Power grid fault scheduling system and method based on knowledge graph

Abstract

The invention discloses a power grid fault scheduling system and method based on a knowledge graph. The power grid fault scheduling system comprises an Internet of Things sensing subsystem, a fault scheduling decision subsystem and an industrial control system. The Internet of Things sensing subsystem is connected with the fault scheduling subsystem; the internet-of-things sensing subsystem is used for monitoring a power grid system in real time by using various sensors and is used for acquiring operation data of power grid equipment and sending characteristic information data and the operation data of the power grid equipment to the fault scheduling decision subsystem; wherein the fault scheduling decision subsystem comprises a data receiving module, a knowledge graph module and a scheduling plan generation module; and the knowledge graph module is used for acquiring a fault scheduling decision corresponding to the characteristic information data and the operation data of the power grid equipment from a preset scheduling knowledge graph, and sending the scheduling decision to the scheduling plan generation module. The technical problems that the current power dispatching process is tedious and complex, excessively depends on the experience of dispatchers and is low in dispatching efficiency are solved.

Description

Technical Field

[0001] The present invention belongs to the field of power grid operation and maintenance, and specifically relates to a power grid fault dispatching system and method based on knowledge graph. Background Art

[0002] The power system is a large-scale industrial system that operates strictly in accordance with the laws of physics. The dispatching and operation system is the foundation of its safe, stable, and reliable operation. Traditional power dispatch relies on dispatchers to manually judge and implement dispatch operations based on dispatch procedures and plans, and the actual operation of the power system, supported by professional control expertise. This process is cumbersome and complex, and overly reliant on the dispatcher's experience. In actual dispatch work, field personnel often repeat or report dispatch information in natural language, and dispatch operators in the control room manually dispatch the power grid according to the instructions of field personnel. This results in low efficiency and a low degree of automation.

[0003] Ultra-large-scale power grids, as complex, nonlinear systems, have accumulated vast amounts of data over years of operation. With the increasing number of new elements within the system, dispatch operations are no longer solely focused on data mining and application, but face the technical bottleneck of transforming data into knowledge. With the development of artificial intelligence and deep learning, as well as the improvement of computing power, algorithms, and data technology, knowledge graphs are rapidly advancing, along with other technologies such as relational understanding and knowledge mining, knowledge graph construction and learning, knowledge evolution and reasoning, and intelligent description and generation. Knowledge graphs are poised to become a core technology for next-generation dispatch system applications. Summary of the Invention

[0004] To solve the above problems, the present invention provides a knowledge graph-based power grid fault dispatching system and method to solve the technical problems in the existing technology of excessive reliance on manual labor, low efficiency and low degree of automation during power grid operation.

[0005] In order to achieve the above-mentioned purpose of the invention, the present invention proposes a power grid fault dispatching system based on knowledge graph, which includes an Internet of Things perception subsystem, a fault dispatching decision subsystem and an industrial control system; The IoT sensing subsystem is connected to the fault dispatching subsystem; The IoT sensing subsystem uses a variety of sensors to monitor the power grid system in real time, to obtain the operating data of the power grid equipment, and to send the characteristic information data and operating data of the power grid equipment to the fault scheduling decision subsystem; The fault scheduling decision subsystem includes a data receiving module, a knowledge graph module and a scheduling plan generation module; The data receiving module is connected to the knowledge graph module; The knowledge graph module is connected to the scheduling plan generation module; The data receiving module receives the grid device characteristic information data and operation data, and sends the grid device characteristic information data and operation data to the knowledge graph module; The knowledge graph module is used to obtain the fault scheduling decision corresponding to the grid equipment characteristic information data and operation data from the preset scheduling knowledge graph, and send the scheduling decision to the scheduling plan generation module; The scheduling plan generation module is used to generate a scheduling plan according to the scheduling decision and output the scheduling plan to the industrial control system.

[0006] Furthermore, the IoT sensing subsystem includes a voltage detection module, a leakage detection module, a vibration detection module, a temperature detection module, and a humidity detection module; The voltage detection module is used for voltage detection of power grid equipment; The leakage detection module is used for leakage current detection of power grid equipment; The vibration detection module is used for detecting mechanical vibration of the power grid equipment housing; The temperature detection module is used to detect the surface temperature of the power grid equipment; The humidity detection module is used for detecting the humidity of the working environment of the power grid equipment.

[0007] The present invention also provides a knowledge graph-based power grid fault dispatching method, which is applied to a knowledge graph-based power grid fault dispatching system as described in any one of claims 1-2. The method mainly includes: Step S1, building a fault scheduling knowledge graph library; Step S2: acquiring characteristic information data and operating data of power grid equipment through the IoT sensing subsystem, and sending the characteristic information data and operating data of the power grid equipment to the fault dispatch decision subsystem; Step S3: The data receiving module receives the grid equipment characteristic information data and operation data, and sends the grid equipment characteristic information data and operation data to the knowledge graph module; Step S4, obtaining a scheduling decision corresponding to the grid equipment characteristic information data and operation data from a preset knowledge graph library; Step S5: generating a scheduling instruction according to the scheduling decision, and outputting the scheduling plan to the industrial control system.

[0008] Furthermore, the implementation of step S1 is as follows: Step S101: Taking power grid equipment as the object, a knowledge chain is established around the equipment components to form a structured knowledge base. Step S102, generating a graph database from the structured knowledge base; Step S103: Store the graph database in the graph data network to form a chain-related knowledge graph.

[0009] Furthermore, the knowledge nodes contained in the structured knowledge base include equipment, components, defect types, defect causes, identification methods, phenomenon characteristics, data characteristics, identification rules, feature quantities, technical standards, solutions and preventive measures.

[0010] Furthermore, the graph database generation is to separate and reorganize the knowledge in the structured knowledge base into data in the graph database that can be recognized by the algorithm. The knowledge node relationship on the knowledge chain includes the starting node, the ending node, and the node relationship.

[0011] Furthermore, the chain-type associative knowledge graph is formed by importing a graph database to generate a knowledge chain network graph, in which there are knowledge nodes and relationship data between nodes.

[0012] Compared with the prior art, the beneficial effects of the present invention are at least as follows: The present invention establishes a structured knowledge base, generates a graph database from the structured knowledge base, and then stores it in a graph data network to form a knowledge graph. The graph relationship diagram is used to realize the chain association of all knowledge nodes. The knowledge graph created by the knowledge graph has a very high matching degree with the actual business needs. When an alarm occurs in the equipment, the cause and probability value of the alarm can be automatically pushed through the knowledge graph network. After further investigation by the operation and maintenance personnel based on the guidance suggestions given by the software system, it is found that the defect diagnosis accuracy is extremely high. The knowledge graph is used to solve the defect problem in time, ensuring the safe and stable operation of the power grid equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 A schematic diagram of a knowledge graph-based power grid fault dispatching system for implementing an embodiment of the present invention; Figure 2 A schematic diagram of a knowledge graph-based power grid fault dispatching method for implementing an embodiment of the present invention; Figure 3 Schematic diagram of a knowledge graph creation method in step S1 of a power grid fault scheduling method based on a knowledge graph according to an embodiment of the present invention; Figure 4 A schematic diagram of an application example of a knowledge graph-based power grid fault dispatching system to implement an embodiment of the present invention. DETAILED DESCRIPTION

[0014] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0015] It should be noted that the terms "first", "second", "third", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0016] Example 1

[0017] like Figure 1 As shown, the first embodiment of the present invention provides a power grid fault dispatching system based on a knowledge graph, the system including an Internet of Things perception subsystem, a fault dispatching decision subsystem and an industrial control system; The IoT sensing subsystem is connected to the fault dispatching subsystem; The IoT sensing subsystem uses a variety of sensors to monitor the power grid system in real time, to obtain the operating data of the power grid equipment, and to send the characteristic information data and operating data of the power grid equipment to the fault scheduling decision subsystem; The fault scheduling decision subsystem includes a data receiving module, a knowledge graph module and a scheduling plan generation module; The data receiving module is connected to the knowledge graph module; The knowledge graph module is connected to the scheduling plan generation module; The data receiving module receives the grid device characteristic information data and operation data, and sends the grid device characteristic information data and operation data to the knowledge graph module; The knowledge graph module is used to obtain the fault scheduling decision corresponding to the grid equipment characteristic information data and operation data from the preset scheduling knowledge graph, and send the scheduling decision to the scheduling plan generation module; The scheduling plan generation module is used to generate a scheduling plan according to the scheduling decision and output the scheduling plan to the industrial control system.

[0018] The dispatch plan generation module includes generator voltage value, adjusted voltage distribution, capacitor voltage and current value, generator temperature, humidity value, etc.

[0019] The specific IoT sensing subsystem includes a voltage detection module, a leakage detection module, a vibration detection module, a temperature detection module and a humidity detection module; the voltage detection module is used for voltage detection of power grid equipment; the leakage detection module is used for leakage current detection of power grid equipment; the vibration detection module is used for mechanical vibration detection of the power grid equipment casing; the temperature detection module is used for surface temperature detection of power grid equipment; and the humidity detection module is used for humidity detection in the working environment of power grid equipment.

[0020] like Figure 2 As shown, this embodiment also relates to a power grid fault dispatching method based on a knowledge graph, which is applied to a power grid fault dispatching system based on a knowledge graph as described in any one of claims 1-2, including: Step S1, building a fault scheduling knowledge graph library; Among them, Figure 3 As shown in the figure, the specific steps to build a fault scheduling knowledge graph library are: Step S101: Taking power grid equipment as the object, a knowledge chain is established around the equipment components to form a structured knowledge base. The knowledge nodes included in the structured knowledge base in step S101 include equipment, components, defect types, defect causes, identification methods, phenomenon characteristics, data characteristics, identification rules, feature quantities, technical standards, solutions and preventive measures.

[0021] Step S102, generating a graph database from the structured knowledge base; The graph database generation in step S102 is to separate and reorganize the knowledge in the structured knowledge base into data in the graph database that can be recognized by the algorithm. The knowledge node relationship on the knowledge chain includes the starting node, the ending node, and the node relationship.

[0022] Step S103: Store the graph database in the graph data network to form a chain-related knowledge graph.

[0023] The chain-type associative knowledge graph in step S103 is formed by importing a graph database to generate a knowledge chain network graph, in which there are knowledge nodes and relationship data between nodes.

[0024] Step S2: acquiring characteristic information data and operating data of power grid equipment through the IoT sensing subsystem, and sending the characteristic information data and operating data of the power grid equipment to the fault dispatch decision subsystem; Step S3: The data receiving module receives the grid equipment characteristic information data and operation data, and sends the grid equipment characteristic information data and operation data to the knowledge graph module; Step S4, obtaining a scheduling decision corresponding to the grid equipment characteristic information data and operation data from a preset knowledge graph library; Step S5: generating a scheduling instruction according to the scheduling decision, and outputting the scheduling plan to the industrial control system.

[0025] Example 2

[0026] like Figure 4 As shown, in this embodiment, the existing knowledge graph-based power grid fault system preliminarily determines whether to trigger an alarm. If the judgment result is no, it returns to execute real-time collection of equipment operation data. If the judgment result is yes, it executes equipment full life cycle display and / or management indicator display, and then through knowledge retrieval combined with intelligent diagnosis analysis of the expert knowledge base, it is determined whether the alarm cause can be retrieved and / or whether the alarm situation is serious. If the alarm cause can be retrieved, the alarm cause is displayed in a list. If the alarm cause cannot be retrieved, manual troubleshooting is performed, and then the expert knowledge obtained from manual troubleshooting is imported into the expert knowledge base (i.e., the knowledge graph is updated). If it is determined that the alarm situation is not serious, the alarm level and / or alarm information is displayed. If it is determined that the alarm situation is serious, an alarm reminder is issued and alarm handling suggestions are provided.

[0027] In other embodiments, the grid equipment operation data at least determines a grid operation area, and the grid operation area at least includes a corresponding process of a grid equipment in a grid operation link in a region.

[0028] Based on the above embodiment, it also includes: using multi-layer relationships to search for the relationship between various transactions in the power grid operation link, obtaining and displaying the predicted abnormal information of any of the power grid operation areas, wherein the predicted abnormal information includes the name of the abnormal object, the name of the abnormal device, the abnormal type and the abnormal prediction time.

[0029] In an embodiment of the present invention, each area includes at least one substation group, and each substation group includes at least one set of transformers, circuit breakers, and relay protection components. After obtaining prediction information for each area, information such as the number of voltage deviations, voltage fluctuations and flickers, three-phase voltage imbalance, frequency deviations, harmonics, and intermittent wave prediction information included in each area is obtained separately.

[0030] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0031] The above embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0032] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A power grid fault dispatching system based on knowledge graph, characterized in that: Including IoT sensing subsystem, fault dispatch decision subsystem and industrial control system; The IoT sensing subsystem is connected to the fault dispatching subsystem; The IoT sensing subsystem uses a variety of sensors to monitor the power grid system in real time, to obtain the operating data of the power grid equipment, and to send the characteristic information data and operating data of the power grid equipment to the fault dispatch decision subsystem; The fault scheduling decision subsystem includes a data receiving module, a knowledge graph module and a scheduling plan generation module; The data receiving module is connected to the knowledge graph module; The knowledge graph module is connected to the scheduling plan generation module; The data receiving module receives the characteristic information data and operation data of the power grid equipment, and sends the characteristic information data and operation data of the power grid equipment to the knowledge graph module; The knowledge graph module is used to obtain the fault dispatch decision corresponding to the characteristic information data and operation data of the power grid equipment from the preset dispatch knowledge graph, and send the dispatch decision to the dispatch plan generation module; The scheduling plan generation module is used to generate a scheduling plan according to the scheduling decision, and output the scheduling plan to the industrial control system.

2. According to the knowledge graph-based power grid fault dispatching system of claim 1, it is characterized in that: The IoT sensing subsystem includes a voltage detection module, a leakage detection module, a vibration detection module, a temperature detection module and a humidity detection module; The voltage detection module is used for voltage detection of power grid equipment; The leakage detection module is used for leakage current detection of power grid equipment; The vibration detection module is used for mechanical vibration detection of the housing of the power grid equipment; The temperature detection module is used to detect the surface temperature of the power grid equipment; The humidity detection module is used for humidity detection of the working environment of the power grid equipment.

3. A knowledge graph-based power grid fault dispatching method, applied to a knowledge graph-based power grid fault dispatching system as claimed in any one of claims 1-2, characterized in that: include: Step S1, constructing a fault scheduling knowledge graph library; Step S2: Acquire the characteristic information data and operation data of the power grid equipment through the IoT sensing subsystem, and send the characteristic information data and operation data of the power grid equipment to the fault dispatch decision subsystem. Step S3, the data receiving module receives the characteristic information data and operation data of the power grid equipment, and sends the characteristic information data and operation data of the power grid equipment to the knowledge graph module; Step S4, obtaining a dispatch decision corresponding to the characteristic information data and operation data of the power grid equipment from a preset knowledge graph library; Step S5, generating a scheduling instruction according to the scheduling decision, and outputting the scheduling plan to the industrial control system.

4. A power grid fault dispatching method based on knowledge graph according to claim 3, characterized in that: The implementation of step S1 is as follows: Step S101, taking power grid equipment as the object, establishing a knowledge chain of related knowledge nodes around equipment components to form a structured knowledge base; Step S102, generating a graph database from the structured knowledge base; Step S103, storing the graph database in the graph data network to form a chain-type associated knowledge graph.

5. A power grid fault dispatching method based on knowledge graph according to claim 3, characterized in that: The implementation of step S1 is as follows: Step S101, taking power grid equipment as the object, establishing a knowledge chain of related knowledge nodes around equipment components to form a structured knowledge base; Step S102, generating a graph database from the structured knowledge base; Step S103, storing the graph database in the graph data network to form a chain-type associated knowledge graph.

6. A method for dispatching power grid faults based on knowledge graph according to claim 4, characterized in that: The knowledge nodes contained in the structured knowledge base include equipment, components, defect types, defect causes, identification methods, phenomenon characteristics, data characteristics, identification rules, feature quantities, technical standards, solutions and preventive measures.

7. A method for dispatching power grid faults based on knowledge graph according to claim 4, characterized in that: The graph database generation is to separate and reorganize the knowledge in the structured knowledge base into data in the graph database that can be recognized by the algorithm. The knowledge node relationship on the knowledge chain includes the starting node, the ending node, and the node relationship.

8. A method for dispatching power grid faults based on knowledge graph according to claim 4, characterized in that: The chain-type associative knowledge graph is formed by importing a graph database to generate a knowledge chain network graph, in which there are knowledge nodes and relationship data between nodes.

Images