Power grid fault automatic diagnosis method and system based on big data analysis

Abstract

The invention discloses a power grid fault automatic diagnosis method and system based on big data analysis, and relates to the technical field of electrical variable measurement. The power grid fault automatic diagnosis method based on big data analysis comprises the following steps: current mutual inductance accuracy analysis; analyzing the voltage mutual inductance accuracy; influence adjustment; and power grid fault response evaluation. According to the method, a current mutual inductance fluctuation judgment value and a voltage mutual inductance fluctuation judgment value are obtained through a current mutual inductance fluctuation value and a voltage mutual inductance fluctuation value obtained through current mutual inductance accuracy analysis and voltage mutual inductance accuracy analysis respectively, and then whether current mutual inductance influence adjustment and voltage mutual inductance influence adjustment are carried out or not is judged; and finally, performing fault response analysis to obtain a power grid fault response evaluation value and judging whether fault response adjustment is performed or not, so that the effect of improving the accuracy of power grid fault automatic diagnosis based on big data analysis is achieved, and the problem of inaccurate data acquisition of power grid fault automatic diagnosis in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of measuring electrical variables, and in particular to a method and system for automatically diagnosing power grid faults based on big data analysis. Background Art

[0002] With the rapid development and continuous innovation of big data technology, its application scope in the field of power grid fault detection is expanding and deepening. Big data technology has demonstrated its powerful ability to quickly identify the existence of power grid faults and their specific locations by comprehensively and efficiently collecting, safely and stably storing, accurately and quickly processing, and deeply and meticulously analyzing the massive data generated in the power grid. Compared with traditional fault detection methods, this fault detection method based on big data has a series of advantages such as significant real-time performance, high accuracy, and excellent efficiency. It can monitor the operating status of the power grid in real time, and once an abnormality or fault is found, it can immediately issue an early warning and locate the fault, thereby greatly shortening the fault response time and reducing the impact of the fault on the operation of the power grid. At the same time, the fault detection method based on big data can also continuously optimize its own diagnostic model and improve the accuracy and reliability of diagnosis by analyzing and learning historical data. Therefore, this advanced fault detection method plays a vital role in improving the safety and reliability of power grid operation, and provides strong technical support for the sustainable development of the power industry.

[0003] Existing methods mainly use artificial intelligence and machine learning algorithms to analyze and recognize patterns in large amounts of power grid data to predict and diagnose possible faults.

[0004] For example, the invention patent application with publication number: CN115219840A discloses an automated fault diagnosis method and system based on a distribution network, including: step 1, establishing a fault center point based on historical equipment data and historical fault data; step 2, collecting synchronous phase data of the power equipment to generate equipment sample data, and finding the closest fault center point and sample fault state from the set of fault center points based on the equipment sample data; step 3, when the number of sample fault states corresponding to the equipment sample data exceeds a set threshold, determining that a current sample fault has occurred in the power equipment.

[0005] For example, the invention patent application with publication number: CN115061006A discloses a method for automatic fault diagnosis of complex distribution network based on traveling waves, which includes: obtaining traveling wave signals and power frequency signals on the distribution network; identifying the power frequency signals to determine whether a fault occurs on the line, if yes, proceeding to the next step, if not, ending the diagnosis; judging the fault phase and fault type of the traveling wave signals and the power frequency signals according to the fault characteristics; monitoring the instantaneous change points of the power frequency signals based on the wavelet analysis method to determine the fault moment; judging the fault interval based on the fault location matrix; and locating the fault point within the determined fault interval based on the double-end positioning principle.

[0006] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems: In the prior art, during the peak period of industrial production, when a transmission line fails, the load changes significantly, which may affect the operating status of equipment such as transformers and switches, causing inaccurate current mutual inductance and voltage mutual inductance data, and leading to inaccurate data acquisition for automatic diagnosis of power grid faults. Summary of the invention

[0007] The embodiments of the present application solve the problem of inaccurate data acquisition for automatic diagnosis of power grid faults in the prior art by providing a method and system for automatic diagnosis of power grid faults based on big data analysis, and achieve improved accuracy of automatic diagnosis of power grid faults based on big data analysis.

[0008] The embodiment of the present application provides a method for automatic diagnosis of power grid faults based on big data analysis, comprising the following steps: S1, obtaining current mutual inductance related data and performing current mutual inductance accuracy analysis to obtain a current mutual inductance fluctuation value, and obtaining a current mutual inductance fluctuation judgment value based on the current mutual inductance fluctuation value and a reference current mutual inductance fluctuation average value obtained from a database, wherein the current mutual inductance fluctuation value is used to reflect the degree of data fluctuation of the current transformer during the automatic diagnosis of power grid faults; S2, obtaining voltage mutual inductance related data and performing voltage mutual inductance accuracy analysis to obtain a voltage mutual inductance fluctuation value, and obtaining a current mutual inductance fluctuation judgment value based on the voltage mutual inductance fluctuation value and a reference voltage mutual inductance fluctuation average value obtained from a database. Voltage mutual inductance fluctuation judgment value, the voltage mutual inductance fluctuation value is used to reflect the data fluctuation degree of the voltage transformer during the automatic diagnosis of power grid faults; S3, based on the obtained current mutual inductance fluctuation judgment value and voltage mutual inductance fluctuation judgment value, determine whether to adjust the current mutual inductance influence and the voltage mutual inductance influence; S4, perform fault response analysis based on the obtained qualified current mutual inductance fluctuation value, qualified voltage mutual inductance fluctuation value and fault response delay time to obtain a power grid fault response evaluation value, and determine whether to adjust the fault response based on the power grid fault response evaluation value, the power grid fault response evaluation value is used to reflect the power grid fault response situation during the automatic diagnosis of power grid faults.

[0009] Furthermore, the current mutual inductance related data include the maximum current value, the minimum current value, the grid load change and the first output power change; the voltage mutual inductance related data include the maximum voltage value, the minimum voltage value and the second output power change; the first output power change represents the change of the current transformer output power during the automatic diagnosis of grid faults; the second output power change represents the change of the voltage transformer output power during the automatic diagnosis of grid faults.

[0010] Furthermore, the specific acquisition process of the current mutual inductance fluctuation judgment value is as follows: the current maximum value, the current minimum value and the preset grid current fluctuation maximum threshold obtained from the database are processed to obtain the current fluctuation compliance value; the current fluctuation compliance value is represented by the result of the ratio operation between the difference between the current maximum value and the current minimum value and the preset grid current fluctuation maximum threshold; the grid load change and the preset grid load change maximum threshold obtained from the database are processed to obtain the load fluctuation compliance value; the load fluctuation compliance value is represented by the result of the ratio operation between the grid load change and the preset grid load change maximum threshold; the first output power change and the preset current output power maximum threshold obtained from the database are processed to obtain the current mutual inductance output power compliance value; the current mutual inductance output power compliance value is represented by the result of the ratio operation between the first output power change and the preset current output power maximum threshold; the current fluctuation compliance value, the load fluctuation compliance value and the current mutual inductance output power compliance value are combined to obtain the current mutual inductance fluctuation value; the current mutual inductance fluctuation judgment value is obtained based on the current mutual inductance fluctuation value and the reference current mutual inductance fluctuation average value.

[0011] Furthermore, the specific acquisition process of the voltage mutual inductance fluctuation judgment value is as follows: the maximum voltage value, the minimum voltage value and the preset maximum threshold value of the grid voltage fluctuation obtained from the database are processed to obtain the voltage fluctuation compliance value; the voltage fluctuation compliance value is used to reflect the degree of compliance of the grid voltage fluctuation within the preset time period; the second output power change and the preset voltage output power maximum threshold value obtained from the database are processed to obtain the voltage mutual inductance output power compliance value; the voltage mutual inductance output power compliance value is used to reflect the compliance of the output power fluctuation of the voltage transformer within the preset time period; the voltage fluctuation compliance value and the voltage mutual inductance output power compliance value are combined for processing to obtain the voltage mutual inductance fluctuation value; the voltage mutual inductance fluctuation judgment value is obtained based on the voltage mutual inductance fluctuation value and the reference voltage mutual inductance fluctuation average value.

[0012] Furthermore, the specific process of judging whether to adjust the influence of current mutual inductance and voltage mutual inductance based on the acquired current mutual inductance fluctuation judgment value and voltage mutual inductance fluctuation judgment value is as follows: judging whether the current mutual inductance fluctuation judgment value and voltage mutual inductance fluctuation judgment value meet condition one; when the current mutual inductance fluctuation judgment value and voltage mutual inductance fluctuation judgment value meet condition one, directly obtaining the corresponding qualified current mutual inductance fluctuation value and qualified voltage mutual inductance fluctuation value; when the current mutual inductance fluctuation judgment value and voltage mutual inductance fluctuation judgment value do not meet condition one, performing current mutual inductance influence adjustment and voltage mutual inductance influence adjustment; condition one indicates that the current mutual inductance fluctuation judgment value and voltage mutual inductance fluctuation judgment value are both not greater than 1.

[0013] Furthermore, the specific process of adjusting the influence of current mutual inductance is as follows: QQ1, sending a prompt to the preset personnel to increase the number of power supply points of the secondary side circuit. When the monitored current mutual inductance fluctuation judgment value is not greater than 1, the current mutual inductance influence adjustment is stopped, otherwise QQ2 is executed. The increase in the number of power supply points of the secondary side circuit is used to reduce the load resistance of the current mutual inductance circuit; QQ2, performing capacitor shunt compensation. When the monitored current mutual inductance fluctuation judgment value is not greater than 1, the current mutual inductance influence adjustment is stopped, otherwise a prompt is sent to the preset personnel to diagnose the corresponding power grid circuit as abnormal.

[0014] Furthermore, the specific process of adjusting the influence of voltage mutual inductance is as follows: WW1, filtering the voltage mutual inductance output signal, and sending a prompt to the preset personnel. When the monitored voltage mutual inductance fluctuation judgment value is not greater than 1, the voltage mutual inductance influence adjustment is stopped, otherwise WW2 is executed; WW2, smoothing the voltage mutual inductance output signal, when the monitored voltage mutual inductance fluctuation judgment value is not greater than 1, the voltage mutual inductance influence adjustment is stopped, otherwise a prompt is sent to the preset personnel to diagnose the corresponding power grid circuit as abnormal.

[0015] Further, the specific process of performing fault response analysis to obtain a power grid fault response evaluation value based on the obtained qualified current mutual inductance fluctuation value, qualified voltage mutual inductance fluctuation value, and fault response delay time is as follows: the fault response delay time and a preset fault response time threshold obtained from a database are processed to obtain a fault response delay compliance value; the fault response delay compliance value is represented by a result of a ratio operation between the sum of the fault response delay time and the preset fault response time threshold and twice the preset fault response time threshold; the power grid fault response evaluation value is obtained by the qualified current mutual inductance fluctuation value, the qualified voltage mutual inductance fluctuation value, the fault response delay compliance value, and a preset fault response first weight, a preset fault response second weight, and a preset fault response third weight obtained from a database; Among them, the power grid fault response evaluation value is obtained by the following method: ; In the formula, represents the grid fault response evaluation value of the grid in the bth preset qualified time period, , b represents the number of the preset qualified time period, f represents the total number of preset qualified time periods, Indicates the fault response delay compliance value of the power grid in the bth preset qualified time period, represents the qualified current mutual inductance fluctuation value of the power grid in the bth preset qualified time period, represents the qualified voltage mutual inductance fluctuation value of the power grid in the bth preset qualified time period, represents the first weight of the preset fault response, represents the second weight of the preset fault response, represents the third weight of the preset fault response, and e represents a natural constant.

[0016] Furthermore, the specific process of judging whether to adjust the fault response based on the power grid fault response evaluation value is as follows: judging whether the power grid fault response evaluation value is not lower than the reference power grid fault response threshold value obtained from the database, when the power grid fault response evaluation value is not lower than the reference power grid fault response threshold value, no fault response adjustment is performed, otherwise EE2 is executed; EE2, differential protection is performed, when the monitored power grid fault response evaluation value is not lower than the reference power grid fault response threshold value, fault response adjustment is stopped, otherwise EE3 is executed; EE3, adaptive filtering is performed, when the monitored power grid fault response evaluation value is not lower than the reference power grid fault response threshold value, fault response adjustment is stopped, otherwise a prompt is sent to the preset personnel to diagnose the corresponding power grid circuit as abnormal.

[0017] The embodiment of the present application provides a power grid fault automatic diagnosis system based on big data analysis, including a current mutual inductance accuracy analysis module, a voltage mutual inductance accuracy analysis module, an impact adjustment module and a power grid fault response evaluation module: wherein the current mutual inductance accuracy analysis module is used to obtain current mutual inductance related data and perform current mutual inductance accuracy analysis to obtain a current mutual inductance fluctuation value, and obtain a current mutual inductance fluctuation judgment value based on the current mutual inductance fluctuation value and a reference current mutual inductance fluctuation average value obtained from a database, and the current mutual inductance fluctuation value is used to reflect the data fluctuation degree of the current transformer during the power grid fault automatic diagnosis process; the voltage mutual inductance accuracy analysis module is used to obtain voltage mutual inductance related data and perform voltage mutual inductance accuracy analysis to obtain a voltage mutual inductance fluctuation value, and obtain a voltage mutual inductance fluctuation judgment value based on the voltage mutual inductance fluctuation value. The voltage mutual inductance fluctuation judgment value is obtained by combining the obtained current mutual inductance fluctuation judgment value and the reference voltage mutual inductance fluctuation average value obtained from the database, and the voltage mutual inductance fluctuation value is used to reflect the data fluctuation degree of the voltage transformer during the automatic diagnosis of power grid faults; the impact adjustment module is used to judge whether to perform current mutual inductance impact adjustment and voltage mutual inductance impact adjustment based on the obtained current mutual inductance fluctuation judgment value and voltage mutual inductance fluctuation judgment value; the power grid fault response evaluation module is used to perform fault response analysis according to the obtained qualified current mutual inductance fluctuation value, qualified voltage mutual inductance fluctuation value and fault response delay time to obtain a power grid fault response evaluation value, and judge whether to perform fault response adjustment based on the power grid fault response evaluation value, and the power grid fault response evaluation value is used to reflect the power grid fault response situation during the automatic diagnosis of power grid faults.

[0018] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By performing current mutual inductance accuracy analysis and voltage mutual inductance accuracy analysis to obtain current mutual inductance fluctuation values ​​and voltage mutual inductance fluctuation values, current mutual inductance fluctuation judgment values ​​and voltage mutual inductance fluctuation judgment values ​​are obtained, and then it is determined whether to perform current mutual inductance influence adjustment and voltage mutual inductance influence adjustment. Finally, a fault response analysis is performed to obtain a power grid fault response evaluation value and determine whether to perform a fault response adjustment, thereby improving the timeliness of automatic diagnosis of power grid faults, and further improving the accuracy of automatic diagnosis of power grid faults based on big data analysis, effectively solving the problem of inaccurate data acquisition for automatic diagnosis of power grid faults in the prior art.

[0019] 2. The current mutual inductance fluctuation value is obtained by combining the current fluctuation compliance value, the load fluctuation compliance value and the current mutual inductance output power compliance value, and then the voltage mutual inductance fluctuation value is obtained by combining the voltage fluctuation compliance value and the voltage mutual inductance output power compliance value. Finally, the power grid fault response evaluation value is obtained by the qualified current mutual inductance fluctuation value, the qualified voltage mutual inductance fluctuation value, the fault response delay compliance value, the preset fault response first weight, the preset fault response second weight and the preset fault response third weight, thereby achieving the improvement of the accuracy of obtaining the relevant data of the automatic diagnosis of the power grid fault, and then realizing the dynamic evaluation of the accuracy of the automatic diagnosis of the power grid fault.

[0020] 3. By judging whether the grid fault response evaluation value is not lower than the reference grid fault response threshold, when the grid fault response evaluation value is not lower than the reference grid fault response threshold, no fault response adjustment is performed, otherwise differential protection and adaptive filtering are performed, thereby quantifying the grid fault response situation during the automatic diagnosis of grid faults, thereby achieving the improvement of the accuracy of grid fault response. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A flowchart of a method for automatic diagnosis of power grid faults based on big data analysis provided in an embodiment of the present application; Figure 2 A statistical diagram of changes in the current mutual inductance fluctuation value-current mutual inductance fluctuation judgment value provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of a power grid fault automatic diagnosis system based on big data analysis provided in an embodiment of the present application; Figure 4 An overall flow chart provided for an embodiment of the present application. DETAILED DESCRIPTION

[0022] The embodiment of the present application solves the problem of inaccurate data acquisition for automatic diagnosis of power grid faults in the prior art by providing a method and system for automatic diagnosis of power grid faults based on big data analysis. The current mutual inductance fluctuation value is obtained by performing a current mutual inductance accuracy analysis, and a current mutual inductance fluctuation judgment value is obtained based on the current mutual inductance fluctuation value and a reference current mutual inductance fluctuation average value. Then, the voltage mutual inductance fluctuation value is obtained by performing a voltage mutual inductance accuracy analysis, and a voltage mutual inductance fluctuation judgment value is obtained based on the voltage mutual inductance fluctuation value and a reference voltage mutual inductance fluctuation average value. Subsequently, based on the obtained current mutual inductance fluctuation judgment value and voltage mutual inductance fluctuation judgment value, it is determined whether to perform current mutual inductance influence adjustment and voltage mutual inductance influence adjustment. Finally, a fault response analysis is performed according to the obtained qualified current mutual inductance fluctuation value, qualified voltage mutual inductance fluctuation value and fault response delay time to obtain a power grid fault response evaluation value and determine whether to perform a fault response adjustment, thereby improving the accuracy of automatic diagnosis of power grid faults based on big data analysis.

[0023] The technical solution in the embodiment of the present application is to solve the problem of inaccurate data acquisition for automatic diagnosis of power grid faults. The overall idea is as follows: The corresponding current mutual inductance fluctuation judgment value and voltage mutual inductance fluctuation judgment value are obtained by obtaining the current mutual inductance fluctuation value and the voltage mutual inductance fluctuation value, and then it is judged whether to adjust the current mutual inductance influence and the voltage mutual inductance influence. Finally, a fault response analysis is performed to obtain the power grid fault response evaluation value and judge whether to adjust the fault response, thereby achieving the effect of improving the accuracy of automatic diagnosis of power grid faults based on big data analysis.

[0024] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0025] like Figure 1 As shown, it is a flow chart of a method for automatic diagnosis of power grid faults based on big data analysis provided by an embodiment of the present application, the method comprising the following steps: S1, current mutual inductance accuracy analysis: obtaining current mutual inductance related data and performing current mutual inductance accuracy analysis to obtain current mutual inductance fluctuation value, obtaining current mutual inductance fluctuation judgment value based on current mutual inductance fluctuation value and reference current mutual inductance fluctuation average value obtained from a database, the current mutual inductance fluctuation value is used to reflect the data fluctuation degree of the current transformer in the process of automatic diagnosis of power grid faults; S2, voltage mutual inductance accuracy analysis: obtaining voltage mutual inductance related data and performing voltage mutual inductance accuracy analysis to obtain voltage mutual inductance fluctuation value, obtaining voltage mutual inductance fluctuation judgment value based on voltage mutual inductance fluctuation value and reference voltage mutual inductance fluctuation average value obtained from a database, the voltage mutual inductance fluctuation value is used to reflect the data fluctuation degree of the voltage transformer in the process of automatic diagnosis of power grid faults; S3, impact adjustment: adjusting the current mutual inductance fluctuation judgment value and voltage mutual inductance fluctuation judgment value based on the obtained The cutoff value determines whether to adjust the influence of current mutual inductance and voltage mutual inductance. The influence adjustment of current mutual inductance is used to reduce the influence of current mutual inductance on the response time of power grid faults, and the influence adjustment of voltage mutual inductance is used to reduce the influence of voltage mutual inductance on the response time of power grid faults. S4, power grid fault response evaluation: perform fault response analysis according to the obtained qualified current mutual inductance fluctuation value, qualified voltage mutual inductance fluctuation value and fault response delay time to obtain a power grid fault response evaluation value, and determine whether to adjust the fault response based on the power grid fault response evaluation value. The qualified current mutual inductance fluctuation value indicates the current mutual inductance fluctuation value corresponding to the reference current mutual inductance fluctuation average value, and the qualified voltage mutual inductance fluctuation value indicates the voltage mutual inductance fluctuation value corresponding to the reference voltage mutual inductance fluctuation average value. The power grid fault response evaluation value is used to reflect the power grid fault response situation during the automatic diagnosis of power grid faults, and the fault response adjustment is used to reduce the power grid fault response delay.

[0026] It should be added that the current mutual inductance related data include the maximum current value, the minimum current value, the grid load change and the first output power change; the voltage mutual inductance related data include the maximum voltage value, the minimum voltage value and the second output power change; the maximum current value represents the maximum value of the grid current during the automatic diagnosis of grid faults; the maximum voltage value represents the maximum value of the grid voltage during the automatic diagnosis of grid faults; the grid load change represents the change of the grid load during the automatic diagnosis of grid faults; the first output power change represents the change of the current transformer output power during the automatic diagnosis of grid faults; the second output power change represents the change of the voltage transformer output power during the automatic diagnosis of grid faults.

[0027] It needs to be explained that the grid current within the preset time period is measured by a current transformer and the maximum and minimum values ​​of the grid current within the preset time period are obtained by statistics. The maximum value of the grid current is the maximum current value, and the minimum value of the grid current is the minimum current value. The grid voltage within the preset time period is measured by a voltage transformer and the maximum and minimum values ​​of the grid voltage within the preset time period are obtained by statistics. The maximum value of the grid voltage is the maximum voltage value, and the minimum value of the grid voltage is the minimum voltage value. The power meter is used to measure the change in the output power of the current transformer and the change in the output power of the voltage transformer within the preset time period to obtain the first output power change and the second output power change. The power load detector is used to monitor the changing trend of the grid load within the preset time period to obtain the grid load change. The response time tester is used to measure the time from the time the fault occurs to the time when the system recognizes the fault and triggers the corresponding action (such as sending an alarm prompt to the preset personnel) within the preset time period to obtain the fault response delay time.

[0028] In this embodiment, the current mutual inductance fluctuation value and the voltage mutual inductance fluctuation value respectively reflect the data fluctuation degree of the current transformer and the voltage transformer in the process of automatic diagnosis of power grid faults. The current mutual inductance fluctuation value and the voltage mutual inductance fluctuation value directly affect the accuracy of the automatic diagnosis system of power grid faults. When the current mutual inductance fluctuation value and the voltage mutual inductance fluctuation value are larger, it may cause the system to misjudge or miss the fault, thereby affecting the power grid fault response evaluation value. When the current mutual inductance fluctuation value and the voltage mutual inductance fluctuation value are smaller, the system can more accurately identify the fault and respond quickly, thereby increasing the power grid fault response evaluation value. For example, during the peak period of industrial production, when a short circuit fault occurs in the power grid, the current will increase, resulting in an increase in the current mutual inductance fluctuation value; at the same time, due to the existence of power grid impedance, the voltage will decrease accordingly, which may cause the voltage mutual inductance fluctuation value to change.

[0029] This application utilizes big data technology to collect relevant data of current transformers (current mutual inductance related data and voltage mutual inductance related data) from multiple data sources (such as current transformers, voltage transformers, etc.) in real time. When the current mutual inductance adjustment and the voltage mutual inductance adjustment are abnormal, an alarm prompt is sent to the preset personnel in a timely manner based on big data technology. Through big data analysis, data can be processed and analyzed in real time, providing timely information support for the automatic diagnosis system of power grid faults, shortening the fault response time, and realizing the improvement of the timeliness of the automatic diagnosis system of power grid faults, thereby realizing the improvement of the accuracy of automatic diagnosis of power grid faults based on big data analysis.

[0030] Furthermore, the specific process of obtaining the current mutual inductance fluctuation judgment value is as follows: the maximum current value, the minimum current value and the preset maximum grid current fluctuation threshold obtained from the database are processed to obtain the current fluctuation compliance value (i.e., the current mutual inductance fluctuation value in the restriction expression). The current fluctuation compliance value is represented by the result of the ratio operation of the difference between the maximum current value and the minimum current value and the preset maximum grid current fluctuation threshold value; the current fluctuation compliance value is used to reflect the fluctuation compliance degree of the grid current within the preset time period; the grid load change amount and the preset grid load change maximum threshold value obtained from the database are processed to obtain the load fluctuation compliance value (that is, the current mutual inductance fluctuation value in the limiting expression The load fluctuation compliance value is represented by the result of the ratio operation between the grid load change and the preset grid load change maximum threshold value; the load fluctuation compliance value is used to reflect the degree of grid load fluctuation compliance within the preset time period; the first output power change and the preset current output power maximum threshold value obtained from the database are processed to obtain the current mutual inductance output power compliance value (i.e., the current mutual inductance fluctuation value in the limiting expression The current mutual inductance output power compliance value is represented by the result of a ratio operation between the first output power change amount and the preset current output power maximum threshold value; the current mutual inductance output power compliance value is used to reflect the fluctuation compliance of the output power of the current transformer within a preset time period; the current mutual inductance fluctuation value is obtained by combining the current fluctuation compliance value, the load fluctuation compliance value and the current mutual inductance output power compliance value; the current mutual inductance fluctuation judgment value is obtained based on the current mutual inductance fluctuation value and the reference current mutual inductance fluctuation average value.

[0031] Among them, the limiting expression of the current mutual inductance fluctuation judgment value is as follows: ; ; ; ; ; In the formula, represents the current mutual inductance fluctuation judgment value of the power grid in the a-th preset time period, , a represents the number of the preset time period, h represents the total number of preset time periods, represents the current mutual inductance fluctuation value of the power grid in the a-th preset time period, Indicates that the current fluctuation of the power grid in the a-th preset time period meets the value, Indicates the load fluctuation compliance value of the power grid in the a-th preset time period, Indicates the current mutual inductance output power compliance value of the power grid in the a-th preset time period, Indicates the maximum current of the power grid in the a-th preset time period, Indicates the minimum current value of the power grid in the a-th preset time period, It represents the load change of the power grid in the a-th preset time period. represents the first output power change of the power grid in the a-th preset time period, Represents the average value of the reference current mutual inductance fluctuation, Indicates the preset maximum threshold of grid current fluctuation. Indicates the maximum threshold of preset grid load change. represents the maximum threshold of preset current output power, and e represents a natural constant.

[0032] In this embodiment, the aforementioned database is a database for storing various types of setting data established before the design of an automatic diagnosis method for power grid faults based on big data analysis provided in an embodiment of the present application. The database includes but is not limited to load changes, current transformer output power, voltage transformer output power, etc., and the various numerical values ​​therein are directly set by technical personnel. For example, the reference current mutual inductance fluctuation average value is represented by the average of the current mutual inductance fluctuation values ​​in the historical time period in the database, the preset power grid current fluctuation maximum threshold is represented by the maximum value of the power grid current change in the historical time period in the database, the preset power grid load change maximum threshold is represented by the maximum value of the power grid load change in the historical time period in the database, and the preset current output power maximum threshold is represented by the maximum value of the current transformer output power in the historical time period in the database.

[0033] It should be understood that the algorithm of this embodiment combines the analysis of the current mutual inductance related data to obtain the current mutual inductance fluctuation value. The current mutual inductance related data in the algorithm of this embodiment does not exist independently, but has mutual correlation. The larger the maximum current value and the grid load change, the larger the current mutual inductance fluctuation value. The influence of the first output power change should also be considered comprehensively. The maximum current value and the maximum current value, the minimum current value and the load change jointly determine the range and degree of current fluctuation. When the grid load changes, the output signal of the current transformer will also fluctuate accordingly. The larger the grid load change, the greater the current maximum value will usually change accordingly. This is because the increase or decrease in load will directly lead to an increase or decrease in the current in the grid. The difference between the maximum current value and the minimum current value reflects the range of current fluctuation. The larger the difference, the more violent the current fluctuation. The rapid change in load will cause the rapid change of the current in the grid, which will cause significant fluctuations in the output signal of the current transformer. The first output power change reflects the performance of the current transformer in responding to grid load changes. When the output power changes less, it means that the current transformer has better stability and anti-fluctuation ability.

[0034] Specifically, assuming that the current mutual inductance fluctuation value The range is 2-5, referring to the average value of current mutual inductance fluctuation Fixed to 3, such as Figure 2 As shown, it is a statistical diagram of the change of the current mutual inductance fluctuation value-current mutual inductance fluctuation judgment value provided by the embodiment of the present application, Figure 2 It can be seen that as the current mutual inductance fluctuation value gradually increases, the current mutual inductance fluctuation judgment value also gradually increases, which means that the data fluctuation degree of the current transformer in the process of automatic diagnosis of power grid faults is getting larger and larger, realizing the accurate quantification of the data fluctuation degree of the current transformer in the process of automatic diagnosis of power grid faults; and thus realizing the improvement of the accuracy of automatic diagnosis of power grid faults based on big data analysis.

[0035] Furthermore, the specific process of obtaining the voltage mutual inductance fluctuation judgment value is as follows: the maximum voltage value, the minimum voltage value and the preset maximum threshold value of the grid voltage fluctuation obtained from the database are processed to obtain the voltage fluctuation compliance value (i.e., the voltage mutual inductance fluctuation value in the restriction expression). The voltage fluctuation compliance value is represented by the result of the ratio operation of the maximum voltage value and the minimum voltage value with the preset maximum threshold value of the grid voltage fluctuation; the voltage fluctuation compliance value is used to reflect the degree of compliance of the grid voltage fluctuation within the preset time period; the second output power change amount and the preset voltage output power maximum threshold value obtained from the database are processed to obtain the voltage mutual inductance output power compliance value (that is, the voltage mutual inductance fluctuation value in the limiting expression ); the voltage mutual inductance output power compliance value is represented by the result of the ratio operation between the second output power change and the preset voltage output power maximum threshold value; the voltage mutual inductance output power compliance value is used to reflect the fluctuation compliance of the output power of the voltage transformer within a preset time period; the voltage mutual inductance fluctuation value is obtained by combining the voltage fluctuation compliance value and the voltage mutual inductance output power compliance value; the voltage mutual inductance fluctuation judgment value is obtained based on the voltage mutual inductance fluctuation value and the reference voltage mutual inductance fluctuation average value.

[0036] Among them, the voltage mutual inductance fluctuation judgment value is obtained by the following method: ; ; ; ; In the formula, represents the voltage mutual inductance fluctuation judgment value of the power grid in the a-th preset time period, , a represents the number of the preset time period, h represents the total number of preset time periods, represents the voltage mutual inductance fluctuation value of the power grid in the a-th preset time period, Indicates that the voltage fluctuation of the power grid in the a-th preset time period meets the value, Indicates the voltage mutual inductance output power compliance value of the power grid in the a-th preset time period, Indicates the maximum voltage of the power grid in the a-th preset time period, Indicates the minimum voltage of the power grid in the a-th preset time period, represents the second output power change of the power grid in the a-th preset time period, Represents the average value of the reference voltage mutual inductance fluctuation, Indicates the preset maximum threshold of grid voltage fluctuation. represents the maximum threshold of the preset voltage output power, and e represents a natural constant.

[0037] In this embodiment, the reference voltage mutual inductance fluctuation average value is represented by the average value of the voltage mutual inductance fluctuation value in the historical time period in the database, the preset grid voltage fluctuation maximum threshold value is represented by the maximum value of the grid voltage change in the historical time period in the database, and the preset voltage output power maximum threshold value is represented by the maximum value of the voltage transformer output power in the historical time period in the database.

[0038] It should be understood that the algorithm of this embodiment combines the voltage mutual inductance related data analysis to obtain the voltage mutual inductance fluctuation value. The voltage mutual inductance related data in the algorithm of this embodiment does not exist independently, and there is mutual correlation between them. The larger the maximum voltage value, the larger the voltage mutual inductance fluctuation value. The combined influence of the minimum voltage value and the second output power change should also be considered. When the grid load changes, the output signal of the voltage transformer will also fluctuate. When the grid load changes, the voltage will also fluctuate. The difference between the maximum and minimum voltage values ​​reflects the range of voltage fluctuation. The larger the difference, the more violent the voltage fluctuation. When the grid voltage changes, the output power of the voltage transformer is related to its input voltage and load impedance. When the input voltage fluctuates, the output power will also change. The output signal of the voltage transformer will also fluctuate, which will lead to changes in its output power. The smaller the second output power change, the better the stability and anti-fluctuation ability of the voltage transformer in dealing with voltage fluctuations. The accurate quantification of the data fluctuation degree of the voltage transformer in the process of evaluating the automatic diagnosis of power grid faults is achieved; thereby improving the accuracy of automatic diagnosis of power grid faults based on big data analysis.

[0039] Furthermore, the specific process of judging whether to adjust the influence of current mutual inductance and voltage mutual inductance based on the obtained current mutual inductance fluctuation judgment value and voltage mutual inductance fluctuation judgment value is as follows: judging whether the current mutual inductance fluctuation judgment value and voltage mutual inductance fluctuation judgment value meet condition one; when the current mutual inductance fluctuation judgment value and voltage mutual inductance fluctuation judgment value meet condition one, it indicates that the degree of influence of current mutual inductance and voltage mutual inductance is small, and directly obtaining the corresponding qualified current mutual inductance fluctuation value and qualified voltage mutual inductance fluctuation value (that is, the current mutual inductance fluctuation value and voltage mutual inductance fluctuation value that meet condition one are respectively recorded as qualified current mutual inductance fluctuation value and qualified voltage mutual inductance fluctuation value); when the current mutual inductance fluctuation judgment value and voltage mutual inductance fluctuation judgment value do not meet condition one, it indicates that the degree of influence of current mutual inductance and voltage mutual inductance is large, and current mutual inductance adjustment and voltage mutual inductance adjustment are performed; condition one indicates that the current mutual inductance fluctuation judgment value and voltage mutual inductance fluctuation judgment value are both not greater than 1.

[0040] Specifically, the specific process of adjusting the influence of current mutual inductance is as follows: QQ1, sending a prompt to the preset personnel to increase the number of power supply points of the secondary circuit. When the monitored current mutual inductance fluctuation judgment value is not greater than 1, stop adjusting the influence of current mutual inductance, otherwise execute QQ2, increase the number of power supply points of the secondary circuit to reduce the load resistance of the current mutual inductance circuit; QQ2, perform capacitor shunt compensation. When the monitored current mutual inductance fluctuation judgment value is not greater than 1, stop adjusting the influence of current mutual inductance, otherwise send a prompt to the preset personnel to diagnose the corresponding power grid circuit as abnormal. Capacitor shunt compensation is used to reduce the impact of load changes on current transformer related data.

[0041] The specific process of adjusting the influence of voltage mutual inductance is as follows: WW1, filtering the voltage mutual inductance output signal, and sending a prompt to the preset personnel. When the monitored voltage mutual inductance fluctuation judgment value is not greater than 1, stop adjusting the influence of voltage mutual inductance, otherwise execute WW2. Voltage mutual inductance output signal filtering means removing high-frequency load change fluctuations through low-pass filtering; WW2, smoothing the voltage mutual inductance output signal. When the monitored voltage mutual inductance fluctuation judgment value is not greater than 1, stop adjusting the influence of voltage mutual inductance, otherwise send a prompt to the preset personnel to diagnose the corresponding power grid circuit as abnormal. Voltage mutual inductance output signal smoothing means reducing the instantaneous fluctuations caused by load changes through a sliding average algorithm.

[0042] In this embodiment, by increasing the power-taking points, the load of the secondary circuit can be dispersed, so that the current borne by each power-taking point is reduced, thereby reducing the load resistance of the entire circuit. The load changes in the power system will affect the relevant data of the current transformer, resulting in measurement errors and performance degradation. A prompt is sent to the preset personnel to connect a capacitor in parallel on the secondary side of the current transformer. The capacitor can absorb or release electrical energy, thereby balancing the impact of load changes on the current transformer. When the load increases, the capacitor releases electrical energy to reduce the impact of the secondary current reduction; when the load decreases, the capacitor absorbs electrical energy to prevent the secondary current from being too large, thereby improving the measurement accuracy and stability of the current transformer, and further achieving the improvement of the accuracy of automatic diagnosis of power grid faults based on big data analysis.

[0043] Frequent changes in load will produce high-frequency fluctuation components, which will be superimposed on the output signal of the voltage transformer, resulting in measurement errors. In order to eliminate these high-frequency fluctuations, a low-pass filter can be used to filter the output signal of the voltage transformer. By inputting the output signal of the voltage transformer into the low-pass filter, the high-frequency load change fluctuations can be filtered out and the low-frequency voltage signal components can be retained. After filtering, the voltage signal may still have some instantaneous fluctuations caused by load changes. The sliding average algorithm is used to smooth the voltage signal. The voltage data within the preset time period is used as a window. The smoothed voltage signal is obtained by calculating the average value of the data in the window. The instantaneous fluctuations caused by load changes can be reduced, thereby achieving a stable and smooth voltage signal, and then realizing the improvement of the accuracy of automatic diagnosis of power grid faults based on big data analysis.

[0044] Further, the specific process of performing fault response analysis to obtain the power grid fault response evaluation value according to the obtained qualified current mutual inductance fluctuation value, qualified voltage mutual inductance fluctuation value and fault response delay time is as follows: the fault response delay time and the preset fault response time threshold obtained from the database are processed to obtain the fault response delay compliance value (that is, the qualified current mutual inductance fluctuation value in the power grid fault response evaluation value in the restriction expression) ); the fault response delay compliance value is represented by the result of the ratio operation of the sum of the fault response delay time and the preset fault response time threshold and twice the preset fault response time threshold; the fault response delay compliance value is used to reflect the compliance of the power grid fault response delay within the preset qualified time period; the preset qualified time period represents the preset time period corresponding to the time when the current mutual inductance fluctuation judgment value and the voltage mutual inductance fluctuation judgment value meet the condition; the power grid fault response evaluation value is obtained by the qualified current mutual inductance fluctuation value, the qualified voltage mutual inductance fluctuation value, the fault response delay compliance value and the preset fault response first weight, the preset fault response second weight and the preset fault response third weight obtained from the database; the preset fault response first weight is used to describe the influence of the fault response delay compliance value on the power grid fault response evaluation value; the preset fault response second weight is used to describe the influence of the qualified current mutual inductance fluctuation value on the power grid fault response evaluation value; the preset fault response third weight is used to describe the influence of the qualified voltage mutual inductance fluctuation value on the power grid fault response evaluation value.

[0045] Among them, the power grid fault response evaluation value is obtained by the following method: ; ; In the formula, represents the grid fault response evaluation value of the grid in the bth preset qualified time period, , b represents the number of the preset qualified time period, f represents the total number of preset qualified time periods, represents the qualified current mutual inductance fluctuation value of the power grid in the bth preset qualified time period, represents the qualified voltage mutual inductance fluctuation value of the power grid in the bth preset qualified time period, Indicates the fault response delay compliance value of the power grid in the bth preset qualified time period, represents the fault response delay of the power grid in the bth preset qualified time period, Indicates the preset fault response time threshold. represents the first weight of the preset fault response, represents the second weight of the preset fault response, represents the third weight of the preset fault response, and e represents a natural constant.

[0046] In this embodiment, the preset fault response time threshold is represented by the maximum value of the power grid fault response time in the historical time period in the database, and the preset fault response first weight, the preset fault response second weight, and the preset fault response third weight respectively reflect the influence of the fault response delay compliance value, the qualified current mutual inductance fluctuation value, and the qualified voltage mutual inductance fluctuation value on the power grid fault response evaluation value. A mapping set of weights corresponding to the fault response delay compliance value, the qualified current mutual inductance fluctuation value, and the qualified voltage mutual inductance fluctuation value is pre-set in the database, and the mapping set reflects the fault response delay compliance value, the qualified current mutual inductance fluctuation value, and the qualified voltage mutual inductance fluctuation value. A mapping relationship between dynamic values ​​and corresponding weights, for example, a fault response delay compliance value, a qualified current mutual inductance fluctuation value, and a qualified voltage mutual inductance fluctuation value and the weights corresponding to the preset fault response delay compliance value, qualified current mutual inductance fluctuation value, and qualified voltage mutual inductance fluctuation value in a database form a mapping set, and the real-time fault response delay compliance value, qualified current mutual inductance fluctuation value, and qualified voltage mutual inductance fluctuation value are input into the mapping set to obtain the weights corresponding to the fault response delay compliance value, qualified current mutual inductance fluctuation value, and qualified voltage mutual inductance fluctuation value, wherein the mapping relationship can be a one-to-one correspondence or a many-to-one relationship, and the value range in this embodiment is 0-1.

[0047] It should be understood that the algorithm of this embodiment combines the current mutual inductance fluctuation value, the voltage mutual inductance fluctuation value and the fault response delay time to analyze and obtain the power grid fault response evaluation value. The current mutual inductance fluctuation value, the voltage mutual inductance fluctuation value and the fault response delay time in the algorithm of this embodiment do not exist independently, but are interrelated. The larger the current mutual inductance fluctuation value and the voltage mutual inductance fluctuation value, it does not mean that the power grid fault response evaluation value is smaller. The influence of the fault response delay time should also be comprehensively considered. When a power grid fault occurs, both the current and voltage may fluctuate, and the degree of fluctuation may affect each other (for example, when a short circuit fault occurs in the power grid, the current near the fault point will increase sharply. Due to the existence of resistance and inductance in the power grid, this increase in current may cause a decrease in voltage). The magnitude of the current mutual inductance fluctuation value and the voltage mutual inductance fluctuation value directly affects the judgment accuracy and response speed of fault diagnosis. The larger the current mutual inductance fluctuation value and the voltage mutual inductance fluctuation value, the more serious the power grid fault is. For example, when a short circuit fault occurs in the power grid, the current will increase sharply and the voltage may drop at the same time, which may cause the current mutual inductance fluctuation value and the voltage mutual inductance fluctuation value to increase. This synchronous change of current and voltage helps the fault diagnosis system to more accurately determine the fault type and location.

[0048] Specifically, assuming that the fault response delay meets the value The range is 1-1.5, the qualified current mutual inductance fluctuation value The range is 2-5, the qualified voltage mutual inductance fluctuation value The range is 2-5, the preset fault response first weight, the preset fault response second weight and the preset fault response third weight are fixed to 0.4, 0.3 and 0.3 respectively, as shown in Table 1, which is a statistical table of changes in the power grid fault response evaluation value provided in an embodiment of the present application: Table 1 Statistics of changes in power grid fault response evaluation values As can be seen from the table above, as the fault response delay meets the value , qualified current mutual inductance fluctuation value And qualified voltage mutual inductance fluctuation value The power grid fault response evaluation value It gradually decreases, which means that the power grid fault response performance gradually decreases during the power grid fault automatic diagnosis process, realizing the accurate quantification of the power grid fault response situation during the power grid fault automatic diagnosis process, and thus realizing the improvement of the accuracy of power grid fault automatic diagnosis based on big data analysis.

[0049] Furthermore, the specific process of judging whether to adjust the fault response based on the power grid fault response evaluation value is as follows: judging whether the power grid fault response evaluation value is not lower than the reference power grid fault response threshold obtained from the database, when the power grid fault response evaluation value is not lower than the reference power grid fault response threshold, it indicates that the power grid fault response is qualified and no fault response adjustment is performed, otherwise EE2 is executed; EE2, differential protection is performed, when the monitored network fault response evaluation value is not lower than the reference power grid fault response threshold, the fault response adjustment is stopped, otherwise EE3 is executed, differential protection means improving the fault response speed of the power grid through the distribution network differential protection method; EE3, adaptive filtering is performed, when the monitored network fault response evaluation value is not lower than the reference power grid fault response threshold, the fault response adjustment is stopped, otherwise a prompt is sent to the preset personnel to diagnose the corresponding power grid circuit as abnormal, and adaptive filtering means automatically adjusting the stability of the output signals of the current transformer and the voltage transformer through an adaptive filtering algorithm, such as LMS (Least Mean Squares, least mean square algorithm).

[0050] In this embodiment, the distribution network differential protection method monitors the difference between the current or voltage signals of each node in the distribution network and compares it with a preset threshold value. It has the characteristics of fast response and accurate judgment of the fault location, can significantly improve the fault response speed of the power grid, and reduce the impact of the fault on the power grid. In the power grid, the output signals of the current transformer and the voltage transformer can be used as the input signals of the adaptive filter, and the expected stable signal can be used as the expected signal. Through the adaptive adjustment of the LMS (Least Mean Squares) algorithm, the output signal of the filter can be made smoother and the influence of interference and noise can be reduced; the accuracy of automatic diagnosis of power grid faults based on big data analysis is improved.

[0051] like Figure 3 As shown, it is a structural schematic diagram of a power grid fault automatic diagnosis system based on big data analysis provided by an embodiment of the present application. An power grid fault automatic diagnosis system based on big data analysis provided by an embodiment of the present application includes a current mutual inductance accuracy analysis module, a voltage mutual inductance accuracy analysis module, an impact adjustment module and a power grid fault response evaluation module: wherein the current mutual inductance accuracy analysis module is used to obtain current mutual inductance related data and perform current mutual inductance accuracy analysis to obtain a current mutual inductance fluctuation value, and obtain a current mutual inductance fluctuation judgment value based on the current mutual inductance fluctuation value and a reference current mutual inductance fluctuation average value obtained from a database, and the current mutual inductance fluctuation value is used to reflect the data fluctuation degree of the current transformer during the automatic diagnosis of power grid faults; the voltage mutual inductance accuracy analysis module is used to obtain voltage mutual inductance related data and perform voltage mutual inductance accuracy analysis to obtain a voltage mutual inductance fluctuation value, and obtain a voltage mutual inductance fluctuation judgment value based on the voltage mutual inductance fluctuation value and a reference voltage mutual inductance fluctuation average value obtained from a database, and the voltage mutual inductance fluctuation value is used to reflect the data fluctuation degree of the voltage transformer during the automatic diagnosis of power grid faults. The influence adjustment module is used to determine whether to adjust the influence of current mutual inductance and voltage mutual inductance based on the obtained current mutual inductance fluctuation judgment value and voltage mutual inductance fluctuation judgment value. The current mutual inductance influence adjustment is used to reduce the influence of current mutual inductance on the power grid fault response time, and the voltage mutual inductance influence adjustment is used to reduce the influence of voltage mutual inductance on the power grid fault response time; the power grid fault response evaluation module is used to perform fault response analysis according to the obtained qualified current mutual inductance fluctuation value, qualified voltage mutual inductance fluctuation value and fault response delay time to obtain a power grid fault response evaluation value, and determine whether to adjust the fault response based on the power grid fault response evaluation value. The qualified current mutual inductance fluctuation value indicates the current mutual inductance fluctuation value corresponding to the reference current mutual inductance fluctuation average value, and the qualified voltage mutual inductance fluctuation value indicates the voltage mutual inductance fluctuation value corresponding to the reference voltage mutual inductance fluctuation average value. The power grid fault response evaluation value is used to reflect the power grid fault response during the automatic diagnosis of power grid faults, and the fault response adjustment is used to reduce the power grid fault response delay.

[0052] like Figure 4 As shown, it is an overall flow chart provided in an embodiment of the present application. The current mutual inductance accuracy analysis module, the voltage mutual inductance accuracy analysis module, the impact adjustment module and the power grid fault response evaluation module constitute a power grid fault automatic diagnosis system through data transmission and interaction. The impact adjustment module determines whether to perform current mutual inductance impact adjustment and voltage mutual inductance impact adjustment based on the current mutual inductance fluctuation judgment value and the voltage mutual inductance fluctuation judgment value, aiming to reduce the influence of the mutual inductor on the power grid fault response time, jointly ensure the stable operation of the power grid and the rapid response to the fault, and realize the improvement of the accuracy of automatic diagnosis of power grid faults based on big data analysis.

[0053] To summarize, the embodiment of the present application obtains current mutual inductance fluctuation values ​​and voltage mutual inductance fluctuation values ​​by performing current mutual inductance accuracy analysis and voltage mutual inductance accuracy analysis, obtains current mutual inductance fluctuation judgment values ​​and voltage mutual inductance fluctuation judgment values, then determines whether to perform current mutual inductance influence adjustment and voltage mutual inductance influence adjustment, and finally performs fault response analysis to obtain power grid fault response evaluation values ​​and determines whether to perform fault response adjustment, thereby achieving improved reliability of automatic diagnosis of power grid faults based on big data analysis, and further achieving improved accuracy of automatic diagnosis of power grid faults based on big data analysis, effectively solving the problem of inaccurate data acquisition for automatic diagnosis of power grid faults in the prior art.

[0054] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0055] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0056] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0057] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0058] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0059] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for automatic diagnosis of power grid faults based on big data analysis, characterized in that: The following steps are involved: S1, obtaining current mutual inductance related data and performing current mutual inductance accuracy analysis to obtain a current mutual inductance fluctuation value, and obtaining a current mutual inductance fluctuation judgment value based on the current mutual inductance fluctuation value and a reference current mutual inductance fluctuation average value obtained from a database, wherein the current mutual inductance fluctuation value is used to reflect the data fluctuation degree of the current transformer in the process of automatic diagnosis of power grid faults; S2, obtaining voltage mutual inductance related data to perform voltage mutual inductance accuracy analysis to obtain a voltage mutual inductance fluctuation value, and obtaining a voltage mutual inductance fluctuation judgment value based on the voltage mutual inductance fluctuation value and a reference voltage mutual inductance fluctuation average value obtained from a database, wherein the voltage mutual inductance fluctuation value is used to reflect the data fluctuation degree of the voltage transformer during the automatic diagnosis of power grid faults; S3, judging whether to perform current mutual inductance influence adjustment and voltage mutual inductance influence adjustment based on the acquired current mutual inductance fluctuation judgment value and voltage mutual inductance fluctuation judgment value; S4, performing fault response analysis according to the obtained qualified current mutual inductance fluctuation value, qualified voltage mutual inductance fluctuation value and fault response delay time to obtain a power grid fault response evaluation value, and judging whether to make a fault response adjustment based on the power grid fault response evaluation value, wherein the power grid fault response evaluation value is used to reflect the power grid fault response situation during the power grid fault automatic diagnosis process.

2. The method for automatic diagnosis of power grid faults based on big data analysis as claimed in claim 1, characterized in that: The current mutual inductance related data include the maximum current value, the minimum current value, the grid load change and the first output power change; The voltage mutual inductance related data includes a maximum voltage value, a minimum voltage value, and a second output power variation; The first output power variation represents the variation of the output power of the current transformer during the automatic diagnosis of power grid faults; The second output power variation represents the variation of the output power of the voltage transformer during the automatic diagnosis of power grid faults.

3. The method for automatic diagnosis of power grid faults based on big data analysis as claimed in claim 2, characterized in that: The specific process of obtaining the current mutual inductance fluctuation judgment value is as follows: The maximum current value, the minimum current value and the preset maximum threshold value of grid current fluctuation obtained from the database are processed to obtain a current fluctuation compliance value; The current fluctuation compliance value is represented by the result of a ratio calculation between the difference between the maximum current value and the minimum current value and a preset grid current fluctuation maximum threshold value; The load change amount of the power grid and the preset maximum threshold value of the power grid load change obtained from the database are processed to obtain a load fluctuation compliance value; The load fluctuation compliance value is represented by the result of a ratio calculation between the power grid load change amount and a preset power grid load change maximum threshold value; Processing the first output power variation and the preset current output power maximum threshold obtained from the database to obtain a current mutual inductance output power compliance value; The current mutual inductance output power compliance value is represented by the result of a ratio operation between the first output power variation and a preset current output power maximum threshold value; The current mutual inductance fluctuation value is obtained by combining the current fluctuation compliance value, the load fluctuation compliance value and the current mutual inductance output power compliance value; A current mutual inductance fluctuation judgment value is obtained based on the current mutual inductance fluctuation value and a reference current mutual inductance fluctuation average value.

4. The method for automatic diagnosis of power grid faults based on big data analysis as claimed in claim 2, characterized in that: The specific process of obtaining the voltage mutual inductance fluctuation judgment value is as follows: The maximum voltage value, the minimum voltage value and the preset maximum threshold value of the grid voltage fluctuation obtained from the database are processed to obtain a voltage fluctuation compliance value; The voltage fluctuation compliance value is used to reflect the fluctuation compliance degree of the grid voltage within a preset time period; Processing the second output power variation and the preset voltage output power maximum threshold obtained from the database to obtain a voltage mutual inductance output power compliance value; The voltage transformer output power compliance value is used to reflect the fluctuation compliance of the output power of the voltage transformer within a preset time period; The voltage fluctuation compliance value and the voltage mutual inductance output power compliance value are combined to obtain the voltage mutual inductance fluctuation value; A voltage mutual inductance fluctuation judgment value is obtained based on the voltage mutual inductance fluctuation value and a reference voltage mutual inductance fluctuation average value.

5. The method for automatic diagnosis of power grid faults based on big data analysis as claimed in claim 1, characterized in that: The specific process of judging whether to perform current mutual inductance influence adjustment and voltage mutual inductance influence adjustment based on the acquired current mutual inductance fluctuation judgment value and voltage mutual inductance fluctuation judgment value is as follows: Determine whether the current mutual inductance fluctuation judgment value and the voltage mutual inductance fluctuation judgment value meet condition one, and directly obtain the corresponding qualified current mutual inductance fluctuation value and qualified voltage mutual inductance fluctuation value when the current mutual inductance fluctuation judgment value and the voltage mutual inductance fluctuation judgment value meet condition one; When the current mutual inductance fluctuation judgment value and the voltage mutual inductance fluctuation judgment value do not meet condition 1, current mutual inductance influence adjustment and voltage mutual inductance influence adjustment are performed; The condition one indicates that both the current mutual inductance fluctuation judgment value and the voltage mutual inductance fluctuation judgment value are not greater than 1.

6. The method for automatic diagnosis of power grid faults based on big data analysis as claimed in claim 5, characterized in that: The specific process of adjusting the influence of current mutual inductance is as follows: QQ1, sending a prompt to the preset personnel to increase the number of power points of the secondary side circuit. When the monitored current mutual inductance fluctuation judgment value is not greater than 1, stop adjusting the current mutual inductance influence. Otherwise, execute QQ2. The increase in the number of power points of the secondary side circuit is used to reduce the load resistance of the current mutual inductance circuit. QQ2, perform capacitor shunt compensation. When the monitored current mutual inductance fluctuation judgment value is not greater than 1, stop adjusting the current mutual inductance influence. Otherwise, send a prompt to the preset personnel to diagnose the corresponding power grid circuit as abnormal.

7. The method for automatic diagnosis of power grid faults based on big data analysis as claimed in claim 5, characterized in that: The specific process of adjusting the voltage mutual inductance effect is as follows: WW1, filter the voltage mutual inductance output signal and send a prompt to the preset personnel. When the monitored voltage mutual inductance fluctuation judgment value is not greater than 1, stop adjusting the voltage mutual inductance influence, otherwise execute WW2; WW2, smooth the voltage mutual inductance output signal. When the monitored voltage mutual inductance fluctuation judgment value is not greater than 1, stop adjusting the voltage mutual inductance influence. Otherwise, send a prompt to the preset personnel to diagnose the corresponding power grid circuit as abnormal.

8. The method for automatic diagnosis of power grid faults based on big data analysis as claimed in claim 1, characterized in that: The specific process of performing fault response analysis to obtain a power grid fault response evaluation value based on the obtained qualified current mutual inductance fluctuation value, qualified voltage mutual inductance fluctuation value, and fault response delay time is as follows: Processing the fault response delay time and the preset fault response time threshold obtained from the database to obtain a fault response delay compliance value; The fault response delay compliance value is represented by the result of a ratio operation between the sum of the fault response delay time and the preset fault response time threshold and twice the preset fault response time threshold; Obtaining a power grid fault response evaluation value through a qualified current mutual inductance fluctuation value, a qualified voltage mutual inductance fluctuation value, a fault response delay compliance value, and a preset fault response first weight, a preset fault response second weight, and a preset fault response third weight obtained from a database; Among them, the power grid fault response evaluation value is obtained by the following method: ； In the formula, represents the grid fault response evaluation value of the grid in the bth preset qualified time period, , b represents the number of the preset qualified time period, f represents the total number of preset qualified time periods, Indicates the fault response delay compliance value of the power grid in the bth preset qualified time period, represents the qualified current mutual inductance fluctuation value of the power grid in the bth preset qualified time period, represents the qualified voltage mutual inductance fluctuation value of the power grid in the bth preset qualified time period, represents the first weight of the preset fault response, represents the second weight of the preset fault response, represents the third weight of the preset fault response, and e represents a natural constant.

9. The method for automatic diagnosis of power grid faults based on big data analysis as claimed in claim 8, characterized in that: The specific process of judging whether to adjust the fault response based on the power grid fault response evaluation value is as follows: Determine whether the power grid fault response evaluation value is not lower than the reference power grid fault response threshold obtained from the database. When the power grid fault response evaluation value is not lower than the reference power grid fault response threshold, no fault response adjustment is performed. Otherwise, EE2 is executed. EE2, perform differential protection. When the monitored network fault response evaluation value is not lower than the reference grid fault response threshold, stop the fault response adjustment. Otherwise, execute EE3; EE3, performs adaptive filtering. When the monitored network fault response evaluation value is not lower than the reference grid fault response threshold, the fault response adjustment is stopped. Otherwise, a prompt is sent to the preset personnel to diagnose the corresponding grid circuit as abnormal.

10. A power grid fault automatic diagnosis system based on big data analysis, characterized in that: It includes current mutual inductance accuracy analysis module, voltage mutual inductance accuracy analysis module, impact adjustment module and power grid fault response evaluation module: The current mutual inductance accuracy analysis module is used to obtain current mutual inductance related data and perform current mutual inductance accuracy analysis to obtain a current mutual inductance fluctuation value, and obtain a current mutual inductance fluctuation judgment value based on the current mutual inductance fluctuation value and a reference current mutual inductance fluctuation average value obtained from a database. The current mutual inductance fluctuation value is used to reflect the data fluctuation degree of the current transformer during the automatic diagnosis of power grid faults; The voltage mutual inductance accuracy analysis module is used to obtain voltage mutual inductance related data to perform voltage mutual inductance accuracy analysis to obtain a voltage mutual inductance fluctuation value, and to obtain a voltage mutual inductance fluctuation judgment value based on the voltage mutual inductance fluctuation value and a reference voltage mutual inductance fluctuation average value obtained from a database. The voltage mutual inductance fluctuation value is used to reflect the data fluctuation degree of the voltage transformer during the automatic diagnosis of power grid faults; The influence adjustment module is used to determine whether to perform current mutual inductance influence adjustment and voltage mutual inductance influence adjustment based on the acquired current mutual inductance fluctuation judgment value and voltage mutual inductance fluctuation judgment value; The power grid fault response evaluation module is used to perform fault response analysis based on the obtained qualified current mutual inductance fluctuation value, qualified voltage mutual inductance fluctuation value and fault response delay time to obtain a power grid fault response evaluation value, and judge whether to adjust the fault response based on the power grid fault response evaluation value. The power grid fault response evaluation value is used to reflect the power grid fault response situation during the automatic diagnosis of power grid faults.

Images