High-voltage circuit breaker partial discharge monitoring and early warning method and system

Abstract

The invention provides a high-voltage circuit breaker partial discharge monitoring and early warning method and system, and relates to the technical field of partial discharge monitoring, and the method comprises the steps: obtaining the feature information of a target circuit; a circuit analysis model is called for analysis, and a target analysis result is obtained and comprises a plurality of target point locations; dynamically monitoring the first target point location through an ultrahigh frequency sensor to obtain first partial discharge information; calling a signal analysis model for processing and analysis to obtain a first signal feature set; activating a fault diagnosis model to analyze the first signal feature set to obtain a first diagnosis tag; and when the partial discharge fault of the target high-voltage circuit breaker at the first target point location is displayed, a first early warning signal is sent out. The technical problems that in the prior art, partial discharge monitoring mostly depends on artificial experience or fixed rules, intelligent analysis means are lacked, misjudgment or missed judgment is prone to occurring, accurate positioning is difficult, and the safety of the high-voltage circuit breaker is reduced are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of partial discharge monitoring, and in particular to a partial discharge monitoring and early warning method and system for a high-voltage circuit breaker. Background Art

[0002] Partial discharge is a common electrical phenomenon that usually occurs in insulation defects or aging parts of high-voltage equipment. Partial discharge will not only affect the insulation performance of high-voltage circuit breakers, but may eventually lead to equipment failure, power outages or other serious accidents. Therefore, monitoring the partial discharge of high-voltage circuit breakers and issuing early warnings before failures occur are of great significance for preventing equipment damage and ensuring the operation of the power grid.

[0003] However, traditional partial discharge monitoring mostly relies on manual experience or fixed rules and lacks intelligent analysis methods. This method is not only prone to misjudgment or missed judgment, but also difficult to cope with complex and diverse fault types. The operating environment of modern power systems is becoming increasingly complex, and the types of faults are becoming increasingly diverse. Manual or static rules alone are difficult to adapt to the real-time fault analysis needs of high-voltage circuit breakers; in addition, the internal structure of high-voltage circuit breakers is complex, and the location of partial discharge is difficult to accurately locate. The traditional troubleshooting process often takes a lot of time to find the specific fault point, which will prolong the downtime of the equipment, affect the operation of the entire power grid, and bring huge losses to power supply and economic operation. Summary of the invention

[0004] The present application provides a method and system for monitoring and early warning of partial discharge of a high-voltage circuit breaker, aiming to solve the technical problem that the existing technology for partial discharge monitoring mostly relies on manual experience or fixed rules, lacks intelligent analysis means, is not only prone to misjudgment or missed judgment, but also difficult to accurately locate, resulting in reduced safety of high-voltage circuit breakers.

[0005] The first aspect disclosed in the present application provides a method for monitoring and early warning of partial discharge of a high-voltage circuit breaker, the method comprising: obtaining target circuit characteristic information, the target circuit characteristic information refers to multi-dimensional characteristic information of the target circuit, the target circuit refers to a circuit including a target high-voltage circuit breaker; calling a circuit analysis model to analyze the target circuit characteristic information to obtain a target analysis result, the target analysis result including multiple target points; dynamically monitoring a first target point among the multiple target points through a UHF sensor to obtain first partial discharge information; calling a signal analysis model to process and analyze the first partial discharge information to obtain a first signal feature set; activating a fault diagnosis model to analyze the first signal feature set to obtain a first diagnostic label; and when the first diagnostic label shows that the target high-voltage circuit breaker has a partial discharge fault at the first target point, issuing a first early warning signal.

[0006] Furthermore, the target circuit characteristic information includes target circuit topology characteristics, target circuit load characteristics and target historical fault characteristics. The calling circuit analysis model analyzes the target circuit characteristic information to obtain a target analysis result. The target analysis result includes multiple target points, including: The circuit analysis model includes a first analysis channel, a second analysis channel and a third analysis channel; wherein, the first analysis channel is used to determine whether the number of first connection lines corresponding to a first circuit connection point is within a predetermined line threshold, and the first circuit connection point is any circuit connection point obtained based on the target circuit topology feature; if so, the first circuit connection point is added to a candidate key point list; wherein, the second analysis channel is used to determine whether a first circuit load corresponding to a first circuit point satisfies a predetermined load constraint, and the first circuit load refers to the load corresponding to the first circuit point in the target circuit load; if so, the first circuit point is added to the candidate key point list; wherein, the third analysis channel is used to determine whether a second circuit point belongs to a historical fault point library, and the historical fault point library refers to a point set obtained by analyzing the target historical fault feature; if so, the second circuit point is added to the candidate key point list; the candidate point list is deduplicated to obtain the multiple target points.

[0007] Furthermore, the predetermined load constraint includes a load peak constraint and a load type constraint, and judging whether the first circuit load corresponding to the first circuit point satisfies the predetermined load constraint through the second analysis channel includes: Determine whether the first load value in the first circuit load satisfies the load peak constraint to obtain a first constraint condition; determine whether the first device type of the first load device in the first circuit load satisfies the load type constraint to obtain a second constraint condition; when the first constraint condition or the second constraint condition is satisfied, it is determined that the first circuit point satisfies the predetermined load constraint.

[0008] Furthermore, the calling of the signal analysis model to process and analyze the first partial discharge information to obtain a first signal feature set includes: According to the first corresponding relationship between the first monitoring time and the first electromagnetic wave signal in the first partial discharge information, a first electromagnetic wave signal time series is generated; time domain features of the first electromagnetic wave signal time series are collected through the signal analysis model to obtain a first time domain feature; frequency domain features of the first electromagnetic wave signal spectrum obtained by converting the first electromagnetic wave signal time series are collected through the signal analysis model to obtain a first frequency domain feature; and the first signal feature set is formed according to the first time domain feature and the first frequency domain feature.

[0009] Furthermore, obtaining the first signal feature set further includes: Activate a signal calibration model, the signal calibration model includes a first calibrator and a second calibrator, the first calibrator is a model constructed based on the principle of convolutional neural network, and the second calibrator is a model constructed based on the principle of long short-term memory network; perform spatial feature analysis on the first local discharge information by the first calibrator to obtain a first spatial feature; perform temporal feature analysis on the first spatial feature by the second calibrator to obtain a first time feature; connect and fuse the first spatial feature with the first time feature to obtain a first comprehensive feature, and add the first comprehensive feature to the first signal feature set.

[0010] Furthermore, the activation fault diagnosis model analyzes the first signal feature set to obtain a first diagnosis label, including: A first historical fault record is obtained according to the target historical fault feature, wherein the first historical fault record includes a first historical fault point and a first historical signal feature set when the first historical fault point fails; a first historical normal record is obtained, wherein the first historical normal record includes a first historical normal point and a second historical signal feature set when the first historical normal point operates normally; the first historical signal feature set is labeled to obtain a first historical label and form a first training data group; the first historical signal feature set is labeled to obtain a second historical label and form a second training data group; the first training data group and the second training data group are supervisedly learned and tested to obtain the fault diagnosis model.

[0011] Furthermore, the high-voltage circuit breaker partial discharge monitoring and early warning method further includes: Activate the fault prediction model, and analyze the first signal feature set through the fault prediction model to obtain a first predicted fault type; when the first warning signal is issued, display the first predicted fault type on the remote center display; wherein, the construction process of the fault prediction model is as follows: the first historical fault record also includes the first fault type of the first historical fault point, and train the third training data group composed of the first historical signal feature set and the first fault type to obtain the fault prediction model.

[0012] In a second aspect disclosed in the present application, a high-voltage circuit breaker partial discharge monitoring and early warning system is provided, the system is used for the above-mentioned high-voltage circuit breaker partial discharge monitoring and early warning method, the system comprises: a circuit feature acquisition module, the circuit feature acquisition module is used to acquire target circuit feature information, the target circuit feature information refers to multi-dimensional feature information of the target circuit, the target circuit refers to a circuit containing a target high-voltage circuit breaker; a circuit feature analysis module, the circuit feature analysis module is used to call a circuit analysis model to analyze the target circuit feature information to obtain a target analysis result, the target analysis result includes a plurality of target points; a point dynamic monitoring module, the point dynamic monitoring module A dynamic monitoring module is used to dynamically monitor the first target point among the multiple target points through a UHF sensor to obtain first partial discharge information; a discharge information analysis module is used to call a signal analysis model to process and analyze the first partial discharge information to obtain a first signal feature set; a signal feature analysis module is used to activate a fault diagnosis model to analyze the first signal feature set to obtain a first diagnostic label; and a warning signal issuing module is used to issue a first warning signal when the first diagnostic label shows that the target high-voltage circuit breaker has a partial discharge fault at the first target point.

[0013] One or more technical solutions provided in this application have at least the following technical effects or advantages: By collecting multi-dimensional characteristic information of the target circuit, a multi-angle data foundation is provided for fault analysis. This data foundation can accurately reflect the operating status of the circuit, so that the subsequent analysis model has comprehensive input information; calling the circuit analysis model to conduct a comprehensive analysis of the multi-dimensional data can identify multiple target points of potential faults, narrow the scope of fault monitoring, improve the pertinence of fault detection, and avoid the waste of resources caused by full network monitoring; through the dynamic monitoring of the target point by the UHF sensor, the partial discharge information is captured, and the potential partial discharge problem in the high-voltage circuit breaker can be sensitively detected. This non-contact monitoring method not only ensures the accuracy of monitoring, but also improves the safety and real-time nature of monitoring; calling the signal analysis model, The partial discharge signal is processed and analyzed, and the time domain and frequency domain features of the signal are extracted. The obtained signal feature set not only covers the electromagnetic wave features monitored in real time, but also provides comprehensive signal analysis results, which makes the subsequent diagnosis more accurate; through the fault diagnosis model, the signal feature set is automatically analyzed and the diagnostic label is generated. The model identifies whether the circuit breaker has a fault and the specific fault type based on historical data and real-time signal features. This intelligent diagnosis method reduces the need for manual intervention and improves the efficiency of fault detection and diagnosis; when a partial discharge fault is detected, an early warning signal is immediately issued. This real-time early warning can help operation and maintenance personnel respond quickly, prevent the fault from further expanding, and reduce the risk of equipment damage and downtime. In summary, this method achieves accurate positioning of faults through real-time monitoring and intelligent fault diagnosis, reduces the blindness in traditional regular maintenance, and issues an early warning before the fault occurs, avoiding serious damage to the equipment, thereby reducing the repair time and downtime of sudden faults, and directly reducing the repair and maintenance costs of the equipment.

[0014] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic flow chart of a method for monitoring and early warning of partial discharge of a high-voltage circuit breaker provided in an embodiment of the present application.

[0016] Figure 2 A schematic structural diagram of a high-voltage circuit breaker partial discharge monitoring and early warning system provided in an embodiment of the present application.

[0017] Explanation of the reference numerals: circuit characteristic acquisition module 10 , circuit characteristic analysis module 20 , point dynamic monitoring module 30 , discharge information analysis module 40 , signal characteristic analysis module 50 , warning signal issuing module 60 . DETAILED DESCRIPTION

[0018] The embodiments of the present application provide a method and system for monitoring and early warning of partial discharge of a high-voltage circuit breaker, thereby solving the technical problem that the existing technology for partial discharge monitoring mostly relies on manual experience or fixed rules and lacks intelligent analysis means, which is not only prone to misjudgment or missed judgment, but also difficult to accurately locate, resulting in reduced safety of high-voltage circuit breakers.

[0019] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0020] Embodiment 1, as Figure 1 As shown, an embodiment of the present application provides a high-voltage circuit breaker partial discharge monitoring and early warning method, the method comprising: Acquire target circuit characteristic information, wherein the target circuit characteristic information refers to multi-dimensional characteristic information of the target circuit, and the target circuit refers to a circuit including a target high-voltage circuit breaker.

[0021] The target circuit characteristic information is the multi-dimensional characteristic information of the target circuit, involving data of multiple angles and types, including: target circuit topology characteristics, which describe the structure and connection relationship of the circuit, including the connection method of each node in the circuit, such as circuit breakers, transformers, loads, etc., as well as the number of lines and network layout; target circuit load characteristics, which record the load conditions in the circuit, such as the type of load, the power of the load, the working status of the load, and the load type such as motors, generators, transformers, etc.; target historical fault characteristics, including fault information that has occurred in the circuit in the past, such as historical fault records of circuit breakers, types of faults that have occurred, fault locations, etc.

[0022] In order to obtain the above information, the following methods can be used: real-time data of physical quantities such as current and voltage in the circuit can be obtained through sensor monitoring systems, such as current sensors, voltage sensors, etc.; historical fault information and historical operation data can be queried through the database of the power grid management system, such as the SCADA system or other monitoring systems; circuit topology characteristics can be extracted through existing power system diagrams or other power grid planning data.

[0023] The collected multi-dimensional features are integrated to form the target circuit feature information, which is the basis for subsequent analysis and helps to determine possible fault points, key monitoring locations for partial discharge, etc.

[0024] The circuit analysis model is called to analyze the target circuit characteristic information to obtain a target analysis result, wherein the target analysis result includes a plurality of target points.

[0025] The circuit analysis model consists of multiple analysis channels, each of which evaluates different types of circuit feature information. The first analysis channel determines whether the number of lines at the circuit connection point is within the predetermined threshold range based on topological feature analysis; the second analysis channel determines whether the load characteristics of the circuit point meet the predetermined load constraints based on load feature analysis; the third analysis channel determines whether the circuit point belongs to the point in the historical fault point library based on historical fault analysis. The model analyzes each point of the circuit in parallel through the above three analysis channels, and finally generates multiple target points, which are circuit points with partial discharge faults.

[0026] A first target point among the multiple target points is dynamically monitored by a UHF sensor to obtain first partial discharge information.

[0027] Ultra-high frequency (UHF) sensors are used to capture electromagnetic wave signals generated by partial discharge in power equipment. Partial discharge is a tiny electrical discharge in power equipment. This discharge is often a precursor to equipment aging or failure. By monitoring partial discharge, potential faults in equipment can be discovered in advance to avoid large-scale failures. The advantages of ultra-high frequency sensors are high sensitivity, non-invasive monitoring, and remote monitoring. They are suitable for high-frequency electromagnetic interference environments and can detect discharges at long distances and hidden locations.

[0028] One of the target points is randomly selected as the analysis object as the first target point. The UHF sensor is installed in a suitable position to monitor the electromagnetic wave signal of the first target point. The sensor needs to be configured according to the actual situation of the target point to ensure the effectiveness and accuracy of the monitoring. After the installation is completed, the UHF sensor collects electromagnetic wave signals in real time during the operation of the circuit. When partial discharge occurs, electromagnetic waves within a specific frequency range will be generated. The sensor can capture these signals and record them to obtain the first partial discharge information. The first partial discharge information contains the partial discharge state at the first target point, reflecting the intensity, frequency, and timing characteristics of the partial discharge.

[0029] A signal analysis model is called to process and analyze the first partial discharge information to obtain a first signal feature set.

[0030] The signal analysis model is used to process partial discharge information. The partial discharge signal is a complex signal containing rich time domain and frequency domain features. The main function of the signal analysis model is to extract key features from these complex signals for subsequent fault diagnosis.

[0031] Specifically, the signal analysis model first performs a time domain analysis on the first local discharge information, including monitoring the changes of the signal at different time points, extracting time domain features such as amplitude, duration, and signal waveform, and the obtained time domain features reflect the distribution of the local discharge signal on the time axis; then, the local discharge information is converted from the time domain to the frequency domain through the signal analysis model, and its frequency components are analyzed. The frequency domain features obtained can be represented by Fourier transform or other spectrum analysis methods to represent the frequency distribution of the local discharge signal, such as which frequency ranges the discharge intensity is mainly concentrated in; further, the signal calibration model is used to analyze the spatial features of the local discharge signal to reveal the distribution characteristics of the local discharge in the physical space. The obtained time domain, frequency domain, and space features are integrated to obtain the first signal feature set, which is a comprehensive description of the multi-dimensional features of the local discharge signal, including time domain features, frequency domain features, and space features.

[0032] The fault diagnosis model is activated to analyze the first signal feature set to obtain a first diagnosis label.

[0033] The fault diagnosis model is a model trained based on historical data, specifically, it is constructed through supervised learning of historical fault records and historical normal records. Therefore, this model can identify and classify different types of partial discharge signal features. The first signal feature set is input into the fault diagnosis model. The model analyzes the input feature set to determine whether these features match the known partial discharge fault features, and outputs the first diagnostic label to mark the status of the point, including whether there is a partial discharge fault and the possible fault type.

[0034] When the first diagnostic tag indicates that a partial discharge fault occurs in the target high-voltage circuit breaker at the first target point, a first warning signal is issued.

[0035] When the first diagnostic tag shows that the target high-voltage circuit breaker has a partial discharge fault at the first target point, it is confirmed that the partial discharge signal has exceeded the normal range and the circuit breaker at the target point is facing a failure risk. In this case, a first warning signal is generated, and the first warning signal will be transmitted to the remote monitoring center or other related systems to notify the operation and maintenance personnel or the automation system to perform corresponding fault processing to prevent the partial discharge from further expanding and causing serious accidents.

[0036] Furthermore, the target circuit characteristic information includes target circuit topology characteristics, target circuit load characteristics and target historical fault characteristics. The high-voltage circuit breaker partial discharge monitoring and early warning method includes: The circuit analysis model includes a first analysis channel, a second analysis channel and a third analysis channel; wherein, the first analysis channel is used to determine whether the number of first connection lines corresponding to a first circuit connection point is within a predetermined line threshold, and the first circuit connection point is any circuit connection point obtained based on the target circuit topology feature; if so, the first circuit connection point is added to a candidate key point list; wherein, the second analysis channel is used to determine whether a first circuit load corresponding to a first circuit point satisfies a predetermined load constraint, and the first circuit load refers to the load corresponding to the first circuit point in the target circuit load; if so, the first circuit point is added to the candidate key point list; wherein, the third analysis channel is used to determine whether a second circuit point belongs to a historical fault point library, and the historical fault point library refers to a point set obtained by analyzing the target historical fault feature; if so, the second circuit point is added to the candidate key point list; the candidate key point list is deduplicated to obtain the multiple target points.

[0037] The target circuit characteristic information is the multi-dimensional characteristic information of the target circuit, involving data of multiple angles and types, including: target circuit topology characteristics, which describe the structure and connection relationship of the circuit, including the connection method of each node in the circuit, such as circuit breakers, transformers, loads, etc., as well as the number of lines and network layout; target circuit load characteristics, which record the load conditions in the circuit, such as the type of load, the power of the load, the working status of the load, and the load type such as motors, generators, transformers, etc.; target historical fault characteristics, including fault information that has occurred in the circuit in the past, such as historical fault records of circuit breakers, types of faults that have occurred, fault locations, etc.

[0038] The circuit analysis model includes three parallel analysis channels, each of which is evaluated based on different circuit characteristics. The first analysis channel is based on topological characteristics, mainly analyzing the circuit connection method to find key nodes; the second analysis channel is based on load characteristics, giving priority to protecting important loads and sensitive equipment; the third analysis channel is based on historical fault characteristics, identifying high-fault areas by analyzing past fault data. These channels are processed in parallel, and can independently judge the characteristics of different dimensions of the circuit, thereby quickly screening out potential key points. Because they are parallel, the analysis of each channel is not interdependent, which can significantly improve the efficiency of the entire analysis process.

[0039] Circuit topology features describe the connection relationship between nodes in the power system. In high-voltage circuits, each connection point may be connected to multiple lines to form a complex network. Each connection point in the circuit can be identified as an intersection node of the electrical network. The goal is to analyze the number of lines on these connection points to determine whether they are high-risk. Extract any circuit connection point from the target circuit topology features as the analysis object and mark it as the first circuit connection point.

[0040] The predetermined line threshold is a pre-set threshold used to determine whether the number of lines at a circuit connection point is in a high load or critical state. By analyzing the target circuit topology characteristics, the model checks the number of first connection lines corresponding to the first circuit connection point to determine whether it has reached the predetermined line threshold. If this threshold value is reached, it means that the connection point is a critical node in the entire circuit system, because the more lines there are, the greater the impact of the node on the entire system, which also means that it is more likely to have problems or failures. For example, assuming that the threshold value is set to 4, if a circuit connection point is connected to 4 or more lines, then this connection point is considered to be a high load or critical point. At this time, the point is marked as a potential critical point and added to the candidate critical point list.

[0041] This process is dynamic. Each connection point in the circuit is analyzed one by one, and the points that meet the conditions are added to the candidate list in turn. The candidate list is continuously filled in the three analysis channels. It contains key points in the circuit that may have partial discharge or other fault risks, which serve as key areas for subsequent monitoring and analysis.

[0042] The first circuit load refers to the electrical load borne by the first circuit point. The load information usually includes current, voltage, power, load type, etc. The predetermined load constraint is a pre-set judgment condition used to determine whether the load at a certain point is normal or in a high-risk state. The predetermined load constraint includes a load peak constraint and a load type constraint.

[0043] Analyze the load of the first circuit to determine whether it meets the set load peak constraint or load type constraint. If the load exceeds the rated value or safe operation peak of the equipment, it is determined that the point is in a high load state; if the load type is a specific type, such as equipment sensitive to partial discharge, it is determined that there may be a failure risk at this point.

[0044] When any of the conditions is met, it is determined that the point has a potential failure risk. In this case, the point is marked as a point that needs to be monitored and added to the candidate key point list.

[0045] The historical fault point library is a database that stores the fault points that have occurred in the target circuit and the characteristic information related to these fault points. These fault points are extracted from the analysis of historical fault records and operating data, including partial discharge faults that have occurred at certain specific points of the circuit breaker.

[0046] When judging the second circuit point, by comparing the second circuit point with the historical fault points in the historical fault point library, it is determined whether the point belongs to the historical fault point library. Matching can be performed based on the unique identification of the point, such as device ID, location, connection method, etc. If the second circuit point has failed in the past, the point is judged to have a higher failure risk. In this case, the second circuit point is added to the candidate key point list.

[0047] The candidate key point list is jointly generated by three parallel analysis channels. Each channel will screen out some key points during the analysis process. These points may have overlapping parts, that is, some points may meet the conditions of multiple channels at the same time. For example, they are historical fault points and meet the load constraint conditions. In order to avoid repeated monitoring of the same point, the candidate key point list is deduplicated to ensure that each point only appears once in the list. After deduplication, multiple non-repetitive target points are finally generated. These points represent the locations where partial discharge may occur in the circuit, which serve as the focus of subsequent monitoring and fault analysis.

[0048] Furthermore, the predetermined load constraint includes a load peak constraint and a load type constraint, and the high-voltage circuit breaker partial discharge monitoring and early warning method includes: Determine whether the first load value in the first circuit load satisfies the load peak constraint to obtain a first constraint condition; determine whether the first device type of the first load device in the first circuit load satisfies the load type constraint to obtain a second constraint condition; when the first constraint condition or the second constraint condition is satisfied, it is determined that the first circuit point satisfies the predetermined load constraint.

[0049] The preset load constraint is an evaluation standard set for the load at each circuit point, which is used to determine whether the load equipment in the circuit is in a normal or overloaded state, including load peak constraint and load type constraint. Among them, the load peak constraint is used to evaluate whether the load at a circuit point exceeds its rated capacity or the maximum load that the equipment can withstand. The load peak constraint can set specific thresholds based on different equipment types and operating conditions; the load type constraint determines whether the equipment has special monitoring requirements based on the type of load equipment in the circuit. For example, large motors, transformers, etc. are more likely to cause partial discharge during operation, so they may be subject to more stringent monitoring.

[0050] Obtain a first load value corresponding to the first circuit load at the first circuit point, such as current, voltage, power, etc., compare the first load value with the load peak constraint corresponding to the point, and determine whether it exceeds the allowable peak range; if the load value exceeds the set peak threshold, determine that the point satisfies the peak constraint, and record the judgment result as the first constraint situation, including satisfaction and non-satisfaction.

[0051] Obtain a first device type corresponding to a first load device of a first circuit load at a first circuit point, and determine whether the device type belongs to a pre-set specific type. The type of the load device can be classified according to its operating characteristics and failure risk. If the device type belongs to a device type that requires key monitoring, it is considered to satisfy the load type constraint, and the determination result is recorded as a second constraint condition, which also includes satisfaction and non-satisfaction.

[0052] Based on the first constraint and the second constraint, when any one constraint condition is met, that is, the load peak value exceeds the standard or the load device type belongs to a specific type, it is determined that the first circuit point meets the predetermined load constraint.

[0053] Furthermore, the method for monitoring and early warning of partial discharge of a high-voltage circuit breaker comprises: According to the first corresponding relationship between the first monitoring time and the first electromagnetic wave signal in the first partial discharge information, a first electromagnetic wave signal time series is generated; time domain features of the first electromagnetic wave signal time series are collected through the signal analysis model to obtain a first time domain feature; frequency domain features of the first electromagnetic wave signal spectrum obtained by converting the first electromagnetic wave signal time series are collected through the signal analysis model to obtain a first frequency domain feature; and the first signal feature set is formed according to the first time domain feature and the first frequency domain feature.

[0054] The first partial discharge information includes multiple monitoring time points and corresponding electromagnetic wave signal data. These time points are matched with corresponding signal values ​​to generate a first electromagnetic wave signal time series. Specifically, the monitoring time includes the moment when the partial discharge event occurs, and the electromagnetic wave signal is the electromagnetic wave amplitude and frequency information corresponding to these moments. These data points are arranged in chronological order to form a time series, which is convenient for subsequent analysis.

[0055] The time domain features of the first electromagnetic wave signal time series are extracted. The time domain features include the amplitude of the signal (maximum value, minimum value, mean value, etc.), the waveform characteristics of the signal (such as zero crossing point, waveform symmetry), and the time domain statistical characteristics of the signal (such as variance, standard deviation). These features can reflect the temporal variation characteristics of the electromagnetic wave signal. After time domain analysis, a series of time domain features are extracted and recorded as the first time domain features.

[0056] The first electromagnetic wave signal time series is subjected to Fourier transform to convert the time domain signal into a frequency domain signal. The obtained spectrum of the first electromagnetic wave signal provides the signal intensity information at different frequencies and can reveal the frequency components in the signal. The frequency domain features of the first electromagnetic wave signal spectrum are collected. The frequency domain features include the main frequency components (such as the main frequency and its amplitude), the bandwidth of the spectrum (the range of signal energy distribution), and the frequency domain statistical features (such as the frequency mean, frequency variance, etc.). The collected frequency domain features form the first frequency domain features.

[0057] The first time domain feature and the first frequency domain feature are integrated to obtain a first signal feature set. This signal feature set integrates the information of the time domain and the frequency domain, provides comprehensive characteristics of the electromagnetic wave signal, and can effectively support subsequent fault diagnosis.

[0058] Furthermore, the high-voltage circuit breaker partial discharge monitoring and early warning method further includes: Activate a signal calibration model, the signal calibration model includes a first calibrator and a second calibrator, the first calibrator is a model constructed based on the principle of convolutional neural network, and the second calibrator is a model constructed based on the principle of long short-term memory network; perform spatial feature analysis on the first local discharge information by the first calibrator to obtain a first spatial feature; perform temporal feature analysis on the first spatial feature by the second calibrator to obtain a first time feature; connect and fuse the first spatial feature with the first time feature to obtain a first comprehensive feature, and add the first comprehensive feature to the first signal feature set.

[0059] The signal calibration model includes a first calibrator and a second calibrator, wherein the first calibrator is constructed based on a convolutional neural network (CNN) for spatial feature analysis. Convolutional neural networks are good at processing signals or data with spatial structures, such as images, signal distributions, etc., and identify spatial relationships and patterns by extracting local features; the second calibrator is constructed based on a long short-term memory network (LSTM) for time series feature analysis. The long short-term memory network can process time series data and extract dynamic characteristics of signals that change over time.

[0060] The convolutional neural network extracts the spatial features of the data layer by layer through multiple convolutional layers and pooling layers. Each convolutional layer extracts the features of the local area by applying filters or convolution kernels, and the pooling layer is used to reduce the dimension and extract more abstract features. The partial discharge signal can be expressed as the signal intensity of spatial distribution, such as the signal amplitude and frequency detected by multiple sensors at different spatial locations. The convolutional neural network extracts the specific spatial patterns related to partial discharge by processing these spatial data, extracts the spatial features of the partial discharge signal, such as the signal intensity difference at a specific sensor location, the spatial distribution of the partial discharge source location, and the electromagnetic wave signal diffusion pattern in space, and obtains the first spatial feature.

[0061] The long short-term memory network performs well in processing sequence data with time correlation because it can remember dependencies over a longer period of time. Starting from the first spatial feature, it further analyzes the temporal variation patterns of these spatial features, such as the variation of the amplitude of the signal over time, the periodicity or randomness of the discharge, and the fluctuation characteristics of the local discharge signal, such as whether there is a trend of gradual strengthening or attenuation. Through the long short-term memory network model, these temporal characteristics are identified and the timing features are extracted, which facilitates the understanding of the temporal evolution of the local discharge signal. The first time feature obtained can reflect the change of the local discharge signal on the time axis.

[0062] The first spatial feature and the first temporal feature are connected and fused. Connection fusion refers to combining features of different dimensions into a more representative feature set in order to capture the comprehensive characteristics of the partial discharge signal. The fused feature set can simultaneously reflect the spatial distribution of the partial discharge signal and the changes of the signal at different time points. Through connection fusion, the first comprehensive feature is finally generated. This comprehensive feature integrates information from both spatial and temporal dimensions and can more comprehensively describe the partial discharge phenomenon. The first comprehensive feature is added to the first signal feature set.

[0063] Furthermore, the method for monitoring and early warning of partial discharge of a high-voltage circuit breaker comprises: A first historical fault record is obtained according to the target historical fault feature, wherein the first historical fault record includes a first historical fault point and a first historical signal feature set when the first historical fault point fails; a first historical normal record is obtained, wherein the first historical normal record includes a first historical normal point and a second historical signal feature set when the first historical normal point operates normally; the first historical signal feature set is labeled to obtain a first historical label, and a first training data group is formed; the second historical signal feature set is labeled to obtain a second historical label, and a second training data group is formed; the first training data group and the second training data group are supervisedly learned and tested to obtain the fault diagnosis model.

[0064] The target historical fault characteristics include fault information that has occurred in the circuit in the past, such as the historical fault records of the circuit breaker, the type of fault that occurred, the fault point, etc. The first historical fault record is the historical data extracted from the target historical fault characteristics, wherein the first historical fault point refers to the specific location or equipment where the fault occurred during a certain historical fault; the first historical signal feature set includes the signal feature data collected when a fault occurs at the first historical fault point, including information such as the time domain, frequency domain and spatial characteristics at the time of the fault.

[0065] The first historical normal record refers to the historical data of the circuit under normal operation. Normal records are opposite to fault records and can provide comparison samples for the model to help the model distinguish between normal and abnormal signal patterns. Among them, the first historical normal point refers to the point when the equipment was operating normally in history. Unlike the fault point, the record of the normal point represents the operating state without partial discharge or other abnormal events; the second historical signal feature set is the signal feature data of the equipment in the normal state, which includes the current, voltage waveform, frequency domain characteristics, load conditions and other signal data of the equipment in healthy operation. Normal records and fault records together constitute the positive and negative sample sets required for model training.

[0066] Labeling is to assign a corresponding fault label to each historical signal sample. The label represents the actual state of the signal. The first historical signal feature set corresponds to the fault state, so a fault label will be assigned. For example, if a signal feature set indicates that the device has had a partial discharge fault in history, the signal can be assigned a label of fault, or a more specific label such as partial discharge fault. The first historical label obtained is the annotation result corresponding to the first historical signal feature set, indicating that these signal feature data originate from the fault state. The label provides a clear reference for the model, allowing the model to identify the association between similar features and faults. The first training data group is a data set consisting of the first historical signal feature set and its corresponding fault label. This data set is used to train the machine learning model to help the model learn the signal performance of the device when a fault occurs.

[0067] Similarly, the normal signal data of the second historical signal feature set are labeled. Since these data come from the normal state of the equipment, a normal state label is assigned, such as normal operation or no fault. The second historical label corresponds to the label under the normal operation state, indicating that these signal data come from the normal operation process of the equipment. The label provides the model with reference data for the normal operation of the equipment, helping the model to distinguish the difference between faults and normal states. The second training data group consists of the second historical signal feature set and the corresponding normal operation label, which helps the model learn the signal performance of the equipment in a healthy state.

[0068] Supervised learning is a method of machine learning in which the training dataset consists of input features and output labels. By learning the correspondence between input data and output labels, the model is able to predict the corresponding labels based on new input data.

[0069] In the supervised learning process, the first training data group and the second training data group are input into a machine learning algorithm, such as a neural network, a support vector machine, etc. The model learns the difference between the signal characteristics of the device in normal and fault states through these data. Through the training algorithm, the model gradually learns how to predict the correct output label based on the input features.

[0070] Specifically, by inputting a large amount of historical signal features, the model will try to fit this data and find the mapping relationship between signal features and fault / normal status. The training goal is to enable the model to recognize and distinguish normal and fault signals. The goal of model training is to minimize the prediction error of the model, that is, to minimize the gap between the label predicted by the model and the actual label. After training, an independent test set is used to test the actual performance of the model. The test set contains data that the model has not seen during training, which can evaluate the performance of the model in real scenarios. After training and verification, the model finally learns how to judge whether the equipment is in a normal state or a faulty state based on the input signal features. This model is the fault diagnosis model.

[0071] Furthermore, the high-voltage circuit breaker partial discharge monitoring and early warning method further includes: Activate the fault prediction model, and analyze the first signal feature set through the fault prediction model to obtain a first predicted fault type; when the first warning signal is issued, display the first predicted fault type on the remote center display; wherein, the construction process of the fault prediction model is as follows: the first historical fault record also includes the first fault type of the first historical fault point, and train the third training data group composed of the first historical signal feature set and the first fault type to obtain the fault prediction model.

[0072] Activate the pre-built fault prediction model, the model analyzes the input first signal feature set, and predicts whether the first target point has a potential fault risk by identifying various signal features in the feature set. After the analysis is completed, the first predicted fault type is output, that is, the type of fault that may currently occur at the first target point determined by the model, such as partial discharge fault, short circuit fault, overload fault and other specific fault types.

[0073] When the first warning signal is triggered, the first predicted fault type will be displayed on the remote monitoring center display, including the fault location and fault type. By displaying the predicted fault type in the remote center, the monitoring personnel can grasp the health status of the equipment in real time and make timely responses.

[0074] The construction process of the fault prediction model is as follows: The first historical fault record also includes the first fault type of the first historical fault point. The fault type refers to the specific form or category of the equipment failure, such as partial discharge fault, short circuit fault, and overload fault. The first historical fault point is associated with the corresponding specific fault type. These fault types provide labeled data for subsequent model training.

[0075] The first historical signal feature set includes signal features collected from the first historical fault point when a fault occurs, and these features record the operating status of the equipment during the fault. The first historical signal feature set is associated with a specific first fault type to form a complete sample, namely, the third training data group, wherein the input of each sample is historical fault signal features, which describe the electrical parameters of the equipment when a fault occurs, and the output is a fault type label, which indicates which specific fault type these signal features correspond to.

[0076] The fault prediction model is a multi-category classification model. Its goal is to predict the fault type based on the input signal features. Therefore, the model needs to be trained on the third training data set so that it can classify faults according to signal features. Specifically, the model receives a set of historical signal features as input, learns the relationship between them and the fault type based on the input features, and the output is the predicted fault type. During the model training process, the goal is to minimize the error between the predicted result and the actual fault type. By continuously adjusting the parameters, the model eventually learns to extract the association between signal features and fault types from historical data. After training, a fault prediction model that meets the accuracy requirements is finally obtained.

[0077] In summary, the high-voltage circuit breaker partial discharge monitoring and early warning method provided in the embodiment of the present application has the following technical effects: By collecting multi-dimensional characteristic information of the target circuit, a multi-angle data foundation is provided for fault analysis. This data foundation can accurately reflect the operating status of the circuit, so that the subsequent analysis model has comprehensive input information; calling the circuit analysis model to conduct a comprehensive analysis of the multi-dimensional data can identify multiple target points of potential faults, narrow the scope of fault monitoring, improve the pertinence of fault detection, and avoid the waste of resources caused by full network monitoring; through the dynamic monitoring of the target point by the UHF sensor, the partial discharge information is captured, and the potential partial discharge problem in the high-voltage circuit breaker can be sensitively detected. This non-contact monitoring method not only ensures the accuracy of monitoring, but also improves the safety and real-time nature of monitoring; calling the signal analysis model, The partial discharge signal is processed and analyzed, and the time domain and frequency domain features of the signal are extracted. The obtained signal feature set not only covers the electromagnetic wave features monitored in real time, but also provides comprehensive signal analysis results, which makes the subsequent diagnosis more accurate; through the fault diagnosis model, the signal feature set is automatically analyzed and the diagnostic label is generated. The model identifies whether the circuit breaker has a fault and the specific fault type based on historical data and real-time signal features. This intelligent diagnosis method reduces the need for manual intervention and improves the efficiency of fault detection and diagnosis; when a partial discharge fault is detected, an early warning signal is immediately issued. This real-time early warning can help operation and maintenance personnel respond quickly, prevent the fault from further expanding, and reduce the risk of equipment damage and downtime. In summary, this method achieves accurate positioning of faults through real-time monitoring and intelligent fault diagnosis, reduces the blindness in traditional regular maintenance, and issues an early warning before the fault occurs, avoiding serious damage to the equipment, thereby reducing the repair time and downtime of sudden faults, and directly reducing the repair and maintenance costs of the equipment.

[0078] Embodiment 2 is based on the same inventive concept as a method for monitoring and warning partial discharge of a high-voltage circuit breaker in the above embodiment. Figure 2 As shown, an embodiment of the present application provides a high-voltage circuit breaker partial discharge monitoring and early warning system, the system comprising: A circuit feature acquisition module 10, the circuit feature acquisition module 10 is used to acquire target circuit feature information, the target circuit feature information refers to the multi-dimensional feature information of the target circuit, and the target circuit refers to a circuit including a target high-voltage circuit breaker; a circuit feature analysis module 20, the circuit feature analysis module 20 is used to call a circuit analysis model to analyze the target circuit feature information to obtain a target analysis result, and the target analysis result includes multiple target points; a point dynamic monitoring module 30, the point dynamic monitoring module 30 is used to dynamically monitor a first target point among the multiple target points through a UHF sensor to obtain first partial discharge information; a discharge information analysis module 40, the discharge information analysis module 40 is used to call a signal analysis model to process and analyze the first partial discharge information to obtain a first signal feature set; a signal feature analysis module 50, the signal feature analysis module 50 is used to activate a fault diagnosis model to analyze the first signal feature set to obtain a first diagnostic label; an early warning signal issuing module 60, the early warning signal issuing module 60 is used to issue a first early warning signal when the first diagnostic label indicates that the target high-voltage circuit breaker has a partial discharge fault at the first target point.

[0079] Furthermore, the target circuit characteristic information includes target circuit topology characteristics, target circuit load characteristics and target historical fault characteristics. The system also includes multiple target point acquisition modules to perform the following operation steps: The circuit analysis model includes a first analysis channel, a second analysis channel and a third analysis channel; wherein, the first analysis channel is used to determine whether the number of first connection lines corresponding to a first circuit connection point is within a predetermined line threshold, and the first circuit connection point is any circuit connection point obtained based on the target circuit topology feature; if so, the first circuit connection point is added to a candidate key point list; wherein, the second analysis channel is used to determine whether a first circuit load corresponding to a first circuit point satisfies a predetermined load constraint, and the first circuit load refers to the load corresponding to the first circuit point in the target circuit load; if so, the first circuit point is added to the candidate key point list; wherein, the third analysis channel is used to determine whether a second circuit point belongs to a historical fault point library, and the historical fault point library refers to a point set obtained by analyzing the target historical fault feature; if so, the second circuit point is added to the candidate key point list; the candidate key point list is deduplicated to obtain the multiple target points.

[0080] Furthermore, the predetermined load constraint includes a load peak constraint and a load type constraint, and the system further includes a first circuit point determination module to perform the following operation steps: Determine whether the first load value in the first circuit load satisfies the load peak constraint to obtain a first constraint condition; determine whether the first device type of the first load device in the first circuit load satisfies the load type constraint to obtain a second constraint condition; when the first constraint condition or the second constraint condition is satisfied, it is determined that the first circuit point satisfies the predetermined load constraint.

[0081] Furthermore, the system further includes a first signal feature set acquisition module to perform the following operation steps: According to the first corresponding relationship between the first monitoring time and the first electromagnetic wave signal in the first partial discharge information, a first electromagnetic wave signal time series is generated; time domain features of the first electromagnetic wave signal time series are collected through the signal analysis model to obtain a first time domain feature; frequency domain features of the first electromagnetic wave signal spectrum obtained by converting the first electromagnetic wave signal time series are collected through the signal analysis model to obtain a first frequency domain feature; and the first signal feature set is formed according to the first time domain feature and the first frequency domain feature.

[0082] Furthermore, the system further includes a first comprehensive feature adding module to perform the following operation steps: Activate a signal calibration model, the signal calibration model includes a first calibrator and a second calibrator, the first calibrator is a model constructed based on the principle of convolutional neural network, and the second calibrator is a model constructed based on the principle of long short-term memory network; perform spatial feature analysis on the first local discharge information by the first calibrator to obtain a first spatial feature; perform temporal feature analysis on the first spatial feature by the second calibrator to obtain a first time feature; connect and fuse the first spatial feature with the first time feature to obtain a first comprehensive feature, and add the first comprehensive feature to the first signal feature set.

[0083] Furthermore, the system further includes a fault diagnosis model acquisition module to perform the following operation steps: A first historical fault record is obtained according to the target historical fault feature, wherein the first historical fault record includes a first historical fault point and a first historical signal feature set when the first historical fault point fails; a first historical normal record is obtained, wherein the first historical normal record includes a first historical normal point and a second historical signal feature set when the first historical normal point operates normally; the first historical signal feature set is labeled to obtain a first historical label, and a first training data group is formed; the second historical signal feature set is labeled to obtain a second historical label, and a second training data group is formed; the first training data group and the second training data group are supervisedly learned and tested to obtain the fault diagnosis model.

[0084] Furthermore, the system further includes a fault type display module to perform the following operation steps: Activate the fault prediction model, and analyze the first signal feature set through the fault prediction model to obtain a first predicted fault type; when the first warning signal is issued, display the first predicted fault type on the remote center display; wherein, the construction process of the fault prediction model is as follows: the first historical fault record also includes the first fault type of the first historical fault point, and train the third training data group composed of the first historical signal feature set and the first fault type to obtain the fault prediction model.

[0085] Through the above-mentioned detailed description of a high-voltage circuit breaker partial discharge monitoring and early warning method in this specification, those skilled in the art can clearly understand a high-voltage circuit breaker partial discharge monitoring and early warning system in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0086] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. 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 application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for monitoring and early warning of partial discharge of a high-voltage circuit breaker, characterized in that: The method comprises: Acquire target circuit characteristic information, wherein the target circuit characteristic information refers to multi-dimensional characteristic information of the target circuit, and the target circuit refers to a circuit including a target high-voltage circuit breaker; Calling a circuit analysis model to analyze the target circuit characteristic information to obtain a target analysis result, wherein the target analysis result includes a plurality of target points; Dynamically monitoring a first target point among the multiple target points by using a UHF sensor to obtain first partial discharge information; Calling a signal analysis model to process and analyze the first partial discharge information to obtain a first signal feature set; activating the fault diagnosis model to analyze the first signal feature set to obtain a first diagnosis label; When the first diagnostic tag indicates that a partial discharge fault occurs in the target high-voltage circuit breaker at the first target point, a first warning signal is issued.

2. A method for monitoring and early warning of partial discharge of a high-voltage circuit breaker according to claim 1, characterized in that: The target circuit characteristic information includes target circuit topology characteristics, target circuit load characteristics and target historical fault characteristics. The calling circuit analysis model analyzes the target circuit characteristic information to obtain a target analysis result. The target analysis result includes multiple target points, including: The circuit analysis model includes a first analysis channel, a second analysis channel and a third analysis channel; Wherein, determining whether the number of first connection lines corresponding to a first circuit connection point is within a predetermined line threshold through the first analysis channel, the first circuit connection point being any circuit connection point obtained based on the target circuit topology feature; If yes, add the first circuit connection point to the candidate key point list; Wherein, judging whether a first circuit load corresponding to a first circuit point satisfies a predetermined load constraint through the second analysis channel, wherein the first circuit load refers to a load corresponding to the first circuit point in the target circuit load; If satisfied, adding the first circuit point to the candidate key point list; Wherein, judging whether the second circuit point belongs to a historical fault point library through the third analysis channel, the historical fault point library refers to a point set obtained by analyzing the target historical fault characteristics; If yes, adding the second circuit point to the candidate key point list; The candidate key point list is deduplicated to obtain the multiple target points.

3. A method for monitoring and early warning of partial discharge of a high-voltage circuit breaker according to claim 2, characterized in that: The predetermined load constraint includes a load peak constraint and a load type constraint, and judging whether the first circuit load corresponding to the first circuit point satisfies the predetermined load constraint through the second analysis channel includes: Determine whether a first load value in the first circuit load satisfies the load peak constraint to obtain a first constraint condition; Determine whether a first device type of a first load device in the first circuit load satisfies the load type constraint, and obtain a second constraint condition; When the first constraint condition or the second constraint condition is satisfied, it is determined that the first circuit point satisfies the predetermined load constraint.

4. A method for monitoring and early warning of partial discharge of a high-voltage circuit breaker according to claim 2, characterized in that: The calling of the signal analysis model to process and analyze the first partial discharge information to obtain a first signal feature set includes: Generate a first electromagnetic wave signal time sequence according to a first corresponding relationship between a first monitoring time and a first electromagnetic wave signal in the first partial discharge information; Collecting time domain features of the first electromagnetic wave signal time series through the signal analysis model to obtain a first time domain feature; Collect frequency domain features of the first electromagnetic wave signal spectrum obtained by converting the first electromagnetic wave signal time series through the signal analysis model to obtain first frequency domain features; The first signal feature set is established according to the first time domain feature and the first frequency domain feature.

5. A method for monitoring and early warning of partial discharge of a high-voltage circuit breaker according to claim 4, characterized in that: The obtaining of the first signal feature set further includes: Activate a signal calibration model, wherein the signal calibration model includes a first calibrator and a second calibrator, wherein the first calibrator is a model constructed based on the principle of a convolutional neural network, and the second calibrator is a model constructed based on the principle of a long short-term memory network; Performing spatial feature analysis on the first partial discharge information by the first calibrator to obtain a first spatial feature; Performing a time series feature analysis on the first spatial feature by the second calibrator to obtain a first time feature; The first spatial feature and the first temporal feature are connected and fused to obtain a first comprehensive feature, and the first comprehensive feature is added to the first signal feature set.

6. A method for monitoring and early warning of partial discharge of a high-voltage circuit breaker according to claim 4, characterized in that: The activating fault diagnosis model analyzes the first signal feature set to obtain a first diagnosis label, including: Acquire a first historical fault record according to the target historical fault feature, where the first historical fault record includes a first historical fault point and a first historical signal feature set when the first historical fault point fails; Acquire a first historical normal record, where the first historical normal record includes a first historical normal point and a second historical signal feature set of the first historical normal point during normal operation; Labeling the first historical signal feature set to obtain a first historical label and forming a first training data group; Labeling the second historical signal feature set to obtain a second historical label and forming a second training data group; Supervised learning and verification are performed on the first training data group and the second training data group to obtain the fault diagnosis model.

7. A method for monitoring and early warning of partial discharge of a high-voltage circuit breaker according to claim 6, characterized in that: The high-voltage circuit breaker partial discharge monitoring and early warning method further comprises: activating a fault prediction model, and analyzing the first signal feature set through the fault prediction model to obtain a first predicted fault type; When the first warning signal is issued, the first predicted fault type is displayed on a remote center display; The construction process of the fault prediction model is as follows: The first historical fault record also includes a first fault type of the first historical fault point, and a third training data group consisting of the first historical signal feature set and the first fault type is trained to obtain the fault prediction model.

8. A high voltage circuit breaker partial discharge monitoring and early warning system, characterized in that: A method for monitoring and early warning of partial discharge of a high-voltage circuit breaker according to any one of claims 1 to 7, wherein the method comprises: A circuit feature acquisition module, the circuit feature acquisition module is used to acquire target circuit feature information, the target circuit feature information refers to multi-dimensional feature information of the target circuit, and the target circuit refers to a circuit including a target high-voltage circuit breaker; A circuit characteristic analysis module, wherein the circuit characteristic analysis module is used to call a circuit analysis model to analyze the target circuit characteristic information to obtain a target analysis result, wherein the target analysis result includes a plurality of target points; A point dynamic monitoring module, the point dynamic monitoring module is used to dynamically monitor a first target point among the multiple target points through a UHF sensor to obtain first partial discharge information; A discharge information analysis module, the discharge information analysis module is used to call a signal analysis model to process and analyze the first partial discharge information to obtain a first signal feature set; A signal feature analysis module, the signal feature analysis module is used to activate the fault diagnosis model to analyze the first signal feature set to obtain a first diagnosis label; A warning signal issuing module is used to issue a first warning signal when the first diagnostic tag indicates that the target high-voltage circuit breaker has a partial discharge fault at the first target point.

Images