Power distribution network fault line selection sensing measurement and control method and system thereof

Abstract

The invention discloses a power distribution network fault line selection sensing measurement and control method and system, and belongs to the technical field of power grid situation awareness, and the method comprises the steps: obtaining composition lines of a preset power distribution network, collecting the historical fault occurrence frequency of each line in the composition lines, and carrying out the marking and dividing of the composition lines based on the historical fault occurrence frequency; in the composition lines, operation data of all the lines are collected, and the collected operation data are distinguished according to a power distribution network data collection and monitoring data end and a power distribution geographic information data end; according to the invention, the composition lines of the preset power distribution network are divided, other lines which may be affected can be monitored according to the collected data when each line of the preset power distribution network fails, the fault line object can be quickly locked, the fault position can be accurately obtained, and the sensitivity and accuracy of fault line selection judgment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid situation awareness, and in particular to a method and system for sensing and controlling fault line selection in a distribution network. Background Art

[0002] In recent years, many power grid accidents have occurred in various regions of the world, causing serious economic losses and social harm, and have attracted widespread attention from researchers. One of the research directions is to predict the line selection of faulty lines. Its core purpose is to quickly and accurately identify the faulty lines in the power system, thereby improving the reliability and operation efficiency of the power grid. This process involves the precise identification and positioning of the faulty lines so that timely measures can be taken to restore power supply, thereby reducing the duration and scope of power outages. In real life, the topological structure of the distribution network system is complex and the distribution changes are diverse. In order to realize the line selection of the distribution network fault line, the technical application number CN202410260090.1 provides a method and system for online monitoring of power distribution line faults in the power grid. The technical method of this technical application is to respond to the client, receive the distribution network fault monitoring request, and feedback the fault nodes of each monitored line to the client, so as to achieve high-precision fault node analysis and positioning, improve the timeliness of distribution network operation and maintenance, and thus ensure the operation reliability and safety of the distribution network; and another technical application number CN202111549513.4 provides a distribution network situation awareness method and system suitable for new power systems. The technical method provided is to conduct all-round and visual operation and dispatch of the distribution network operation status, thereby effectively improving the dispatching efficiency of the distribution network, so as to perceive and predict the fault line, so as to ensure the smooth operation of the distribution network and improve the power supply reliability.

[0003] The fault line selection in the prior art is based on the conductor resistance and reactance characteristics of the power system. When a fault occurs in the power system, a short circuit will be formed. Since the short-circuit current will generate a large voltage drop loss, the fault location can be determined based on the conductor resistance and reactance characteristics of the power grid by measuring the voltage and current at different positions. In the distribution network, the feeder is a branch connected to any distribution network node, which is the most common transmission line in the power system. However, the line selection method of the above technical application is mostly limited to the feeder. When selecting the fault line, various types of conductors, such as transition lines and branch lines, need to be considered. If only the feeder is selected as the object of fault detection, the problems of other conductors will be ignored, resulting in errors and delays. At the same time, the above technical solution does not consider the distribution of the resistance of the power grid conductor, because even for the same type of conductor, the conductor resistance at different positions will also be greatly different. In this case, it is easy to misjudge the fault location. Summary of the invention

[0004] In view of the above-mentioned problems existing in the technical field of existing power grid situation awareness, the present invention is proposed.

[0005] Therefore, one of the objects of the present invention is to provide a distribution network fault line selection perception measurement and control method and system thereof, which divides the constituent lines of a preset distribution network, and can monitor other lines that may be affected based on the collected data when a fault occurs in each line of the preset distribution network, and can analyze the operating characteristics of these lines separately, and then, when a fault occurs in a future period, these line objects can be analyzed and checked in time, thereby not only being able to quickly lock the fault line object, but also being able to accurately obtain the fault location, thereby improving the sensitivity and accuracy of fault line selection judgment.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] On the one hand, the present invention provides a method for sensing and controlling fault line selection in a distribution network, comprising the following steps:

[0008] Obtaining constituent lines of a preset power distribution network, collecting the number of historical fault occurrences of each line in the constituent lines, and marking and dividing the constituent lines based on the number of historical fault occurrences;

[0009] In the component lines, the operation data of each line is collected, and the collected operation data is distinguished according to the distribution network data collection and monitoring data terminal and the distribution geographic information data terminal;

[0010] In each of the distinguished data ends, the associated features of the changes in the operating data of each data end are analyzed, and a data set is generated, and in the data set, a training set, a test set and a validation set based on the distribution network data acquisition and monitoring data end are divided;

[0011] Based on the distribution network data acquisition and monitoring data terminal, the operation data is divided into ▽1, ▽2, ..., ▽ n , wherein n represents the nth type of operation data, and in each of the divided operation data, the operation data corresponding to the occurrence of the line fault is collected, and the data characteristics of the operation data are analyzed;

[0012] In each of the divided operation data, the operation data is divided into safety levels according to the number of historical line fault occurrences, and a prediction model is generated.

[0013] As a preferred solution of the present invention, the constituent lines are marked and divided, including dividing the constituent lines into lines with a large number of fault occurrences and lines with a small number of fault occurrences, wherein the number of divided lines with a large number of fault occurrences is at least more than half of the total number of constituent lines, and at the same time, among the lines with a large number of fault occurrences, the lines are divided into main fault lines and secondary fault lines, wherein the secondary fault line is an affected line, and the main fault line is an original fault line, and the correlation between the fault characteristics of the main fault line and the secondary fault line is analyzed.

[0014] As a preferred solution of the present invention, wherein: the distribution network data acquisition and monitoring data terminal includes monitoring the bus voltage, line current, active and / or reactive power and electric energy data of the power supply line;

[0015] The power distribution geographic information includes spatial data and non-spatial data, wherein the spatial data includes the geographical location, terrain and / or land features of the preset power distribution network, and the non-spatial data includes environmental parameters, which include natural environmental condition data, and the natural environmental condition data includes temperature, humidity, altitude and air pressure.

[0016] As a preferred solution of the present invention, the operation data includes line resistance data, the change characteristics of the resistance data are obtained in the main fault line, and the change characteristics are uploaded to the prediction model, the prediction model is updated, and the change characteristics are divided into a first change characteristic, a second change characteristic and a third change characteristic, the affected lines under different change characteristics are collected, and the characteristic value is collected in each change characteristic, and the data change of the affected line under the characteristic value is calculated, and the data change includes voltage and current data changes, which are calculated according to the following formula:

[0017] Z = [(T + A x ×V x )]·Ω; where Z represents the characteristic value of resistance;

[0018] Where, Τ represents the monitoring time, Α x represents the fault current data collected by the affected line at the xth time point, V x represents the fault voltage data collected at the xth time point of the affected line, wherein both of the two time points include the time point when the fault of the affected line occurs; Ω represents the resistance data corresponding to the fault current data collected at the xth time point and the fault voltage data collected at the xth time point.

[0019] As a preferred solution of the present invention, the data changes of current and voltage ten minutes before the time point when the affected line fault occurs are collected based on the time point when the fault occurs, and the current and voltage data change trends within the ten minutes are analyzed based on the current and voltage data at the time point when the fault occurs, and the median data of the current and voltage are intercepted in the data change trend, and a safety threshold is preset based on the median data. When the main fault line fails in a future period, the current and voltage data changes of the secondary fault line are collected. If the collected current and voltage data changes exceed the safety threshold, it is determined that the fault of the main fault line will cause the collected line to fail, and an early warning is issued. Otherwise, no determination is made.

[0020] As a preferred solution of the present invention, in the secondary fault line, the line is divided into high-risk impact line and low-risk impact line according to the number of times each line is affected, and based on the high-risk impact line, the resistance data of different characteristic segments of the line are collected, wherein the different characteristic segments include an ambient temperature segment and an air pressure segment, and in the ambient temperature segment, based on the collected ambient temperature, a temperature data set δ=[δ1, δ2, ..., δ n ], where n represents the nth temperature feature, and the variation pattern of the resistance data of the high-risk impact line under different temperature features is analyzed, and the correlation pattern with the resistance data of the main fault line is analyzed based on the variation pattern.

[0021] As a preferred solution of the present invention, resistance data when a fault occurs in the high-risk affecting line is collected in different temperature characteristics, and the resistance data is sorted in the order before and after the fault occurs, and the first 3 to 5 resistance data closest to the resistance data are intercepted in the sorted resistance data. When the resistance change trend of the high-risk affecting line in the future time period conforms to the change law of the first 3 intercepted resistance data, it is determined that the line will fail and an early warning is issued. Otherwise, no determination is made.

[0022] As a preferred solution of the present invention, the resistance change trends of each component line in the high-risk impact line are compared and analyzed, and the same resistance data within at least ten minutes before the fault occurs is collected in the comparison and analysis results, and the resistance data is calibrated as risk data. When the resistance change data of a line in the high-risk impact line in a future period is the same as the risk data, it is determined that the line will fail and an early warning is issued. Otherwise, no determination is made.

[0023] As a preferred solution of the present invention, the risk data is sampled using the Monte Carlo method, the ambient temperature corresponding to the sampled data is monitored, and the changing trend of the ambient temperature is monitored. When the changing trend of the ambient temperature changes toward the ambient temperature corresponding to the sampled data, the lines matching the sampled data in the high-risk impact lines are monitored, otherwise, they are not monitored.

[0024] On the other hand, the present invention provides a distribution network fault line selection sensing and measurement control system, which is applied to a distribution network fault line selection sensing and measurement control method as claimed in claim 1, comprising:

[0025] An information acquisition module is used to acquire constituent lines of a preset power distribution network, collect the number of historical fault occurrences of each line in the constituent lines, and mark and divide the constituent lines based on the number of historical fault occurrences;

[0026] A data collection module, in the component lines, is used to collect the operation data of each line, and distinguish the collected operation data according to the distribution network data collection and monitoring data terminal and the distribution geographic information data terminal;

[0027] A data analysis module, in each of the distinguished data terminals, is used to analyze the associated features of the changes in the operating data of each data terminal, and generate a data set, and in the data set, divide the training set, the test set and the validation set based on the distribution network data acquisition and monitoring data terminal;

[0028] A data division module is used to divide the operation data into ▽1, ▽2, ..., ▽ based on the distribution network data acquisition and monitoring data terminal. n , wherein n represents the nth type of operation data, and in each of the divided operation data, the operation data corresponding to the occurrence of the line fault is collected, and the data characteristics of the operation data are analyzed;

[0029] A data early warning module is used to classify the operation data into safety levels according to the number of historical line faults in each divided operation data, and generate a prediction model;

[0030] A fault determination module, which responds to the constituent line data of the preset power distribution network acquired by the information acquisition module, is used to divide the constituent lines into lines with a high number of faults and lines with a low number of faults, and analyzes and determines the change trend of the line current and voltage data collected, and presets a safety threshold according to the current and voltage data of the line during safe operation, and performs fault warning judgment on the change trend of the current and voltage according to the safety threshold.

[0031] By dividing the constituent lines of the preset distribution network, the present invention can monitor other lines that may be affected based on the collected data when a fault occurs in each line of the preset distribution network, and can analyze the operating characteristics of these lines separately, so that when a fault occurs in a future period, these line objects can be analyzed and checked in time, thereby not only quickly locking the fault line object, but also accurately obtaining the fault location, thereby improving the sensitivity and accuracy of fault line selection judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0033] Figure 1 A schematic diagram of a method flow of an embodiment of the present invention;

[0034] Figure 2 This is a schematic diagram of the modular structure of a distribution network fault line selection sensing and control system according to an embodiment of the present invention;

[0035] Figure 3 It is a schematic diagram of the process structure of an embodiment of the present invention;

[0036] Numbers in the figure: 110 - information acquisition module; 120 - data acquisition module; 130 - data analysis module; 140 - data warning module; 150 - fault determination module. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0038] Since the line selection methods of the prior art are mostly limited to feeder lines, various types of conductors, such as transition lines and branch lines, need to be considered when selecting fault lines. If only feeder lines are selected as the object of troubleshooting, problems with other conductors will be ignored, resulting in errors and delays. At the same time, the prior art also does not consider the distribution of grid conductor resistance, because even for the same type of conductor, the conductor resistance at different locations will vary greatly, in which case, it is easy to misjudge the fault location.

[0039] Based on this, the present invention proposes a distribution network fault line selection perception measurement and control method and system, which divides the constituent lines of the preset distribution network, and can monitor other lines that may be affected according to the collected data when faults occur in the lines of the preset distribution network, and can analyze the operating characteristics of these lines separately, and then, when a fault occurs in the future period, these line objects can be analyzed and checked in time, so that not only can the fault line object be quickly locked, but also the fault location can be accurately obtained, thereby improving the sensitivity and accuracy of fault line selection judgment.

[0040] The present invention is further described in detail below through embodiments and in conjunction with the accompanying drawings.

[0041] Reference Figures 1 to 3 , is an embodiment of the present invention, which provides a method for sensing and controlling fault line selection in a distribution network, comprising the following steps:

[0042] S10: Obtain constituent lines of a preset distribution network, collect the number of historical faults of each line in the constituent lines, and mark and divide the constituent lines based on the number of historical faults;

[0043] It should be emphasized in this embodiment that the constituent lines are marked and divided, including dividing the constituent lines into lines with a large number of fault occurrences and lines with a small number of fault occurrences, wherein the number of divided lines with a large number of fault occurrences is at least more than half of the total number of constituent lines, and at the same time, among the lines with a large number of fault occurrences, the lines are divided into main fault lines and secondary fault lines, wherein the secondary fault line is the affected line and the main fault line is the original fault line, and the correlation between the fault characteristics of the main fault line and the secondary fault line is analyzed;

[0044] This embodiment further obtains the change characteristics of the resistance data in the main fault line, uploads the change characteristics to the prediction model, updates the prediction model, and divides the change characteristics into the first change characteristics, the second change characteristics, and the third change characteristics. The affected lines under different change characteristics are collected, and the characteristic values ​​are collected in each change characteristic. The data changes of the affected lines under the characteristic value are calculated, and the data changes include voltage and current data changes, which are calculated according to the following formula:

[0045] Z = [(T + A x ×V x )]·Ω; where Z represents the characteristic value of resistance;

[0046] Where, Τ represents the monitoring time, Α x represents the fault current data collected by the affected line at the xth time point, V xrepresents the fault voltage data collected at the xth time point of the affected line, wherein both time points include the time point when the fault of the affected line occurs; Ω represents the resistance data corresponding to the fault current data collected at the xth time point and the fault voltage data collected at the xth time point;

[0047] On the basis of the above, it is important to emphasize in this embodiment that the data changes of current and voltage ten minutes before the time point when the affected line fault occurs are collected based on the time point when the fault occurs, and the current and voltage data change trends within ten minutes are analyzed based on the current and voltage data at the time point when the fault occurs, and the median data of the current and voltage are intercepted from the data change trend, and the safety threshold is preset based on the median data. When the main fault line fails in the future period, the current and voltage data changes of the secondary fault line are collected. If the collected current and voltage data changes exceed the safety threshold, it is determined that the fault of the main fault line will cause the collected line to fail, and an early warning is issued. Otherwise, no determination is made.

[0048] S20: Collecting the operation data of each line in the constituent lines, and distinguishing the collected operation data according to the distribution network data collection and monitoring data terminal and the distribution geographic information data terminal;

[0049] Specifically, in this embodiment, the distribution network data acquisition and monitoring data terminal includes monitoring the bus voltage, line current, active and / or reactive power, and electric energy data of the power supply line;

[0050] The power distribution geographic information includes spatial data and non-spatial data, wherein the spatial data includes the geographical location, terrain and / or features of the preset power distribution network, and the non-spatial data includes environmental parameters, which include natural environmental condition data, and the natural environmental condition data includes temperature, humidity, altitude and air pressure;

[0051] According to the operation of the power grid, through the above distinction, real-time data collection of the distribution network can be carried out, including voltage, current and power factor, and segmented collection can be carried out as needed to more accurately monitor and analyze the line operation status; it needs to be further explained that the advantage of end-to-end collection is that it can more accurately locate and analyze the problem areas in the distribution network. When a failure occurs in the distribution network, the data collected by segmentation can help quickly determine the fault location, reduce the scope of power outage and recovery time. In addition, end-to-end collection can also optimize the operation mode of the distribution network and improve the quality and efficiency of power supply;

[0052] Wherein, the operation data includes line resistance data;

[0053] S30: Analyze the correlation characteristics of the operation data changes of each data end in each of the distinguished data ends, and generate a data set, and divide the data set into a training set, a test set and a validation set based on the distribution network data collection and monitoring data end;

[0054] S40: Based on the distribution network data collection and monitoring data terminal, the operation data is divided into Wherein, n represents the nth type of operation data, and among the divided operation data, the operation data corresponding to the occurrence of the line fault is collected, and the data characteristics of the operation data are analyzed at the same time;

[0055] It should be emphasized in this embodiment that, in the secondary fault line, the line is divided into high-risk impact line and low-risk impact line according to the number of times each line is affected, and based on the high-risk impact line, the resistance data of different characteristic segments of the line are collected, wherein the different characteristic segments include the ambient temperature segment and the air pressure segment, and in the ambient temperature segment, based on the collected ambient temperature, a temperature data set δ=[δ1, δ2, ..., δ n ], where n represents the nth temperature feature, and the resistance data variation law of the high-risk impact line under different temperature features is analyzed, and the correlation law with the resistance data of the main fault line is analyzed based on the variation law;

[0056] At the same time, based on the above, this embodiment collects resistance data when a fault occurs in a high-risk impact line in different temperature characteristics, and sorts the resistance data according to the order of the fault occurrence, and intercepts the first 3 to 5 resistance data closest to the resistance data in the sorted resistance data. When the resistance change trend of the high-risk impact line in the future period conforms to the change law of the first 3 resistance data intercepted, it is determined that the line will fail and an early warning is issued, otherwise, no determination is made;

[0057] This embodiment further compares and analyzes the resistance change trends of each component line in the high-risk impact line, collects the same resistance data at least ten minutes before the fault occurs in the comparison and analysis results, and marks the resistance data as risk data. When the resistance change data of a line in the high-risk impact line in the future period is the same as the risk data, it is determined that the line will fail and issue an early warning. Otherwise, no determination is made.

[0058] At the same time, the present embodiment also includes sampling the risk data using the Monte Carlo method, monitoring the ambient temperature corresponding to the sampled data, and monitoring the change trend of the ambient temperature. When the change trend of the ambient temperature changes toward the ambient temperature corresponding to the sampled data, the line matching the sampled data is monitored among the high-risk impact lines, otherwise, it is not monitored.

[0059] S50: classifying the operation data into safety levels according to the number of historical line faults in the divided operation data, and generating a prediction model;

[0060] It should be noted that in this embodiment, the operating data is divided into security levels, including dividing the operating data into high-security operating data, medium-security operating data and low-security operating data in a step-by-step manner. When the operating data of a line with a high number of faults changes from high-security operating data to medium-security operating data, monitoring of the line with a high number of faults is started, otherwise, no monitoring is performed.

[0061] Based on the above, it can be known that the present application divides the constituent lines of the preset distribution network. When a fault occurs in any line of the preset distribution network, other lines that may be affected can be monitored based on the collected data, and the operating characteristics of these lines can be analyzed separately. Therefore, when a fault occurs in a future period, these line objects can be analyzed and checked in a timely manner, thereby not only being able to quickly lock the faulty line object, but also being able to accurately obtain the fault location, thereby improving the sensitivity and accuracy of faulty line selection.

[0062] In combination with the above-mentioned distribution network fault line selection sensing and control method, this embodiment also proposes a working system applied to the method, as follows:

[0063] The information acquisition module 110 is used to acquire the constituent lines of the preset power distribution network, collect the number of historical faults of each line in the constituent lines, and mark and divide the constituent lines based on the number of historical faults;

[0064] The data collection module 120 is used to collect the operation data of each line in the composition line, and distinguish the collected operation data according to the distribution network data collection and monitoring data terminal and the distribution geographic information data terminal;

[0065] The data analysis module 130 is used to analyze the associated features of the changes in the operating data of each data end in each of the distinguished data ends, and generate a data set, and divide the data set into a training set, a test set and a validation set based on the distribution network data collection and monitoring data end;

[0066] The data division module is used to divide the operation data into ▽1, ▽2, ..., ▽ based on the distribution network data acquisition and monitoring data terminal. n ,in, n Indicates the nth type of operation data, and collects the operation data corresponding to the occurrence of the line fault in each divided operation data, and analyzes the data characteristics of the operation data;

[0067] The data warning module 140 is used to classify the operation data into safety levels according to the number of historical line faults in each divided operation data, and generate a prediction model;

[0068] The fault judgment module 150 responds to the constituent line data of the preset power distribution network obtained by the information acquisition module, and is used to divide the constituent lines into lines with a large number of faults and lines with a small number of faults, and analyze and judge the changing trend of the line current and voltage data collected, and preset a safety threshold according to the current and voltage data of the line during safe operation, and make a fault warning judgment on the changing trend of the current and voltage according to the safety threshold.

[0069] In summary, the present invention divides the constituent lines of the preset distribution network, and can monitor other lines that may be affected based on the collected data when a fault occurs in each line of the preset distribution network, and can analyze the operating characteristics of these lines separately, so that when a fault occurs in a future period, these line objects can be analyzed and checked in time, thereby not only quickly locking the fault line object, but also accurately obtaining the fault location, thereby improving the sensitivity and accuracy of fault line selection.

[0070] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for sensing and controlling fault line selection in a distribution network, characterized in that: The following steps are involved: Obtaining constituent lines of a preset power distribution network, collecting the number of historical fault occurrences of each line in the constituent lines, and marking and dividing the constituent lines based on the number of historical fault occurrences; In the component lines, the operation data of each line is collected, and the collected operation data is distinguished according to the distribution network data collection and monitoring data terminal and the distribution geographic information data terminal; In each of the distinguished data ends, the associated features of the changes in the operating data of each data end are analyzed, and a data set is generated, and in the data set, a training set, a test set and a validation set based on the distribution network data acquisition and monitoring data end are divided; Based on the distribution network data acquisition and monitoring data terminal, the operation data is divided into Wherein, n represents the nth type of operation data, and among the divided operation data, the operation data corresponding to the occurrence of the line fault is collected, and the data characteristics of the operation data are analyzed at the same time; In each of the divided operation data, the operation data is divided into safety levels according to the number of historical line fault occurrences, and a prediction model is generated.

2. A method for sensing and controlling fault line selection in a distribution network according to claim 1, characterized in that: The component lines are marked and divided, including dividing the component lines into lines with a large number of fault occurrences and lines with a small number of fault occurrences, wherein the number of divided lines with a large number of fault occurrences is at least more than half of the total number of the component lines, and at the same time, among the lines with a large number of fault occurrences, the lines are divided into main fault lines and secondary fault lines, wherein the secondary fault line is an affected line and the main fault line is an original fault line, and the correlation between the fault characteristics of the main fault line and the secondary fault line is analyzed.

3. A method for sensing and controlling fault line selection in a distribution network according to claim 1, characterized in that: The distribution network data acquisition and monitoring data terminal includes monitoring the bus voltage, line current, active and / or reactive power and electric energy data of the power supply line; The power distribution geographic information includes spatial data and non-spatial data, wherein the spatial data includes the geographical location, terrain and / or land features of the preset power distribution network, and the non-spatial data includes environmental parameters, which include natural environmental condition data, and the natural environmental condition data includes temperature, humidity, altitude and air pressure.

4. A method for sensing and controlling fault line selection in a distribution network as claimed in claim 2, characterized in that: The operation data includes line resistance data, and the change characteristics of the resistance data are obtained in the main fault line, and the change characteristics are uploaded to the prediction model, and the prediction model is updated. At the same time, the change characteristics are divided into a first change characteristic, a second change characteristic, and a third change characteristic, and the affected lines under different change characteristics are collected, and the characteristic value is collected in each change characteristic, and the data change of the affected line under the characteristic value is calculated, and the data change includes the voltage and current data change, which is calculated according to the following formula: Z = [(T + A x ×V x )]·Ω; where Z Indicates the characteristic value of resistance; Where, Τ represents the monitoring time, Α x represents the fault current data collected by the affected line at the xth time point, V x represents the fault voltage data collected at the xth time point of the affected line, wherein both of the two time points include the time point when the fault of the affected line occurs; Ω represents the resistance data corresponding to the fault current data collected at the xth time point and the fault voltage data collected at the xth time point.

5. A method for sensing and controlling fault line selection in a distribution network as claimed in claim 4, characterized in that: Based on the time point when the affected line fault occurs, the data changes of current and voltage in the ten minutes before the time point are collected, and based on the current and voltage data at the time point when the fault occurs, the trend of current and voltage data changes within the ten minutes is analyzed, and at the same time, the median data of current and voltage are intercepted in the data change trend, and a safety threshold is preset with the median data. When the main fault line fails in a future period, the current and voltage data changes of the secondary fault line are collected. If the collected current and voltage data changes exceed the safety threshold, it is determined that the fault of the main fault line will cause the collected line to fail, and an early warning is issued. Otherwise, no determination is made.

6. A method for sensing and controlling fault line selection in a distribution network as claimed in claim 5, characterized in that: In the secondary fault line, the line is divided into high-risk impact lines and low-risk impact lines according to the number of times each line is affected, and based on the high-risk impact line, resistance data of different characteristic segments of the line are collected, wherein the different characteristic segments include an ambient temperature segment and an air pressure segment, and in the ambient temperature segment, based on the collected ambient temperature, a temperature data set δ=[δ1, δ2, ..., δ n ], where n represents the nth temperature feature, and the variation pattern of the resistance data of the high-risk impact line under different temperature features is analyzed, and the correlation pattern with the resistance data of the main fault line is analyzed based on the variation pattern.

7. A method for sensing, measuring and controlling fault line selection in a distribution network according to claim 6, characterized in that: The resistance data when a fault occurs in the high-risk impact line is collected in different temperature characteristics, and the resistance data is sorted in the order before and after the fault occurs, and the first 3 to 5 resistance data closest to the resistance data are intercepted in the sorted resistance data. When the resistance change trend of the high-risk impact line in the future time period conforms to the change law of the first 3 intercepted resistance data, it is determined that the line will fail and an early warning is issued. Otherwise, no determination is made.

8. A method for sensing, measuring and controlling fault line selection in a distribution network as claimed in claim 7, characterized in that: The resistance change trends of each component line in the high-risk impact line are compared and analyzed, and the same resistance data within at least ten minutes before the fault occurs is collected in the comparison and analysis results, and the resistance data is calibrated as risk data. When the resistance change data of a line in the high-risk impact line in a future period is the same as the risk data, it is determined that the line will fail and an early warning is issued. Otherwise, no determination is made.

9. A method for sensing, measuring and controlling fault line selection in a distribution network as claimed in claim 8, characterized in that: The risk data is sampled using the Monte Carlo method, the ambient temperature corresponding to the sampled data is monitored, and the changing trend of the ambient temperature is monitored. When the changing trend of the ambient temperature changes toward the ambient temperature corresponding to the sampled data, the lines matching the sampled data in the high-risk impact lines are monitored, otherwise, they are not monitored.

10. A distribution network fault line selection sensing and measurement control system, applied to a distribution network fault line selection sensing and measurement control method as claimed in claim 1, characterized in that: include: An information acquisition module is used to acquire constituent lines of a preset power distribution network, collect the number of historical fault occurrences of each line in the constituent lines, and mark and divide the constituent lines based on the number of historical fault occurrences; A data collection module, in the component lines, is used to collect the operation data of each line, and distinguish the collected operation data according to the distribution network data collection and monitoring data terminal and the distribution geographic information data terminal; A data analysis module, in each of the distinguished data terminals, is used to analyze the associated features of the changes in the operating data of each data terminal, and generate a data set, and in the data set, divide the training set, the test set and the validation set based on the distribution network data acquisition and monitoring data terminal; The data division module is used to divide the operation data into Wherein, n represents the nth type of operation data, and among the divided operation data, the operation data corresponding to the occurrence of the line fault is collected, and the data characteristics of the operation data are analyzed at the same time; A data early warning module is used to classify the operation data into safety levels according to the number of historical line faults in each divided operation data, and generate a prediction model; A fault determination module, wherein the fault determination module responds to the constituent line data of the preset power distribution network acquired by the information acquisition module, and is used to divide the constituent lines into lines with a high number of fault occurrences and lines with a low number of fault occurrences, and analyze and determine the change trend of the line current and voltage according to the collected line current and voltage data, and preset a safety threshold according to the current and voltage data of the line during safe operation, and perform fault warning determination on the change trend of the current and voltage according to the safety threshold.

Images