Power distribution network fault power failure analysis method and device

Abstract

The invention provides a power distribution network fault power failure analysis method and device, and belongs to the field of power grid fault analysis. The method comprises the following steps: acquiring power failure information, wherein the power failure information comprises power failure alarm information and power failure fault coordinates acquired by a terminal; the power failure information is input into a pre-trained alarm topology model, a regional power utilization topology fault graph of superior branch topology is generated, and the regional power utilization topology fault graph comprises all power failure fault positions; obtaining a fault data record set of all branch switches in the regional power utilization topology fault graph based on the regional power utilization topology fault graph; inputting the regional power utilization topology fault diagram and the fault data record set into a pre-trained fault type determination model, and generating a fault type corresponding to each fault position; and performing fault analysis based on all fault positions, fault types and historical fault information. According to the invention, the power failure fault can be accurately analyzed.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid fault analysis, and in particular to a method and device for analyzing power outage caused by a power distribution network fault. Background Art

[0002] Power supply service is one of the important tasks of power grid enterprises. It runs through various links and departments such as production safety, marketing services, power grid construction, and power regulation, and is a key reflection of the comprehensive management level of power grid enterprises.

[0003] With the rapid development of society, people's quality of life is constantly improving, and daily electricity consumption is also increasing, which puts higher requirements on the reliability of power supply of the power grid. Power supply reliability reflects the level of power supply development in a province. It is very necessary to enhance the speed and efficiency of power outage perception, solve the problem of rapid perception and accurate positioning of power outages in substations, effectively shorten the line fault recovery time, and improve the operation and maintenance level of the distribution network, so as to improve the overall quality of users' service to the power industry.

[0004] However, the equipment in the power grid is numerous and widespread, and their health levels and operating environments vary greatly. At present, the judgment and processing are mainly based on the power outage signal of a single automation system, which makes the existing fault analysis accuracy low and the real-time performance poor. It cannot effectively support the service dispatch to carry out active warning services for fault power outages, and cannot adapt to the development of digital transformation of distribution networks. Summary of the invention

[0005] The embodiment of the present invention provides a method and device for analyzing power outage due to a power distribution network fault, so as to solve the problem that the current analysis method cannot accurately analyze the power outage fault that occurs.

[0006] In a first aspect, an embodiment of the present invention provides a method for analyzing power outages caused by power distribution network faults, comprising:

[0007] Obtain power outage information, which includes power outage alarm information and power outage fault coordinates obtained by the terminal;

[0008] The power outage information is input into a pre-trained alarm topology model to generate a regional power consumption topology fault map of the upper branch topology, where the regional power consumption topology fault map includes all power outage fault locations;

[0009] Based on the regional power consumption topology fault map, a fault data record set of all branch switches in the regional power consumption topology fault map is obtained; wherein the data record set includes a sequential record of current mutation events of each branch switch;

[0010] Input the regional power topology fault map and the fault data record set into the pre-trained fault type determination model to generate the fault type corresponding to each fault location;

[0011] Perform fault analysis based on all fault locations, fault types, and historical fault information.

[0012] In one possible implementation, the alarm topology model includes the topological relationship of the distribution network and the alarm information set of the distribution network. The alarm terminal of the upper-level branch topology associated with the power outage alarm information is determined based on the power outage alarm information obtained by the terminal and the alarm information set of the distribution network; the alarm topology model generates a power consumption topology fault map based on the alarm terminal, power outage fault coordinates and topological relationship of the upper-level branch topology.

[0013] In a possible implementation, the fault type determination model is obtained based on the sequential records of historical current mutation events of branch switches at various locations in the distribution network area and the corresponding fault type training of the branch switches at various locations.

[0014] In a possible implementation, based on all fault locations and fault types and historical fault information, fault analysis is performed, including:

[0015] Based on historical fault information, count the number of occurrences of each fault type at each fault location;

[0016] When the number of faults occurring at the same fault location within a first preset time interval is greater than a first threshold, determining the fault location as a focus area;

[0017] When the number of faults occurring at the same fault location within a first preset time interval is greater than a first threshold value and less than a second preset threshold value, the fault location is determined as a focus area;

[0018] Based on the areas of concern and key areas, corresponding early warning strategies are formulated respectively.

[0019] In a possible implementation, corresponding early warning strategies are formulated based on the concerned areas and the focused areas, including:

[0020] When the fault location is determined as the area of ​​concern, if the fault type of the fault location is a user-side fault, the monitoring frequency of the electrical signal at the fault location is increased; if the fault type of the fault location is a line fault, power protection equipment or smart power meters are added to the line at the fault location.

[0021] In a possible implementation, corresponding early warning strategies are formulated based on the concerned areas and the focused areas, and also include:

[0022] When the fault location is determined as a focus area, if the fault type of the fault location is a user-side fault, the fault location is repaired; if the fault type of the fault location is a line fault, the line inspection of the fault location is strengthened.

[0023] In a possible implementation, after performing fault analysis based on all fault locations, fault types, and historical fault information, the following steps are further included:

[0024] Generate early warning information for users, areas and lines affected by the power outage location based on all fault locations and fault analysis;

[0025] Send power outage information to users based on early warning information.

[0026] In a possible implementation, after performing fault analysis based on all fault locations, fault types, and historical fault information, the following steps are further included:

[0027] Generate a fault repair work order based on all fault locations and the fault type of each fault location;

[0028] Determine emergency repair methods based on the fault report work order and carry out fault repair.

[0029] In a possible implementation, the fault repair work order includes the electricity usage type of the faulty user corresponding to the fault location, the meter status of the faulty user, and the line information of the faulty user.

[0030] In a second aspect, an embodiment of the present invention provides a distribution network fault power outage analysis device, comprising:

[0031] A first acquisition module is used to acquire power outage information, where the power outage information includes power outage alarm information and power outage fault coordinates acquired by the terminal;

[0032] A topology generation module is used to input the power outage information into a pre-trained alarm topology model to generate a regional power consumption topology fault map of the upper branch topology, wherein the regional power consumption topology fault map includes all power outage fault locations;

[0033] The second acquisition module is used to acquire the fault data record set of all branch switches in the regional power consumption topology fault map based on the regional power consumption topology fault map; wherein the data record set includes the sequence record of the current mutation event of each branch switch;

[0034] A type determination module is used to input the regional power consumption topology fault map and the fault data record set into a pre-trained fault type determination model to generate a fault type corresponding to each fault location;

[0035] The fault analysis module is used to perform fault analysis based on all fault locations and fault types as well as historical fault information.

[0036] In one possible implementation, the alarm topology model includes the topological relationship of the distribution network and the alarm information set of the distribution network. The alarm terminal of the upper-level branch topology associated with the power outage alarm information is determined based on the power outage alarm information obtained by the terminal and the alarm information set of the distribution network; the alarm topology model generates a power consumption topology fault map based on the alarm terminal, power outage fault coordinates and topological relationship of the upper-level branch topology.

[0037] In a possible implementation, the fault type determination model is obtained based on the sequential records of historical current mutation events of branch switches at various locations in the distribution network area and the corresponding fault type training of the branch switches at various locations.

[0038] In a possible implementation, the fault analysis module is used to count the number of occurrences of each fault type at each fault location based on historical fault information;

[0039] When the number of faults occurring at the same fault location within a first preset time interval is greater than a first threshold, determining the fault location as a focus area;

[0040] When the number of faults occurring at the same fault location within a first preset time interval is greater than a first threshold value and less than a second preset threshold value, the fault location is determined as a focus area;

[0041] Based on the areas of concern and key areas, corresponding early warning strategies are formulated respectively.

[0042] In one possible implementation, the fault analysis module is used to increase the monitoring frequency of the electrical signal at the fault location when the fault location is determined as a focus area, if the fault type of the fault location is a user-side fault; if the fault type of the fault location is a line fault, then add a power protection device or an intelligent power meter to the line at the fault location.

[0043] In one possible implementation, the fault analysis module is used to, when the fault location is determined as a focus area, if the fault type of the fault location is a user-side fault, then repair the fault location; if the fault type of the fault location is a line fault, then strengthen the inspection of the line at the fault location.

[0044] In a possible implementation, the fault analysis module is used to generate warning information for users, areas and lines affected by the power outage location based on all fault locations and fault analysis;

[0045] Send power outage information to users based on early warning information.

[0046] In a possible implementation, the fault analysis module is used to generate a fault repair work order based on all fault locations and the fault type of each fault location;

[0047] Determine emergency repair methods based on the fault report work order and carry out fault repair.

[0048] In a possible implementation, the fault repair work order includes the electricity usage type of the faulty user corresponding to the fault location, the meter status of the faulty user, and the line information of the faulty user.

[0049] The embodiment of the present invention provides a method and device for analyzing power outages caused by distribution network faults. First, power outage information is obtained, and then the power outage information is input into a pre-trained alarm topology model to generate a regional power topology fault map of an upper-level branch topology. Then, based on the regional power topology fault map, a fault data record set of all branch switches in the regional power topology fault map is obtained. Secondly, the regional power topology fault map and the fault data record set are input into a pre-trained fault type determination model to generate a fault type corresponding to each fault location. Finally, based on all fault locations and their fault types and historical fault information, a fault analysis is performed. The present invention can generate a regional power topology fault map of an upper-level branch topology and determine all power outage fault locations by inputting the power outage alarm information and power outage fault coordinates obtained by the terminal into the alarm topology model. Then, the fault data record set of all branch switches in the regional power topology fault map is obtained, and then the fault data record set and the regional power topology fault map are input into the fault type determination model to generate the fault type corresponding to each fault location, and finally, the fault type of the current fault location and the historical fault are combined to perform a fault analysis. Thereby, the fault analysis can be completed quickly and accurately, improving the accuracy of the fault analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative work.

[0051] Figure 1 It is a flow chart of the implementation of the distribution network fault power outage analysis method provided by an embodiment of the present invention;

[0052] Figure 2 It is a structural schematic diagram of a distribution network fault power outage analysis device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0054] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0055] Figure 1 The implementation flow chart of the distribution network fault power outage analysis method provided by the embodiment of the present invention is detailed as follows:

[0056] S110. Obtain power outage information.

[0057] The power outage information includes the power outage alarm information and the power outage fault coordinates obtained by the terminal.

[0058] The power outage fault coordinates can be determined based on 95598 user repair report records, published power outage information, or information collected by the power consumption information collection system.

[0059] The terminal can be a terminal for running any one of the collection and metering automation system, distribution network automation system, dispatching automation system, distribution network OMS system, and main network OMS system.

[0060] The power outage alarm information includes phase A current, phase B current, phase C current, phase A voltage, phase B voltage, phase C voltage, switch quantity abnormality alarm signal, device power failure alarm signal, and device lockout alarm signal.

[0061] After the power outage information is obtained, the obtained power outage alarm information needs to be pre-processed.

[0062] For example, the acquired power outage alarm information is filtered according to some pre-set filtering rules to eliminate interference signals.

[0063] S120: Input the power outage information into a pre-trained alarm topology model to generate a regional power consumption topology fault map of an upper-level branch topology.

[0064] In some embodiments, the alarm topology model includes the topological relationship of the distribution network and the alarm information set of the distribution network. The topological relationship of the distribution network includes the association relationship of the station-line-transformer-box-meter-user in the area. The alarm information set of the distribution network includes the alarm information that may occur at each node in the topological relationship.

[0065] When the power outage information is input into the pre-trained alarm topology model, the alarm topology model determines the alarm location of the upper branch topology associated with the power outage alarm information based on the power outage alarm information obtained by the terminal and the alarm information set of the distribution network.

[0066] Specifically, first, the alarm topology model will determine all alarm terminals that may have such alarms based on the power outage alarm information obtained by the terminal and the alarm information set of the distribution network. The alarm information that may occur at each alarm terminal is different. First, the alarm terminals can be preliminarily screened based on the power outage alarm information obtained by the terminal and the alarm information set of the distribution network, thereby improving the processing speed in subsequent operations, without having to judge all terminals, and reducing the difficulty of processing.

[0067] Then, the alarm topology model generates a power consumption topology fault map based on the obtained alarm terminals, power outage fault coordinates and topological relationships where such alarms may occur. The regional power consumption topology fault map includes all power outage fault locations.

[0068] By determining the first fault location based on the power outage fault coordinates, topological relationships, and alarm terminals where such alarms may occur, the first fault location can be determined based on the topological relationship according to all alarm terminals where such alarms may occur. Then, the second fault location can be determined based on the power outage fault coordinates and the topological relationship. Finally, the final power topology fault map can be determined based on the first fault location and the second fault location.

[0069] Specifically, the final power consumption topology fault map may be determined based on the intersection of the first fault location and the second fault location.

[0070] S130. Based on the regional power consumption topology fault map, a fault data record set of all branch switches in the regional power consumption topology fault map is obtained.

[0071] The data record set includes a sequential record of current mutation events of each branch switch.

[0072] The sequential record of current mutation events is that when the power equipment changes position, the power protection device or intelligent power meter will automatically record the change time, the change reason, and the corresponding telemetered value when the switch trips. The telemetered value is such as three-phase current or active power, thus forming a sequential record of current mutation events for subsequent analysis.

[0073] The sequence record of current mutation events can be determined by the fault indicator installed on the line. The fault indicator refers to a device installed on the power line (overhead line, cable and busbar) to indicate the fault current. The fault indicator usually includes current and voltage detection, fault discrimination, fault indicator drive, fault status indication and signal output and automatic delay reset control. The fault indicator is generally installed on overhead lines, overhead cables or buried cables, and switch cabinet busbars. Therefore, it detects voltage by detecting the potential gradient of the electric field in space and detects line current by electromagnetic induction.

[0074] After determining the regional power consumption topology fault diagram, that is, determining all power outage fault locations, the sequence record of current mutation events at each power outage fault location can be obtained based on the fault indicators at all power outage fault locations.

[0075] S140: Input the regional power consumption topology fault map and the fault data record set into a pre-trained fault type determination model to generate a fault type corresponding to each fault location.

[0076] Fault types include main line tripping, branch line fault, substation low voltage fault, line overload, distribution transformer overload, distribution transformer low voltage, frequent power outages, user-side fault and line fault.

[0077] In some embodiments, the fault type determination model is obtained based on the sequential records of historical current mutation events of branch switches at various locations in the distribution network area, and the corresponding fault types of the branch switches at various locations are trained.

[0078] S150: Perform fault analysis based on all fault locations, fault types, and historical fault information.

[0079] In some embodiments, first, based on historical fault information, the number of occurrences of each fault type at each fault location may be counted.

[0080] Then, when the number of faults occurring at the same fault location within the first preset time interval is greater than a first threshold, the fault location is determined as a focus area.

[0081] Next, when the number of faults occurring at the same fault location within the first preset time interval is greater than a first threshold and less than a second preset threshold, the fault location is determined as a focus area. The second preset threshold is greater than the first preset threshold.

[0082] Finally, corresponding early warning strategies are formulated based on the areas of concern and emphasis.

[0083] Based on the above fault analysis, some hidden dangers in the line can be found out, which is convenient for early prevention and repair.

[0084] In this embodiment, when the fault location is determined as a focus area, if the fault type of the fault location is a user-side fault, the monitoring frequency of the electrical signal at the fault location is increased. If the fault type of the fault location is a line fault, a power protection device or a smart power meter is added to the line at the fault location.

[0085] When the fault location is determined as the focus area, if the fault type of the fault location is a user-side fault, the fault location is repaired. If the fault type of the fault location is a line fault, the line inspection of the fault location is strengthened.

[0086] Among them, the inspection of the fault location can be done manually or by using a drone. After the inspection is completed, it is also necessary to upload photos of the inspection, photos of the inspection line or equipment, etc.

[0087] In addition, after the fault analysis is performed, it is also possible to first generate warning information for users, areas, and lines affected by the power outage location based on all fault locations and fault analysis. Then, power outage information is sent to users based on the warning information. In this way, users can obtain relevant information about power outages in a timely manner and reduce customer complaints.

[0088] User power outage information may include information such as the estimated end time of the power outage and the cause of the power outage.

[0089] In addition, after the fault analysis is performed, a fault repair work order may be generated based on all fault locations and the fault type of each fault location, and then an emergency repair method may be determined based on the fault repair work order, and the fault repair may be performed.

[0090] The fault repair work order includes the electricity usage type of the faulty user corresponding to the fault location, the meter status of the faulty user, and the line information of the faulty user.

[0091] Of course, faults can also be classified according to the severity of the fault type, and the execution level of the fault repair work order can be determined according to the severity of the fault type.

[0092] In addition, after the fault repair work order is generated, it can also be sent to the user end of the maintenance personnel and the large visual screen of the distribution network, so that management personnel and operation and maintenance personnel can promptly grasp the faults that have occurred and the fault repair work orders issued for related faults.

[0093] The embodiment of the present invention provides a method and device for analyzing power outages caused by distribution network faults. First, power outage information is obtained, and then the power outage information is input into a pre-trained alarm topology model to generate a regional power topology fault map of an upper-level branch topology. Then, based on the regional power topology fault map, a fault data record set of all branch switches in the regional power topology fault map is obtained. Secondly, the regional power topology fault map and the fault data record set are input into a pre-trained fault type determination model to generate a fault type corresponding to each fault location. Finally, based on all fault locations and their fault types and historical fault information, a fault analysis is performed. The present invention can generate a regional power topology fault map of an upper-level branch topology and determine all power outage fault locations by inputting the power outage alarm information and power outage fault coordinates obtained by the terminal into the alarm topology model. Then, the fault data record set of all branch switches in the regional power topology fault map is obtained, and then the fault data record set and the regional power topology fault map are input into the fault type determination model to generate the fault type corresponding to each fault location, and finally, the fault type of the current fault location and the historical fault are combined to perform a fault analysis. Thereby, the fault analysis can be completed quickly and accurately, improving the accuracy of the fault analysis.

[0094] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0095] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0096] Figure 2 The structure diagram of the power distribution network fault outage analysis device provided by the embodiment of the present invention is shown. For the convenience of description, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:

[0097] like Figure 2 As shown, the distribution network fault power outage analysis device 200 includes:

[0098] A first acquisition module 210 is used to acquire power outage information, where the power outage information includes power outage alarm information and power outage fault coordinates acquired by the terminal;

[0099] A topology generation module 220 is used to input the power outage information into a pre-trained alarm topology model to generate a regional power consumption topology fault map of an upper branch topology, wherein the regional power consumption topology fault map includes all power outage fault locations;

[0100] The second acquisition module 230 is used to acquire the fault data record set of all branch switches in the regional power consumption topology fault map based on the regional power consumption topology fault map; wherein the data record set includes the sequence record of the current mutation event of each branch switch;

[0101] A type determination module 240 is used to input the regional power consumption topology fault map and the fault data record set into a pre-trained fault type determination model to generate a fault type corresponding to each fault location;

[0102] The fault analysis module 250 is used to perform fault analysis based on all fault locations and fault types as well as historical fault information.

[0103] In one possible implementation, the alarm topology model includes the topological relationship of the distribution network and the alarm information set of the distribution network. The alarm terminal of the upper-level branch topology associated with the power outage alarm information is determined based on the power outage alarm information obtained by the terminal and the alarm information set of the distribution network; the alarm topology model generates a power consumption topology fault map based on the alarm terminal, power outage fault coordinates and topological relationship of the upper-level branch topology.

[0104] In a possible implementation, the fault type determination model is obtained based on the sequential records of historical current mutation events of branch switches at various locations in the distribution network area and the corresponding fault type training of the branch switches at various locations.

[0105] In a possible implementation, the fault analysis module 250 is used to count the number of occurrences of each fault type at each fault location based on historical fault information;

[0106] When the number of faults occurring at the same fault location within a first preset time interval is greater than a first threshold, determining the fault location as a focus area;

[0107] When the number of faults occurring at the same fault location within a first preset time interval is greater than a first threshold value and less than a second preset threshold value, the fault location is determined as a focus area;

[0108] Based on the areas of concern and key areas, corresponding early warning strategies are formulated respectively.

[0109] In one possible implementation, the fault analysis module 250 is used to increase the monitoring frequency of the electrical signal at the fault location when the fault location is determined as a focus area, if the fault type of the fault location is a user-side fault; if the fault type of the fault location is a line fault, then add a power protection device or a smart power meter to the line at the fault location.

[0110] In one possible implementation, the fault analysis module 250 is used to, when the fault location is determined as a focus area, if the fault type of the fault location is a user-side fault, then perform maintenance on the fault location; if the fault type of the fault location is a line fault, then strengthen the inspection of the line at the fault location.

[0111] In a possible implementation, the fault analysis module 250 is used to generate warning information for users, areas and lines affected by the power outage location based on all fault locations and fault analysis;

[0112] Send power outage information to users based on early warning information.

[0113] In a possible implementation, the fault analysis module 250 is used to generate a fault repair work order based on all fault locations and the fault type of each fault location;

[0114] Determine emergency repair methods based on the fault report work order and carry out fault repair.

[0115] In a possible implementation, the fault repair work order includes the electricity usage type of the faulty user corresponding to the fault location, the meter status of the faulty user, and the line information of the faulty user.

[0116] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0117] Those of ordinary skill in the art will appreciate that the templates, units, and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0118] If the module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned distribution network fault power outage analysis method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal and software distribution medium.

[0119] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for analyzing power outages caused by power distribution network faults, characterized in that: include: Obtain power outage information, which includes power outage alarm information and power outage fault coordinates obtained by the terminal; Inputting the power outage information into a pre-trained alarm topology model to generate a regional power consumption topology fault map of an upper-level branch topology, wherein the regional power consumption topology fault map includes all power outage fault locations; Based on the regional power consumption topology fault map, a fault data record set of all branch switches in the regional power consumption topology fault map is obtained; wherein the data record set includes a sequential record of current mutation events of each branch switch; Inputting the regional power consumption topology fault map and the fault data record set into a pre-trained fault type determination model to generate a fault type corresponding to each fault location; Perform fault analysis based on all fault locations, fault types, and historical fault information.

2. The method for analyzing power outages caused by power distribution network faults according to claim 1, characterized in that: The alarm topology model includes a topological relationship of a distribution network and an alarm information set of the distribution network, and determines an alarm terminal of an upper branch topology associated with the power outage alarm information based on the power outage alarm information obtained by the terminal and the alarm information set of the distribution network; The alarm topology model generates the power consumption topology fault map based on the alarm terminal of the upper branch topology, the power outage fault coordinates and the topological relationship.

3. The method for analyzing power outage caused by a power distribution network fault according to claim 1, characterized in that: The fault type determination model is obtained based on the sequential records of historical current mutation events of branch switches at various locations in the distribution network area and the corresponding fault types of branch switches at various locations.

4. The method for analyzing power outage caused by a power distribution network fault according to claim 1, characterized in that: The fault analysis is performed based on all fault locations, fault types and historical fault information, including: Based on historical fault information, count the number of occurrences of each fault type at each fault location; When the number of faults occurring at the same fault location within a first preset time interval is greater than a first threshold, determining the fault location as a focus area; When the number of faults occurring at the same fault location within a first preset time interval is greater than a first threshold value and less than a second preset threshold value, the fault location is determined as a focus area; Based on the concerned area and the focused area, corresponding early warning strategies are formulated respectively.

5. The method for analyzing power outages caused by power distribution network faults according to claim 4, characterized in that: The corresponding early warning strategies are formulated based on the concerned area and the focused area, respectively, including: When the fault location is determined as the area of ​​concern, if the fault type of the fault location is a user-side fault, the monitoring frequency of the electrical signal at the fault location is increased; if the fault type of the fault location is a line fault, power protection equipment or smart power meters are added to the line at the fault location.

6. The method for analyzing power outages caused by power distribution network faults according to claim 5, characterized in that: The formulating corresponding early warning strategies based on the concerned area and the focused area respectively further includes: When the fault location is determined as a focus area, if the fault type of the fault location is a user-side fault, the fault location is repaired; if the fault type of the fault location is a line fault, the line inspection of the fault location is strengthened.

7. The method for analyzing power outages caused by power distribution network faults according to claim 1, characterized in that: After the fault analysis is performed based on all fault locations, fault types and historical fault information, the following steps are also included: Generate early warning information for users, areas and lines affected by the power outage location based on all fault locations and fault analysis; Power outage information is sent to users based on the warning information.

8. The method for analyzing power outages caused by power distribution network faults according to claim 1, characterized in that: After the fault analysis is performed based on all fault locations, fault types and historical fault information, the following steps are also included: Generate a fault repair work order based on all fault locations and the fault type of each fault location; An emergency repair method is determined based on the fault repair work order, and the fault repair is performed.

9. The method for analyzing power outages caused by power distribution network faults according to claim 8, characterized in that: The fault repair work order includes the electricity usage type of the faulty user corresponding to the fault location, the electric meter status of the faulty user and the line information of the faulty user.

10. A distribution network fault power outage analysis device, characterized in that: include: A first acquisition module is used to acquire power outage information, where the power outage information includes power outage alarm information and power outage fault coordinates acquired by the terminal; A topology generation module is used to input the power outage information into a pre-trained alarm topology model to generate a regional power consumption topology fault map of an upper-level branch topology, wherein the regional power consumption topology fault map includes all power outage fault locations; A second acquisition module is used to acquire a fault data record set of all branch switches in the regional power topology fault map based on the regional power topology fault map; wherein the data record set includes a sequential record of current mutation events of each branch switch; A type determination module, used to input the regional power consumption topology fault map and the fault data record set into a pre-trained fault type determination model to generate a fault type corresponding to each fault location; The fault analysis module is used to perform fault analysis based on all fault locations and fault types as well as historical fault information.

Images