A power grid fault processing system and method

By designing a power grid fault processing system, using real-time data and deep reinforcement learning technology, rapid location of power grid faults and automatic operation ticket generation are achieved, solving the problem of low efficiency of traditional fault processing methods and improving processing efficiency and safety.

CN113765100BActive Publication Date: 2025-02-07STATE GRID SHANGHAI MUNICIPAL ELECTRIC POWER CO
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202111059765.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-09-10
Publication Date
2025-02-07
Estimated Expiration
2041-09-10

AI Technical Summary

Technical Problem

Traditional power grid fault handling methods rely on manual experience and operation tickets, which consumes time and effort, resulting in low fault handling efficiency and increased risk.

Method used

Design a power grid fault processing system, including a database, fault diagnosis module, operation ticket inference module and operation ticket generation module, and generate scheduling instructions through real-time data acquisition, fault positioning model construction and deep reinforcement learning, and automatically generate operation tickets.

Benefits of technology

It realizes rapid location of power grid faults and automatic operation ticket generation, improves fault handling efficiency, reduces labor costs and fault time, and reduces economic losses.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113765100B_ABST
    Figure CN113765100B_ABST
Patent Text Reader

Abstract

The present invention discloses a power grid fault processing system, including: a database for storing an operation task set, an operation rule set, power grid configuration information, and real-time operation data of each power device in the power grid; a fault diagnosis module connected to the database, for obtaining the location information of the power grid fault according to the symptom information of the power grid fault, the power grid configuration information, and the real-time operation data of each power device; an operation ticket reasoning module, respectively connected to the database and the fault diagnosis module, for generating a dispatch instruction according to the location information of the power grid fault, the operation task set, the operation rule set, and the power grid configuration information; and an operation ticket generation module, connected to the operation ticket reasoning module, for generating an operation ticket according to the dispatch instruction to repair the power grid fault. The present invention combines power grid fault diagnosis with operation ticket generation, and realizes the integration of fault handling processes such as fault diagnosis, generation of operation tickets, and fault repair under artificial intelligence.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a power grid fault processing system and method. Background Art

[0002] The stable operation of the power system is an important guarantee for the normal life and production of residents and enterprises in various regions. When the power system fails and cannot supply power normally, it is necessary to troubleshoot and handle the fault as soon as possible, so as to restore power supply as soon as possible and minimize the risks and losses caused by power outages. However, the traditional prediction, location and attribution of faults all rely on the experience and inspections of staff; at the same time, when performing daily operations and fault repairs on the power grid, it also relies on operation tickets for scheduling, and operation tickets usually need to be filled out, analyzed and reviewed manually. It can be seen that if the traditional method is used to handle power grid faults, it will not only be time-consuming and labor-intensive, but will also lead to increased risks and losses caused by power outages.

[0003] At present, there are some systems for automatic generation and verification of operation tickets in industrial fields such as electrical system automation and power grid. These systems can effectively improve work efficiency and safety in their respective fields by establishing dynamic template solutions to realize automatic reasoning of complex operation tasks, or converting topological structure diagrams into association matrices or adjacency tables for scheduling. However, the above systems mainly rely on external information to input fault point information, and fail to combine power grid fault troubleshooting with operation ticket generation. Summary of the invention

[0004] The object of the present invention is to provide a power grid fault processing system and method, which can quickly locate the power grid fault and generate an operation ticket according to the location information of the power grid fault, so as to repair the power grid fault.

[0005] In order to achieve the above object, the present invention is implemented by the following technical solutions:

[0006] A power grid fault processing system, comprising:

[0007] A database for storing operation task sets, operation rule sets, power grid configuration information, and real-time operation data of each power device in the power grid;

[0008] A fault diagnosis module connected to the database, for obtaining location information of the power grid fault according to symptom information of the power grid fault, the power grid configuration information and real-time operation data of each of the power equipment;

[0009] an operation ticket reasoning module, connected to the database and the fault diagnosis module respectively, for generating a dispatch instruction according to the location information of the power grid fault, the operation task set, the operation rule set and the power grid configuration information; and

[0010] An operation ticket generation module is connected to the operation ticket reasoning module and is used to generate an operation ticket according to the dispatch instruction to repair the power grid fault.

[0011] Preferably, the fault diagnosis module includes:

[0012] A data analysis unit connected to the database, used to analyze the real-time operation data of each of the power equipment to obtain the voltage and current data of each grid node;

[0013] A path analysis unit connected to the database, and configured to obtain a fault service path according to the symptom information of the power grid fault and the power grid configuration information;

[0014] a model building unit, connected to the data parsing unit and the path analysis unit respectively, for building a fault location model according to the symptom information of the power grid fault, the fault service path, the voltage and current data of each of the power grid nodes, and Boolean equations and linear equations; and

[0015] A fault location unit is connected to the model building unit and is used to solve the fault location model to obtain the location information of the power grid fault.

[0016] Preferably, the operation ticket reasoning module includes:

[0017] a task selection unit, connected to the database and the fault location unit respectively, and configured to select a corresponding operation task from the operation task set according to the location information of the power grid fault;

[0018] a rule selection unit, connected to the database and the task selection unit respectively, and configured to select a corresponding operation rule from the operation rule set according to the selected operation task; and

[0019] An instruction generation unit is respectively connected to the database, the task selection unit and the rule selection unit, and is used to obtain the orderly scheduling instructions by using a deep reinforcement learning method according to the selected operation tasks, the operation rules and the power grid configuration information.

[0020] Preferably, the operation ticket generation module includes:

[0021] An operation sequence generating unit, connected to the instruction generating unit, for generating ordered operation items according to the ordered scheduling instructions;

[0022] a verification unit, connected to the operation sequence generating unit, and configured to verify the ordered operation items to obtain a verification result; and

[0023] The ticket generating unit is connected to the operation sequence generating unit and the verification unit respectively, and is used to generate the operation ticket according to the ordered operation items and the verification results.

[0024] Preferably, the power grid fault processing system further includes: a visualization module; the visualization module includes:

[0025] A power grid display unit, connected to the database, for displaying the power grid configuration information;

[0026] a fault display unit, connected to the fault location unit and the power grid display unit, respectively, and configured to display location information of the power grid fault in the power grid configuration information; and

[0027] An operation ticket printing unit is connected to the ticket generating unit and is used for displaying and printing the operation ticket.

[0028] Preferably, the symptom information of the power grid fault includes fault logs, alarm events and change events;

[0029] The grid configuration information includes a grid topology and a name and an IP address of each of the electrical devices.

[0030] On the other hand, the present invention also provides a method for handling a power grid fault, comprising:

[0031] Collect symptom information of power grid faults, power grid configuration information and real-time operation data of each power equipment in the power grid;

[0032] Acquire location information of the power grid fault according to symptom information of the power grid fault, the power grid configuration information and real-time operation data of each of the power equipment;

[0033] Generate a dispatch instruction according to the location information of the power grid fault, the operation task set, the operation rule set and the power grid configuration information; and

[0034] An operation ticket is generated according to the dispatch instruction to repair the power grid fault.

[0035] Preferably, the step of acquiring the location information of the power grid fault according to the symptom information of the power grid fault, the power grid configuration information and the real-time operation data of each of the power equipment comprises:

[0036] Analyze the real-time operation data of each power device to obtain the voltage and current data of each grid node;

[0037] Acquire a fault service path according to the symptom information of the power grid fault and the power grid configuration information;

[0038] Constructing a fault location model using a hybrid equation of Boolean equations and linear equations according to the symptom information of the power grid fault, the fault service path and the voltage and current data of each of the power grid nodes; and

[0039] The fault location model is solved to obtain location information of the power grid fault.

[0040] Preferably, the step of generating a dispatch instruction according to the location information of the power grid fault, the operation task set, the operation rule set and the power grid configuration information comprises:

[0041] Selecting a corresponding operation task from the operation task set according to the location information of the power grid fault;

[0042] Selecting a corresponding operation rule from the operation rule set according to the selected operation task; and

[0043] According to the selected operation tasks, operation rules and power grid configuration information, a deep reinforcement learning method is used to obtain the orderly scheduling instructions.

[0044] Preferably, the step of generating an operation ticket according to the dispatch instruction comprises:

[0045] Generate ordered operation items according to the ordered scheduling instructions;

[0046] Verifying the ordered operation items to obtain verification results; and

[0047] The operation ticket is generated according to the ordered operation items and the verification results.

[0048] Compared with the prior art, the present invention has at least one of the following advantages:

[0049] The present invention provides a power grid fault processing system and method, which can obtain the location information of the power grid fault based on the symptom information of the power grid fault, the power grid configuration information and the real-time operation data of each power equipment, and generate a dispatch instruction based on the location information of the power grid fault, and then generate an operation ticket to repair the power grid fault, while realizing the combination of power grid fault diagnosis and operation ticket generation.

[0050] In the present invention, a fault location model can be constructed based on the symptom information of the power grid fault, the fault service path and the voltage and current data of each of the power grid nodes, and by using a hybrid equation of Boolean equations and linear equations; by solving the fault location model, the location information of the power grid fault can be obtained, thereby achieving rapid positioning of the power grid fault, thereby improving the processing efficiency of the power grid fault.

[0051] The present invention can accurately and intelligently generate orderly dispatching instructions based on the selected operation tasks, operation rules and power grid configuration information, using deep reinforcement learning methods, thereby improving the accuracy of operation tickets and further improving the efficiency of handling power grid faults.

[0052] The present invention can also display the location information of the power grid fault in the power grid topology structure, so that the staff can view the detailed information of the power grid fault; the present invention can also preview and print the generated operation ticket.

[0053] The present invention combines the diagnosis of power grid faults with the generation of operation tickets, thereby realizing the integration of fault handling processes such as fault diagnosis, generation of operation tickets and fault repair under artificial intelligence, greatly saving labor costs, improving power grid fault handling efficiency, and effectively shortening power grid fault time, thereby greatly reducing economic losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a structural schematic diagram of a power grid fault processing system provided by an embodiment of the present invention;

[0055] Figure 2 The present invention provides a flowchart of a method for handling power grid faults according to an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The following is a further detailed description of a power grid fault handling system and method proposed by the present invention in combination with the accompanying drawings and specific embodiments. According to the following description, the advantages and features of the present invention will be clearer. It should be noted that the drawings are in a very simplified form and use non-precise proportions, which are only used to conveniently and clearly assist in explaining the purpose of the embodiments of the present invention. In order to make the purposes, features and advantages of the present invention more obvious and easy to understand, please refer to the accompanying drawings. It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the limiting conditions for the implementation of the present invention, so they have no technical substantive significance. Any structural modification, change in proportional relationship or adjustment of size, without affecting the effects that the present invention can produce and the purposes that can be achieved, should still fall within the scope of the technical content disclosed by the present invention.

[0057] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0058] Combined with Figure 1 As shown, this embodiment provides a power grid fault processing system, including: a database 110, used to store an operation task set, an operation rule set, power grid configuration information and real-time operation data of each power device in the power grid; a fault diagnosis module 120, connected to the database 110, used to obtain the location information of the power grid fault according to the symptom information of the power grid fault, the power grid configuration information and the real-time operation data of each power device; an operation ticket reasoning module 130, connected to the database 110 and the fault diagnosis module 120 respectively, used to generate a dispatch instruction according to the location information of the power grid fault, the operation task set, the operation rule set and the power grid configuration information; and an operation ticket generation module 140, connected to the operation ticket reasoning module 130, used to generate an operation ticket according to the dispatch instruction to repair the power grid fault.

[0059] Specifically, in this embodiment, the operation task set stored in the database 110 may include several operation tasks, and each operation task may be preset according to the working switching mode of each power device in the power grid; since each power device includes at least two switching modes of activation and deactivation, each power device may correspond to at least two operation tasks. For example, the two operation tasks corresponding to a transformer are activation of the transformer and deactivation of the transformer; the two operation tasks corresponding to a tie switch may be changing the tie switch from operation to hot standby and changing the tie switch from hot standby to operation. The operation rule set may include several operation rules, and each operation rule may be preset according to the operation task and in combination with the power grid dispatching regulations and dispatching operation management details; the operation rule is a structured knowledge that maps the operation task to the dispatching command, and the operation rule and the operation task may correspond one to one, but the present invention is not limited thereto.

[0060] Specifically, in this embodiment, the database 110 may also be connected to an external power SCADA system so that the power SCADA system can transmit the real-time operation data of each power device to the database 110, but the present invention is not limited thereto.

[0061] Please continue to refer to Figure 1 The fault diagnosis module 120 includes: a data parsing unit 1201, connected to the database 110, for parsing the real-time operation data of each of the power equipment to obtain the voltage and current data of each grid node; a path analysis unit 1202, connected to the database 110, for obtaining the fault service path according to the symptom information of the grid fault and the grid configuration information; a model construction unit 1203, respectively connected to the data parsing unit 1201 and the path analysis unit 1202, for constructing a fault location model according to the symptom information of the grid fault, the fault service path, the voltage and current data of each of the grid nodes, and Boolean equations and linear equations; and a fault location unit 1204, connected to the model construction unit 1203, for solving the fault location model to obtain the location information of the grid fault.

[0062] It is understandable that, in some other embodiments, the symptom information of the power grid fault includes fault logs, alarm events and change events; the power grid configuration information includes the power grid topology and the name and IP address of each of the power devices.

[0063] Specifically, in this embodiment, when a power grid fault occurs, the external power SCADA system or power grid fault monitoring system will generate symptom information of the power grid fault; if the database 110 is not connected to the power SCADA system or the power grid fault monitoring system, the staff can input the symptom information of the power grid fault into the path analysis unit 1202; if the database 110 is connected to the power SCADA system or the power grid fault monitoring system, the power SCADA system or the power grid fault monitoring system can transmit the symptom information of the power grid fault to the database 110, and the path analysis unit 1202 can load the symptom information of the power grid fault from the database 110, so that the path analysis unit 1202 can determine the fault service path, but the present invention is not limited to this.

[0064] Specifically, in this embodiment, the model construction unit 1203 can list the hybrid equation of the Boolean equation and the linear equation based on Kirchhoff's law according to the symptom information of the power grid fault, the fault service path and the voltage and current data of each of the power grid nodes, and add the protection action information when the power grid fails to the hybrid equation to complete the construction of the fault location model. The location information of the power grid fault can be obtained by solving and optimizing the constructed fault location model through the fault location unit 1204, thereby realizing the rapid location of the power grid fault and improving the processing efficiency of the power grid fault, but the present invention is not limited to this.

[0065] Please continue to refer to Figure 1 The operation ticket reasoning module 130 includes: a task selection unit 1301, which is connected to the database 110 and the fault location unit 1204 respectively, and is used to select a corresponding operation task from the operation task set according to the location information of the power grid fault; a rule selection unit 1302, which is connected to the database 110 and the task selection unit 1301 respectively, and is used to select a corresponding operation rule from the operation rule set according to the selected operation task; and an instruction generation unit 1303, which is connected to the database 110, the task selection unit 1301 and the rule selection unit 1302 respectively, and is used to obtain the ordered scheduling instructions by using a deep reinforcement learning method according to the selected operation task, the operation rule and the power grid configuration information.

[0066] Specifically, in this embodiment, the power equipment related to the power grid fault can be determined according to the location information of the power grid fault; according to the power equipment related to the power grid fault, the corresponding operation task can be selected from the operation task set by the task selection unit 1301. The rule selection unit 1302 can select the operation rule corresponding to the operation task from the operation rule set. The instruction generation unit 1303 can use the selected operation task and the operation rule as well as the power grid topology structure in the power grid configuration information as input data, and use a deep reinforcement learning method (Deep Q network, DQN) to infer the action selection sequence of the power equipment related to the operation task, thereby obtaining the ordered scheduling instructions; wherein the power grid topology structure provides the connection logic of all the power equipment in the power grid. More specifically, the deep reinforcement learning method combines convolutional neural networks with Q-learning learning and introduces an experience replay mechanism, so that the deep reinforcement learning method can learn decision-making strategies based on high-dimensional input data, and the deep reinforcement learning method can treat states and actions as inputs to the neural network, directly generate values ​​after processing by the neural network, and then select the action with the maximum reward value as the next action according to the principle of Q-learning; therefore, based on the deep reinforcement learning method, the operation ticket reasoning module 130 can accurately and intelligently generate the ordered scheduling instructions, thereby improving the accuracy of the subsequently generated operation tickets, and then improving the efficiency of handling the power grid faults, but the present invention is not limited to this.

[0067] Please continue to refer to Figure 1 The operation ticket generation module 140 includes: an operation sequence generation unit 1401, connected to the instruction generation unit 1303, and used to generate ordered operation items according to the ordered scheduling instructions; a verification unit 1402, connected to the operation sequence generation unit 1401, and used to verify the ordered operation items to obtain verification results; and a ticket generation unit 1403, respectively connected to the operation sequence generation unit 1401 and the verification unit 1402, and used to generate the operation ticket according to the ordered operation items and the verification results.

[0068] Specifically, in this embodiment, the inspection unit 1402 can verify the ordered operation items according to preset inspection rules, and generate two inspection results, qualified and unqualified; if the inspection result is unqualified, the ticket generation unit 1403 cannot generate the operation ticket; if the inspection result is qualified, the ticket generation unit 1403 can generate the operation ticket according to the ordered operation items, so that the staff can repair the power grid fault according to the operation ticket, but the present invention is not limited to this.

[0069] Please continue to refer to Figure 1 The power grid fault handling system also includes: a visualization module; the visualization module includes: a power grid display unit, connected to the database 110, for displaying the power grid configuration information; a fault display unit, respectively connected to the fault location unit 1204 and the power grid display unit, for displaying the location information of the power grid fault in the power grid configuration information; and an operation ticket printing unit, connected to the ticket generation unit 1403, for displaying and printing the operation ticket.

[0070] Specifically, in this embodiment, the grid display unit can display the grid topology structure and the name of each of the power equipment, and the fault display unit can display the location information of the grid fault in the grid topology structure, so that the staff can view the detailed information of the grid fault; in addition, the staff can also preview and print the generated operation ticket through the operation ticket printing unit, but the present invention is not limited to this.

[0071] In this embodiment, the power grid fault processing system further includes: a system control center and a user management module; the system control center can be connected to the database 110, the fault diagnosis module 120, the operation ticket reasoning module 130 and the operation ticket generation module 140 respectively, for intelligent management and optimization of each module, and calling the corresponding module according to the power grid fault processing process. The user management module can be connected to the system control center to authenticate the login user and prevent malicious users from logging into the power grid fault processing system, but the present invention is not limited thereto.

[0072] On the other hand, combined with Figure 2 As shown, this embodiment also provides a power grid fault processing method, including: step S110, collecting power grid fault symptom information, power grid configuration information and real-time operation data of each power device in the power grid; step S120, obtaining the location information of the power grid fault according to the power grid fault symptom information, the power grid configuration information and the real-time operation data of each power device; step S130, generating a dispatch instruction according to the power grid fault location information, operation task set, operation rule set and the power grid configuration information; and step S140, generating an operation ticket according to the dispatch instruction to repair the power grid fault.

[0073] Specifically, in this embodiment, the symptom information of the power grid fault includes fault logs, alarm events and change events; the power grid configuration information includes the power grid topology and the name and IP address of each of the power devices, but the present invention is not limited to this.

[0074] Specifically, in the present embodiment, in the step S110, when a power grid fault occurs, an external power SCADA system or a power grid fault monitoring system will generate symptom information of the power grid fault, and the symptom information of the power grid fault can be collected from the power SCADA system or the power grid fault monitoring system; the real-time operation data of each of the power equipment can also be collected from the power SCADA system, and the power grid configuration information can be collected from other power grid systems, but the present invention is not limited to this.

[0075] Please continue to refer to Figure 2 , the step S120 includes: parsing the real-time operation data of each of the electric power equipment to obtain the voltage and current data of each grid node; obtaining the fault service path according to the symptom information of the grid fault and the grid configuration information; constructing a fault location model using a hybrid equation of Boolean equations and linear equations according to the symptom information of the grid fault, the fault service path and the voltage and current data of each of the grid nodes; and solving the fault location model to obtain the location information of the grid fault.

[0076] Specifically, in this embodiment, according to the symptom information of the power grid fault, the fault service path and the voltage and current data of each of the power grid nodes, a hybrid equation of the Boolean equation and the linear equation can be listed based on Kirchhoff's law, and the protection action information when the power grid fault occurs can be added to the hybrid equation to complete the construction of the fault location model; then, by solving and optimizing the constructed fault location model, the location information of the power grid fault can be obtained, thereby realizing the rapid positioning of the power grid fault and further improving the processing efficiency of the power grid fault, but the present invention is not limited to this.

[0077] Please continue to refer to Figure 2 , the step S130 includes: selecting a corresponding operation task from the operation task set according to the location information of the power grid fault; selecting a corresponding operation rule from the operation rule set according to the selected operation task; and using a deep reinforcement learning method to obtain the ordered scheduling instructions according to the selected operation task, the operation rule and the power grid configuration information.

[0078] Specifically, in this embodiment, the power equipment related to the power grid fault can be determined according to the location information of the power grid fault, and the corresponding operation task can be selected from the operation task set according to the power equipment related to the power grid fault; then the corresponding operation rule can be selected from the operation rule set according to the selected operation task; then the selected operation task and the operation rule and the power grid topology structure in the power grid configuration information are used as input data, and a deep reinforcement learning method (Deep Q network, DQN) can be used to infer the action selection sequence of each power equipment to achieve the operation task, thereby obtaining the ordered scheduling instructions, wherein the power grid topology structure provides the connection logic of all the power equipment in the power grid. Based on the deep reinforcement learning method, the ordered scheduling instructions can be accurately generated, thereby improving the accuracy of the subsequently generated operation tickets, and then improving the efficiency of processing the power grid fault, but the present invention is not limited to this.

[0079] Please continue to refer to Figure 2 , the step S140 includes: generating ordered operation items according to the ordered scheduling instructions; verifying the ordered operation items to obtain verification results; and generating the operation ticket according to the ordered operation items and the verification results.

[0080] Specifically, in this embodiment, the ordered operation items can be verified according to preset inspection rules, and two verification results, qualified and unqualified, can be generated; if the verification result is unqualified, the operation ticket cannot be generated; if the verification result is qualified, the operation ticket can be generated according to the ordered operation items, so that the staff can repair the power grid fault according to the operation ticket, but the present invention is not limited to this.

[0081] In summary, the present embodiment provides a power grid fault processing system and method, which can obtain the location information of the power grid fault according to the symptom information of the power grid fault, the power grid configuration information and the real-time operation data of each power device through the fault diagnosis module; generate a dispatch instruction according to the location information of the power grid fault, the operation task set, the operation rule set and the power grid configuration information through the operation ticket reasoning module; and generate an operation ticket according to the dispatch instruction through the operation ticket generation module, so as to repair the power grid fault. The present embodiment combines the diagnosis of power grid faults with the generation of operation tickets, and realizes the integration of fault handling processes such as fault diagnosis to generation of operation tickets and fault repair under artificial intelligence, which greatly saves labor costs, improves the efficiency of power grid fault handling, and effectively shortens the power grid fault time, thereby greatly reducing economic losses.

[0082] Although the content of the present invention has been described in detail through the above preferred embodiments, it should be appreciated that the above description should not be considered as a limitation of the present invention. After reading the above content, it will be apparent to those skilled in the art that various modifications and substitutions of the present invention will occur. Therefore, the protection scope of the present invention should be limited by the appended claims.

Claims

1. A power grid fault processing system, characterized in that: include: A database (110) for storing an operation task set, an operation rule set, power grid configuration information, and real-time operation data of each power device in the power grid; A fault diagnosis module (120) is connected to the database (110) and is used to obtain location information of the power grid fault based on symptom information of the power grid fault, the power grid configuration information and real-time operation data of each of the power equipment; An operation ticket reasoning module (130) is connected to the database (110) and the fault diagnosis module (120) respectively, and is used to generate a dispatch instruction according to the location information of the power grid fault, the operation task set, the operation rule set and the power grid configuration information; as well as An operation ticket generation module (140) is connected to the operation ticket reasoning module (130) and is used to generate an operation ticket according to the dispatching instruction to repair the power grid fault; The fault diagnosis module (120) comprises: A data analysis unit (1201), connected to the database (110), is used to analyze the real-time operation data of each of the electric power equipment to obtain the voltage and current data of each grid node; A path analysis unit (1202), connected to the database (110), configured to obtain a fault service path according to the symptom information of the power grid fault and the power grid configuration information; a model building unit (1203), connected to the data parsing unit (1201) and the path analysis unit (1202), respectively, for building a fault location model according to the symptom information of the power grid fault, the fault service path, the voltage and current data of each power grid node, and the Boolean equation and the linear equation; and A fault location unit (1204) is connected to the model building unit (1203) and is used to solve the fault location model to obtain the location information of the power grid fault.

2. A power grid fault processing system according to claim 1, characterized in that: The operation ticket reasoning module (130) comprises: A task selection unit (1301) is connected to the database (110) and the fault location unit (1204) respectively, and is used to select a corresponding operation task from the operation task set according to the location information of the power grid fault; A rule selection unit (1302), connected to the database (110) and the task selection unit (1301), respectively, for selecting a corresponding operation rule from the operation rule set according to the selected operation task; and An instruction generation unit (1303) is respectively connected to the database (110), the task selection unit (1301) and the rule selection unit (1302), and is used to obtain the orderly scheduling instructions using a deep reinforcement learning method based on the selected operation tasks, operation rules and power grid configuration information.

3. A power grid fault processing system as claimed in claim 2, characterized in that: The operation ticket generation module (140) comprises: An operation sequence generating unit (1401), connected to the instruction generating unit (1303), is used to generate ordered operation items according to the ordered scheduling instructions; A verification unit (1402), connected to the operation sequence generation unit (1401), configured to verify the ordered operation items to obtain a verification result; and The ticket generation unit (1403) is connected to the operation sequence generation unit (1401) and the verification unit (1402) respectively, and is used to generate the operation ticket according to the ordered operation items and the verification results.

4. A power grid fault processing system as claimed in claim 3, characterized in that: Also includes: Visualization module; The visualization module comprises: A power grid display unit, connected to the database (110), for displaying the power grid configuration information; a fault display unit, connected to the fault location unit (1204) and the power grid display unit, respectively, and used to display the location information of the power grid fault in the power grid configuration information; and An operation ticket printing unit is connected to the ticket generating unit (1403) and is used to display and print the operation ticket.

5. A power grid fault processing system according to claim 1, characterized in that: The symptom information of the power grid fault includes fault logs, alarm events and change events; The grid configuration information includes a grid topology and a name and an IP address of each of the electrical devices.

6. A method for handling power grid faults, characterized in that: include: Collect symptom information of power grid faults, power grid configuration information and real-time operation data of each power equipment in the power grid; Acquire location information of the power grid fault according to symptom information of the power grid fault, the power grid configuration information and real-time operation data of each of the power equipment; Generate a dispatch instruction according to the location information of the power grid fault, the operation task set, the operation rule set and the power grid configuration information; as well as Generate an operation ticket according to the dispatch instruction to repair the power grid fault; The step of acquiring the location information of the power grid fault according to the symptom information of the power grid fault, the power grid configuration information and the real-time operation data of each of the power equipment comprises: Analyze the real-time operation data of each power device to obtain the voltage and current data of each grid node; Acquire a fault service path according to the symptom information of the power grid fault and the power grid configuration information; Constructing a fault location model using a hybrid equation of Boolean equations and linear equations according to the symptom information of the power grid fault, the fault service path and the voltage and current data of each of the power grid nodes; and The fault location model is solved to obtain location information of the power grid fault.

7. A method for handling power grid faults according to claim 6, characterized in that: The step of generating a dispatch instruction according to the location information of the power grid fault, the operation task set, the operation rule set and the power grid configuration information comprises: Selecting a corresponding operation task from the operation task set according to the location information of the power grid fault; Selecting a corresponding operation rule from the operation rule set according to the selected operation task; and According to the selected operation tasks, operation rules and power grid configuration information, a deep reinforcement learning method is used to obtain the orderly scheduling instructions.

8. A method for handling power grid faults according to claim 6, characterized in that: The step of generating an operation ticket according to the dispatch instruction comprises: Generate ordered operation items according to the ordered scheduling instructions; Verifying the ordered operation items to obtain verification results; and The operation ticket is generated according to the ordered operation items and the verification results.

Citation Information

Patent Citations

  • Rules-based intelligent system for grid fault diagnosis

    CN104679828A

  • Power grid fault intelligent processing system and method based on knowledge graph

    CN113283704A