Power communication network fault positioning method based on alarm association rule mining
Through the method based on alarm association rules mining, combined with historical fault data and environmental data, the deviation problem in the fault location of the power communication network is solved, and more efficient and accurate fault location is achieved.
Patent Information
- Application Number
- CN202410968356.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-18
- Publication Date
- 2024-11-15
AI Technical Summary
The existing fault location methods for power communication networks lack analysis and comparison of historical data, resulting in large deviations in fault location, and the alarm correlation rules cannot be effectively analyzed, making it difficult to accurately determine line failures.
Using the method based on the alarm association rule mining, through alarm association analysis, preliminary deviation coefficient analysis, positioning deviation coefficient analysis, electrical variable detection and fault type judgment, comprehensively analyze historical fault data and environmental data, filter and match alarm signals, and calculate fault location The deviation coefficient ultimately achieves fault location.
It improves the efficiency and accuracy of fault positioning of power communication networks, provides a data basis, effectively analyzes fault types and line faults, and reduces positioning deviations.
Smart Images

Figure CN118972241A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of power communication network fault location, and in particular to a power communication network fault location method based on alarm association rule mining. Background Art
[0002] As a key support network of the power system, the stability and security of the power communication network are crucial to the normal operation of the power system. However, with the continuous expansion of the network scale and the increase in the number of services carried, the difficulty of managing network faults has also increased. The power communication network fault location method based on alarm association rule mining analyzes historical alarm data and discovers the correlation between alarms, thereby quickly locating the root cause of the fault, which is of great significance to improving the operation and maintenance efficiency of the power communication network;
[0003] The existing technology mainly uses traditional fault location methods to locate faults in power communication networks, which lacks analysis and comparison of historical data and causes large deviations in fault location of power communication networks.
[0004] The existing technology lacks rule association for alarm association rules in fault location of power communication network, and cannot effectively analyze the fault type and effectively locate the line fault. Summary of the invention
[0005] The purpose of the present invention is to provide a method for locating faults in a power communication network based on alarm association rule mining, so as to solve the problems raised in the above-mentioned background technology.
[0006] To achieve the above object, the present invention provides the following technical solution: a method for locating faults in a power communication network based on mining of alarm association rules, comprising:
[0007] Alarm correlation analysis step: used to obtain historical fault data of the power communication network, obtain historical fault data corresponding to the target power communication network, and further match and analyze to obtain the main alarm judgment data set and secondary alarm data set corresponding to various line faults of the target power communication network;
[0008] Preliminary deviation coefficient analysis step: used to perform data analysis on the main alarm judgment data set corresponding to various line faults of the target power communication network, and obtain preliminary deviation coefficients of the alarm signal strength of various ordered main judgment alarm signals corresponding to various line faults;
[0009] Positioning deviation coefficient analysis step: used to detect the line conditions corresponding to the target power communication network and the environmental conditions of the target power communication network, obtain the line maintenance data and environmental data corresponding to the target power communication network, and perform comprehensive analysis to obtain the fault positioning deviation coefficients corresponding to various line faults;
[0010] An electric variable detection step; used to monitor the electric variable of the target electric power communication network and obtain the electric variable data corresponding to the target electric power communication network;
[0011] Fault type judgment step: used to collect various alarm signals issued when the target power communication network fails, obtain the alarm signal set corresponding to the target power communication network failure, and further screen and match to obtain the fault type corresponding to the target power communication network;
[0012] Fault location step: used to analyze the fault type corresponding to the target power communication network and the electrical variable data corresponding to the target power communication network to obtain the fault location result of the target power communication network.
[0013] In the preferred embodiment of this scheme, the specific implementation method of the alarm correlation analysis step is as follows:
[0014] Establishing a data extraction relationship between the alarm correlation analysis step and the database, extracting historical fault data corresponding to various line faults stored in the database, wherein the historical fault data includes the fault time point and alarm data set of each line fault, and the alarm data set includes the alarm signal type, alarm signal strength and alarm signal issuance timestamp of each alarm signal corresponding to each line fault;
[0015] Perform alarm signal matching analysis on the alarm signal types of various line faults corresponding to various line faults to obtain the main alarm judgment data set and the secondary alarm data set corresponding to various line faults;
[0016] The main alarm judgment data set refers to the type of alarm signal issued by a type of line fault, and the secondary alarm data set refers to the type of alarm signal issued by a type of line fault. Each alarm signal in the main alarm judgment data set is recorded as a main judgment alarm signal, and the main alarm judgment signals corresponding to each type of line fault are screened to obtain.
[0017] In the preferred embodiment of this scheme, the specific implementation method of the preliminary deviation coefficient analysis step is as follows:
[0018] By screening various main alarm judgment signals corresponding to various line faults, various main alarm judgment signal sets corresponding to various line faults are obtained; and according to the fault time point of each line fault, various main alarm judgment signals in various main alarm judgment signal sets corresponding to various line faults are time-sorted to obtain various ordered main judgment alarm signal sets corresponding to various line faults;
[0019] According to the alarm signal strength of each type of orderly main judgment alarm signal in each type of orderly main judgment alarm signal set, a signal strength change curve of each type of line fault corresponding to each type of orderly main judgment alarm signal is obtained, and the signal strength change curve of each type of line fault corresponding to each type of orderly main judgment alarm signal is divided according to a preset curve division method to obtain each sub-signal strength change curve of each type of line fault corresponding to each type of orderly main judgment alarm signal, and further screen to obtain the latest sub-signal strength change curve of each type of orderly main judgment alarm signal corresponding to each type of line fault;
[0020] Perform curve overlap analysis on the latest sub-signal strength change curve of each type of ordered main judgment alarm signal and the remaining sub-signal strength change curves of the ordered main judgment alarm signal to obtain the curve overlap between the latest sub-signal strength change curve of each type of ordered main judgment alarm signal and the remaining sub-signal strength change curves, screen each sub-signal strength change curve greater than the curve overlap threshold, record each sub-signal strength change curve greater than the curve overlap threshold as each reference sub-signal strength change curve, and screen to obtain the latest sub-signal strength change curve and each reference sub-signal strength change curve of each type of ordered main judgment alarm signal corresponding to each type of line fault;
[0021] Extract information from the latest sub-signal strength change curves of various ordered main judgment alarm signals corresponding to various line faults and various reference sub-signal strength change curves to obtain the latest sub-signal strength change curves. and the slope of each reference signal strength change curve i=1,2,...,l, i represents the number corresponding to each type of line fault, p=1,2,...,q, p represents the number corresponding to each type of ordered main judgment alarm signal, i~p represent the number of each type of ordered main judgment alarm signal corresponding to each type of line fault, m=1,2,...,n, m represents the number of each reference sub-signal strength change curve;
[0022] By calculating the formula Get the initial deviation coefficient df of the alarm signal strength corresponding to various ordered main judgment alarm signals of various line faults i~p , where α1 represents the preset curve slope deviation influencing factor, and α2 represents the preset signal strength preliminary deviation coefficient influencing factor.
[0023] In the preferred embodiment of this scheme, the specific implementation method of the positioning deviation coefficient analysis step is as follows:
[0024] Establish a data extraction relationship between the positioning deviation coefficient analysis step and the database, extract the line impedance coefficient corresponding to each maintenance time difference and each maintenance scale stored in the database, and extract the ideal environment data corresponding to the target power communication network stored in the database, wherein the ideal environment data includes the ideal temperature t′, the ideal humidity h′ and the ideal wind speed wp′;
[0025] The environmental data set corresponding to the target power communication network is obtained through the meteorological website, where the environmental data includes the temperature t, humidity h and wind speed wp corresponding to the area where the target power communication network is located.
[0026] By calculating the formula The initial positioning deviation coefficient pd corresponding to the target power communication network is obtained, wherein β1 represents the preset environmental data correction factor, and β2 represents the preset initial positioning deviation coefficient influencing factor;
[0027] Obtain maintenance data corresponding to the target power communication network through the line maintenance log corresponding to the target power communication network, wherein the maintenance data includes a maintenance time difference and a maintenance scale, and obtain the line impedance coefficient la corresponding to the target power communication network according to the maintenance time difference and the maintenance scale corresponding to the target power communication network;
[0028] By calculating the formula Calculate the fault location deviation coefficient pd corresponding to each type of line fault i ′, where η represents the preset fault location deviation coefficient influencing factor.
[0029] In a preferred embodiment of the present invention, the specific implementation method of the electric variable detection step is as follows:
[0030] The electrical variable data when a fault occurs in the target power communication network is detected by a fault recorder, wherein the electrical variable data includes a current value I and a voltage value U.
[0031] In a preferred embodiment of the present invention, the specific implementation method of the fault type determination step is as follows:
[0032] Receive various alarm signals when a fault occurs in the target power communication network through a signal receiver, establish a fault alarm signal data set, compare and match the fault alarm signal data set corresponding to the target power communication network with the main alarm judgment data set corresponding to various line faults, and obtain the alarm signal coincidence CR of the fault alarm signal data set corresponding to the target power communication network and the main alarm judgment data set corresponding to various line faults. The main alarm judgment data set corresponding to the maximum coincidence of the alarm signal is obtained by screening, and the line fault type corresponding to the main alarm judgment data set is recorded as the fault type of the target power communication network, and the fault location deviation coefficient pd corresponding to the target power communication network is obtained by screening. i ′.
[0033] In a preferred embodiment of the present invention, the specific implementation method of the fault location step is as follows:
[0034] Establishing a data extraction relationship between the fault location step and the database, extracting each standard fault location data set stored in the database and the fault location corresponding to each standard fault location data set;
[0035] By calculating the formula The effective impedance Z corresponding to the target power communication network is obtained, where μ represents a preset impedance influence factor;
[0036] The effective impedance Z corresponding to the target power communication network, the line impedance coefficient la corresponding to the target power communication network, and the fault location deviation coefficient pd corresponding to the target power communication network are calculated. i 'Establish a fault location data set corresponding to the target power communication network, compare the fault location data set corresponding to the target power communication network with each standard fault location data set, obtain the matching degree between the fault location data set corresponding to the target power communication network and each standard fault location data set, select the standard fault location data set corresponding to the maximum matching degree, record the fault location corresponding to the standard fault location data set as the fault location corresponding to the target power communication network, record the fault location corresponding to the target power communication network as the fault location result corresponding to the target power communication network, and upload the fault location result corresponding to the target power communication network to the system for relevant processing.
[0037] Compared with the prior art, the present invention has the following beneficial effects:
[0038] The present invention analyzes the alarm association rules of the historical fault data of the target power communication network, effectively providing a data basis for fault locating the target power communication network. At the same time, the electrical variable data of the target power communication network when a fault occurs is detected by detection equipment, and a fault locating data set is established for comprehensive analysis, which effectively improves the efficiency and accuracy of fault locating the target power communication network. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.
[0040] Figure 1 It is a schematic diagram of the connection steps of the present invention. DETAILED DESCRIPTION
[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0042] See also Figure 1 , the present invention provides a technical solution: a method for locating faults in a power communication network based on alarm association rule mining includes an alarm association analysis step, a preliminary deviation coefficient analysis step, a positioning deviation coefficient analysis step, an electric variable detection step, a fault type judgment step and a fault location step;
[0043] The alarm association analysis step is connected with the preliminary deviation coefficient analysis step and the fault type judgment step, the preliminary deviation coefficient analysis step is connected with the positioning deviation coefficient analysis step and the fault location step, the positioning deviation coefficient analysis step is connected with the fault location step, the electrical variable detection step is connected with the fault location step, and the fault type judgment step is connected with the fault location step;
[0044] The alarm correlation analysis step is used to obtain the historical fault data of the power communication network, obtain the historical fault data corresponding to the target power communication network, and further match and analyze to obtain the main alarm judgment data set and the secondary alarm data set corresponding to various line faults of the target power communication network;
[0045] Furthermore, the specific execution method of the alarm correlation analysis step is as follows:
[0046] Establishing a data extraction relationship between the alarm correlation analysis step and the database, extracting historical fault data corresponding to various line faults stored in the database, wherein the historical fault data includes the fault time point and alarm data set of each line fault, and the alarm data set includes the alarm signal type, alarm signal strength and alarm signal issuance timestamp of each alarm signal corresponding to each line fault;
[0047] Perform alarm signal matching analysis on the alarm signal types of various line faults corresponding to various line faults to obtain the main alarm judgment data set and the secondary alarm data set corresponding to various line faults;
[0048] The main alarm judgment data set refers to the type of alarm signal issued by a type of line fault, and the secondary alarm data set refers to the type of alarm signal issued by a type of line fault. Each alarm signal in the main alarm judgment data set is recorded as a main judgment alarm signal, and the main alarm judgment signals corresponding to each type of line fault are screened to obtain.
[0049] The preliminary deviation coefficient analysis step is used to perform data analysis on the main alarm judgment data set corresponding to various line faults of the target power communication network, and obtain the preliminary deviation coefficient of the alarm signal strength of various ordered main judgment alarm signals corresponding to various line faults;
[0050] Furthermore, the specific implementation of the preliminary deviation coefficient analysis step is as follows:
[0051] By screening various main alarm judgment signals corresponding to various line faults, various main alarm judgment signal sets corresponding to various line faults are obtained; and according to the fault time point of each line fault, various main alarm judgment signals in various main alarm judgment signal sets corresponding to various line faults are time-sorted to obtain various ordered main judgment alarm signal sets corresponding to various line faults;
[0052] According to the alarm signal strength of each type of orderly main judgment alarm signal in each type of orderly main judgment alarm signal set, a signal strength change curve of each type of line fault corresponding to each type of orderly main judgment alarm signal is obtained, and the signal strength change curve of each type of line fault corresponding to each type of orderly main judgment alarm signal is divided according to a preset curve division method to obtain each sub-signal strength change curve of each type of line fault corresponding to each type of orderly main judgment alarm signal, and further screen to obtain the latest sub-signal strength change curve of each type of orderly main judgment alarm signal corresponding to each type of line fault;
[0053] Perform curve overlap analysis on the latest sub-signal strength change curve of each type of ordered main judgment alarm signal and the remaining sub-signal strength change curves of the ordered main judgment alarm signal to obtain the curve overlap between the latest sub-signal strength change curve of each type of ordered main judgment alarm signal and the remaining sub-signal strength change curves, screen each sub-signal strength change curve greater than the curve overlap threshold, record each sub-signal strength change curve greater than the curve overlap threshold as each reference sub-signal strength change curve, and screen to obtain the latest sub-signal strength change curve and each reference sub-signal strength change curve of each type of ordered main judgment alarm signal corresponding to each type of line fault;
[0054] Extract information from the latest sub-signal strength change curves of various ordered main judgment alarm signals corresponding to various line faults and various reference sub-signal strength change curves to obtain the latest sub-signal strength change curves. and the slope of each reference signal strength change curve i=1,2,...,l, i represents the number corresponding to each type of line fault, p=1,2,...,q, p represents the number corresponding to each type of ordered main judgment alarm signal, i~p represent the number of each type of ordered main judgment alarm signal corresponding to each type of line fault, m=1,2,...,n, m represents the number of each reference sub-signal strength change curve;
[0055] By calculating the formula Get the initial deviation coefficient df of the alarm signal strength corresponding to various ordered main judgment alarm signals of various line faults i~p , where α1 represents the preset curve slope deviation influencing factor, and α2 represents the preset signal strength preliminary deviation coefficient influencing factor.
[0056] The location deviation coefficient analysis step is used to detect the line conditions corresponding to the target power communication network and the environmental conditions of the target power communication network, obtain the line maintenance data and environmental data corresponding to the target power communication network, and perform comprehensive analysis to obtain the fault location deviation coefficients corresponding to various line faults;
[0057] Furthermore, the specific execution method of the positioning deviation coefficient analysis step is as follows:
[0058] Establish a data extraction relationship between the positioning deviation coefficient analysis step and the database, extract the line impedance coefficient corresponding to each maintenance time difference and each maintenance scale stored in the database, and extract the ideal environment data corresponding to the target power communication network stored in the database, wherein the ideal environment data includes the ideal temperature t′, the ideal humidity h′ and the ideal wind speed wp′;
[0059] The environmental data set corresponding to the target power communication network is obtained through the meteorological website, where the environmental data includes the temperature t, humidity h and wind speed wp corresponding to the area where the target power communication network is located.
[0060] By calculating the formula The initial positioning deviation coefficient pd corresponding to the target power communication network is obtained, wherein β1 represents the preset environmental data correction factor, and β2 represents the preset initial positioning deviation coefficient influencing factor;
[0061] Obtain maintenance data corresponding to the target power communication network through the line maintenance log corresponding to the target power communication network, wherein the maintenance data includes a maintenance time difference and a maintenance scale, and obtain the line impedance coefficient la corresponding to the target power communication network according to the maintenance time difference and the maintenance scale corresponding to the target power communication network;
[0062] By calculating the formula Calculate the fault location deviation coefficient pd corresponding to each type of line fault i ′, where η represents the preset fault location deviation coefficient influencing factor.
[0063] The electric variable detection step is used to monitor the electric variable of the target power communication network and obtain the electric variable data corresponding to the target power communication network;
[0064] Furthermore, the specific execution method of the electrical variable detection step is as follows:
[0065] The electrical variable data when a fault occurs in the target power communication network is detected by a fault recorder, wherein the electrical variable data includes a current value I and a voltage value U.
[0066] The fault type judgment step is used to collect various alarm signals issued when the target power communication network fails, obtain the alarm signal set corresponding to the target power communication network failure, and further screen and match to obtain the fault type corresponding to the target power communication network;
[0067] Furthermore, the specific execution method of the fault type determination step is as follows:
[0068] Receive various alarm signals when a fault occurs in the target power communication network through a signal receiver, establish a fault alarm signal data set, compare and match the fault alarm signal data set corresponding to the target power communication network with the main alarm judgment data set corresponding to various line faults, and obtain the alarm signal coincidence degree CR of the fault alarm signal data set corresponding to the target power communication network and the main alarm judgment data set corresponding to various line faults. The main alarm judgment data set corresponding to the maximum coincidence degree of the alarm signal is obtained by screening, and the line fault type corresponding to the main alarm judgment data set is recorded as the fault type of the target power communication network, and the fault location deviation coefficient pd′ corresponding to the target power communication network is obtained by screening. i .
[0069] The fault location step is used to analyze the fault type corresponding to the target power communication network and the electrical variable data corresponding to the target power communication network to obtain the fault location result of the target power communication network.
[0070] Furthermore, the specific implementation method of the fault location step is as follows:
[0071] Establishing a data extraction relationship between the fault location step and the database, extracting each standard fault location data set stored in the database and the fault location corresponding to each standard fault location data set;
[0072] By calculating the formula The effective impedance Z corresponding to the target power communication network is obtained, where μ represents a preset impedance influence factor;
[0073] The effective impedance Z corresponding to the target power communication network, the line impedance coefficient la corresponding to the target power communication network, and the fault location deviation coefficient pd′ corresponding to the target power communication network are calculated. iA fault location data set corresponding to the target electric power communication network is established, and the fault location data set corresponding to the target electric power communication network is compared with each standard fault location data set to obtain the matching degree between the fault location data set corresponding to the target electric power communication network and each standard fault location data set, and the standard fault location data set corresponding to the maximum matching degree is selected, and the fault location corresponding to the standard fault location data set is recorded as the fault location corresponding to the target electric power communication network, and the fault location corresponding to the target electric power communication network is recorded as the fault location result corresponding to the target electric power communication network, and the fault location result corresponding to the target electric power communication network is uploaded to the system for relevant processing by the system.
[0074] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.
Claims
1. A method for locating faults in a power communication network based on alarm association rule mining, characterized in that: include: Alarm correlation analysis step: used to obtain historical fault data of the power communication network, obtain historical fault data corresponding to the target power communication network, and further match and analyze to obtain the main alarm judgment data set and secondary alarm data set corresponding to various line faults of the target power communication network; Preliminary deviation coefficient analysis step: used to perform data analysis on the main alarm judgment data set corresponding to various line faults of the target power communication network, and obtain preliminary deviation coefficients of the alarm signal strength of various ordered main judgment alarm signals corresponding to various line faults; Positioning deviation coefficient analysis step: used to detect the line conditions corresponding to the target power communication network and the environmental conditions of the target power communication network, obtain the line maintenance data and environmental data corresponding to the target power communication network, and perform comprehensive analysis to obtain the fault positioning deviation coefficients corresponding to various line faults; Electrical variable detection steps; Used to monitor the electric variables of the target electric power communication network and obtain the electric variable data corresponding to the target electric power communication network; Fault type judgment step: used to collect various alarm signals issued when the target power communication network fails, obtain the alarm signal set corresponding to the target power communication network failure, and further screen and match to obtain the fault type corresponding to the target power communication network; Fault location step: used to analyze the fault type corresponding to the target power communication network and the electrical variable data corresponding to the target power communication network to obtain the fault location result of the target power communication network.
2. The method for locating faults in a power communication network based on alarm association rule mining according to claim 1, characterized in that: The specific implementation method of the alarm correlation analysis step is as follows: Establishing a data extraction relationship between the alarm correlation analysis step and the database, extracting historical fault data corresponding to various line faults stored in the database, wherein the historical fault data includes the fault time point and alarm data set of each line fault, and the alarm data set includes the alarm signal type, alarm signal strength and alarm signal issuance timestamp of each alarm signal corresponding to each line fault; Perform alarm signal matching analysis on the alarm signal types of various line faults corresponding to various line faults to obtain the main alarm judgment data set and the secondary alarm data set corresponding to various line faults; The main alarm judgment data set refers to the type of alarm signal issued by a type of line fault, and the secondary alarm data set refers to the type of alarm signal issued by a type of line fault. Each alarm signal in the main alarm judgment data set is recorded as a main judgment alarm signal, and the main alarm judgment signals corresponding to each type of line fault are screened to obtain.
3. The method for locating faults in a power communication network based on mining alarm association rules according to claim 2, characterized in that: The specific implementation method of the preliminary deviation coefficient analysis step is as follows: By screening various main alarm judgment signals corresponding to various line faults, various main alarm judgment signal sets corresponding to various line faults are obtained; and according to the fault time point of each line fault, various main alarm judgment signals in various main alarm judgment signal sets corresponding to various line faults are time-sorted to obtain various ordered main judgment alarm signal sets corresponding to various line faults; According to the alarm signal strength of each type of orderly main judgment alarm signal in each type of orderly main judgment alarm signal set, a signal strength change curve of each type of line fault corresponding to each type of orderly main judgment alarm signal is obtained, and the signal strength change curve of each type of line fault corresponding to each type of orderly main judgment alarm signal is divided according to a preset curve division method to obtain each sub-signal strength change curve of each type of line fault corresponding to each type of orderly main judgment alarm signal, and further screen to obtain the latest sub-signal strength change curve of each type of orderly main judgment alarm signal corresponding to each type of line fault; Perform curve overlap analysis on the latest sub-signal strength change curve of each type of ordered main judgment alarm signal and the remaining sub-signal strength change curves of the ordered main judgment alarm signal to obtain the curve overlap between the latest sub-signal strength change curve of each type of ordered main judgment alarm signal and the remaining sub-signal strength change curves, screen each sub-signal strength change curve greater than the curve overlap threshold, record each sub-signal strength change curve greater than the curve overlap threshold as each reference sub-signal strength change curve, and screen to obtain the latest sub-signal strength change curve and each reference sub-signal strength change curve of each type of ordered main judgment alarm signal corresponding to each type of line fault; Extract information from the latest sub-signal strength change curves of various ordered main judgment alarm signals corresponding to various line faults and various reference sub-signal strength change curves to obtain the latest sub-signal strength change curves. and the slope of each reference signal strength change curve i=1,2,...,l, i represents the number corresponding to each type of line fault, p=1,2,...,q, p represents the number corresponding to each type of ordered main judgment alarm signal, i~p represent the number of each type of ordered main judgment alarm signal corresponding to each type of line fault, m=1,2,...,n, m represents the number of each reference sub-signal strength change curve; By calculating the formula Get the initial deviation coefficient df of the alarm signal strength corresponding to various ordered main judgment alarm signals of various line faults i~p , where α1 represents the preset curve slope deviation influencing factor, and α2 represents the preset signal strength preliminary deviation coefficient influencing factor.
4. The method for locating faults in a power communication network based on mining alarm association rules according to claim 3 is characterized in that: The specific implementation method of the positioning deviation coefficient analysis step is as follows: Establish a data extraction relationship between the positioning deviation coefficient analysis step and the database, extract the line impedance coefficient corresponding to each maintenance time difference and each maintenance scale stored in the database, and extract the ideal environment data corresponding to the target power communication network stored in the database, wherein the ideal environment data includes the ideal temperature t′, the ideal humidity h′ and the ideal wind speed wp′; The environmental data set corresponding to the target power communication network is obtained through the meteorological website, where the environmental data includes the temperature t, humidity h and wind speed wp corresponding to the area where the target power communication network is located. By calculating the formula The initial positioning deviation coefficient pd corresponding to the target power communication network is obtained, wherein β1 represents the preset environmental data correction factor, and β2 represents the preset initial positioning deviation coefficient influencing factor; Obtain maintenance data corresponding to the target power communication network through the line maintenance log corresponding to the target power communication network, wherein the maintenance data includes a maintenance time difference and a maintenance scale, and obtain the line impedance coefficient la corresponding to the target power communication network according to the maintenance time difference and the maintenance scale corresponding to the target power communication network; By calculating the formula Calculate the fault location deviation coefficient pd corresponding to each type of line fault i ′, where η represents the preset fault location deviation coefficient influencing factor.
5. The method for locating faults in a power communication network based on mining alarm association rules according to claim 1, characterized in that: The specific implementation method of the electrical variable detection step is as follows: The electrical variable data when a fault occurs in the target power communication network is detected by a fault recorder, wherein the electrical variable data includes a current value I and a voltage value U.
6. The method for locating faults in a power communication network based on mining alarm association rules according to claim 1, characterized in that: The specific implementation method of the fault type judgment step is as follows: Receive various alarm signals when a fault occurs in the target power communication network through a signal receiver, establish a fault alarm signal data set, compare and match the fault alarm signal data set corresponding to the target power communication network with the main alarm judgment data set corresponding to various line faults, and obtain the alarm signal coincidence CR of the fault alarm signal data set corresponding to the target power communication network and the main alarm judgment data set corresponding to various line faults. The main alarm judgment data set corresponding to the maximum coincidence of the alarm signal is obtained by screening, and the line fault type corresponding to the main alarm judgment data set is recorded as the fault type of the target power communication network, and the fault location deviation coefficient pd corresponding to the target power communication network is obtained by screening. i ′.
7. The method for locating faults in a power communication network based on alarm association rule mining according to claim 1, characterized in that: The specific implementation method of the fault location step is as follows: Establishing a data extraction relationship between the fault location step and the database, extracting each standard fault location data set stored in the database and the fault location corresponding to each standard fault location data set; By calculating the formula The effective impedance Z corresponding to the target power communication network is obtained, where μ represents a preset impedance influence factor; The effective impedance Z corresponding to the target power communication network, the line impedance coefficient la corresponding to the target power communication network, and the fault location deviation coefficient pd corresponding to the target power communication network are calculated. i 'Establish a fault location data set corresponding to the target power communication network, compare the fault location data set corresponding to the target power communication network with each standard fault location data set, obtain the matching degree between the fault location data set corresponding to the target power communication network and each standard fault location data set, select the standard fault location data set corresponding to the maximum matching degree, record the fault location corresponding to the standard fault location data set as the fault location corresponding to the target power communication network, record the fault location corresponding to the target power communication network as the fault location result corresponding to the target power communication network, and upload the fault location result corresponding to the target power communication network to the system for relevant processing.
