Fault detection and early warning method and system for circuit breaker

Abstract

The present invention discloses a fault detection and early warning method and system for circuit breakers, and relates to the field of fault detection technology. The method comprises: reading the power grid network architecture, obtaining the distribution of power equipment and circuit breakers, and establishing the protection association of the circuit breaker. Constructing a fault scheme set, simulating fault signals, obtaining the data of the circuit breaker through monitoring sensors, and forming a time series data monitoring result. Based on the fault scheme set, a calibrated response parameter and a scoring network are established, and the time series data monitoring result is input into the scoring network to generate a response scoring result. Read the timing control data of the circuit breaker, map and compare it with the monitoring result, and generate an additional fault prediction result. Perform a joint response analysis based on the protection association and the time series data, and perform circuit breaker fault detection and early warning based on the response score, the additional fault prediction and the joint response analysis result. Thereby achieving the technical effect of improving the accuracy of detection and early warning and the response speed.

Description

Technical Field

[0001] The present invention relates to the technical field of fault detection, and in particular to a fault detection and early warning method and system for a circuit breaker. Background Art

[0002] In the power system, circuit breakers are key equipment to ensure the stable operation of the power grid. The existing circuit breaker fault detection and early warning methods mainly rely on fixed protection settings and manual monitoring. They cannot effectively identify potential fault signals and are difficult to respond in time, resulting in fault expansion. At the same time, there is a lack of comprehensive analysis of the causes and impact range of the faults, and there are technical problems such as insufficient early warning sensitivity and delayed response time. Summary of the invention

[0003] The present invention provides a fault detection and early warning method and system for a circuit breaker, so as to solve the technical problems of insufficient early warning sensitivity and delayed response time in the prior art, and achieve the technical effect of improving the accuracy of detection and early warning and the response speed.

[0004] In a first aspect, the present invention provides a fault detection and early warning method for a circuit breaker, wherein the method comprises:

[0005] The network architecture of the power grid network is read, the distribution of power equipment and circuit breakers is obtained based on the network architecture, and the protection association of the circuit breaker is established through the distribution of power equipment, the distribution of circuit breakers and the network architecture; a fault scheme set of the power grid network is established, the fault signal of the power grid network is simulated through the fault scheme set, the data of the circuit breaker is monitored through the monitoring sensor, and a time series data monitoring result is established; a calibration response parameter is established based on the fault scheme set, and a scoring network is established with the calibration response parameter; the time series data monitoring result is input into the scoring network to generate a response scoring result; the timing control data of the circuit breaker is read, the timing control data has a mapping relationship with the timing data monitoring result, a mapping comparison verification is performed according to the timing control data and the timing data monitoring result, and an additional fault prediction result is established; a joint response analysis is performed according to the protection association and the timing data monitoring result, and a joint response analysis result is established; a fault detection and early warning of the circuit breaker is performed according to the response scoring result, the additional fault prediction result and the joint response analysis result.

[0006] In a second aspect, the present invention further provides a fault detection and early warning system for a circuit breaker, wherein the system comprises:

[0007] A network architecture acquisition module is used to read the network architecture of the power grid network, acquire the power equipment distribution and circuit breaker distribution based on the network architecture, and establish a protection association of the circuit breaker through the power equipment distribution, circuit breaker distribution and network architecture.

[0008] The simulation monitoring module is used to establish a fault scenario set for the power grid network, simulate the fault signal of the power grid network through the fault scenario set, monitor the data of the circuit breaker through the monitoring sensor, and establish the time series data monitoring result.

[0009] A scoring definition module is used to establish calibration response parameters based on the fault solution set, and to establish a scoring network with the calibration response parameters.

[0010] A response scoring module is used to input the time series data monitoring results into the scoring network to generate a response scoring result.

[0011] A comparison and verification module is used to read the timing control data of the circuit breaker. The timing control data has a mapping relationship with the timing data monitoring result. A mapping comparison and verification is performed according to the timing control data and the timing data monitoring result to establish an additional fault prediction result.

[0012] A joint analysis module is used to perform a joint response analysis based on the protection association and time series data monitoring results, and establish a joint response analysis result.

[0013] An early warning module is used to perform fault detection and early warning of the circuit breaker according to the response scoring result, the additional fault prediction result, and the joint response analysis result.

[0014] The present invention discloses a fault detection and early warning method and system for circuit breakers, including: reading the architecture information of the power grid network, obtaining the distribution of power equipment and circuit breakers, and establishing the protection association of the circuit breaker based on this information; constructing a fault scheme set of the power grid network, monitoring the data of the circuit breaker by simulating fault signals, and establishing a time series data monitoring result; establishing a calibration response parameter based on the fault scheme set, and using these parameters to construct a scoring network; inputting the time series data monitoring result into the scoring network to generate a response scoring result; reading the time series control data of the circuit breaker, mapping and comparing and verifying with the time series data monitoring result, and generating an additional fault prediction result; combining the protection association and the time series data monitoring result to perform a joint response analysis, and generating a joint response analysis result; comprehensively responding to the scoring result, the additional fault prediction result and the joint response analysis result, and performing fault detection and early warning on the circuit breaker. The fault detection and early warning method and system for circuit breakers disclosed by the present invention solve the technical problems of insufficient early warning sensitivity and delayed response time, and achieve the technical effect of improving the accuracy of detection and early warning and the response speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of a fault detection and early warning method for a circuit breaker according to the present invention;

[0016] Figure 2 The figure is a schematic diagram of the structure of the fault detection and early warning system for circuit breakers of the present invention.

[0017] Explanation of the reference numerals: network architecture acquisition module 11, simulation monitoring module 12, scoring definition module 13, response scoring module 14, comparison and verification module 15, joint analysis module 16, early warning module 17. DETAILED DESCRIPTION

[0018] The technical solution provided in the embodiments of the present invention is to solve the technical problems of insufficient warning sensitivity and delayed response time in the prior art. The overall idea adopted is as follows:

[0019] First, the network architecture of the power grid network is read, and the distribution of power equipment and circuit breakers is obtained based on the network architecture, and the protection association of the circuit breaker is established through the distribution of power equipment, the distribution of circuit breakers and the network architecture. Then, a fault scheme set of the power grid network is established, and the fault signal of the power grid network is simulated through the fault scheme set, and the data of the circuit breaker is monitored by the monitoring sensor to establish the time series data monitoring result. Then, a calibration response parameter is established based on the fault scheme set, and a scoring network is established with this parameter. Then, the time series data monitoring result is input into the scoring network to generate a response scoring result. Then, the timing control data of the circuit breaker is read, and the timing control data has a mapping relationship with the timing data monitoring result. The mapping comparison verification is performed according to the timing control data and the timing data monitoring result, and the additional fault prediction result is established. Finally, a joint response analysis is performed according to the protection association and the timing data monitoring result, and a joint response analysis result is established; the circuit breaker fault detection and early warning is performed based on the comprehensive response scoring result, the additional fault prediction result and the joint response analysis result.

[0020] The above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods of the specification to better understand the above technical solution. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments used only to explain the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In addition, it should be noted that, for the convenience of description, only the parts related to the present invention are shown in the drawings, rather than all of them.

[0021] Embodiment 1: Figure 1 The present invention is a flow chart of a fault detection and early warning method for a circuit breaker, wherein the method comprises:

[0022] The network architecture of the power grid network is read, the power equipment distribution and the circuit breaker distribution are obtained based on the network architecture, and the protection association of the circuit breaker is established through the power equipment distribution, the circuit breaker distribution and the network architecture.

[0023] Optionally, the network architecture of the power grid network refers to the network topology of the target power grid, which reflects all the power equipment, circuit breakers, connection relationships and distribution locations contained in the target power grid. Specifically, first, the system database or distribution management system (DMS) of the interactive power grid obtains the network architecture information of the power grid. Among them, the network architecture includes the connection relationship and topological structure between substations, transmission lines, loads, generators, circuit breakers and other equipment. Then, based on the network architecture information, the distribution information of various types of power equipment in the power grid is extracted. Including the location of the substation, the connection point of the generator, the location of the load, etc. Next, in the power grid, the distribution information of the circuit breakers equipped on each node and line is obtained, including the location, control range, model, circuit breaker capacity, etc. of the circuit breaker.

[0024] Specifically, establishing a protection association for a circuit breaker refers to determining the scope or power equipment to be protected by the circuit breaker. Exemplary includes: determining the protection requirements of each device and line based on the type, capacity and connection of the power equipment. This includes overcurrent protection, short circuit protection, ground fault protection, etc.; determining the scope of equipment protected by each circuit breaker by analyzing the distribution of power equipment and circuit breaker distribution information. For example, a circuit breaker may protect a specific line, substation or load; determining the protection hierarchy relationship of each circuit breaker and the coordination relationship between different circuit breakers based on the network architecture and equipment distribution information, including the coordination of selective protection and reliability protection.

[0025] A fault scenario set for the power grid network is established, fault signal simulation of the power grid network is performed through the fault scenario set, data monitoring of the circuit breaker is performed through monitoring sensors, and time series data monitoring results are established.

[0026] Optionally, a fault scenario set is established. First, various possible fault types are defined, such as short circuit faults, ground faults, overload faults, disconnection faults, etc. Each fault type should include detailed information such as the nature of the fault, the location of occurrence, and the scope of fault impact. Then, the fault history records of the power grid network are obtained, including the local fault history records of the target power grid and the same-source fault history records of other similar power grids. Next, according to the defined fault types, cluster analysis is performed on the acquired fault history records to obtain clusters of multiple categories of faults, each of which contains one category of faults. Furthermore, typical fault scenarios are extracted from the above-mentioned clusters of multiple categories of faults and stored in the fault scenario set.

[0027] Optionally, typical fault scenarios are extracted, including random extraction or asymmetric extraction based on frequency of occurrence. Random selection is to randomly select several scenarios from the set of fault scenarios. Ensure that the selected fault types and location distributions are representative so as to cover different fault scenarios. Asymmetric extraction based on frequency of occurrence requires first analyzing the fault frequency, statistically analyzing the frequency of occurrence of different types of faults in historical fault data, and the distribution of faults under different locations and conditions. Then, based on the frequency of fault occurrence, weight the fault scenarios. High-frequency faults are assigned higher weights to ensure that these faults receive more attention. Finally, based on the weighted results, fault scenarios are selected asymmetrically to prioritize the extraction of fault types and scenarios with higher frequencies, so as to improve test efficiency and ensure that high-risk areas and common problems are tested in focus.

[0028] Specifically, to simulate the fault signal, first build a power grid network model on the power grid simulation platform, including detailed information of all equipment and lines. Then, according to the established fault scenario set, inject the corresponding fault signal into the simulation environment. This includes simulating circuit breaker tripping, voltage and current anomalies, etc. Next, simulate the propagation of the fault signal in the power grid and analyze the impact of the fault on the power grid system, including current, voltage fluctuations and circuit breaker action.

[0029] Specifically, multiple monitoring sensors arranged at key nodes and equipment in the power grid are obtained, including current sensors, voltage sensors, circuit breaker status sensors, etc. Then, according to the layout positions of multiple monitoring sensors, the key data such as the circuit breaker's action status, fault current, voltage waveform, etc. in the power grid network model corresponding to the power grid real-time monitoring simulation process are obtained to obtain the time series data monitoring results.

[0030] Through the above steps, the fault conditions in the power grid can be fully simulated and analyzed, providing a basic basis for optimizing the power grid protection strategy and improving the stability and reliability of the system.

[0031] Calibrated response parameters are established based on the fault scenario set, and a scoring network is established using the calibrated response parameters.

[0032] Optionally, the response parameters include: fault detection time, i.e., the time it takes for the system to detect a fault and respond; protection action time, i.e., the action time of protection devices such as circuit breakers; fault isolation time, i.e., the time it takes to isolate the fault area and restore normal power supply; recovery time, i.e., the time it takes for the system to fully recover to a normal state; fault impact scope, i.e., the scope of areas and equipment affected by the fault; and post-recovery stability, i.e., the stability and reliability of the system after recovery.

[0033] Specifically, the calibration response parameters are the benchmark for performance evaluation. The calibration response parameters are established by collecting historical data of the calibration response parameters based on historical fault data and simulation test results. Then, the collected data is statistically analyzed to determine the statistical characteristics such as the mean value and standard deviation of each indicator. Then, based on the statistical characteristics, the calibration values ​​of each response parameter are set.

[0034] Optionally, establishing calibrated response parameters also includes obtaining response control constraints of the target power grid, and extracting corresponding constraint data as calibrated values ​​of various response parameters, and outputting them as calibrated influence parameters.

[0035] Specifically, a scoring network is established. First, according to the response evaluation system or rules of the target power grid, a scoring standard based on the calibrated response parameters is formulated. For example, detection time, action time, recovery time, etc. are used as indicators, and different score ranges are set for each indicator, and weights are assigned according to the importance of different response parameters. Key indicators may have higher weights to highlight their importance. Then, based on the parameter meanings and unit magnitudes of multiple calibrated response parameters, a scoring function is designed to score according to the degree of deviation between the actual response parameters and the calibrated values. The smaller the deviation, the higher the score; the larger the deviation, the lower the score. Finally, the scoring function is used as the computing architecture of the scoring network, and the input and output interfaces are configured to ensure that fault response data can be received and the scoring results can be output.

[0036] The above method steps, by establishing calibration response parameters and scoring networks, can systematically evaluate the fault response capability of the power grid network, identify weak links in the system, and guide system optimization and improvement to improve the reliability and stability of the power grid.

[0037] The time series data monitoring result is input into the scoring network to generate a response scoring result.

[0038] In some embodiments, inputting the time series data monitoring result into the scoring network to generate a response scoring result further includes:

[0039] Calling a mapping comparison subnetwork, which is a processing subnetwork of the scoring network and stores calibration response parameters, using the mapping comparison subnetwork to perform deviation comparison of the time series data monitoring results to establish a first scoring result; calling a comprehensive scoring subnetwork, which is a processing subnetwork of the scoring network and includes a response accuracy score, a response time score, a decision hazard score, a weighted feature score, and a risk change score, using the comprehensive scoring subnetwork to score and authenticate the time series data monitoring results to establish a second scoring result; synchronizing the first scoring result and the second scoring result to an integration channel to generate a response scoring result.

[0040] Specifically, the mapping comparison subnetwork is called to perform a preliminary scoring of the monitoring results and evaluate the degree of deviation from the expected results. The mapping comparison subnetwork is a processing subnetwork of the scoring network and stores calibration response parameters. It is used to perform deviation comparison of the time series data monitoring results and establish a first scoring result.

[0041] Specifically, the comprehensive scoring subnetwork is called to conduct in-depth analysis and evaluation of the monitoring results to generate a more comprehensive and accurate score. Among them, the comprehensive scoring subnetwork is another processing subnetwork of the scoring network, including multiple scoring modules such as response accuracy scoring, response time scoring, decision hazard scoring, weighted feature scoring, and risk change scoring. This subnetwork conducts comprehensive scoring and certification of the time series data monitoring results through the above-mentioned multiple scoring modules to establish a second scoring result.

[0042] Furthermore, the first scoring result and the second scoring result are synchronized to the integration channel, and the scoring results of the two sub-networks are integrated to generate the final response scoring result. Among them, the first scoring result reflects the impact level of the fault, and the second scoring result reflects the response performance of multiple circuit breakers to the fault. By integrating the first scoring result and the second scoring result, the working and response capabilities of the circuit breaker reflected in the time series data monitoring results can be effectively evaluated, thereby providing high-confidence early warning information.

[0043] In some implementations, the comprehensive scoring subnetwork is as follows:

[0044] ;

[0045] in, Characterize the second scoring result, is the true number of cases, is the number of false negative cases, is the number of false positive cases, is the actual response time, The response time range is set. To assess the decision hazard level, The maximum possible value of the decision hazard, is the total number of features, including temperature features and current fluctuation features. is the index of the feature, For the The weight of the feature, For the The eigenvalues ​​of the features, In response to the risk changes of the system before and after, Characterize the maximum possible risk change, They are the weight coefficients of response accuracy score, response time score, decision hazard score, weighted feature score, and risk change score.

[0046] Furthermore, synchronizing the first scoring result and the second scoring result to the integration channel to generate a response scoring result further includes:

[0047] The external environmental characteristics of the power grid network are acquired, a balance coefficient of the integrated channel is established based on the external environmental characteristics and the fault solution set, and the integrated channel is initialized with the balance coefficient; the first scoring result and the second scoring result are synchronized to the initialized integrated channel to generate a response scoring result.

[0048] Specifically, the scoring results of the power grid network are integrated into a response scoring result. First, the external environmental characteristic data that affects the power grid network, such as climate conditions, load changes, equipment aging, etc., are collected. The data collection path includes sensors, monitoring systems, and historical records. In addition, the acquired environmental characteristic data is cleaned and standardized for subsequent use.

[0049] Specifically, the role of the balance coefficient is to incorporate the impact of external environmental characteristics into the scoring results and to correct the scoring benchmark so that the scoring conforms to the actual situation of the target power grid, thereby making the scoring more comprehensive and accurate.

[0050] Specifically, based on regression analysis, statistical models or expert experience, the relationship between external environmental characteristics and scoring results is analyzed, a mathematical model is established to calculate and set the balance coefficient, and based on the calculated balance coefficient, the integration channel is initialized to adapt to the adjustment of the scoring results by environmental factors. For example, if the external environmental characteristic data is lower than the standard environmental characteristic data, the balance coefficient is less than 1, and the more stringent the external environmental characteristic data is, the smaller the corresponding balance coefficient is.

[0051] Through the above-mentioned method steps, combined with the balance coefficient, the response score results are obtained to evaluate the actual fault response capability and performance of the power grid network, providing accurate data support for the maintenance, optimization and improvement of the power grid network.

[0052] The timing control data of the circuit breaker is read, the timing control data has a mapping relationship with the timing data monitoring result, and a mapping comparison and verification is performed according to the timing control data and the timing data monitoring result to establish an additional fault prediction result.

[0053] Specifically, the timing control data refers to the original control data transmitted to the circuit breaker, including the actions to be executed, control signals, status information, operating parameters, etc. The timing data monitoring results can be considered as the actual execution results of the circuit breaker. Due to conditions such as signal transmission data delay, there may be differences between the timing control data and the timing data monitoring results. Therefore, it is necessary to compare and verify based on the mapping relationship between the two to determine whether there are abnormalities or failures in the transmission and execution process of the control data.

[0054] Specifically, a mapping comparison verification is performed based on the timing control data and the timing data monitoring results to check the consistency between the two. For example, if at a certain time point, the control signal of the circuit breaker indicates that it should be closed, but the monitoring result shows that it is still in the open state, there is a fault in the transmission, decoding, and execution of the control signal.

[0055] Additional fault prediction results can be established through mapping comparison and verification, which helps to further determine the link where the fault occurs and identify possible faults, so as to provide early warning and disposal in a timely manner.

[0056] A joint response analysis is performed based on the protection association and time series data monitoring results to establish a joint response analysis result.

[0057] In some embodiments, performing joint response analysis according to the protection association and time series data monitoring results and establishing a joint response analysis result further includes:

[0058] The association matrix of the circuit breaker is established according to the protection association and the fault scheme set; a joint response analysis is performed through the association matrix and the time series data monitoring results, and the analysis formula is as follows:

[0059] ;

[0060] in, To analyze the results of the joint response, Characterizing Circuit Breakers and circuit breakers The correlation matrix of Indicates no response relationship. Indicates that there is a response relationship. Characterize the time matching function, , is a time scale constant.

[0061] Specifically, first, a circuit breaker association matrix is ​​established based on the protection association and fault scheme set. This matrix describes the association relationship between different circuit breakers, and joint response analysis can be performed through the association matrix and time series data monitoring results.

[0062] Optionally, a correlation matrix of the circuit breaker is established based on the connectivity and covariance between the circuit breaker and the power grid equipment to provide more accurate response relationship information. Specifically, if the state change of a circuit breaker is highly correlated with the state change of a specific power grid equipment, then their covariance is large, and conversely, if the covariance is small, then their response relationship is weak.

[0063] The above process can effectively evaluate the response performance of the circuit breaker and provide useful feedback information. At the same time, the introduced correlation matrix and time matching function are suitable for processing complex correlation relationships and time dependencies, improving the accuracy of response analysis.

[0064] A fault detection and early warning of the circuit breaker is performed according to the response scoring result, the additional fault prediction result, and the joint response analysis result.

[0065] Specifically, the response scoring result is used to determine the failure probability or failure confidence of the circuit breaker, the additional fault prediction result is used to determine the fault location or fault link of the circuit breaker, and the joint response analysis result determines the predicted fault impact range of the circuit breaker.

[0066] By combining the above three results, circuit breaker fault detection and early warning can be carried out more comprehensively and accurately, and a basis and direction can be provided for relevant technical personnel to discover and deal with problems in advance, which in turn helps to prevent the occurrence of faults and improve the reliability and safety of the power grid.

[0067] Furthermore, the method further comprises:

[0068] The fault scheme set is identified and sorted to establish an identification and sorting result; continuous trigger response evaluation of the same type of faults is performed based on the identification and sorting result to establish a sensitive response result of the same type of faults; and fault detection and early warning of the circuit breaker is performed based on the sensitive response result of the same type of faults.

[0069] Specifically, the fault solutions are first sorted. The basis for sorting can be factors such as the time of occurrence, severity, frequency of occurrence, and scope of impact of the fault. Preferably, identification and sorting are performed based on the time of occurrence of the fault. Then, the same type of faults are continuously triggered and responded to according to the sorting results. Specifically, if the same type of fault occurs continuously, and the number of consecutive occurrences or the duration are large, the sensitive response of this type of fault is high, and fault warning needs to be given priority. The above steps help to more effectively identify and handle the most common faults.

[0070] In addition, the method further comprises:

[0071] An early warning level trigger evaluation is performed based on the response scoring results, additional fault prediction results, and joint response analysis results, and an early warning result with an early warning level identifier is generated; a feedback verification window is established based on the early warning level identifier, and maintenance management is performed through the feedback verification window and the early warning result.

[0072] Specifically, the emergency response plan set of the target power grid is obtained, and a response matrix is ​​constructed. Then, the emergency response plan of the corresponding level is called in the response matrix according to the response scoring results, additional fault prediction results, and joint response analysis results. Among them, the emergency response plan set includes fault handling strategies of different levels to deal with various possible fault situations.

[0073] Exemplarily, in the response matrix, each row represents a fault type, each column represents a warning level, and each cell corresponds to an emergency response plan.

[0074] Specifically, a feedback verification window is established according to the warning level identification to collect and analyze the feedback information of fault handling to verify the accuracy and effectiveness of the warning results. Among them, the feedback verification window is used to obtain the monitoring data of the actual operation of the target power grid during the corresponding time period in the warning result. By comparing the monitoring data obtained in the feedback verification window with the warning result, the accuracy of the warning result can be verified, and the points with errors can be identified for feedback optimization.

[0075] In summary, the fault detection and early warning method for circuit breaker provided by the present invention has the following technical effects:

[0076] By reading the architecture information of the power grid network, the distribution of power equipment and circuit breakers is obtained, and the protection association of the circuit breaker is established based on this information; the fault scheme set of the power grid network is constructed, the data of the circuit breaker is monitored by simulating fault signals, and the time series data monitoring results are established; the calibration response parameters are established based on the fault scheme set, and these parameters are used to build a scoring network; the time series data monitoring results are input into the scoring network to generate a response scoring result; the time series control data of the circuit breaker is read, and the mapping comparison and verification with the time series data monitoring results are performed to generate additional fault prediction results; the protection association and the time series data monitoring results are combined for joint response analysis to generate joint response analysis results; the response scoring results, additional fault prediction results and joint response analysis results are combined to perform fault detection and early warning on the circuit breaker. Thus, the technical effect of improving the accuracy of detection and early warning and the response speed is achieved.

[0077] Embodiment 2

[0078] Figure 2 Schematic diagram of the structure of the fault detection and early warning system for circuit breakers of the present invention. Figure 1 The flow chart of the fault detection and early warning method for circuit breaker of the present invention can be shown as follows: Figure 2 The structure shown is implemented.

[0079] Based on the same concept as the fault detection and early warning method for a circuit breaker in the above embodiment, the present invention also provides a fault detection and early warning system for a circuit breaker, comprising:

[0080] The network architecture acquisition module 11 is used to read the network architecture of the power grid network, acquire the power equipment distribution and circuit breaker distribution based on the network architecture, and establish the protection association of the circuit breaker through the power equipment distribution, circuit breaker distribution and network architecture.

[0081] The simulation monitoring module 12 is used to establish a fault scheme set for the power grid network, simulate the fault signal of the power grid network through the fault scheme set, monitor the data of the circuit breaker through the monitoring sensor, and establish the time series data monitoring result.

[0082] The scoring definition module 13 is used to establish calibration response parameters based on the fault solution set, and to establish a scoring network with the calibration response parameters.

[0083] The response scoring module 14 is used to input the time series data monitoring result into the scoring network to generate a response scoring result.

[0084] The comparison and verification module 15 is used to read the timing control data of the circuit breaker. The timing control data has a mapping relationship with the timing data monitoring result. The mapping comparison and verification is performed according to the timing control data and the timing data monitoring result to establish an additional fault prediction result.

[0085] The joint analysis module 16 is used to perform a joint response analysis based on the protection association and time series data monitoring results, and establish a joint response analysis result.

[0086] The early warning module 17 is used to perform fault detection and early warning of the circuit breaker according to the response scoring result, the additional fault prediction result, and the joint response analysis result.

[0087] Among them, the response scoring module 14 includes:

[0088] The first scoring unit is used to call a mapping comparison subnetwork, which is a processing subnetwork of the scoring network and stores calibration response parameters. The mapping comparison subnetwork is used to perform deviation comparison of time series data monitoring results to establish a first scoring result.

[0089] The second scoring unit is used to call the comprehensive scoring subnetwork, which is the processing subnetwork of the scoring network, and the comprehensive scoring subnetwork includes a response accuracy score, a response time score, a decision hazard score, a weighted feature score, and a risk change score. The time series data monitoring result is scored and authenticated by the comprehensive scoring subnetwork to establish a second scoring result.

[0090] The integrated scoring unit is used to synchronize the first scoring result and the second scoring result to the integrated channel to generate a response scoring result.

[0091] In some embodiments, the integrated scoring unit in the response scoring module 14 includes:

[0092] The acquisition unit is used to acquire external environmental characteristics of the power grid network, establish a balance coefficient of the integrated channel based on the external environmental characteristics and the fault solution set, and initialize the integrated channel with the balance coefficient.

[0093] The synchronization and generation unit is used to synchronize the first scoring result and the second scoring result to the initialized integration channel to generate a response scoring result.

[0094] In some implementations, the comprehensive scoring subnetwork is as follows:

[0095] .

[0096] in, Characterize the second scoring result, is the true number of cases, is the number of false negative cases, is the number of false positive cases, is the actual response time, The response time range is set. To assess the decision hazard level, The maximum possible value of the decision hazard, is the total number of features, including temperature features and current fluctuation features. is the index of the feature, For the The weight of the feature, For the The eigenvalues ​​of the features, In response to the risk changes of the system before and after, Characterize the maximum possible risk change, They are the weight coefficients of response accuracy score, response time score, decision hazard score, weighted feature score, and risk change score.

[0097] In some embodiments, the joint analysis module 16 includes:

[0098] The circuit breaker association matrix establishing unit is used to establish the circuit breaker association matrix according to the protection association and fault scheme set.

[0099] The joint response analysis unit is used to perform joint response analysis based on the correlation matrix and the time series data monitoring results. The analysis formula is as follows:

[0100] .

[0101] in, To analyze the results of the joint response, Characterizing Circuit Breakers and circuit breakers The correlation matrix of Indicates no response relationship. Indicates that there is a response relationship. Characterize the time matching function, , is a time scale constant.

[0102] In some embodiments, the system further comprises:

[0103] The fault solution set identification and sorting unit is used to identify and sort the fault solution set and establish an identification and sorting result.

[0104] The continuous trigger response evaluation unit is used to perform continuous trigger response evaluation of the same type of faults according to the identification and sorting results, and establish sensitive response results of the same type of faults.

[0105] The fault detection and early warning unit is used to perform fault detection and early warning of the circuit breaker according to the sensitive response results of the same type of faults.

[0106] In some embodiments, the system further comprises:

[0107] The warning level evaluation unit is used to perform warning level trigger evaluation based on the response scoring results, additional fault prediction results, and joint response analysis results, and generate a warning result with a warning level identifier.

[0108] A feedback management unit is used to establish a feedback verification window according to the warning level identifier, and perform maintenance management through the feedback verification window and the warning result.

[0109] It should be understood that the embodiments mentioned in this specification focus on their differences from other embodiments. The specific embodiments in the aforementioned embodiment 1 are also applicable to the fault detection and early warning system for circuit breaker described in embodiment 2. For the sake of brevity of the specification, no further elaboration is given here.

[0110] It should be understood that the embodiments disclosed in the present invention and the above description can enable those skilled in the art to use the present invention to implement the present invention. At the same time, the present invention is not limited to the above-mentioned embodiments. It should be understood that those skilled in the art can still modify the technical solutions recorded in the above-mentioned embodiments, or replace some of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A fault detection and early warning method for a circuit breaker, characterized in that: The method comprises: Reading the network architecture of the power grid network, acquiring the power equipment distribution and the circuit breaker distribution based on the network architecture, and establishing the protection association of the circuit breaker through the power equipment distribution, the circuit breaker distribution and the network architecture; Establishing a fault scenario set for the power grid network, simulating fault signals of the power grid network through the fault scenario set, monitoring data of the circuit breaker through monitoring sensors, and establishing time series data monitoring results; Establishing calibration response parameters based on the fault scenario set, and establishing a scoring network with the calibration response parameters; Inputting the time series data monitoring result into the scoring network to generate a response scoring result; Reading the timing control data of the circuit breaker, wherein the timing control data has a mapping relationship with the timing data monitoring result, performing a mapping comparison and verification based on the timing control data and the timing data monitoring result, and establishing an additional fault prediction result; Perform joint response analysis based on the protection association and time series data monitoring results, and establish joint response analysis results; Perform fault detection and early warning of the circuit breaker according to the response scoring result, the additional fault prediction result, and the joint response analysis result; The step of inputting the time series data monitoring result into the scoring network to generate a response scoring result further includes: Calling a mapping comparison subnetwork, wherein the mapping comparison subnetwork is a processing subnetwork of the scoring network and the mapping comparison subnetwork stores a calibration response parameter, and using the mapping comparison subnetwork to perform a deviation comparison of the time series data monitoring result to establish a first scoring result; Calling a comprehensive scoring subnetwork, the comprehensive scoring subnetwork is a processing subnetwork of the scoring network, and the comprehensive scoring subnetwork includes a response accuracy score, a response time score, a decision hazard score, a weighted feature score, and a risk change score, and using the comprehensive scoring subnetwork to score and authenticate the time series data monitoring result to establish a second scoring result; Synchronize the first scoring result and the second scoring result to the integration channel to generate a response scoring result; Among them, the comprehensive scoring sub-network is as follows: ； in, Characterize the second scoring result, is the true number of cases, is the number of false negative cases, is the number of false positive cases, is the actual response time, For the set response time range, To assess the decision hazard level, The maximum possible value of the decision hazard, is the total number of features, including temperature features, current fluctuation features is the index of the feature, For the The weight of the feature, For the The eigenvalues ​​of the features, In response to the risk changes of the system before and after, Characterize the maximum possible risk change, , , , , They are the weight coefficients of response accuracy score, response time score, decision hazard score, weighted feature score, and risk change score.

2. The fault detection and early warning method for circuit breaker according to claim 1, characterized in that: The step of synchronizing the first scoring result and the second scoring result to the integration channel to generate a response scoring result further includes: Acquire external environmental characteristics of the power grid network, establish a balance coefficient of the integration channel based on the external environmental characteristics and the fault solution set, and initialize the integration channel with the balance coefficient; The first scoring result and the second scoring result are synchronized to the initialized integration channel to generate a response scoring result.

3. The fault detection and early warning method for circuit breaker according to claim 1, characterized in that: The performing of joint response analysis according to the protection association and time series data monitoring results and establishing a joint response analysis result also includes: Establishing a circuit breaker association matrix according to the protection association and fault scheme set; The joint response analysis is performed through the correlation matrix and the time series data monitoring results. The analysis formula is as follows: ； in, To analyze the results of the joint response, Characterizing Circuit Breakers and circuit breakers The correlation matrix of Indicates no response relationship. Indicates that there is a response relationship. Characterize the time matching function, , is a time scale constant.

4. The fault detection and early warning method for circuit breaker according to claim 1, characterized in that: The method further comprises: Identify and sort the fault solution set, and establish an identification and sorting result; Conduct continuous trigger response evaluation for the same type of faults based on the identification and sorting results, and establish sensitive response results for the same type of faults; A fault detection and early warning of the circuit breaker is performed according to the sensitive response results of the same type of faults.

5. The fault detection and early warning method for circuit breaker according to claim 1, characterized in that: The method further comprises: Perform warning level trigger evaluation based on response scoring results, additional fault prediction results, and joint response analysis results, and generate warning results with warning level identification; A feedback verification window is established according to the warning level identifier, and maintenance management is performed through the feedback verification window and the warning result.

6. A fault detection and early warning system for a circuit breaker, characterized in that: The system is used to implement the fault detection and early warning method for a circuit breaker according to any one of claims 1 to 5, and the system includes: A network architecture acquisition module, the network architecture acquisition module is used to read the network architecture of the power grid network, acquire the power equipment distribution and the circuit breaker distribution based on the network architecture, and establish a protection association of the circuit breaker through the power equipment distribution, the circuit breaker distribution and the network architecture; A simulation monitoring module, which is used to establish a fault scheme set for the power grid network, simulate the fault signal of the power grid network through the fault scheme set, monitor the data of the circuit breaker through the monitoring sensor, and establish a time series data monitoring result; A scoring definition module, the scoring definition module is used to establish a calibration response parameter based on the fault solution set, and establish a scoring network with the calibration response parameter; A response scoring module, the response scoring module is used to input the time series data monitoring result into the scoring network to generate a response scoring result; A comparison and verification module, wherein the comparison and verification module is used to read the timing control data of the circuit breaker, wherein the timing control data and the timing data monitoring result have a mapping relationship, and a mapping comparison and verification is performed according to the timing control data and the timing data monitoring result to establish an additional fault prediction result; A joint analysis module, the joint analysis module is used to perform a joint response analysis based on the protection association and time series data monitoring results, and establish a joint response analysis result; An early warning module is used to perform fault detection and early warning of the circuit breaker according to the response scoring result, the additional fault prediction result, and the joint response analysis result.

Images