Current transformer fault diagnosis system
By designing the current transformer fault diagnosis system, using abnormal detection algorithms to analyze false positive faults and missed faults, it solves the problem that existing systems are difficult to accurately analyze faults, and achieves efficient and accurate fault handling, reducing maintenance costs and production line downtime.
Patent Information
- Application Number
- CN202510326718.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-19
- Publication Date
- 2025-06-06
AI Technical Summary
The existing current transformer fault diagnosis system is difficult to accurately analyze false alarm faults and missed faults, resulting in high maintenance costs, long downtime of production line, and affecting the stability of the equipment.
A current transformer fault diagnosis system is designed, including a data analysis unit, a detection and judgment unit, a fault diagnosis unit, a fault assessment unit and a measure formulation unit. By obtaining current data and historical fault data in real time, using abnormal detection algorithms to analyze false positive faults and missed faults, and improving the efficiency and accuracy of fault handling through fault evaluation and measure formulation units.
The system can accurately identify false alarm faults and missed faults, reduce the frequency of false alarm faults, improve the efficiency and accuracy of fault handling, reduce maintenance costs and production line downtime, ensure the normal operation of the production system, and improve the reliability and stability of equipment.
Smart Images
Figure CN120103248A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of fault diagnosis, and in particular to a current transformer fault diagnosis system. Background Art
[0002] The current transformer fault diagnosis system is a device used to detect and diagnose problems or faults in current transformers (CT). Current transformers (CT) are devices used to measure current in circuits and are usually used to monitor current in power equipment. Current transformer (CT) fault diagnosis aims to improve the reliability and safety of power equipment. By real-time monitoring and diagnosis of the status of current transformers (CT), potential fault problems can be discovered and solved in a timely manner. When the circuit or equipment connected to the current transformer (CT) is overloaded and exceeds its rated current range, the current output of the current transformer (CT) will suddenly increase. High or low, due to the sudden increase or decrease in the current output by the current transformer (CT), the current transformer (CT) has a bad circuit fault phenomenon. When the current transformer (CT) has a bad circuit fault, it is impossible to accurately analyze the existence of false alarm faults and missed alarm faults in the current transformer (CT). False alarm faults increase maintenance costs and production line downtime. At the same time, missed alarm faults affect the normal operation of the current transformer (CT) and reduce the stability of the equipment. In order to avoid false alarm faults that increase maintenance costs and missed alarm faults that reduce equipment stability, we provide a current transformer fault diagnosis system. Summary of the invention
[0003] The object of the present invention is to provide a current transformer fault diagnosis system to solve the problems raised in the above background technology.
[0004] To achieve the above object, the present invention provides a current transformer fault diagnosis system, comprising a data analysis unit, a detection and judgment unit, a fault diagnosis unit, a fault assessment unit, and a measure formulation unit; The data analysis unit is used to obtain the current data and historical fault data in the current transformer in real time and analyze the current trend change and false alarm fault and missed alarm fault of the obtained data; The detection and judgment unit is used to receive the current trend change data analyzed in the data analysis unit and detect the increase or decrease of the current data through the current trend change data; The fault diagnosis unit is used to receive the data in the detection and judgment unit to perform fault diagnosis of the circuit failure, and transmit the diagnosed circuit failure fault data to the data analysis unit. The data analysis unit uses an abnormality detection algorithm to perform abnormality analysis of false alarm faults and missed alarm faults based on the diagnosed circuit failure fault data; The implementation steps of using anomaly detection algorithm to analyze false positive and false negative faults are as follows: Step 1: First collect the fault data of the circuit to be diagnosed and processed historical fault data , and then the diagnosed circuit fault data and processed historical fault data Aggregate into abnormal data sets , and identify abnormal data sets Outliers in or abnormal point ; Step 2: Abnormal Dataset Include abnormal sample points, and the abnormal sample points are represented as , ,when At this time Expressed as , Refers to the abnormal sample points, when At this time Expressed as , Refers to the Abnormal sample points, Represents the number of abnormal sample points, and uses abnormal sample points Calculate local density , local density Indicates abnormal sample points Neighborhood Density of internal abnormal sample points, local density The specific algorithm formula is: ; in, Indicates abnormal sample points to The distance between the nearest abnormal sample points, Indicates this The average value of the distances, is a constant, Represents the uth nearest neighbor abnormal sample point; Step 3: Reuse sample points Calculate the local outlier factor , local anomaly factor Indicates abnormal sample points The degree of abnormality, local abnormality factor The specific algorithm formula is: ; in, Indicates abnormal sample points Neighborhood of represents the number of sample points in the neighborhood, Represents the neighborhood Each abnormal sample point in Perform a sum operation, Indicates abnormal sample points The local density is a relative density concept, indicating The density of abnormal sample points in the area where it is located, Indicates abnormal sample points in the neighborhood The local density of Step 4: Use the set local anomaly factor The local anomaly factor calculated with Conduct analysis and judgment, specifically analyze and judge the situation: Case ①: When the local abnormal factor is set Less than the calculated local anomaly factor , indicating that there is a false alarm fault, the command data of the false alarm fault will be sent to the outside world; Case ②: When the local abnormal factor is set Greater than the calculated local anomaly factor , indicating that there is an underreporting fault, the command data for analyzing the underreporting fault is transmitted to the fault assessment unit; The fault assessment unit is used to receive the command data of the data analysis unit for analyzing the existence of missed faults and to perform fault assessment based on the acquired missed fault data; The measure formulation unit is used to receive the fault data diagnosed in the fault diagnosis unit and obtain the historical maintenance plan corresponding to the fault feature data with the highest similarity in the fault library, and then formulate improvement measures according to the corresponding historical maintenance plan.
[0005] As a further improvement of the technical solution, the data analysis unit includes a processing analysis module and an abnormality analysis module; The processing and analysis module uses sensors to obtain current data and historical fault data in the current transformer in real time, obtains historical data, and then analyzes current trend changes based on the processed real-time current data and historical current data; Historical data includes historical current data, voltage data, frequency data, temperature data, and power supply status data.
[0006] As a further improvement of the present technical solution, the detection and judgment unit is used to receive the current trend change data analyzed in the processing and analysis module, and detect the increase or decrease of the current data based on the analyzed current trend change data, and then use the set current change threshold data and the analyzed current trend change data to perform current abnormality detection and judgment.
[0007] As a further improvement of the technical solution, the specific abnormal detection and judgment situation in the detection and judgment unit is: Case ①: When the current change threshold data is set Less than the current trend change data analyzed , detect and analyze the current trend change data A sudden increase indicates an abnormality, and the abnormality detection command data is transmitted to the fault diagnosis unit; Case ②: When the current change threshold data is set Greater than the current trend change data analyzed , detect and analyze the current trend change data A sudden decrease indicates an abnormality, and the abnormality detection command data is transmitted to the fault diagnosis unit; Case ③: When the current change threshold data is set Equal to the analyzed current trend change data , indicating that there is no abnormality.
[0008] As a further improvement of the present technical solution, the fault diagnosis unit is used to receive abnormal command data detected in the detection and judgment unit, and the fault diagnosis unit obtains the processed historical fault data, processed historical data and processed real-time current data from the processing and analysis module, and uses a fault diagnosis algorithm to perform fault diagnosis of circuit failure based on the processed historical fault data, processed historical data and processed real-time current data.
[0009] As a further improvement of the present technical solution, the abnormality analysis module is used to receive the loop fault data diagnosed in the fault diagnosis unit and the historical fault data processed in the processing analysis module, and use an abnormality detection algorithm to perform abnormality analysis of false alarm faults and missed faults based on the diagnosed loop fault data and the processed historical fault data.
[0010] As a further improvement of the present technical solution, the fault assessment unit is used to receive command data for analyzing missed faults in the abnormal analysis module, and the fault assessment unit obtains the processed historical fault data from the processing and analysis module and the results of the abnormal analysis from the abnormal analysis module, and then performs fault assessment based on the processed historical fault data and the results of the abnormal analysis, and transmits the assessed fault data to the fault diagnosis unit. The fault diagnosis unit performs fault diagnosis based on the assessed fault data and the processed historical fault data, and transmits the diagnosed fault data to the measure formulation unit.
[0011] As a further improvement of the present technical solution, the measure formulation unit is used to receive the fault data diagnosed in the fault diagnosis unit, and perform fault feature analysis on the diagnosed fault data, and then use the analyzed fault feature data to perform similarity matching with the fault features in the fault library, and obtain the historical maintenance plan corresponding to the fault feature data with the highest similarity in the fault library, and then formulate improvement measures based on the analyzed fault feature data and the corresponding historical maintenance plan.
[0012] Compared with the prior art, the present invention has the following beneficial effects: 1. In the current transformer fault diagnosis system, the abnormal analysis module performs abnormal analysis of false alarm faults and missed faults based on the circuit fault data diagnosed in the fault diagnosis unit and the historical fault data processed in the processing analysis module. It can identify the characteristics of false alarm faults and missed faults, reduce the frequency of false alarm faults, improve the efficiency and accuracy of fault handling, thereby reducing maintenance costs and production line downtime. At the same time, these potential missed faults are analyzed and corresponding improvement measures are taken to ensure the normal operation of the production system and improve the reliability and stability of the equipment.
[0013] 2. In the current transformer fault diagnosis system, the fault diagnosis unit receives abnormal command data detected in the detection and judgment unit, and the fault diagnosis unit obtains the processed historical fault data, processed historical data and processed real-time current data from the processing and analysis module, and performs fault diagnosis of poor circuit according to the data obtained in the detection and judgment unit. The use of processed real-time current data for fault diagnosis can achieve rapid response and timely detection of abnormal conditions. By combining historical fault data, historical data and real-time current data for comprehensive analysis, the fault of poor circuit can be accurately determined. Such comprehensive analysis can eliminate possibilities, identify the root cause of the fault in a targeted manner, and improve the accuracy of diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] Figure 1 is an overall block diagram of the present invention; Figure 2 It is a block diagram of the data analysis unit of the present invention.
[0015] The meaning of each number in the figure is: 1. Data analysis unit; 11. Processing and analysis module; 12. Abnormal analysis module; 2. Detection and judgment unit; 3. Fault diagnosis unit; 4. Fault assessment unit; 5. Measures formulation unit. DETAILED DESCRIPTION
[0016] The following will be combined with the accompanying drawings in the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0017] Example 1
[0018] The present invention provides a current transformer fault diagnosis system, please refer to Figure 1-Figure 2 , including a data analysis unit 1, a detection and judgment unit 2, a fault diagnosis unit 3, a fault assessment unit 4, and a measure formulation unit 5; The data analysis unit 1 is used to obtain the current data and historical fault data in the current transformer in real time and analyze the current trend change and false alarm faults and missed faults on the acquired data. The detection and judgment unit 2 is used to receive the current trend change data analyzed in the data analysis unit 1 and detect the increase or decrease of the current data through the current trend change data. The fault diagnosis unit 3 is used to receive the data in the detection and judgment unit 2 to perform fault diagnosis of poor circuit, and transmit the diagnosed poor circuit fault data to the data analysis unit 1. The data analysis unit 1 uses an abnormality detection algorithm to perform abnormal analysis of false alarm faults and missed faults based on the diagnosed poor circuit fault data. The fault assessment unit 4 is used to receive the command data for analyzing the existence of missed faults in the data analysis unit 1 and perform fault assessment based on the acquired missed fault data. The measure formulation unit 5 is used to receive the fault data diagnosed in the fault diagnosis unit 3 and obtain the historical maintenance plan corresponding to the fault feature data with the highest similarity in the fault library, and then formulate improvement measures based on the corresponding historical maintenance plan.
[0019] The following is a refinement of the above units, see Figure 1-Figure 2 ; The data analysis unit 1 includes a processing analysis module 11 and an abnormality analysis module 12; The processing and analysis module 11 uses sensors to obtain current data and historical fault data in the current transformer in real time, and also obtains historical data, and processes the obtained data. By processing the obtained data, errors in the obtained data can be reduced and the accuracy of the data can be improved. Then, the current trend change is analyzed based on the processed real-time current data and historical current data. By analyzing the trend change of the real-time current data and historical current data, abnormal changes in the current can be detected. When the current suddenly increases or decreases, possible problems or faults of the equipment can be discovered in time, and responsive maintenance measures can be taken to avoid losses caused by the fault; Historical data includes historical current data, voltage data, frequency data, temperature data, and power supply status data.
[0020] The detection and judgment unit 2 is used to receive the current trend change data analyzed in the processing and analysis module 11, and detect the increase or decrease of the current data according to the analyzed current trend change data, and then use the set current change threshold data and the analyzed current trend change data to perform current abnormality detection and judgment. The specific abnormality detection and judgment situation is: Case ①: When the current change threshold data is set Less than the current trend change data analyzed , detect and analyze the current trend change data A sudden increase indicates that an abnormality exists, and the abnormality detection command data is transmitted to the fault diagnosis unit 3; Case ②: When the current change threshold data is set Greater than the current trend change data analyzed , detect and analyze the current trend change data A sudden decrease indicates an abnormality, and the abnormality detection command data is transmitted to the fault diagnosis unit 3; Case ③: When the current change threshold data is set Equal to the analyzed current trend change data , indicating that there is no abnormality.
[0021] The fault diagnosis unit 3 is used to receive the abnormality command data detected in the detection and judgment unit 2. The fault diagnosis unit 3 obtains the processed historical fault data, the processed historical data and the processed real-time current data from the processing and analysis module 11, and uses the fault diagnosis algorithm to perform fault diagnosis of poor circuit according to the processed historical fault data, the processed historical data and the processed real-time current data. The use of the processed real-time current data for fault diagnosis can make the diagnosis process more real-time. Timely monitoring of the current condition of the equipment can quickly discover, diagnose and repair the fault when it occurs, thereby reducing downtime and production losses. At the same time, by diagnosing the processed historical fault data and the processed historical data, potential fault modes and trends can be identified, so as to perform preventive maintenance, timely discover and solve potential problems, reduce the incidence of equipment failures, and improve the reliability and stability of the equipment; The implementation steps of using fault diagnosis algorithm to diagnose circuit failure: Step 1: First collect and process historical fault data , processed historical data and processed real-time current data and from the processed historical fault data and processed historical data Extract features from the current waveform. , Voltage waveform characteristics , Temperature change characteristics , Equipment status characteristics , and then process the real-time current data Perform feature extraction to obtain the operating status of the current circuit and Features ; Processing historical data Including historical current data , voltage data , frequency data , Temperature data , power supply status data ; Step ②: Extract the features and running status and Features Integrate into data sets , according to the data set Determine the training set and test set The common ratio is 70% of the data as training set. , 30% of the data is used as a test set However, it can also be adjusted according to the amount of data and task requirements. Randomly divide into training sets and test set ; Step 3: Initialize a fault diagnosis model , using the training set Training the initialized fault diagnosis model , by recursively transforming the dataset Split into two subsets, and continue splitting on each subset until the stopping condition is reached. The process of splitting each subset is to select the optimal feature and segmentation points to achieve the optimal features Usually based on the data set The purity or impurity of each subset is then determined based on the optimal features in each subset. Building a complete fault diagnosis model ; Step ④: Process the real-time current data and processed historical fault data , processed historical data Input to the trained fault diagnosis model In the fault diagnosis model Diagnose the input data and diagnose the fault of the bad circuit, and finally obtain the diagnosed bad circuit fault data .
[0022] The abnormality analysis module 12 is used to receive the circuit fault data diagnosed in the fault diagnosis unit 3 and the historical fault data processed in the processing analysis module 11, and use the abnormality detection algorithm to perform abnormality analysis of false alarm faults and missed faults based on the diagnosed circuit fault data and the processed historical fault data. The abnormality analysis based on the processed historical fault data can help identify potential fault modes, thereby improving the fault analysis capability, timely discovering the possibility of potential faults, and helping to take preventive measures to avoid equipment interruption caused by faults, thereby improving equipment safety; The implementation steps of using the anomaly detection algorithm to analyze false alarm faults and missed alarm faults in the anomaly analysis module 12 are as follows: Step 1: First collect the fault data of the circuit to be diagnosed and processed historical fault data , and then the diagnosed circuit fault data and processed historical fault data Aggregate into abnormal data sets , and identify abnormal data sets Outliers in or abnormal point ; Step 2: Abnormal Dataset Include abnormal sample points, and the abnormal sample points are represented as , ,when At this time Expressed as , Refers to the abnormal sample points, when At this time Expressed as , Refers to the Abnormal sample points, Represents the number of abnormal sample points, and uses abnormal sample points Calculate local density , local density Indicates abnormal sample points Neighborhood Density of internal abnormal sample points, local density The specific algorithm formula is: ; in, Indicates abnormal sample points to The distance between the nearest abnormal sample points, Indicates this The average of the distances, is a constant, Represents the uth nearest neighbor abnormal sample point; Step 3: Reuse sample points Calculate the local outlier factor , local anomaly factor Indicates abnormal sample points The degree of abnormality, local abnormality factor The specific algorithm formula is: ; in, Indicates abnormal sample points Neighborhood of represents the number of sample points in the neighborhood, Represents the neighborhood Each abnormal sample point in Perform a sum operation, Indicates abnormal sample points The local density is a relative density concept, indicating The density of abnormal sample points in the area where it is located, Indicates abnormal sample points in the neighborhood The local density of Step 4: Use the set local anomaly factor The local anomaly factor calculated with Conduct analysis and judgment, specifically analyze and judge the situation: Case ①: When the local abnormal factor is set Less than the calculated local anomaly factor , indicating that there is a false alarm fault, the command data of the false alarm fault will be sent to the outside world; Case ②: When the local abnormal factor is set Greater than the calculated local anomaly factor , indicating that there is an underreporting fault, the command data for analyzing the underreporting fault is transmitted to the fault assessment unit 4; The fault assessment unit 4 is used to receive command data for analyzing missed faults in the abnormal analysis module 12. The fault assessment unit 4 obtains the processed historical fault data from the processing and analysis module 11 and the results of the abnormal analysis from the abnormal analysis module 12, and then evaluates the fault based on the processed historical fault data and the results of the abnormal analysis, and transmits the evaluated fault data to the fault diagnosis unit 3. The fault diagnosis unit 3 performs fault diagnosis based on the evaluated fault data and the processed historical fault data, and transmits the diagnosed fault data to the measure formulation unit 5. By evaluating the fault, potential faults that have not been detected can be identified, thereby improving the detection technology, improving the reliability of the equipment, and promptly discovering and resolving missed faults, which helps prevent potential system failures from causing production interruptions or safety problems.
[0023] The measure formulation unit 5 is used to receive the fault data diagnosed in the fault diagnosis unit 3, and perform fault feature analysis on the diagnosed fault data, and then use the analyzed fault feature data to perform similarity matching with the fault features in the fault library, and obtain the historical maintenance plan corresponding to the fault feature data with the highest similarity in the fault library, and then formulate improvement measures based on the analyzed fault feature data and the corresponding historical maintenance plan, so as to more accurately understand the root cause and solution of the fault, and the formulated improvement measures will be more targeted, which can effectively solve specific fault problems and reduce ineffective attempts and waste of resources.
[0024] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.
Claims
1. A current transformer fault diagnosis system, characterized in that: It includes a data analysis unit (1), a detection and judgment unit (2), a fault diagnosis unit (3), a fault assessment unit (4), and a measure formulation unit (5); The data analysis unit (1) is used to obtain the current data and historical fault data in the current transformer in real time and to analyze the current trend change and false alarm faults and missed alarm faults on the obtained data; The detection and judgment unit (2) is used to receive the current trend change data analyzed by the data analysis unit (1) and detect the increase or decrease of the current data through the current trend change data; The fault diagnosis unit (3) is used to receive the data in the detection and judgment unit (2) to perform fault diagnosis of a circuit failure, and transmit the diagnosed circuit failure fault data to the data analysis unit (1). The data analysis unit (1) uses an abnormality detection algorithm to perform abnormality analysis of false alarm faults and missed alarm faults based on the diagnosed circuit failure fault data; The implementation steps of using anomaly detection algorithm to analyze false positive and false negative faults are as follows: Step 1: First collect the fault data of the circuit to be diagnosed and processed historical fault data , and then the diagnosed circuit fault data and processed historical fault data Aggregate into abnormal data sets , and identify abnormal data sets Outliers in or abnormal point ; Step 2: Abnormal Dataset Include abnormal sample points, and the abnormal sample points are represented as , ,when At this time Expressed as , Refers to the abnormal sample points, when At this time Expressed as , Refers to the Abnormal sample points, Represents the number of abnormal sample points, and uses abnormal sample points Calculate local density , local density Indicates abnormal sample points Neighborhood Density of internal abnormal sample points, local density The specific algorithm formula is: ； in, Indicates abnormal sample points to The distance between the nearest abnormal sample points, Indicates this The average of the distances, is a constant, Represents the uth nearest neighbor abnormal sample point; Step 3: Reuse sample points Calculate the local outlier factor , local anomaly factor Indicates abnormal sample points The degree of abnormality, local abnormality factor The specific algorithm formula is: ； in, Indicates abnormal sample points Neighborhood of represents the number of sample points in the neighborhood, Represents the neighborhood Each abnormal sample point in Perform a sum operation, Indicates abnormal sample points The local density is a relative density concept, indicating The density of abnormal sample points in the area where it is located, Indicates abnormal sample points in the neighborhood The local density of Step 4: Use the set local anomaly factor The local anomaly factor calculated with Conduct analysis and judgment, specifically analyze and judge the situation: Case ①: When the local abnormal factor is set Less than the calculated local anomaly factor , indicating that there is a false alarm fault, the command data of the false alarm fault is sent to the outside world; Case ②: When the local abnormal factor is set Greater than the calculated local anomaly factor , indicating that there is an underreporting fault, the command data for analyzing the underreporting fault is transmitted to the fault assessment unit (4); The fault assessment unit (4) is used to receive command data for analyzing the existence of missed faults in the data analysis unit (1) and to perform fault assessment based on the acquired missed fault data; The measure formulation unit (5) is used to receive the fault data diagnosed by the fault diagnosis unit (3) and obtain the historical maintenance plan corresponding to the fault feature data with the highest similarity in the fault library, and then formulate improvement measures according to the corresponding historical maintenance plan.
2. The current transformer fault diagnosis system according to claim 1, characterized in that: The data analysis unit (1) comprises a processing analysis module (11) and an abnormality analysis module (12); The processing and analysis module (11) uses a sensor to obtain current data and historical fault data in the current transformer in real time, obtains historical data, and then analyzes current trend changes based on the processed real-time current data and historical current data; Historical data includes historical current data, voltage data, frequency data, temperature data, and power supply status data.
3. The current transformer fault diagnosis system according to claim 2, characterized in that: The detection and judgment unit (2) is used to receive the current trend change data analyzed in the processing analysis module (11), and detect the increase or decrease of the current data according to the analyzed current trend change data, and then use the set current change threshold data and the analyzed current trend change data to perform current abnormality detection and judgment.
4. The current transformer fault diagnosis system according to claim 3, characterized in that: Specific abnormal detection and judgment situation in the detection and judgment unit (2): Case ①: When the current change threshold data is set Less than the current trend change data analyzed , detect and analyze the current trend change data A sudden increase indicates an abnormality, and the abnormality detection command data is transmitted to the fault diagnosis unit (3); Case ②: When the current change threshold data is set Greater than the current trend change data analyzed , detect and analyze the current trend change data A sudden decrease indicates an abnormality, and the abnormality detection command data is transmitted to the fault diagnosis unit (3); Case ③: When the current change threshold data is set Equal to the analyzed current trend change data , indicating that there is no abnormality.
5. The current transformer fault diagnosis system according to claim 3, characterized in that: The fault diagnosis unit (3) is used to receive abnormality command data detected by the detection judgment unit (2), and the fault diagnosis unit (3) obtains processed historical fault data, processed historical data and processed real-time current data from the processing and analysis module (11), and uses a fault diagnosis algorithm to perform fault diagnosis of a circuit failure based on the processed historical fault data, processed historical data and processed real-time current data.
6. The current transformer fault diagnosis system according to claim 5, characterized in that: The abnormality analysis module (12) is used to receive the circuit fault data diagnosed in the fault diagnosis unit (3) and the historical fault data processed in the processing analysis module (11), and to perform abnormality analysis of false alarm faults and missed alarm faults based on the diagnosed circuit fault data and the processed historical fault data using an abnormality detection algorithm.
7. The current transformer fault diagnosis system according to claim 2, characterized in that: The fault assessment unit (4) is used to receive command data for analyzing the existence of missed faults in the abnormal analysis module (12), and the fault assessment unit (4) obtains the processed historical fault data from the processing and analysis module (11) and the result of the abnormal analysis from the abnormal analysis module (12), and then performs fault assessment based on the processed historical fault data and the result of the abnormal analysis, and transmits the assessed fault data to the fault diagnosis unit (3). The fault diagnosis unit (3) performs fault diagnosis based on the assessed fault data and the processed historical fault data, and transmits the diagnosed fault data to the measure formulation unit (5).
8. The current transformer fault diagnosis system according to claim 7, characterized in that: The measure formulation unit (5) is used to receive the fault data diagnosed in the fault diagnosis unit (3), and perform fault feature analysis on the diagnosed fault data, then use the analyzed fault feature data to perform similarity matching with the fault features in the fault library, and obtain the historical maintenance plan corresponding to the fault feature data with the highest similarity in the fault library, and then formulate improvement measures based on the analyzed fault feature data and the corresponding historical maintenance plan.