The risk propagation direction of the risk edge data set is determined, and the reverse propagation path is excluded, further narrowing the search range and improving the accuracy of path search. The directed risk edge data set is searched for a temporal path, and the temporal logic of fault propagation is considered to ensure that the found path conforms to the actual situation, further improving the reliability of the candidate risk path set.

[0049] Preferably, step S34 includes the following steps:

[0050] Step S341: Calculate the initial path probability based on the historical fault data and the candidate risk path set to obtain an initial path probability set;

[0051] Step S342: extracting environmental factor data from the preprocessed data set, and quantifying the impact of environmental factors to obtain an environmental impact factor set;

[0052] Step S343: quantifying the impact of equipment status on equipment operation and maintenance data to obtain an equipment status factor set;

[0053] Step S344: modifying the initial path probability set according to the environmental impact factor set and the device status factor set to obtain a modified path probability set;

[0054] Step S345: performing path probability confidence evaluation on the modified path probability set to obtain a path probability data set.

[0055] The present invention calculates the initial path probability based on historical fault data and a set of candidate risk paths, assigns a probability value of fault propagation to each candidate path, and provides a quantitative basis for subsequent risk assessment. The environmental factor data is extracted and the impact is quantified on the preprocessed data set, and the impact of environmental factors on the heating probability of the disconnector is taken into consideration, thereby improving the comprehensiveness and accuracy of the path probability calculation. The equipment status impact is quantified on the equipment operation and maintenance data, and the impact of the equipment's own status on the heating probability is taken into consideration, further improving the accuracy and reliability of the path probability calculation. The initial path probability is corrected according to the environmental impact factor set and the equipment status factor set, and the impact of environmental factors and equipment status on fault propagation is comprehensively considered, so that the path probability calculation result is closer to the actual situation. The corrected path probability is evaluated for confidence, and the confidence interval of the path probability is given, the uncertainty of the path probability is quantified, and the reliability and credibility of the risk assessment result are improved.

[0056] Preferably, step S4 comprises the following steps:

[0057] Step S41: quantify the critical path state of the critical risk propagation path to obtain a quantified path data set; construct a fault propagation model based on historical fault data to obtain a fault propagation model;

[0058] Step S42: acquiring real-time monitoring data of the high-voltage circuit breaker and the disconnector; initializing the model state according to the real-time monitoring data of the high-voltage circuit breaker and the disconnector to obtain an initial state probability vector;

[0059] Step S43: using the fault propagation model to perform iterative state probability calculation according to the initial state probability vector to obtain a state probability matrix;

[0060] Step S44: Calculate the path propagation probability according to the state probability matrix to obtain a path probability matrix;

[0061] Step S45: dynamically sliding the time window according to the path probability matrix to obtain a sliding path probability matrix sequence;

[0062] Step S46: integrating the probability matrix time dimension of the sliding path probability matrix sequence to obtain a time-integrated probability matrix; and compressing the time-integrated probability matrix in the time dimension to obtain a dynamic fault probability matrix.

[0063] The present invention quantifies the node states on the key risk propagation path and converts the qualitative description into quantitative data, providing a data basis for subsequent model calculations; at the same time, a fault propagation model is constructed based on historical fault data, and the fault propagation relationship between nodes is quantified, providing a model basis for dynamic fault probability assessment. Real-time monitoring data of high-voltage circuit breakers and disconnectors are obtained, and the real-time data is converted into the initial state probability vector of the model. The static model is combined with the real-time data to provide real-time input for dynamic fault probability assessment. The state probability is iteratively calculated using the fault propagation model and the initial state probability vector, simulating the dynamic propagation process of the fault on the key risk propagation path, and the state probability of each node under each time step is obtained, providing a dynamic probability basis for path propagation probability calculation. The path propagation probability is calculated according to the state probability matrix, and the propagation probability of each key risk propagation path under each time step is obtained, realizing real-time risk assessment of the fault propagation path. The time window is dynamically slid according to the path probability matrix, and the discrete time step is converted into a continuous time window, which is closer to the actual fault development process and provides more refined time dimension information for subsequent dynamic analysis of fault probability. The sliding path probability matrix sequence is integrated and compressed in time dimension, and the path propagation probabilities of different time windows are integrated to finally obtain a dynamic fault probability matrix. This matrix integrates historical data, real-time data and time dimension information, providing a more comprehensive and accurate probability basis for subsequent risk prediction.

[0064] Preferably, step S5 comprises the following steps:

[0065] Step S51: extracting the isolating switch feature from the associated operation feature set to obtain an isolating switch feature data set; extracting the environmental factor feature from the associated operation feature set to obtain an environmental factor feature data set;

[0066] Step S52: performing feature set fusion on the dynamic fault probability matrix, the disconnector feature data set, and the environmental factor feature data set to obtain a fused feature data set;

[0067] Step S53: dividing the fused feature data set into a data set to obtain a training set and a test set; using the training set to construct a prediction model for the preset neural network model to obtain a fever risk prediction training model; using the test set to evaluate the model performance of the fever risk prediction training model to obtain a fever risk prediction model;

[0068] Step S54: using the fever risk prediction model to predict the fever risk and obtain the fever risk probability;

[0069] Step S55: classifying the fever risk probability into risk levels according to a preset risk threshold to obtain risk level data;

[0070] Step S56: Calculate the comprehensive risk index according to the risk level data to obtain a comprehensive fever risk index.

[0071] The present invention constructs a more streamlined and targeted feature data set by extracting the isolating switch features and environmental factor features from the associated operation feature set, providing more valuable input information for subsequent model training, and improving model training efficiency and prediction accuracy. The dynamic fault probability matrix, the isolating switch feature data set and the environmental factor feature data set are fused to construct a fused feature data set containing more comprehensive information, which can more comprehensively characterize the operating status and risk factors of the isolating switch, and provide data guarantee for building a high-precision prediction model. The fused feature data set is divided into a training set and a test set, and the training set is used to train the preset neural network model, and the test set is used to evaluate the model, which ensures the generalization ability and prediction accuracy of the model, and finally obtains a heating risk prediction model with good performance. The trained heating risk prediction model is used to predict the heating risk of the isolating switch, and a quantitative heating risk probability is obtained, which provides a direct basis for risk assessment and early warning. The heating risk probability is divided into risk levels according to the preset risk threshold, and the continuous probability value is converted into a discrete risk level, which more intuitively reflects the risk level, and facilitates the operation and maintenance personnel to quickly judge the risk level and take corresponding measures. The comprehensive risk index is calculated based on the risk level data, and different risk levels are assigned different weights to obtain an indicator that can comprehensively reflect multiple risk factors, providing a more comprehensive and detailed reference basis for risk warning and decision-making.

[0072] Preferably, step S6 comprises the following steps:

[0073] Step S61: Acquire historical warning data; perform fault warning data labeling on the historical warning data to obtain a historical warning data set;

[0074] Step S62: constructing a warning strategy library according to the historical warning data set to obtain a warning strategy library;

[0075] Step S63: Building a reinforcement learning environment based on the historical warning data set and the warning strategy library to obtain a warning simulation environment;

[0076] Step S64: using the early warning simulation environment to perform reinforcement learning model training to obtain an adaptive early warning model;

[0077] Step S65: generating an adaptive warning threshold according to the comprehensive fever risk index and the adaptive warning model to obtain an adaptive warning threshold;

[0078] Step S66: Use the adaptive warning threshold to perform a high-voltage disconnector thermal fault warning to achieve a high-voltage disconnector thermal fault prediction operation.

[0079] The present invention constructs a historical warning data set containing warning information and actual fault conditions by acquiring historical warning data and marking fault warning data, providing a data basis for the subsequent construction of a warning strategy library and training of an adaptive warning model. A warning strategy library is constructed based on the historical warning data set, and a variety of warning strategies are formulated in advance, covering different risk levels and countermeasures, providing a basis for strategy selection for the adaptive warning model. A reinforcement learning environment is built based on the historical warning data set and the warning strategy library, simulating the real power system operating environment and warning decision-making process, and providing a realistic experimental platform for training the adaptive warning model. The reinforcement learning model is trained using the warning simulation environment, so that the model can continuously learn and optimize the warning strategy in the interaction with the environment, and finally obtains an adaptive warning model that can adaptively select the optimal warning strategy according to the real-time risk situation. An adaptive warning threshold is generated based on the comprehensive risk index and the adaptive warning model, and the warning threshold is dynamically adjusted according to the real-time risk situation, thereby improving the sensitivity and accuracy of the warning and avoiding the false alarm and missed alarm problems that are prone to occur in the traditional fixed threshold warning method. Adaptive warning thresholds are used to warn of heating failures of high-voltage disconnectors, and risk prediction results are converted into specific warning actions. Operation and maintenance personnel are notified in a timely manner to take countermeasures, effectively preventing the occurrence of failures and ensuring the safe and stable operation of the power system.

[0080] Preferably, the present invention further provides a thermal fault prediction system for an isolating switch of a high-voltage circuit breaker, which is used to execute the thermal fault prediction method for an isolating switch of a high-voltage circuit breaker as described above. The thermal fault prediction system for an isolating switch of a high-voltage circuit breaker comprises:

[0081] The multi-source data association analysis module is used to collect multi-source data of the high-voltage disconnector and its associated high-voltage circuit breaker through the SCADA system, and perform data preprocessing to obtain a preprocessed data set; perform operation feature association analysis on the preprocessed data set to obtain an associated operation feature set;

[0082] A dynamic association network construction module is used to construct a dynamic association network for the association operation feature set to obtain a dynamic association network graph;

[0083] The risk propagation path identification module is used to obtain historical fault data; search for propagation risk paths based on historical fault data and dynamic association network diagrams to obtain a candidate risk path set; calculate the path propagation probability of the candidate risk path set to obtain a path probability data set; extract key risk propagation paths based on the path probability data set and the candidate risk path set to obtain key risk propagation paths;

[0084] The fault probability dynamic assessment module is used to calculate the path propagation probability according to the key risk propagation path to obtain the path probability matrix; perform a dynamic analysis of the fault probability according to the path probability matrix to obtain a dynamic fault probability matrix;

[0085] The fever risk comprehensive prediction module is used to construct a fever risk prediction model according to the associated operation feature set and the dynamic fault probability matrix to obtain the fever risk prediction model; the fever risk prediction model is used to predict the fever risk and calculate the comprehensive risk index to obtain the comprehensive fever risk index;

[0086] The early warning adaptive adjustment module is used to obtain historical early warning data; construct an adaptive early warning model based on the historical early warning data to obtain an adaptive early warning model; and perform an adaptive early warning of high-voltage disconnector thermal faults based on a comprehensive thermal risk index and an adaptive early warning model to realize the high-voltage disconnector thermal fault prediction operation.

[0087] Preferably, a high-voltage circuit breaker comprises a contact system, an arc extinguishing system, and an operating mechanism connected thereto, and also comprises a controller connected to the operating mechanism, wherein the controller comprises the isolating switch thermal fault prediction system of the high-voltage circuit breaker as described above.

[0088] The present invention not only ensures data quality by collecting multi-source data and performing preprocessing, but also extracts key operating characteristics of associated high-voltage circuit breakers, laying a data foundation for subsequent analysis of mutual influence between devices and construction of prediction models. By constructing a dynamic association network, the association relationship between devices and their trend over time are intuitively displayed, providing intuitive visual guidance for identifying key risk propagation paths. By analyzing historical fault data and dynamic association networks, potential risk propagation paths are found, and the propagation probability of each path is evaluated, providing a basis for accurately locating key risk paths. By constructing a fault propagation model and combining real-time monitoring data for dynamic analysis, real-time risk assessment of key risk propagation paths is achieved, providing a dynamic probability basis for predicting heat failures of disconnectors. By constructing a prediction model based on association characteristics and dynamic fault probabilities, the future heat risk of disconnectors can be predicted more accurately, and a more intuitive reference basis for risk warning can be provided through a comprehensive risk index. By constructing an adaptive warning model and dynamically adjusting the warning threshold according to the comprehensive risk index, a more accurate and flexible warning mechanism is achieved, which effectively reduces the risk of false alarms and missed alarms and improves the efficiency and accuracy of warnings. Therefore, the present invention provides a method for predicting the heating fault of the disconnector of a high-voltage circuit breaker, which effectively solves the problem that the existing method lacks consideration of the impact of the associated high-voltage circuit breaker by introducing the technology of multi-source data association analysis, dynamic association network construction and risk propagation path identification. The method can effectively identify the impact of the associated high-voltage circuit breaker on the heating risk of the disconnector, thereby improving the accuracy of fault prediction and the timeliness of early warning, and providing more reliable protection for the safe and stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] Figure 1 A schematic flow chart of the steps of a method for predicting thermal failure of an isolating switch of a high-voltage circuit breaker;

[0090] Figure 2 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0091] Figure 3 for Figure 1 Detailed implementation steps of step S5 are shown in the flowchart.

[0092] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0093] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0094] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0095] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0096] To achieve this, please refer to Figures 1 to 3 , a method for predicting thermal failure of an isolating switch of a high-voltage circuit breaker, comprising the following steps:

[0097] Step S1: performing multi-source data acquisition on the high-voltage disconnector and its associated high-voltage circuit breaker through the SCADA system, and performing data preprocessing to obtain a preprocessed data set; performing operation feature correlation analysis on the preprocessed data set to obtain a correlated operation feature set;

[0098] Step S2: constructing a dynamic association network for the associated operation feature set to obtain a dynamic association network graph;

[0099] Step S3: Acquire historical fault data; search for propagation risk paths based on historical fault data and the dynamic association network diagram to obtain a candidate risk path set; calculate the path propagation probability of the candidate risk path set to obtain a path probability data set; extract key risk propagation paths based on the path probability data set and the candidate risk path set to obtain key risk propagation paths;

[0100] Step S4: Calculate the path propagation probability according to the key risk propagation path to obtain a path probability matrix; perform a dynamic analysis of the fault probability according to the path probability matrix to obtain a dynamic fault probability matrix;

[0101] Step S5: constructing a fever risk prediction model according to the associated operation feature set and the dynamic fault probability matrix to obtain a fever risk prediction model; using the fever risk prediction model to predict the fever risk, and calculating a comprehensive risk index to obtain a comprehensive fever risk index;

[0102] Step S6: Acquire historical warning data; construct an adaptive warning model based on the historical warning data to obtain an adaptive warning model; perform adaptive warning of heating faults of high-voltage disconnectors based on the comprehensive heating risk index and the adaptive warning model to realize the prediction of heating faults of high-voltage disconnectors.

[0103] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of the method for predicting thermal failure of the isolating switch of a high-voltage circuit breaker of the present invention. In this example, the method for predicting thermal failure of the isolating switch of a high-voltage circuit breaker includes the following steps:

[0104] Step S1: performing multi-source data acquisition on the high-voltage disconnector and its associated high-voltage circuit breaker through the SCADA system, and performing data preprocessing to obtain a preprocessed data set; performing operation feature correlation analysis on the preprocessed data set to obtain a correlated operation feature set;

[0105] In an embodiment of the present invention, multi-source data of a target high-voltage disconnector and its associated high-voltage circuit breaker within a period of time, such as temperature, current, voltage, opening and closing status, etc., are collected through a SCADA system to form an original data set. The original data set is cleaned using a Python script to remove missing values ​​and outliers, and time alignment is performed to obtain a preprocessed data set. Then, the principal component analysis (PCA) method is used to extract associated operation features from the preprocessed data set to obtain an associated operation feature set containing the main operation features of the disconnector and the associated high-voltage circuit breaker.

[0106] Step S2: constructing a dynamic association network for the associated operation feature set to obtain a dynamic association network graph;

[0107] In the embodiment of the present invention, the associated operation feature set is divided into multiple time segments with a period of 24 hours in chronological order, and each segment constitutes a sample to form a time series feature data set. The mutual information method is used to calculate the association relationship between the features in each sample to obtain a daily association relationship matrix, and all matrices are arranged in chronological order to form an association relationship matrix sequence. The association strength threshold is set to screen strong associations, and the Gephi software is used to draw a dynamic association network diagram to display the association relationship and evolution trend between devices.

[0108] Step S3: Acquire historical fault data; search for propagation risk paths based on historical fault data and the dynamic association network diagram to obtain a candidate risk path set; calculate the path propagation probability of the candidate risk path set to obtain a path probability data set; extract key risk propagation paths based on the path probability data set and the candidate risk path set to obtain key risk propagation paths;

[0109] In an embodiment of the present invention, the NetworkX software is used to perform topological structure analysis on the dynamic association network graph to obtain a network topology data set containing node attributes and network structure information. Historical high-voltage circuit breaker fault status data, historical disconnector heating status data, and equipment operation and maintenance data are obtained from the database. According to the historical fault data, the high-voltage circuit breaker nodes and heating disconnector nodes that have faults in the network topology data set are marked, and the potential risk edges connecting the faulty nodes and the heating nodes are screened. The risk propagation direction is determined according to the fault time and the heating time to obtain a directed risk edge data set. A time series path search is performed in the directed risk edge data set to obtain a candidate risk path set.

[0110] Step S4: Calculate the path propagation probability according to the key risk propagation path to obtain a path probability matrix; perform a dynamic analysis of the fault probability according to the path probability matrix to obtain a dynamic fault probability matrix;

[0111] In an embodiment of the present invention, for each candidate risk path, the frequency of each edge on the path appearing simultaneously in the historical data is calculated as the propagation probability, and the propagation probabilities of all edges are multiplied to obtain the initial path propagation probability. Environmental factor data is extracted from the preprocessing data set, and a linear regression model is used to quantify the impact of environmental factors on the probability of heating of the isolating switch to obtain an environmental impact factor set. Equipment status information is extracted from equipment operation and maintenance data, and a decision tree model is used to quantify the impact of equipment status on the probability of heating of the isolating switch to obtain an equipment status factor set. The initial path probability is corrected according to the environmental impact factor and the equipment status factor, and the confidence is evaluated using the Bootstrap method, and finally a path probability data set containing the path propagation probability and its confidence interval is obtained. According to a preset sorting path threshold, such as 0.05, a path with a propagation probability greater than or equal to the threshold is screened out as a key risk propagation path.

[0112] Step S5: constructing a fever risk prediction model according to the associated operation feature set and the dynamic fault probability matrix to obtain a fever risk prediction model; using the fever risk prediction model to predict the fever risk, and calculating a comprehensive risk index to obtain a comprehensive fever risk index;

[0113] In an embodiment of the present invention, the node states on the key risk propagation path are quantified, and a fault propagation model is constructed using a Bayesian network. Real-time monitoring data is obtained to initialize the model state probability vector. The state probability is iteratively calculated using the fault propagation model to obtain a state probability matrix, and the path probability matrix is ​​calculated based on the state probability matrix. The path probability matrix is ​​subjected to time window sliding and time dimension integration to finally obtain a dynamic fault probability matrix. According to the associated operating feature set and the dynamic fault probability matrix, an LSTM model is trained to obtain a fever risk prediction model. The model is used to predict fever risk, obtain the fever risk probability, and divide the risk level according to the preset risk threshold, and finally calculate the comprehensive risk index.

[0114] Step S6: Acquire historical warning data; construct an adaptive warning model based on the historical warning data to obtain an adaptive warning model; perform adaptive warning of heating faults of high-voltage disconnectors based on the comprehensive heating risk index and the adaptive warning model to achieve the prediction of heating faults of high-voltage disconnectors;

[0115] In an embodiment of the present invention, historical warning data is obtained, and it is marked whether each warning data corresponds to a real fault event. A warning strategy library containing multiple warning strategies is constructed based on historical warning data. The reinforcement learning tool OpenAIGym is used to build a warning simulation environment, and the DQN algorithm is used to train the adaptive warning model. The optimal warning strategy is selected based on the comprehensive risk index and the adaptive warning model obtained in S5, and the adaptive warning threshold is determined. The operating status of the disconnector is continuously monitored. When the comprehensive risk index exceeds the adaptive warning threshold, the warning strategy is executed to notify the operation and maintenance personnel to take measures.

[0116] Preferably, step S1 comprises the following steps:

[0117] Step S11: performing multi-source data acquisition on the high-voltage disconnector and its associated high-voltage circuit breaker through the SCADA system to obtain an original data set; performing data preprocessing on the original data set to obtain a preprocessed data set;

[0118] Step S12: performing data time alignment on the preprocessed data set to obtain a time-aligned data set;

[0119] Step S13: establishing an association relationship between the high-voltage disconnector and its associated high-voltage circuit breaker to obtain association relationship data;

[0120] Step S14: performing feature matching of the same time window on the time-aligned data set according to the association relationship data to obtain a feature matching data set;

[0121] Step S15: Generate an associated operation feature set according to the feature matching data set to obtain an associated operation feature set.

[0122] In an embodiment of the present invention, the original data set of the target high-voltage disconnector and its associated high-voltage circuit breaker from January 1, 2023 to December 31, 2023 is collected by the SCADA system. The original data set contains the temperature, current, voltage of the disconnector and the opening and closing state, current, voltage and other data of the associated high-voltage circuit breaker recorded every 1 minute. The data cleaning script is written in Python to remove missing values ​​and outliers in the original data set. For missing values, linear interpolation is used to fill; for outliers, the 3σ criterion is used to identify and eliminate. Finally, a preprocessed data set is obtained. The Pandas library in Python is used to align the data time of the preprocessed data set. First, the acquisition time of all data is uniformly converted into a standard time format (for example: YYYY-MM-DD HH:MM:SS). Then, in seconds, the data of different devices are aligned according to the timestamp to ensure that the data of all devices at the same time point are complete. If there is an inconsistency in the timestamp, the device data with the earliest timestamp is used as the benchmark, and the other device data are linearly interpolated and filled, and finally a time-aligned data set is obtained. According to the primary wiring diagram of the power system and the equipment operation and maintenance records, the association relationship data between the high-voltage disconnector and its associated high-voltage circuit breaker is established. For example, the number of the high-voltage circuit breaker connected to each disconnector is recorded, and the connection mode between the two (for example: series or parallel). These association relationship data are stored in the database to facilitate the subsequent steps. The time window length is set to 1 hour. According to the association relationship data established in step S13, the high-voltage disconnector data and the associated high-voltage circuit breaker data in the same time window in the time alignment data set are feature matched. For example, the temperature, current, and voltage data of a certain disconnector in a certain hour are matched with the opening and closing state, current, and voltage data of its associated high-voltage circuit breaker in the same hour to form a feature vector. Finally, a feature matching data set containing feature matching results in all time windows is obtained. The feature matching data set is used to generate an associated operation feature set. The principal component analysis method (PCA) is used to reduce the dimension of the feature vector in each time window in the feature matching data set, and the main features that can characterize the operating state of the high-voltage disconnector and the associated high-voltage circuit breaker in the time window are extracted, and these main features are combined to form an associated operation feature set. For example, the associated operation feature set within a certain time window includes features such as the average temperature of the disconnector, the number of opening and closing times of the associated high-voltage circuit breaker, and the maximum current of the associated high-voltage circuit breaker.

[0123] Preferably, step S2 comprises the following steps:

[0124] Step S21: performing time series segmentation of the associated operation feature set to obtain a time series feature data set;

[0125] Step S22: Calculate the dynamic correlation relationship of the time series feature data set to obtain a correlation relationship matrix;

[0126] Step S23: dynamically evolving the correlation relationship matrix to obtain a dynamic correlation matrix sequence;

[0127] Step S24: setting the association strength threshold according to the dynamic association matrix sequence, and drawing a network diagram to obtain a dynamic association network diagram.

[0128] In an embodiment of the present invention, the associated operation feature set obtained in step S1 is arranged in chronological order. Taking into account the periodic changes in the operating state of the power system, the time series is divided into multiple time segments with a period of 24 hours, and each time segment corresponds to one day. The associated operation feature data in each time segment is taken as an independent sample to form a time series feature data set. For example, the associated operation feature set from 00:00:00 on January 1, 2023 to 23:59:59 on December 31, 2023 is divided into 365 samples, and each sample contains the associated operation feature data of all time windows on that day. The mutual information method is used to calculate the correlation relationship between every two features in the time series feature data set. For each day's sample data, the mutual information values ​​between all the features in the sample are calculated, and the results are stored in a matrix, which is the correlation relationship matrix. The rows and columns of the matrix represent different features, respectively, and the values ​​of the matrix elements represent the mutual information values ​​between the corresponding features, which are used to quantify the degree of correlation between the features. In order to capture the changing trend of the association relationship over time, the daily association relationship matrix calculated in step S22 is arranged in chronological order to form an association relationship matrix sequence. For example, the association relationship matrix calculated daily within 365 days is arranged in date order to form a matrix sequence of 365 in length, which is used to characterize the dynamic evolution process of the association relationship within one year. The changing trend of each element value in the association relationship matrix sequence is analyzed, and the association strength threshold is set in combination with expert experience. All element values ​​in the matrix sequence are compared with the threshold value, and the elements above the threshold value represent that there is a strong association relationship between the corresponding features, and the elements below the threshold value represent that the association relationship is weak. According to the strong association relationship after screening, the network diagram drawing tool Gephi is used to use the feature as a node and the strong association relationship as an edge to draw a dynamic association network diagram. In the network diagram, the size of the node can represent the importance of the feature, the thickness of the edge can represent the association strength, and the depth of the color can represent the changing trend of the association relationship over time.

[0129] Preferably, step S3 comprises the following steps:

[0130] Step S31: performing network topology structure analysis on the dynamic association network graph to obtain a network topology data set;

[0131] Step S32: Acquire historical fault data, wherein the historical fault data includes historical high-voltage circuit breaker fault state data, historical disconnector heating state data, and equipment operation and maintenance data;

[0132] Step S33: searching for a propagation risk path on the network topology data set according to the historical fault data to obtain a candidate risk path set;

[0133] Step S34: Calculate the path propagation probability of the candidate risk path set to obtain a path probability data set;

[0134] Step S35: sorting the candidate risk path set by path importance according to the path probability data set to obtain a sorted path probability data set;

[0135] Step S36: Use the preset sorting path threshold to perform key path screening on the sorting path probability data set to obtain the key risk propagation path.

[0136] As an example of the present invention, refer to Figure 2 As shown, in this example, step S3 includes:

[0137] Step S31: performing network topology structure analysis on the dynamic association network graph to obtain a network topology data set;

[0138] In the embodiment of the present invention, the network analysis library NetworkX is used to perform network topology analysis on the dynamic association network diagram obtained in step S2. All nodes (representing features) and the connection relationships between nodes (representing association relationships) in the network diagram are extracted to construct a network topology data set. The data set contains topological attribute information such as node degree, centrality, clustering coefficient, and network structure information such as the shortest path length and connectivity between nodes.

[0139] Step S32: Acquire historical fault data, wherein the historical fault data includes historical high-voltage circuit breaker fault state data, historical disconnector heating state data, and equipment operation and maintenance data;

[0140] In an embodiment of the present invention, historical fault data from January 1, 2022 to December 31, 2022 is obtained from the power system operation and maintenance database, including historical high-voltage circuit breaker fault status data, historical disconnector heating status data, and equipment operation and maintenance data. Among them, the historical high-voltage circuit breaker fault status data includes information such as the time of the fault, the type of fault, and the faulty device; the historical disconnector heating status data includes information such as the heating time, the degree of heating, and the heating device; the equipment operation and maintenance data includes information such as the equipment operation time, maintenance records, and ambient temperature.

[0141] Step S33: searching for a propagation risk path on the network topology data set according to the historical fault data to obtain a candidate risk path set;

[0142] In the embodiment of the present invention, the network topology data set constructed in step S31 is searched for propagation risk paths in combination with the historical fault data obtained in step S32. First, based on the historical high-voltage circuit breaker fault state data and the historical disconnector heating state data, the high-voltage circuit breaker node with faults in the network topology data set is marked as the fault source node, and the disconnector node with heating is marked as the target node. Then, the Dijkstra algorithm is used to search for all paths from the fault source node to the target node in the network topology data set, and these paths are used as candidate risk path sets.

[0143] Step S34: Calculate the path propagation probability of the candidate risk path set to obtain a path probability data set;

[0144] In an embodiment of the present invention, the path propagation probability is calculated for each path in the candidate risk path set based on the historical fault data. The calculation method is as follows: for each edge on the path (representing an association relationship), the frequency of the association relationship in the historical fault data is counted as the propagation probability of the edge. For example, if the high-voltage circuit breaker and disconnector connected by an edge have failed simultaneously 10 times in the past year, the propagation probability of the edge is 10 / 365. Multiply the propagation probabilities of all edges on the path to obtain the propagation probability of the path.

[0145] Step S35: sorting the candidate risk path set by path importance according to the path probability data set to obtain a sorted path probability data set;

[0146] In the embodiment of the present invention, the candidate risk path set is sorted by path importance according to the path propagation probability calculated in step S34. The path propagation probability is sorted from high to low, and the path with higher propagation probability represents a higher risk of failure and a higher importance. Finally, a sorted path probability data set is obtained.

[0147] Step S36: Using a preset sorting path threshold to perform critical path screening on the sorting path probability data set to obtain a critical risk propagation path;

[0148] In the embodiment of the present invention, the preset sorting path threshold is 0.05, and the sorting path probability data set is screened for key paths. Paths with a propagation probability greater than or equal to 0.05 are selected as key risk propagation paths. These paths represent high-risk propagation paths that lead to thermal failures of disconnectors and require special attention.

[0149] Preferably, step S33 includes the following steps:

[0150] Step S331: marking fault nodes of the network topology data set according to known high-voltage circuit breaker fault status data to obtain a fault-marked network data set;

[0151] Step S332: marking heating nodes of the fault marking network data set according to the historical isolating switch heating state data to obtain the heating marking network data set;

[0152] Step S333: Screening the fever mark network data set for potential risk edges to obtain a risk edge data set;

[0153] Step S334: determining the risk propagation direction of the risk edge data set to obtain a directed risk edge data set;

[0154] Step S335: Perform a temporal path search on the directed risk edge data set to obtain a candidate risk path set.

[0155] In an embodiment of the present invention, the historical high-voltage circuit breaker fault status data obtained in step S32 is read, and the number of the high-voltage circuit breaker that has failed and the corresponding fault time are extracted. The node corresponding to the number of the faulty high-voltage circuit breaker in the network topology data set is marked as a fault node, and the time of the fault is recorded. For example, assuming that the historical data records that high-voltage circuit breaker A fails at 10:00:00 on March 15, 2022, the node representing high-voltage circuit breaker A in the network topology data set is marked as a fault node, and the fault time is recorded as 10:00:00 on March 15, 2022. After completing the marking of all fault nodes, a fault-marked network data set is obtained. The historical disconnector heating status data obtained in step S32 is read, and the heating disconnector number and the corresponding heating time are extracted. The node corresponding to the heating disconnector number in the fault-marked network data set processed in step S331 is marked as a heating node, and the heating time is recorded. For example, assuming that the historical data records that disconnector B generates heat at 10:30:00 on March 15, 2022, the node representing disconnector B in the fault marking network data set is marked as a heating node, and the heating time is recorded as 10:30:00 on March 15, 2022. After all heating nodes are marked, the heating marking network data set is obtained. In the heating marking network data set, all edges connecting fault nodes and heating nodes are screened out as potential risk edges. For example, assuming that in the heating marking network data set, there is an edge connecting fault node A and heating node B, then the edge is regarded as a potential risk edge, because the fault of high-voltage circuit breaker A may cause heating of disconnector B. All edges that meet the conditions are stored in the risk edge data set. According to the fault time and heating time recorded in steps S331 and S332, the risk propagation direction in the risk edge data set is determined. If the failure time of the faulty node of an edge is earlier than the heating time of the connected heating node, it is considered that the risk propagation direction of the edge is from the faulty node to the heating node, and the edge is set as a directed edge, with the direction from the faulty node to the heating node; otherwise, the edge is considered not to constitute a risk propagation path and is removed from the risk edge data set. After the direction is determined, a directed risk edge data set is obtained. According to the directed risk edge data set obtained in step S334, a temporal path search is performed in the fever mark network data set. Starting from each faulty node, a depth-first search is performed along the direction of the directed edge to find all paths that can reach the heating node. During the search process, the failure time or heating time of each node on the path is required to increase in chronological order to ensure that the path conforms to the temporal logic of risk propagation. All found paths are used as candidate risk path sets.

[0156] Preferably, step S34 includes the following steps:

[0157] Step S341: Calculate the initial path probability based on the historical fault data and the candidate risk path set to obtain an initial path probability set;

[0158] Step S342: extracting environmental factor data from the preprocessed data set, and quantifying the impact of environmental factors to obtain an environmental impact factor set;

[0159] Step S343: quantifying the impact of equipment status on equipment operation and maintenance data to obtain an equipment status factor set;

[0160] Step S344: modifying the initial path probability set according to the environmental impact factor set and the device status factor set to obtain a modified path probability set;

[0161] Step S345: performing path probability confidence evaluation on the modified path probability set to obtain a path probability data set.

[0162] In the embodiment of the present invention, each path in the candidate risk path set obtained in step S33 is traversed. For each path, the propagation probability of each edge on the path is calculated. The specific calculation method is: count the frequency of the two nodes (corresponding to an association relationship) connected by the edge appearing simultaneously in the historical fault data. For example, if the high-voltage circuit breaker and disconnector connected by a certain edge have failed simultaneously 10 times in the past year, the propagation probability of the edge is 10 / 365. Multiply the propagation probabilities of all edges on the path to obtain the initial propagation probability of the path. The initial propagation probabilities of all paths are stored in the initial path probability set. Environmental factor data, including ambient temperature, humidity, wind speed, etc., are extracted from the preprocessed data set obtained in step S1. Using a linear regression model, the relationship model between the environmental factors and the heating state of the disconnector is established respectively. According to the model coefficient, the degree of influence of the environmental factors on the heating probability of the disconnector is quantified, and the quantified results are stored in the environmental impact factor set. For example, if the heating probability of the disconnector increases by 0.01 for every 1 degree Celsius increase in ambient temperature, the impact factor of the ambient temperature is set to 0.01. The equipment status information is extracted from the equipment operation and maintenance data obtained in step S32, including equipment operation time, maintenance times, fault times, etc. A decision tree model is used to establish a relationship model between the equipment status and the heating status of the disconnector. According to the importance of each feature in the model, the degree of influence of the equipment status on the heating probability of the disconnector is quantified, and the quantified results are stored in the equipment status factor set. For example, if the heating probability of the disconnector increases by 0.05 for every 1000 hours of equipment operation time, the impact factor of the equipment operation time is set to 0.0005. According to the environmental impact factor set and the equipment status factor set obtained in steps S342 and S343, the initial path probability set obtained in step S341 is corrected for path probability. The specific correction method is: for each path, according to the environmental factors and equipment status corresponding to each node on the path, the weighted sum of the environmental impact factor and the equipment status factor is calculated, and the weighted sum is used as the correction coefficient. The initial propagation probability of the path is multiplied by the correction coefficient to obtain the corrected path propagation probability, and all corrected path propagation probabilities are stored in the corrected path probability set. The Bootstrap method is used to perform confidence evaluation on each path probability in the corrected path probability set. The specific method is: perform multiple sampling with replacement on the original data set, and calculate the path propagation probability according to the method of steps S341 to S344 after each sampling. Finally, the distribution of each path propagation probability is obtained, and the 95% confidence interval is calculated based on the distribution. The propagation probabilities of all paths and their confidence intervals are stored in the path probability data set.

[0163] Preferably, step S4 comprises the following steps:

[0164] Step S41: quantify the critical path state of the critical risk propagation path to obtain a quantified path data set; construct a fault propagation model based on historical fault data to obtain a fault propagation model;

[0165] Step S42: acquiring real-time monitoring data of the high-voltage circuit breaker and the disconnector; initializing the model state according to the real-time monitoring data of the high-voltage circuit breaker and the disconnector to obtain an initial state probability vector;

[0166] Step S43: using the fault propagation model to perform iterative state probability calculation according to the initial state probability vector to obtain a state probability matrix;

[0167] Step S44: Calculate the path propagation probability according to the state probability matrix to obtain a path probability matrix;

[0168] Step S45: dynamically sliding the time window according to the path probability matrix to obtain a sliding path probability matrix sequence;

[0169] Step S46: integrating the probability matrix time dimension of the sliding path probability matrix sequence to obtain a time-integrated probability matrix; and compressing the time-integrated probability matrix in the time dimension to obtain a dynamic fault probability matrix.

[0170] In the embodiment of the present invention, for each key risk propagation path selected in step S3, the state of each node on the path is quantified to construct a quantized path data set. The quantization method is as follows:

[0171] For high-voltage circuit breaker nodes, their states are quantified to 0 or 1 based on their real-time monitoring data, where 0 represents a normal state and 1 represents a fault state. For example, if the real-time current of a high-voltage circuit breaker exceeds a preset threshold, the high-voltage circuit breaker is considered to be in a fault state and its state is quantified to 1, otherwise it is quantified to 0.

[0172] For the isolating switch node, based on its real-time monitoring data, its state is quantified into a continuous value between 0 and 1, indicating its heating degree, for example, 0 represents no heating and 1 represents severe heating. Fuzzy logic and other methods can be used to quantify the heating degree of the isolating switch based on indicators such as temperature and current.

[0173] Based on historical fault data, a fault propagation model is constructed using a Bayesian network. The model describes the probabilistic dependency between the states of each node on the critical risk propagation path. For example, the model can be expressed as: P(isolator heating|high-voltage circuit breaker failure, ambient temperature), that is, the probability of isolator heating under the conditions of high-voltage circuit breaker failure and ambient temperature.

[0174] The real-time monitoring data of high-voltage circuit breakers and disconnectors, including current, voltage, temperature, etc., are obtained through the SCADA system. According to the state quantification method defined in step S41, the real-time monitoring data is converted into the initial state probability of each node in the model. For example, assuming that a certain key risk propagation path includes high-voltage circuit breaker A and disconnector B, according to the real-time monitoring data, the current of high-voltage circuit breaker A does not exceed the threshold, then its initial state probability is P(A=0)=0.9, P(A=1)=0.1; the temperature of disconnector B is 40 degrees Celsius, and according to fuzzy logic quantification, its heating degree is 0.2, then its initial state probability is P(B=0.2)=1. The initial state probabilities of all nodes are combined into an initial state probability vector. The fault propagation model constructed in step S41 and the initial state probability vector obtained in step S42 are used to perform state probability iterative calculation. During the iteration process, the state probability of each node at each time step is calculated according to the inference mechanism of the Bayesian network. For example, according to the fault propagation model P(B=1|A=1)=0.8 and the initial state probability P(A=1)=0.1, it can be calculated that the probability of disconnector B being in a faulty state in the next time step is 0.8*0.1=0.08. The state probabilities of all nodes at each time step are stored in a matrix to obtain a state probability matrix. According to the state probability matrix, the propagation probability of each key risk propagation path at each time step is calculated. The specific calculation method is: multiply the probabilities of all nodes on the path being in a faulty state at the time step. For example, assuming that a path contains nodes A and B, at a certain time step, P(A=1)=0.2, P(B=1)=0.1, then the propagation probability of the path at the time step is 0.2*0.1=0.02. The propagation probabilities of all paths at all time steps are stored in a matrix to obtain a path probability matrix. Set the time window length to 1 hour, and dynamically slide the path probability matrix according to the time window. For example, assuming that the path probability matrix contains 24 time steps, it can be slid into 23 sliding windows containing 2 time steps. Each sliding window corresponds to a path probability matrix, forming a sliding path probability matrix sequence. All matrices in the sliding path probability matrix sequence are spliced ​​in time order to obtain a time-integrated probability matrix. For example, the path probability matrices corresponding to 23 sliding windows are spliced ​​into a larger matrix in time order. Then, the time-integrated probability matrix is ​​compressed in the time dimension, and the propagation probability in each time window is averaged to obtain the final dynamic fault probability matrix.

[0175] Preferably, step S5 comprises the following steps:

[0176] Step S51: extracting the isolating switch feature from the associated operation feature set to obtain an isolating switch feature data set; extracting the environmental factor feature from the associated operation feature set to obtain an environmental factor feature data set;

[0177] Step S52: performing feature set fusion on the dynamic fault probability matrix, the disconnector feature data set, and the environmental factor feature data set to obtain a fused feature data set;

[0178] Step S53: dividing the fused feature data set into a data set to obtain a training set and a test set; using the training set to construct a prediction model for the preset neural network model to obtain a fever risk prediction training model; using the test set to evaluate the model performance of the fever risk prediction training model to obtain a fever risk prediction model;

[0179] Step S54: using the fever risk prediction model to predict the fever risk and obtain the fever risk probability;

[0180] Step S55: classifying the fever risk probability into risk levels according to a preset risk threshold to obtain risk level data;

[0181] Step S56: Calculate the comprehensive risk index according to the risk level data to obtain a comprehensive fever risk index.

[0182] As an example of the present invention, refer to Figure 3 As shown, in this example, step S5 includes:

[0183] Step S51: extracting the isolating switch feature from the associated operation feature set to obtain an isolating switch feature data set; extracting the environmental factor feature from the associated operation feature set to obtain an environmental factor feature data set;

[0184] In the embodiment of the present invention, features related to the target disconnector are extracted from the associated operation feature set obtained in step S1, including the temperature, current, voltage, etc. of the disconnector, to form a disconnector feature data set. At the same time, features related to environmental factors, such as ambient temperature, humidity, wind speed, etc., are extracted to form an environmental factor feature data set.

[0185] Step S52: performing feature set fusion on the dynamic fault probability matrix, the disconnector feature data set, and the environmental factor feature data set to obtain a fused feature data set;

[0186] In the embodiment of the present invention, the dynamic fault probability matrix obtained in step S4, the disconnector feature data set extracted in step S51, and the environmental factor feature data set are subjected to feature set fusion to form a fused feature data set. The fusion method is: the corresponding dynamic fault probability, disconnector feature, and environmental factor feature at each time step are spliced ​​into a feature vector, and the feature vectors of all time steps constitute the fused feature data set.

[0187] Step S53: dividing the fused feature data set into a data set to obtain a training set and a test set; using the training set to construct a prediction model for the preset neural network model to obtain a fever risk prediction training model; using the test set to evaluate the model performance of the fever risk prediction training model to obtain a fever risk prediction model;

[0188] In an embodiment of the present invention, the fused feature data set is divided into a training set and a test set in a ratio of 7:3. The preset long short-term memory neural network (LSTM) model is trained using the training set to construct a fever risk prediction training model. The input of the LSTM model is the fused feature vector, and the output is the probability of fever of the isolating switch in the future (for example, the next hour). The performance of the trained model is evaluated using the test set, and the evaluation indicators include accuracy, precision, recall, etc., and finally a fever risk prediction model is obtained.

[0189] Step S54: using the fever risk prediction model to predict the fever risk and obtain the fever risk probability;

[0190] In the embodiment of the present invention, the heating risk prediction model trained in step S53 is used to predict the heating risk of the isolating switch at the current moment. The model input is the fused feature vector at the current moment, and the output is the heating risk probability of the isolating switch in the future (for example, the next hour).

[0191] Step S55: classifying the fever risk probability into risk levels according to a preset risk threshold to obtain risk level data;

[0192] In the embodiment of the present invention, the fever risk probability obtained in step S54 is divided into different risk levels according to a preset risk threshold, such as 0.1, 0.5, and 0.9. For example, a case where the fever risk probability is lower than 0.1 is classified as a low risk level, a case where the fever risk probability is between 0.1 and 0.5 is classified as a medium risk level, and a case where the fever risk probability is higher than 0.9 is classified as a high risk level.

[0193] Step S56: Calculate the comprehensive risk index according to the risk level data to obtain a comprehensive fever risk index;

[0194] In the embodiment of the present invention, the comprehensive risk index is calculated according to the risk level data divided in step S55. The calculation method is: assign different weights to each risk level, for example, the weight of the low risk level is 1, the weight of the medium risk level is 3, and the weight of the high risk level is 5. The weight corresponding to the risk level at the current moment is used as the comprehensive risk index. For example, if the fever risk probability at the current moment is 0.6, which belongs to the medium risk level, the comprehensive risk index is 3.

[0195] Preferably, step S6 comprises the following steps:

[0196] Step S61: Acquire historical warning data; perform fault warning data labeling on the historical warning data to obtain a historical warning data set;

[0197] Step S62: constructing a warning strategy library according to the historical warning data set to obtain a warning strategy library;

[0198] Step S63: Building a reinforcement learning environment based on the historical warning data set and the warning strategy library to obtain a warning simulation environment;

[0199] Step S64: using the early warning simulation environment to perform reinforcement learning model training to obtain an adaptive early warning model;

[0200] Step S65: generating an adaptive warning threshold according to the comprehensive fever risk index and the adaptive warning model to obtain an adaptive warning threshold;

[0201] Step S66: Use the adaptive warning threshold to perform a high-voltage disconnector thermal fault warning to achieve a high-voltage disconnector thermal fault prediction operation.

[0202] In an embodiment of the present invention, historical warning data is obtained from the power system operation and maintenance database, including information such as warning time, warning level, warning reason, actual fault situation, etc. The historical warning data is annotated to mark whether each warning data corresponds to a real fault event. For example, if a certain warning data does have a heat failure of an isolating switch within a period of time (for example, within 24 hours), it is marked as a "real warning", otherwise it is marked as a "false alarm". Finally, a historical warning data set containing warning data and annotation information is obtained.

[0203] According to the true warning ratio and false alarm ratio corresponding to different warning levels in the historical warning data set, the warning strategy library is constructed. The warning strategy library contains multiple warning strategies, each of which corresponds to different warning thresholds and warning methods. For example, three warning strategies can be set:

[0204] Strategy 1: When the comprehensive risk index is greater than or equal to 2, send a text message to notify the operation and maintenance personnel to pay attention;

[0205] Strategy 2: When the comprehensive risk index is greater than or equal to 4, notify the operation and maintenance personnel by phone to take measures;

[0206] Strategy 3: When the comprehensive risk index is equal to 5, immediately activate the emergency plan.

[0207] The early warning simulation environment is constructed using the reinforcement learning tool OpenAI Gym. The environment simulates the operating state of the power system and calculates the comprehensive risk index according to the method of steps S1 to S5. The state space of the environment is the value range of the comprehensive risk index, the action space is the number of all early warning strategies in the early warning strategy library, and the reward function is designed as follows: when the early warning strategy adopted can timely and effectively prevent the occurrence of a fault, a positive reward is given; when an underreporting or false alarm occurs, a negative reward is given. The deep Q network (DQN) algorithm is used to train the reinforcement learning model in the early warning simulation environment constructed in step S63. During the training process, the agent selects the early warning strategy in the early warning strategy library according to the current comprehensive risk index, and adjusts the strategy selection strategy according to the feedback of the environment, and finally learns an adaptive early warning model that can adaptively select the optimal early warning strategy according to the comprehensive risk index. According to the comprehensive risk index calculated in step S5 and the adaptive early warning model trained in step S64, the optimal early warning strategy is selected. For example, if the current comprehensive risk index is 3 and the adaptive early warning model selects early warning strategy 1, the early warning threshold is set to 2, and a text message is sent to notify the operation and maintenance personnel to pay attention. The operating status of the disconnector is continuously monitored, and the comprehensive risk index is updated in real time according to the method of steps S1 to S5. When the comprehensive risk index exceeds the adaptive warning threshold determined in step S65, the corresponding warning strategy is immediately executed to notify the operation and maintenance personnel to take corresponding measures to prevent the occurrence of heating failure of the disconnector and ensure the safe and stable operation of the power system.

[0208] Preferably, the present invention further provides a thermal fault prediction system for an isolating switch of a high-voltage circuit breaker, which is used to execute the thermal fault prediction method for an isolating switch of a high-voltage circuit breaker as described above. The thermal fault prediction system for an isolating switch of a high-voltage circuit breaker comprises:

[0209] The multi-source data association analysis module is used to collect multi-source data of the high-voltage disconnector and its associated high-voltage circuit breaker through the SCADA system, and perform data preprocessing to obtain a preprocessed data set; perform operation feature association analysis on the preprocessed data set to obtain an associated operation feature set;

[0210] A dynamic association network construction module is used to construct a dynamic association network for the association operation feature set to obtain a dynamic association network graph;

[0211] The risk propagation path identification module is used to obtain historical fault data; search for propagation risk paths based on historical fault data and dynamic association network diagrams to obtain a candidate risk path set; calculate the path propagation probability of the candidate risk path set to obtain a path probability data set; extract key risk propagation paths based on the path probability data set and the candidate risk path set to obtain key risk propagation paths;

[0212] The fault probability dynamic assessment module is used to calculate the path propagation probability according to the key risk propagation path to obtain the path probability matrix; perform a dynamic analysis of the fault probability according to the path probability matrix to obtain a dynamic fault probability matrix;

[0213] The fever risk comprehensive prediction module is used to construct a fever risk prediction model according to the associated operation feature set and the dynamic fault probability matrix to obtain the fever risk prediction model; the fever risk prediction model is used to predict the fever risk and calculate the comprehensive risk index to obtain the comprehensive fever risk index;

[0214] The early warning adaptive adjustment module is used to obtain historical early warning data; construct an adaptive early warning model based on the historical early warning data to obtain an adaptive early warning model; and perform an adaptive early warning of high-voltage disconnector thermal faults based on a comprehensive thermal risk index and an adaptive early warning model to realize the high-voltage disconnector thermal fault prediction operation.

[0215] Preferably, a high-voltage circuit breaker comprises a contact system, an arc extinguishing system, and an operating mechanism connected thereto, and also comprises a controller connected to the operating mechanism, wherein the controller comprises the isolating switch thermal fault prediction system of the high-voltage circuit breaker as described above.

[0216] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0217] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for predicting thermal failure of an isolating switch of a high-voltage circuit breaker, characterized in that: The following steps are involved: Step S1: collect multi-source data of the high-voltage disconnector and its associated high-voltage circuit breaker through the SCADA system, and perform data preprocessing to obtain a preprocessed data set; Performing operation feature correlation analysis on the preprocessed data set to obtain a correlation operation feature set; Step S2: constructing a dynamic association network for the associated operation feature set to obtain a dynamic association network graph; Step S3: Acquire historical fault data; search for propagation risk paths based on historical fault data and the dynamic association network diagram to obtain a candidate risk path set; calculate the path propagation probability of the candidate risk path set to obtain a path probability data set; extract key risk propagation paths based on the path probability data set and the candidate risk path set to obtain key risk propagation paths; Step S4: Calculate the path propagation probability according to the key risk propagation path to obtain a path probability matrix; perform a dynamic analysis of the fault probability according to the path probability matrix to obtain a dynamic fault probability matrix; Step S5: constructing a fever risk prediction model according to the associated operation feature set and the dynamic fault probability matrix to obtain a fever risk prediction model; using the fever risk prediction model to predict the fever risk, and calculating a comprehensive risk index to obtain a comprehensive fever risk index; Step S6: Obtain historical warning data; An adaptive early warning model is constructed according to historical early warning data to obtain an adaptive early warning model; Based on the comprehensive heating risk index and the adaptive warning model, adaptive warning of heating failure of high-voltage disconnectors is performed to realize the prediction of heating failure of high-voltage disconnectors.

2. The method for predicting thermal failure of the isolating switch of a high-voltage circuit breaker according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: performing multi-source data acquisition on the high-voltage disconnector and its associated high-voltage circuit breaker through the SCADA system to obtain an original data set; performing data preprocessing on the original data set to obtain a preprocessed data set; Step S12: performing data time alignment on the preprocessed data set to obtain a time-aligned data set; Step S13: establishing an association relationship between the high-voltage disconnector and its associated high-voltage circuit breaker to obtain association relationship data; Step S14: performing feature matching of the same time window on the time-aligned data set according to the association relationship data to obtain a feature matching data set; Step S15: generating an associated operation feature set according to the feature matching data set to obtain an associated operation feature set; Step S2 includes the following steps: Step S21: performing time series segmentation of the associated operation feature set to obtain a time series feature data set; Step S22: Calculate the dynamic correlation relationship of the time series feature data set to obtain a correlation relationship matrix; Step S23: dynamically evolving the correlation relationship matrix to obtain a dynamic correlation matrix sequence; Step S24: setting the association strength threshold according to the dynamic association matrix sequence, and drawing a network diagram to obtain a dynamic association network diagram.

3. The method for predicting thermal failure of the isolating switch of a high-voltage circuit breaker according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: performing network topology structure analysis on the dynamic association network graph to obtain a network topology data set; Step S32: Acquire historical fault data, wherein the historical fault data includes historical high-voltage circuit breaker fault state data, historical disconnector heating state data, and equipment operation and maintenance data; Step S33: searching for a propagation risk path on the network topology data set according to the historical fault data to obtain a candidate risk path set; Step S34: Calculate the path propagation probability of the candidate risk path set to obtain a path probability data set; Step S35: sorting the candidate risk path set by path importance according to the path probability data set to obtain a sorted path probability data set; Step S36: Use the preset sorting path threshold to perform key path screening on the sorting path probability data set to obtain the key risk propagation path.

4. The method for predicting thermal failure of the isolating switch of a high-voltage circuit breaker according to claim 3, characterized in that: Step S33 includes the following steps: Step S331: marking fault nodes of the network topology data set according to known high-voltage circuit breaker fault status data to obtain a fault-marked network data set; Step S332: marking heating nodes of the fault marking network data set according to the historical isolating switch heating state data to obtain the heating marking network data set; Step S333: Screening the fever mark network data set for potential risk edges to obtain a risk edge data set; Step S334: determining the risk propagation direction of the risk edge data set to obtain a directed risk edge data set; Step S335: Perform a temporal path search on the directed risk edge data set to obtain a candidate risk path set.

5. The method for predicting thermal failure of the isolating switch of a high-voltage circuit breaker according to claim 3, characterized in that: Step S34 includes the following steps: Step S341: Calculate the initial path probability based on the historical fault data and the candidate risk path set to obtain an initial path probability set; Step S342: extracting environmental factor data from the preprocessed data set, and quantifying the impact of environmental factors to obtain an environmental impact factor set; Step S343: quantifying the impact of equipment status on equipment operation and maintenance data to obtain an equipment status factor set; Step S344: modifying the initial path probability set according to the environmental impact factor set and the device status factor set to obtain a modified path probability set; Step S345: performing path probability confidence evaluation on the modified path probability set to obtain a path probability data set.

6. The method for predicting thermal failure of the isolating switch of a high-voltage circuit breaker according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: quantify the critical path state of the critical risk propagation path to obtain a quantified path data set; construct a fault propagation model based on historical fault data to obtain a fault propagation model; Step S42: acquiring real-time monitoring data of the high-voltage circuit breaker and the disconnector; initializing the model state according to the real-time monitoring data of the high-voltage circuit breaker and the disconnector to obtain an initial state probability vector; Step S43: using the fault propagation model to perform iterative state probability calculation according to the initial state probability vector to obtain a state probability matrix; Step S44: Calculate the path propagation probability according to the state probability matrix to obtain a path probability matrix; Step S45: dynamically sliding the time window according to the path probability matrix to obtain a sliding path probability matrix sequence; Step S46: integrating the probability matrix time dimension of the sliding path probability matrix sequence to obtain a time-integrated probability matrix; and compressing the time-integrated probability matrix in the time dimension to obtain a dynamic fault probability matrix.

7. The method for predicting thermal failure of the isolating switch of a high-voltage circuit breaker according to claim 1, characterized in that: Step S5 includes the following steps: Step S51: extracting the isolating switch feature from the associated operation feature set to obtain an isolating switch feature data set; extracting the environmental factor feature from the associated operation feature set to obtain an environmental factor feature data set; Step S52: performing feature set fusion on the dynamic fault probability matrix, the disconnector feature data set, and the environmental factor feature data set to obtain a fused feature data set; Step S53: dividing the fused feature data set into a data set to obtain a training set and a test set; using the training set to construct a prediction model for the preset neural network model to obtain a fever risk prediction training model; using the test set to evaluate the model performance of the fever risk prediction training model to obtain a fever risk prediction model; Step S54: using the fever risk prediction model to predict the fever risk and obtain the fever risk probability; Step S55: classifying the fever risk probability into risk levels according to a preset risk threshold to obtain risk level data; Step S56: Calculate the comprehensive risk index according to the risk level data to obtain a comprehensive fever risk index.

8. The method for predicting thermal failure of a disconnector of a high-voltage circuit breaker according to claim 1, characterized in that: Step S6 includes the following steps: Step S61: Acquire historical warning data; perform fault warning data labeling on the historical warning data to obtain a historical warning data set; Step S62: constructing a warning strategy library according to the historical warning data set to obtain a warning strategy library; Step S63: Building a reinforcement learning environment based on the historical warning data set and the warning strategy library to obtain a warning simulation environment; Step S64: using the early warning simulation environment to perform reinforcement learning model training to obtain an adaptive early warning model; Step S65: generating an adaptive warning threshold according to the comprehensive fever risk index and the adaptive warning model to obtain an adaptive warning threshold; Step S66: Use the adaptive warning threshold to perform a high-voltage disconnector thermal fault warning to achieve a high-voltage disconnector thermal fault prediction operation.

9. A thermal fault prediction system for a disconnector of a high-voltage circuit breaker, characterized in that: Used to execute the method for predicting thermal failure of the isolating switch of the high-voltage circuit breaker according to claim 1, the thermal failure prediction system of the isolating switch of the high-voltage circuit breaker comprises: The multi-source data association analysis module is used to collect multi-source data of the high-voltage disconnector and its associated high-voltage circuit breaker through the SCADA system, and perform data preprocessing to obtain a preprocessed data set; perform operation feature association analysis on the preprocessed data set to obtain an associated operation feature set; A dynamic association network construction module is used to construct a dynamic association network for the association operation feature set to obtain a dynamic association network graph; The risk propagation path identification module is used to obtain historical fault data; search for propagation risk paths based on historical fault data and dynamic association network diagrams to obtain a candidate risk path set; calculate the path propagation probability of the candidate risk path set to obtain a path probability data set; extract key risk propagation paths based on the path probability data set and the candidate risk path set to obtain key risk propagation paths; The fault probability dynamic assessment module is used to calculate the path propagation probability according to the key risk propagation path to obtain the path probability matrix; perform a dynamic analysis of the fault probability according to the path probability matrix to obtain the dynamic fault probability matrix; The fever risk comprehensive prediction module is used to construct a fever risk prediction model according to the associated operation feature set and the dynamic fault probability matrix to obtain the fever risk prediction model; the fever risk prediction model is used to predict the fever risk and calculate the comprehensive risk index to obtain the comprehensive fever risk index; The early warning adaptive adjustment module is used to obtain historical early warning data; construct an adaptive early warning model based on the historical early warning data to obtain an adaptive early warning model; and perform an adaptive early warning of a high-voltage disconnector thermal fault based on a comprehensive thermal risk index and an adaptive early warning model to realize a high-voltage disconnector thermal fault prediction operation.

10. A high voltage circuit breaker, characterized in that: It comprises a contact system, an arc extinguishing system and an operating mechanism connected to the two, and also comprises a controller connected to the operating mechanism, wherein the controller comprises the isolating switch thermal fault prediction system of the high-voltage circuit breaker as claimed in claim 9.

Images