Fault processing method and device of power distribution network, electronic equipment and medium

Abstract

The application discloses a power distribution network fault processing method and device, electronic equipment and medium, and the method comprises the steps of obtaining the feeder group atlas of the updated power distribution network and the graph model file of the feeder group atlas, wherein the feeder group atlas comprises a feeder group ring network graph and a feeder single-line graph; when the graph model file meets the graph model verification condition, determining the power distribution network level information of the feeder group ring network graph and the corresponding automation mode information; and according to the power distribution network level information, the automation mode information and the preset machine learning model, the fault of the power distribution network is positioned and isolated. Through the improved feeder group ring network graph based on the full-connection topological relationship of the power distribution network, the topological level relationship of the power distribution network is optimized, according to the optimized fault positioning and isolation function, the starting process of the centralized main station and the in-situ collaborative main station is compatible, which is more conducive to the power distribution personnel to comprehensively understand the power distribution network frame structure and the overall operation state, and realizes the intelligentization of the self-healing function of the power distribution main station.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power distribution network fault diagnosis, and in particular to a power distribution network fault processing method and device, an electronic device and a medium. BACKGROUND

[0002] Self-healing of a power distribution network refers to using an automatic device or system to monitor the operation state of a power distribution line, to timely find a line fault, to diagnose a fault section and to isolate the fault section to restore power supply to a non-fault section. According to different implementation methods, the self-healing can be mainly divided into a centralized control type, an on-site control type and a master station on-site coordination type. The master station centralized type has obvious advantages, and therefore, considering the construction and transformation cost and the on-site terminal operation and maintenance workload, the master station centralized type and the master station on-site coordination type in which the master station comprehensively analyzes a transfer power supply scheme have become mainstream self-healing strategies for a power distribution network.

[0003] The prior art usually adopts the master station centralized type and the master station on-site coordination type self-healing strategies based on a power distribution line topological relationship. The power distribution line topological relationship is usually realized by a feeder loop network diagram. The current feeder loop network diagram refers to a loop network diagram of a feeder and other feeders having a direct connection relationship and a secondary connection relationship with the feeder, and the secondary connection relationship is only described by using a connection switch.

[0004] However, this feeder loop network diagram mainly shows the electrical connection between feeders for the direct connection relationship of each feeder, and does not show a branch switch and a line on a T-connection of the direct connection line. When it is necessary to analyze the load condition of the branch switch carried by the sectionalizing switch, it is necessary to re-call a single-line diagram to analyze each line. Since the feeders having the secondary connection relationship only show the connection switch, the power distribution network "3-1" single loop network and "two power supply and one standby" network structure cannot be truly reflected, which is not conducive to a power distribution operator to comprehensively understand the operation condition of the power distribution network for command and dispatch. Moreover, the master station of the master station centralized type and the master station on-site coordination type self-healing strategies bears fault isolation (downstream boundary) and non-fault area transfer power supply, and the difference lies in whether the fault positioning and fault isolation (upstream) are processed by the on-site terminal or the master station. However, these two strategies cannot be compatible, and only one of them can be selected. For the power distribution terminal which is frequently updated and replaced, the terminal function is gradually upgraded and improved, and the self-healing function of the feeder group cannot be automatically adapted, and only the master station function can be modified on the basis of uniform on-site terminal function, which greatly increases the workload of power distribution terminal operation and maintenance and line self-healing management, and also easily causes self-healing failure due to self-healing setting error of the master station. SUMMARY

[0005] The present application provides a power distribution network fault processing method, device, electronic device and medium to accurately determine the traffic light intersection passing time.

[0006] According to a first aspect of the present application, a power distribution network fault processing method is provided, comprising:

[0007] obtain a feeder group atlas of an updated power distribution network and a graph model file of the feeder group atlas, wherein the feeder group atlas comprises a feeder group ring network graph and a feeder single-line graph;

[0008] when the graph model file meets a graph model verification condition, determine power distribution network level information of the feeder group ring network graph and corresponding automation mode information;

[0009] perform fault positioning and isolation on a fault of the power distribution network according to the power distribution network level information, the automation mode information, and a preset machine learning model.

[0010] According to a second aspect of the present application, a power distribution network fault processing apparatus is provided, comprising:

[0011] an obtaining module configured to obtain a feeder group atlas of an updated power distribution network and a graph model file of the feeder group atlas, wherein the feeder group atlas comprises a feeder group ring network graph and a feeder single-line graph;

[0012] a determining module configured to, when the graph model file meets a graph model verification condition, determine power distribution network level information of the feeder group ring network graph and corresponding automation mode information;

[0013] a positioning and isolation module configured to perform fault positioning and isolation on a fault of the power distribution network according to the power distribution network level information, the automation mode information, and a preset machine learning model.

[0014] According to a third aspect of the present application, an electronic device is provided, comprising:

[0015] at least one processor; and

[0016] a memory connected to the at least one processor in communication; wherein

[0017] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the power distribution network fault processing method according to any one of the embodiments of the present application.

[0018] According to a fourth aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to implement the power distribution network fault processing method according to any one of the embodiments of the present application when executed by the processor.

[0019] The technical scheme of the embodiment of the application comprises the following steps: obtaining a feeder group atlas of an updated power distribution network and a graph model file of the feeder group atlas, wherein the feeder group atlas comprises a feeder group ring network graph and a feeder single-line graph; when the graph model file meets graph model verification conditions, determining power distribution network level information of the feeder group ring network graph and corresponding automation mode information; and performing fault positioning and isolation on a fault of the power distribution network according to the power distribution network level information, the automation mode information and a preset machine learning model. The improved feeder group ring network graph based on the full-interlocking topological relationship of the power distribution network optimizes the topological level relationship of the power distribution network, and according to the optimized fault positioning and isolation function, the starting process of the centralized master station type and the master station on-site collaborative type is compatible, which is more conducive to the power distribution personnel to comprehensively understand the power distribution network framework structure and the overall operation state, and realizes the intelligentization of the self-healing function of the power distribution master station.

[0020] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the application, nor is it used to limit the scope of the application. Other features of the application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0022] Figure 1 is a flow chart of a power distribution network fault processing method provided by the first embodiment of the application;

[0023] Figure 2 is a flow chart of a power distribution network fault processing method provided by the second embodiment of the application;

[0024] Figure 3 is an example graph of a feeder group ring network graph in the power distribution network fault processing method provided by the second embodiment of the application;

[0025] Figure 4 is an example graph of a feeder single-line graph in the power distribution network fault processing method provided by the second embodiment of the application;

[0026] Figure 5 is an example graph of a feeder group ring network graph in the power distribution network fault processing method provided by the second embodiment of the application;

[0027] Figure 6 is an example flow chart of a power distribution network fault processing method provided by the second embodiment of the application;

[0028] Figure 7 Fig. 1 is a structural schematic diagram of a power distribution network fault processing device according to an embodiment of the present application;

[0029] Figure 8 Fig. 1 is a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to make the personnel in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the scope of protection of the present application.

[0031] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to the process, method, product, or device.

[0032] Embodiment One

[0033] Figure 1 Fig. 1 is a flowchart of a power distribution network fault processing method according to an embodiment of the present application. The embodiment can be applicable to intelligent analysis and self-healing of power distribution main station faults. The method can be executed by a power distribution network fault processing device, which can be realized in the form of hardware and / or software, and can be configured in an electronic device, preferably a processor. As shown in Fig. 1, the method comprises the following steps. Figure 1

[0034] S110, acquiring an updated feeder group atlas of the power distribution network and a graph model file of the feeder group atlas, wherein the feeder group atlas comprises a feeder group ring network graph and a feeder single-line graph.

[0035] It should be noted that, unlike the existing feeder ring network graph based on direct contact, the present application improves the feeder group ring network graph based on the full-contact topological relationship of the power distribution network.

[0036] ​In the embodiment, the power distribution network can be understood as a power network that receives power from a power transmission network or a regional power plant, and distributes the power to various users through power distribution facilities. The feeder group atlas can be understood as a collection of feeder group ring network diagrams and feeder single-line diagrams used to represent the power distribution network. The graph model file can be understood as a file required to load the feeder group atlas. The feeder group ring network diagram can be understood as a feeder group ring network diagram of the full interconnection topological relationship of the power distribution network. The feeder single-line diagram can be understood as a simplified power distribution feeder line diagram of the feeder.

[0037] Specifically, the processor can obtain the updated feeder group atlas of the power distribution network and the graph model file of the feeder group atlas.

[0038] S120, when the graph model file meets the graph model verification condition, determining the power distribution network level information of the feeder group ring network diagram and the corresponding automation mode information.

[0039] In the embodiment, the graph model verification condition can be understood as a verification condition set for the correctness of the data in the graph model file. The power distribution network level information can be understood as the level of the feeder group in the feeder group ring network diagram of the full interconnection topological relationship, which can be divided into a power distribution network trunk layer and a power distribution network branch layer. The automation mode information can be understood as the function type of the terminal.

[0040] Specifically, the processor can check the data in the graph model file to determine whether the graph model file meets the graph model verification condition. When the graph model file meets the graph model verification condition, the processor can analyze the feeder group ring network diagram, determine the power distribution network level information in the feeder group ring network diagram according to the pre-set level mark in the feeder group ring network diagram, and further determine the corresponding automation mode information according to the power distribution terminal type identifier of the power distribution network trunk level.

[0041] S130, according to the power distribution network level information, the automation mode information, and the pre-set machine learning model, performing fault positioning and isolation on the fault of the power distribution network.

[0042] In the embodiment, the machine learning model can be understood as a trained model used for positioning and isolating faults.

[0043] Specifically, the processor can determine the level of the fault according to the power distribution network level information, determine the automation function corresponding to the level of the fault according to the automation mode information, and further determine the fault positioning and isolation method according to the level of the fault and the corresponding automation function. In combination with the response mechanism, fault alarm action, and switch opening signal provided by the existing functions of the power distribution network terminal, the processor inputs the feeder group ring network diagram of the corresponding fault part into the machine learning model, thereby positioning the fault of the power distribution network, and determines the isolation method according to the level of the fault and the automation function.

[0044] The embodiment I provides a fault processing method of a power distribution network. The method comprises the following steps: obtaining an updated feeder group atlas of the power distribution network and a graph model file of the feeder group atlas, wherein the feeder group atlas comprises a feeder group ring network graph and a feeder single-line graph; when the graph model file meets graph model verification conditions, determining power distribution network hierarchical information of the feeder group ring network graph and corresponding automation mode information; and performing fault positioning and isolation on the power distribution network according to the power distribution network hierarchical information, the automation mode information and a preset machine learning model. The improved feeder group ring network graph based on the full-interlocking topological relationship of the power distribution network optimizes the topological hierarchical relationship of the power distribution network. According to the optimized fault positioning and isolation function, the method is compatible with the starting process of the centralized main station and the in-situ collaborative main station, and is more conducive to the overall understanding of the power distribution network frame structure and the overall operation state by the power distribution personnel, and the intelligentization of the self-healing function of the power distribution main station is realized.

[0045] As a first optional embodiment of the embodiment, the above embodiment can be further optimized, which comprises the following:

[0046] When the graph model file does not meet the graph model verification conditions, or all power distribution terminals of the power distribution backbone layer have at least two in-situ control type functions, the fault positioning and isolation are not performed, and the abnormal reason is determined.

[0047] In the embodiment, the power distribution backbone layer can be understood as a path from the switch of a power distribution 10kV feeder to the switch of a transformer substation, through a plurality of power distribution switches, lines and other devices connected to the switch of the transformer substation through direct interlocking and indirect interlocking, and meeting the theoretical transfer condition. The in-situ control type function can be understood as a function of automatically opening the switch in the case of voltage loss or current loss to isolate the fault and restore partial power supply, based on the switch mode of the recloser and the sectionizer. The abnormal reason can be understood as the reason why the fault positioning and isolation cannot be performed.

[0048] Specifically, when the graph model file does not meet the graph model verification conditions, such as graph model file error, or all power distribution terminals of the power distribution backbone layer have at least two in-situ control type functions, such as at least two of the conventional protection, the voltage and current type and the intelligent distributed type, the processor does not perform fault positioning and isolation. The processor can feed back the alarm messages of "graph model self-checking abnormality" and "fault intelligent analysis function exit" to the user terminal, and determine the abnormal reason and feed back the abnormal reason to the user terminal.

[0049] As a first optional embodiment of the embodiment, when the graph model file does not meet the graph model verification conditions, or all power distribution terminals of the power distribution backbone layer have at least two in-situ control type functions, the fault positioning and isolation are not performed, and the abnormal reason is determined and fed back to the user terminal, realizing the automatic discrimination of abnormal conditions and the automatic analysis of reasons, and ensuring the integrity of the method.

[0050] It is necessary to know that fault tolerance function based on power distribution terminal signal is additionally set in the machine learning model processing process:

[0051] Firstly, when the fault alarm / action signal of the part of the power distribution terminal between the substation switch and the minimum boundary switch upstream of the fault is lost, it belongs to the phenomenon of signal missing upstream of the fault, the processor can continue the fault positioning isolation function, and list the abnormal terminal missing signal.

[0052] Secondly, under the premise of fault positioning isolation operation of part of the "local control type" power distribution terminal, when the fault action signal and the switch position signal are inconsistent (i.e. there is an upper fault action signal, but there is no switch opening position signal; or there is a switch opening position signal, but the fault action signal is missing), the processor can continue the fault positioning isolation, and list the abnormal terminal missing signal.

[0053] Thirdly, when the power distribution automation switch hangs a specific attribute operation card or is placed in a state bit (such as cold standby, defect, debugging, maintenance, etc. operation card), the switch does not participate in the fault positioning isolation of the processor; when the power distribution terminal is offline or in maintenance state, the terminal does not participate in the fault positioning isolation function of the processor.

[0054] Finally, when all power distribution terminals are "main station centralized type" start "intelligent fault positioning isolation", the machine learning model analyzes the disconnecting switch upstream and downstream of the fault section based on the fault section, and there are the following cases when expanding the fault isolation range in the opposite direction of the fault point: the switch hangs an identification card such as a prohibited operation, a debugging card, etc. When the protection state exits, it is abnormal, non-measured, etc. Abnormal state. The switch is uncontrollable (remote control point number-1, terminal working condition abnormal).

[0055] Embodiment two

[0056] Figure 2 A flowchart of a power distribution network fault processing method provided for embodiment two of the application, which is a refinement of the above-mentioned embodiment. As shown in the figure, Figure 2 The method comprises:

[0057] S201, acquiring the updated feeder group atlas of the power distribution network and the graph model file of the feeder group atlas.

[0058] S202, analyzing the feeder group ring network diagram to determine the power distribution network backbone layer and the power distribution network branch layer of the power distribution network.

[0059] It needs to be known that the main layer of the power distribution network can be understood as a path that the power distribution 10kV feeder line starts from the substation switch, passes through a plurality of power distribution switches, lines and other devices, is connected to the substation switch through direct connection and indirect connection, and meets the theoretical transfer supply condition. According to the typical connection requirements of the power distribution network planning, the main layer of the power distribution network is generally a "2-1" single ring network, a "3-1" single ring network, a "two supply and one standby" and the like. The devices of the main layer and the internal connection diagram (including switches, busbars and the like) thereof need to be displayed in the feeder group ring network diagram. The branch layer of the power distribution network can be understood as a local topological connection relationship starting from the common point device (such as a busbar, a line T joint) of the main layer of the power distribution network, which is used to connect power distribution terminal devices such as power distribution transformers, generators, distributed power sources and the like, and the branch layer can also form a ring connection structure. The feeder group ring network diagram does not need to display all the devices of the branch layer, but only displays the first switch of the branch layer (that is, the switch existing in the common point with the main layer), the connection switch (the switch existing in the electrical connection relationship with other lines and the switch state being in the open state), the incoming line switch of the double power supply user and the distributed power source grid connection point switch.

[0060] In the embodiment, the branch layer of the power distribution network can be understood as a local topological connection relationship starting from the common point device (such as a busbar, a line T joint) of the main layer of the power distribution network, which is used to connect power distribution terminal devices such as power distribution transformers, generators, distributed power sources and the like, and the branch layer can also form a ring connection structure.

[0061] Specifically, the processor can analyze the feeder group ring network diagram, and determine the main layer of the power distribution network and the branch layer of the power distribution network according to the distinguishing marks set when the feeder group ring network diagram is drawn.

[0062] Figure 3 A feeder group ring network diagram example in a power distribution network fault processing method provided by the second embodiment of the present application is shown in FIG. 2. Figure 3 As shown in FIG. 2, the feeders of substation switches T1, T2 and T3 jointly form a typical "two supply and one standby" feeder group. The main layer of the power distribution network is switches B1-B14 and the lines passing through the switches, and B3 and B9 are two connection switches of the main layer of the power distribution network; the branch layer is shown in a simple diagram, and only switches C1-C12 are displayed, and the rear section lines and devices thereof are omitted. Among them, "C1-C4-C3", "C5-C9-C10" branches only display the branch first switches (C1, C3, C5, C10) and the connection switches (C4, C9), C6 is a distributed power source grid connection point switch, and C8 and C11 are incoming line switches of double power supply users.

[0063] S203, taking the main layer of the power distribution network and the branch layer of the power distribution network as power distribution network hierarchical information.

[0064] Specifically, the processor can take the main layer of the power distribution network and the branch layer of the power distribution network as power distribution network hierarchical information.

[0065] S204, determining the automation mode information according to the power distribution terminal of the power distribution backbone layer.

[0066] Specifically, the processor can search for the power distribution terminal included in the power distribution backbone layer, determine the corresponding mode identifier, and determine the automation mode information corresponding to the power distribution backbone layer according to the mode identifier.

[0067] S205, when the fault branch layer in the power distribution network meets the alarm tripping condition, determining the fault type of the power distribution network as a branch layer fault according to the power distribution network hierarchical information and the automation mode information.

[0068] In this embodiment, the fault branch layer can be understood as the branch layer that issues a fault alarm / action. The alarm tripping condition can be understood as the condition that the first switch in the branch layer meets that can perform fault positioning and isolation. The branch layer fault can be understood as the fault type that occurs in the branch layer in the feeder group ring network diagram.

[0069] Specifically, the processor can determine the level of the fault power distribution network and the corresponding automation mode according to the power distribution network hierarchical information and the automation mode information. When the level of the fault is a branch layer, the fault branch layer first switch meets the "fault alarm / action" and the "switch tripping" signal to determine the fault type of the power distribution network as a branch layer fault.

[0070] S206, when all power distribution terminals in the first fault backbone layer are master station centralized type and meet the fault condition, determining the fault type as a first main layer fault.

[0071] In this embodiment, the first fault backbone layer can be understood as a backbone layer that all power distribution terminals are master station centralized type and has occurred a fault. The fault condition can be understood as a condition that can start the fault positioning and isolation function. The first main layer fault can be understood as the fault type of the master station centralized backbone layer in the feeder group ring network diagram.

[0072] Specifically, when the processor determines that all power distribution terminals in the first fault backbone layer are "master station centralized type", any master station centralized terminal issues a fault alarm / action signal, and meets one of the two conditions: the substation out-of-line switch of the feeder issues a protection tripping signal, or all power distribution terminals of the feeder issue a voltage loss alarm signal, the fault type is determined as a first main layer fault.

[0073] S207, when part of the power distribution terminals in the second fault backbone layer are the same kind of on-site control type, determining the fault type as a second main layer fault.

[0074] In the embodiment, the second fault backbone layer can be understood as a fault of the same kind of local control type occurring in the partial distribution terminal. The second main layer fault can be understood as a fault type of the local control type in the feeder group ring network diagram.

[0075] Specifically, the partial distribution terminal of the feeder group backbone layer is of the same kind of "local control type" (conventional protection, voltage and current type, intelligent distributed) function. All local control type terminals act within the respective fault location expansion time, and the processor can determine that the fault type is the second main layer fault.

[0076] S208, according to the fault type, determining the fault handling mode of the power distribution network.

[0077] In the embodiment, the fault handling mode can be understood as a processing step of the fault.

[0078] Specifically, according to the pre-set association table, the processor can determine the fault handling mode of the power distribution network corresponding to the fault type.

[0079] S209, according to the fault handling mode and the machine learning model, fault locating and isolating the fault.

[0080] It should be noted that the machine learning model can first collect data in actual operation: GIS system pushes the feeder group ring network diagram and the diagram module file of the feeder single line diagram; data preparation: analyzing the main layer and the branch layer through the line level attribute of the diagram module file; selecting a model: analyzing the fault path based on graph theory algorithm; training: without considering the influence of the closed loop operation of the distribution network and the distributed power supply, defining the switch farthest from the transformer outlet switch along the fault current direction as the fault upstream isolation switch; the first switch without fault alarm / isolation signal or the switch opposite to the fault alarm current direction is the fault downstream isolation switch; evaluation: once the training is completed, the model can be evaluated according to the reserved verification set and test set to determine whether the model is useful.

[0081] Specifically, the processor can determine the processing step according to the fault handling mode corresponding to the fault type, and input the fault corresponding feeder single line diagram or feeder group ring network diagram into the machine learning model, and then locate and isolate the fault through the machine learning model.

[0082] Further, when the fault type is a branch layer fault, according to the fault handling mode and the machine learning model, the fault is located and isolated, including:

[0083] a1, acquiring a target feeder single line diagram corresponding to the fault branch layer.

[0084] In the embodiment, the target feeder single-line diagram can be understood as a feeder single-line diagram corresponding to the fault alarm / action part.

[0085] Specifically, the processor can automatically determine the target feeder single-line diagram corresponding to the fault branch layer and obtain the target feeder single-line diagram.

[0086] b1. Analyze the alarm power distribution terminal and alarm information in the fault branch layer by a machine learning model to obtain a first fault section.

[0087] In the embodiment, the alarm power distribution terminal can be understood as the first switch that performs fault alarm / action. The alarm information can be understood as a switch opening signal. The first fault section can be understood as a located fault range.

[0088] Specifically, the processor can analyze all power distribution terminal fault alarm / action information of the fault branch layer by a machine learning algorithm to preliminarily locate the fault section.

[0089] c1. In the target feeder single-line diagram, the first fault section is fault-identified according to a preset identification mode.

[0090] In the embodiment, the preset identification mode can be understood as a set mode of protruding display of the fault section.

[0091] Specifically, the processor can identify the first fault section in the feeder single-line diagram according to the preset identification mode, for example, the first fault section can be represented in the form of a fault mark added to the first fault section and flashing.

[0092] Figure 4 is a feeder single-line diagram example diagram in a power distribution network fault processing method according to Embodiment Two of the present application, like Figure 4As shown, taking the branches of a certain feeder single-line diagram as an example. First, when the fault point is at F1, the branch head switch C5 of the feeder detects the fault current, sends a fault alarm / action signal, and the switch is tripped due to protection action, triggering fault location analysis of the type of branch level fault: the processor acquires the feeder single-line diagram where the switch C5 is located, and the switch C5 is shown as tripped. After analysis by the machine learning model, since the fault point is at F1, the branch level switch C9-3 also has fault current passing through and sends a fault alarm / action signal, and there is no terminal (such as switch C9-2) after switch C9-3 sending a fault alarm / action signal, therefore, the line and switch equipment line between C9-3 switch and C9-2 of the feeder single-line diagram are shown in bold and a fault mark is added. Secondly, when the fault point is at F2, the branch head switch C6 of the feeder detects the fault current, sends a fault alarm / action signal, and the switch is tripped due to protection action, triggering fault location analysis of the type of branch level fault: the processor acquires the feeder single-line diagram where the switch C6 is located, and the switch C6 is shown as tripped. After analysis by the machine learning model, since the latter section of the branch with C6 as the head switch has a distributed power grid connected, it is possible that the power generation of the power supply will react to the on-grid power flow, therefore, the branch switch C6-1 may also be affected by the distributed power supply and have reverse fault current, and send a fault alarm / action signal, by combining the fault current directions of switches C6 and C6-1, it is determined that the fault point is at F2, the line and switch equipment line between C6 switch and C6-1 of the feeder single-line diagram are shown in bold and a fault mark is added. Thirdly, when the fault point is at F3, the branch head switch C12 of the feeder detects the fault current, sends a fault alarm / action signal, and the switch is tripped due to protection action, triggering fault location analysis of the type of branch level fault: the processor acquires the feeder single-line diagram where the switch C12 is located, and the switch C12 is shown as tripped. After analysis by the machine learning model, since the fault point is at F3, the branch level switch C12-1 also has fault current passing through and sends a fault alarm / action signal, and there is no terminal sending a fault alarm / action signal after switch C12-1, therefore, the line and switch equipment line after C12-1 of the feeder single-line diagram are shown in bold and a fault mark is added. Finally, when the fault point is at F4, the branch head switch C11 of the feeder detects the fault current, sends a fault alarm / action signal, and the switch is tripped due to protection action, triggering fault location analysis of the type of branch level fault: the processor acquires the feeder single-line diagram where the switch C11 is located, and the switch C11 is shown as tripped. After analysis by the machine learning model, since there are double power supplies after C11 switch, the user detects that C11 line loses voltage, and starts the backup power supply to supply power by another line.

[0093] Further, when the fault type is the first main level fault, according to the fault handling mode and the machine learning model, the fault is located and isolated, including:

[0094] a2, acquire a first target ring network diagram corresponding to the first fault backbone layer.

[0095] In this embodiment, the first target ring network diagram can be understood as a ring network diagram corresponding to the first fault backbone layer.

[0096] Specifically, the processor can determine and acquire the first target ring network diagram corresponding to the first fault backbone layer.

[0097] b2, analyze the fault alarm signal in the first fault backbone layer by the machine learning model, and obtain the second fault section and the fault point.

[0098] In this embodiment, the second fault section can be understood as a fault section corresponding to the first fault backbone layer. The fault alarm signal can be understood as an alarm signal automatically sent when there is a fault. The fault point can be understood as the location of the device where the fault is located.

[0099] Specifically, the processor can input the first target ring network diagram into the machine learning model, analyze all the fault alarm signals, and preliminarily locate the second fault section.

[0100] c2, in the first target ring network diagram, the second fault section is marked according to a preset marking method, and the switches before and after the fault point are disconnected.

[0101] Specifically, the processor can mark the second fault section in the first target ring network diagram according to the preset marking method, such as indicating the second fault section with a flashing fault mark. The processor can disconnect the switches before and after the fault point.

[0102] Further, when the fault type is a second master level fault, the fault is located and isolated according to the fault processing method and the machine learning model, including:

[0103] a3, acquire a second target ring network diagram corresponding to the second fault backbone layer.

[0104] In this embodiment, the second target ring network diagram can be understood as a ring network diagram corresponding to the second fault backbone layer.

[0105] Specifically, the processor can determine and acquire the second target ring network diagram corresponding to the second fault backbone layer.

[0106] b3, according to the second target ring network diagram, determine the preliminarily located section which has been isolated locally.

[0107] In this embodiment, the preliminarily located section can be understood as a fault section located when the just-in-time control type function is started.

[0108] Specifically, when the partial "on-site control type" power distribution terminal triggers the start, the processor can determine the preliminary positioning section of the on-site isolation according to the identification in the second target ring network diagram.

[0109] c3, analyze other fault alarm signals of other centralized terminals in the preliminary positioning section through a machine learning model to obtain a third fault section, a first minimum boundary switch upstream of the fault, and a second minimum boundary switch downstream of the fault.

[0110] In the embodiment, the other fault alarm signal can be understood as a fault alarm signal corresponding to the centralized terminal. The third fault section can be understood as a fault section corresponding to the second fault backbone layer. The first minimum boundary switch upstream of the fault can be understood as a switch with a fault alarm signal in the preliminary positioning section of the on-site isolation, which is farthest from the on-site control type function fault isolation (upstream). The second minimum boundary switch downstream of the fault can be understood as a switch with no fault alarm signal in the preliminary positioning section of the on-site isolation, which is closest to the on-site fault isolation (upstream), or a switch with a fault alarm current direction opposite to that of the on-site fault isolation (upstream).

[0111] Specifically, the processor can display the preliminary positioning section that has been isolated on-site through a machine learning model, and can further analyze the fault alarm signals of other centralized terminals in the fault section to narrow down the fault positioning range and determine the third fault section, the first minimum boundary switch upstream of the fault, and the second minimum boundary switch downstream of the fault.

[0112] d3, in the second target ring network diagram, the third fault section is identified according to a preset identification method, and the first minimum boundary switch and the second minimum boundary switch are controlled to be isolated.

[0113] Specifically, the processor can identify the third fault section in the second target ring network diagram according to a preset identification method, for example, in the form of a fault mark added to the third fault section and flashing, and the processor disconnects the minimum boundary switch upstream of the fault and the minimum boundary switch downstream of the fault.

[0114] Figure 5 is a feeder group ring network diagram example diagram of a power distribution network fault processing method according to an embodiment of the present application, a feeder group ring network diagram based on full interconnection topological relationship, wherein the backbone level switches B1, B4, B6, B8, B11 and B14 are put into a "voltage and current type" on-site control type strategy.

[0115] As Figure 5As shown, first, when the fault point F1 occurs between switches B2-B3, the fault current passes through the main level switches B1-B2, switch B1 cooperates with substation switch T1, switch B1 isolates the upstream of the fault point and sends a corresponding blocking signal, switch B3 is a tie switch and a downstream fault isolation switch, because it remains open and sends a corresponding blocking signal. After a certain time delay, the processor determines that the fault type is a second main level fault, and the fault section is between switches B1-B3 through the machine learning model. Since there is a centralized terminal B2 in the fault section, a fault alarm signal is also sent, so the "minimum boundary switch upstream of the fault" is switch B2 (which needs to be remotely disconnected), and the "minimum boundary switch downstream of the fault" is switch B3 (which does not need to be operated). At the same time, because the tie switch sends a blocking signal, the power supply function is not started. Second, when the fault point F2 occurs between switches B4-B6, the fault current passes through the main level switches B8-B5, switches B8 and B6 cooperate with substation switch T2, switch B6 isolates the upstream of the fault point and sends a corresponding blocking signal, and switch B4 isolates the downstream of the fault point and sends a corresponding blocking signal. After a certain time delay, the processor determines that the fault type is a second main level fault, and the fault section is between switches B4-B6 through the machine learning model. Since there is a centralized terminal B5 in the fault section, a fault alarm signal is also sent, so the minimum boundary switch upstream of the fault is switch B5 (which needs to be remotely disconnected), and the minimum boundary switch downstream of the fault is switch B4 (which has been locally isolated). Finally, when the fault point F3 is actually located in the branch "C10-C9-C5", however, due to some reason, the main level switches may malfunction, such as switches B14 and B12 cooperating with substation switch T3, switch B11 isolating the upstream of the fault point and sending a corresponding blocking signal, and switch B9 being a tie switch and a downstream fault isolation switch, because it remains open and sends a corresponding blocking signal. After a certain time delay, the processor determines that the fault type is a second main level fault, and the fault section is between switches B11-B10 through the machine learning model. Therefore, the minimum boundary switch upstream of the fault is switch B11 (which has been locally isolated), and the minimum boundary switch downstream of the fault is switch B10 (which needs to be remotely disconnected).

[0116] The power distribution network fault processing method provided in Embodiment Two determines the power distribution network level information by analyzing the feeder group ring network diagram, determines the type of fault satisfied by the fault, distinguishes the type of fault, uses different fault positioning and isolation processing methods for different types of faults in combination with a machine learning model, and identifies the fault positioning result in a preset identification manner. The determined fault point is isolated and controlled. This is more conducive to the overall understanding of the power distribution network structure and the overall operation status by the distribution personnel, and is compatible with the centralized type of the main station and the start-up process of the main station in situ cooperation type, realizes the automation of fault positioning and isolation, and realizes the intelligentization of the self-healing function of the power distribution main station.

[0117] In order to facilitate better understanding of the technical solutions of the embodiments, the following describes an example implementation of the fault processing method of the power distribution network:

[0118] Figure 6 is an example flowchart of the fault processing method of the power distribution network provided by the second embodiment of the present application, as Figure 6 shown, the second embodiment implements analysis and processing of the fault of the power distribution network by using the following steps.

[0119] S301, acquiring the updated feeder group atlas of the power distribution network and the graph model file of the feeder group atlas;

[0120] S302, whether the graph model file meets the graph model verification condition; if yes, jump to S303, if not, jump to S308;

[0121] S303, analyzing the feeder group ring network graph to determine the main layer and the branch layer of the power distribution network;

[0122] S304, whether all power distribution terminals in the main layer of the power distribution network are main station centralized type and meet the fault condition; if yes, jump to S309, if not, jump to S305;

[0123] S305, part of the power distribution terminals in the main layer of the power distribution network is the same kind of local control type; if yes, jump to S306, if not, jump to S308;

[0124] S306, determining the preliminary positioning section that has been locally isolated;

[0125] S307, accurately determining the third fault section, the minimum boundary switch upstream of the fault, and the minimum boundary switch downstream of the fault through the machine learning model;

[0126] S308, not performing fault positioning and isolation, and determining the abnormal reason;

[0127] S309, analyzing the fault alarm signal in the first fault main layer through the machine learning model to obtain the second fault section;

[0128] S310, when the fault branch layer first switch meets the fault alarm / action and switch tripping signal at the same time;

[0129] S311, analyzing the alarm power distribution terminal and the alarm information in the fault branch layer through the machine learning model to obtain the first fault section;

[0130] S312, performing isolation remote control command processing.

[0131] Embodiment three

[0132] Figure 7 A structure schematic diagram of a fault processing device of a power distribution network is provided for embodiment three of the present application. As shown in the figure, the device comprises an acquisition module 71, a determination module 72 and a positioning and isolation module 73. Among them, Figure 7

[0133] The acquisition module 71 is configured to acquire an updated feeder group atlas of the power distribution network and a graph model file of the feeder group atlas, wherein the feeder group atlas comprises a feeder group ring network graph and a feeder single line graph.

[0134] The determination module 72 is configured to determine power distribution network hierarchical information and corresponding automation mode information of the feeder group ring network graph when the graph model file meets graph model verification conditions.

[0135] The positioning and isolation module 73 is configured to perform fault positioning and isolation on the fault of the power distribution network according to the power distribution network hierarchical information, the automation mode information and a preset machine learning model.

[0136] Optionally, the determination module 72 is specifically configured to:

[0137] analyze the feeder group ring network graph to determine a power distribution network main layer and a power distribution network branch layer of the power distribution network;

[0138] take the power distribution network main layer and the power distribution network branch layer as the power distribution network hierarchical information;

[0139] determine the automation mode information according to power distribution terminals of the power distribution network main layer.

[0140] Optionally, the positioning and isolation module 73 comprises:

[0141] A first determination unit is configured to determine that a fault type of the power distribution network is a branch layer fault when a fault branch layer in the power distribution network meets an alarm and switching off condition according to the power distribution network hierarchical information and the automation mode information.

[0142] A second determination unit is configured to determine that the fault type is a first main layer fault when all power distribution terminals in a first fault main layer are main station centralized type and meet fault conditions.

[0143] A third determination unit is configured to determine that the fault type is a second main layer fault when part of power distribution terminals in a second fault main layer are the same on-site control type.

[0144] A fourth determination unit is configured to determine a fault processing mode of the power distribution network according to the fault type.

[0145] A positioning and isolation unit is configured to perform fault positioning and isolation on the fault according to the fault processing mode and the machine learning model.

[0146] ​Further, when the fault type is a branch level fault, the locating and isolating unit is specifically configured to:

[0147] obtain a target feeder diagram corresponding to the fault branch layer;

[0148] analyze the alarm distribution terminal and the alarm information in the fault branch layer through a machine learning model to obtain a first fault section;

[0149] identify the first fault section in the target feeder diagram according to a preset identification manner.

[0150] Further, when the fault type is a first main level fault, the locating and isolating unit is specifically configured to:

[0151] obtain a first target ring network diagram corresponding to the first fault main layer;

[0152] analyze the fault alarm signal in the first fault main layer through a machine learning model to obtain a second fault section and a fault point;

[0153] identify the second fault section in the first target ring network diagram according to a preset identification manner, and disconnect switches before and after the fault point.

[0154] Further, when the fault type is a second main level fault, the locating and isolating unit is specifically configured to:

[0155] obtain a second target ring network diagram corresponding to the second fault main layer;

[0156] determine a preliminary positioning section that has been locally isolated according to the second target ring network diagram;

[0157] analyze other fault alarm signals of other centralized terminals in the preliminary positioning section through a machine learning model to obtain a third fault section, a first minimum boundary switch upstream of the fault, and a second minimum boundary switch downstream of the fault;

[0158] identify the third fault section in the second target ring network diagram according to a preset identification manner, and isolate and control the first minimum boundary switch and the second minimum boundary switch.

[0159] Optionally, the apparatus further comprises:

[0160] an abnormality determining module configured to, when the graph model file does not satisfy a graph model verification condition, or all distribution terminals of the main layer of the distribution network have at least two local control type functions, not perform fault positioning and isolation, and determine an abnormality reason.

[0161] The power distribution network fault processing device provided by the embodiments of the present application can execute the power distribution network fault processing method provided by any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0162] Embodiment Four

[0163] Figure 8 A structural schematic diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application described and / or claimed in this document.

[0164] As shown in Figure 8 The electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11, wherein the memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0165] A plurality of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, a loudspeaker, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0166] The processor 11 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, processor, microprocessor, etc. The processor 11 performs various methods and processes described above, such as the fault handling method of the power distribution network.

[0167] In some embodiments, the fault handling method of the power distribution network can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded onto the RAM 13 and executed by the processor 11, one or more steps of the fault handling method of the power distribution network described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the fault handling method of the power distribution network by any other suitable means, such as by means of firmware.

[0168] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0169] Computer programs used to implement the methods of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a standalone software package, and partially on a machine or entirely on a remote machine or server.

[0170] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0171] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0172] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), blockchain network, and the Internet.

[0173] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0174] It should be understood that the various forms of flow shown above can be used to reorder, add or delete steps. For example, each step described in the present application can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which is not limited herein.

[0175] The above detailed description does not constitute a limitation on the scope of protection of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method of fault handling in an electrical distribution network, characterized by, The method comprises the following steps: obtaining an updated feeder group atlas of a power distribution network and a graph model file of the feeder group atlas, wherein the feeder group atlas comprises a feeder group ring network diagram and a feeder single-line diagram; the feeder group ring network diagram shows the devices of the trunk layer and their internal connection diagram, as well as the first switch of the branch layer, the tie switch, the incoming line switch of the dual-power supply user, and the switch of the distributed power supply grid connection point; when the graph model file meets the graph model verification condition, determining the power distribution network level information and the corresponding automation mode information of the feeder group ring network diagram; the graph model verification condition is a verification condition set for the correctness of the data in the graph model file; according to the power distribution network level information and the automation mode information, when the fault branch layer in the power distribution network meets the alarm tripping condition, determining that the fault type of the power distribution network is a branch layer fault; when all power distribution terminals in a first fault trunk layer are master station centralized type and meet the fault condition, determining that the fault type is a first main layer fault; when part of the power distribution terminals in a second fault trunk layer are the same type of on-site control, determining that the fault type is a second main layer fault; determining the fault handling mode of the power distribution network according to the fault type; according to the fault handling mode and the machine learning model, performing fault positioning and isolation on the fault; wherein the feeder single-line diagram or the feeder group ring network diagram corresponding to the fault is input into the machine learning model, and then the machine learning model is used to perform fault positioning and isolation on the fault; wherein the determination of the power distribution network level information and the corresponding automation mode information of the feeder group ring network diagram comprises: analyzing the feeder group ring network diagram, and determining the power distribution network trunk layer and the power distribution network branch layer according to the distinguishing mark set when the feeder group ring network diagram is drawn; taking the power distribution network trunk layer and the power distribution network branch layer as the power distribution network level information; determining the automation mode information according to the power distribution terminals of the power distribution network trunk layer; when the fault type is a branch layer fault, the fault positioning and isolation according to the fault handling mode and the machine learning model comprises: obtaining a target feeder single-line diagram corresponding to the fault branch layer; analyzing the alarm power distribution terminal and the alarm information in the fault branch layer through the machine learning model to obtain a first fault section; performing fault identification on the first fault section in the target feeder single-line diagram according to a preset identification method; when the fault type is a first main layer fault, the fault positioning and isolation according to the fault handling mode and the machine learning model comprises: obtaining a first target ring network diagram corresponding to the first fault trunk layer; analyzing the fault alarm signal in the first fault trunk layer through the machine learning model to obtain a second fault section and a fault point; performing fault identification on the second fault section in the first target ring network diagram according to a preset identification method, and disconnecting the switches before and after the fault point. When the fault type is the second main level fault, the fault locating and isolating according to the fault handling mode and the machine learning model comprises: obtaining a second target ring network diagram corresponding to the second fault main layer; determining a preliminary positioning section that has been locally isolated according to the second target ring network diagram; analyzing other fault alarm signals of other centralized terminals in the preliminary positioning section through the machine learning model to obtain a third fault section, a first minimum boundary switch upstream of the fault and a second minimum boundary switch downstream of the fault; identifying the third fault section and performing isolation control on the first minimum boundary switch and the second minimum boundary switch in the second target ring network diagram according to a preset identification mode.

2. The method of claim 1, wherein, Also comprising: When the graph model file does not meet the graph model verification condition, or all distribution terminals of the main layer of the distribution network exist at least two local control type functions, the fault locating and isolating are not performed, and an abnormal reason is determined.

3. A fault handling apparatus for a power distribution network, characterized by, Comprise: The acquisition module is used for acquiring the feeder group graph set of the updated distribution network and a graph model file of the feeder group graph set, wherein the feeder group graph set comprises a feeder group ring network diagram and a feeder single line diagram; wherein the feeder group ring network diagram displays devices with a main layer and internal wiring diagrams thereof, and first switches, tie switches, incoming line switches of dual power supply users and distributed power grid connection point switches of a branch layer; The determination module is used for determining distribution network level information and corresponding automation mode information of the feeder group ring network diagram when the graph model file meets the graph model verification condition; wherein the graph model verification condition is a verification condition set for whether data in the graph model file is correct; The positioning and isolating module is used for locating and isolating a fault of the distribution network according to the distribution network level information, the automation mode information and a preset machine learning model; The positioning and isolating module comprises: The first determination unit is used for determining that the fault type of the distribution network is a branch layer fault when a fault branch layer in the distribution network meets an alarm tripping condition according to the distribution network level information and the automation mode information; The second determination unit is used for determining that the fault type is a first main level fault when all distribution terminals in a first fault main layer are main station centralized type and meet a fault condition; The third determination unit is used for determining that the fault type is a second main level fault when part of distribution terminals in a second fault main layer are of the same local control type; The fourth determination unit is used for determining a fault handling mode of the distribution network according to the fault type; The positioning and isolating unit is used for locating and isolating the fault according to the fault handling mode and the machine learning model; wherein a feeder single line diagram or a feeder group ring network diagram corresponding to the fault is input into the machine learning model, and then the fault is located and isolated through the machine learning model; The determination module is specifically used for: The feeder group ring network diagram is parsed, and according to a distinguishing mark set when the feeder group ring network diagram is drawn, a power distribution network main layer and a power distribution network branch layer of the power distribution network are determined; The power distribution network main layer and the power distribution network branch layer are taken as the power distribution network hierarchical information; According to the power distribution terminal of the power distribution network main layer, the automation mode information is determined; When the fault type is a branch hierarchical fault, the positioning and isolation unit is specifically configured to: Obtain a target feeder single-line diagram corresponding to the fault branch layer; Analyze the alarm power distribution terminal and alarm information in the fault branch layer through the machine learning model to obtain a first fault section; In the target feeder single-line diagram, the first fault section is fault-identified according to a preset identification manner; When the fault type is a first main hierarchical fault, the positioning and isolation unit is specifically configured to: Obtain a first target ring network diagram corresponding to the first fault main layer; Analyze the fault alarm signal in the first fault main layer through the machine learning model to obtain a second fault section and a fault point; In the first target ring network diagram, the second fault section is fault-identified according to a preset identification manner, and the switches before and after the fault point are disconnected; When the fault type is a second main hierarchical fault, the positioning and isolation unit is specifically configured to: Obtain a second target ring network diagram corresponding to the second fault main layer; According to the second target ring network diagram, a preliminary positioning section that has been locally isolated is determined; Analyze other fault alarm signals of other centralized terminals in the preliminary positioning section through the machine learning model to obtain a third fault section, a first minimum boundary switch upstream of the fault, and a second minimum boundary switch downstream of the fault; In the second target ring network diagram, the third fault section is fault-identified according to a preset identification manner, and the first minimum boundary switch and the second minimum boundary switch are isolated and controlled.

4. An electronic device, comprising: The electronic device includes: at least one processor; and a memory connected with the at least one processor in communication; wherein The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the power distribution network fault processing method of any one of claims 1-2.

5. A computer readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for causing the processor to execute when the power distribution network fault processing method of any one of claims 1-2 is implemented.

Images