Fault knowledge graph construction method of transformer substation optical fiber loop and computer equipment

Abstract

The invention belongs to the technical field of transformer substation data fault analysis, and particularly relates to a transformer substation optical fiber loop fault knowledge graph construction method and computer equipment, and the method comprises the steps: 1) obtaining the fault information of equipment in an optical fiber loop; 2) extracting a relationship between entities of the knowledge graph from the fault information; the types of the entities comprise a fault type entity, a device type entity and a fault processing suggestion entity; the relationship between the entities comprises a connection relationship between the equipment type entities, a fault type relationship between the equipment type entities and the fault type entities, and a suggestion relationship between the fault type entities and the fault processing suggestion entities; and 3) constructing the fault knowledge graph of the optical fiber loop of the transformer substation according to the entities extracted from the fault information.The corresponding fault type can be determined according to the corresponding equipment type entities and the fault type relationship thereof, and the fault processing suggestions can be determined according to the opinion relationship, so that fault analysis is facilitated.

Description

Technical Field

[0001] The present invention belongs to the technical field of substation data fault analysis, and specifically relates to a method and computer equipment for constructing a fault knowledge graph of a substation optical fiber loop. Background Art

[0002] The secondary side of a traditional substation has a large number of cables. When a fault occurs on the secondary side, it is not easy to analyze and troubleshoot the fault, which affects the normal operation of the substation. In order to solve the above problems, the prior art proposes a smart substation, which realizes the intelligence and networking of the equipment in the station with the IEC61850 communication standard, and replaces the secondary circuit of the traditional substation with an optical fiber circuit. When an optical fiber circuit fault occurs in a smart substation, the on-site operation and maintenance personnel often identify and troubleshoot these fault information, and restore the faulty equipment to normal as soon as possible to ensure the stable operation of the substation. Since the fault data generated by these operating equipment over time is extremely large, the method of directly analyzing and troubleshooting the fault information in the prior art is often inefficient and cannot restore the normal operation of the substation in time. Summary of the invention

[0003] The purpose of the present invention is to provide a method and computer equipment for constructing a fault knowledge graph of a substation optical fiber loop, so as to solve the technical problem that the optical fiber loop fault analysis and processing efficiency of the intelligent substation is low, resulting in a long fault recovery time and affecting the normal operation of the substation.

[0004] In order to solve the above technical problems, the present invention provides a method for constructing a fault knowledge graph of a substation optical fiber loop, comprising the following steps: 1) Obtain fault information of devices in the optical fiber loop; 2) Extracting entities and relationships between entities in the knowledge graph from fault information; entity types include: fault type entity, equipment type entity, and fault handling suggestion entity; relationships between entities include: connection relationships between equipment type entities used to characterize the connection relationship between entities, fault type relationships between equipment type entities and fault type entities used to characterize the fault type of a certain type of equipment, and recommendation relationships between fault type entities and fault handling suggestion entities used to characterize the handling method of a certain type of fault; 3) Construct a fault knowledge graph of the substation optical fiber loop based on the entities extracted from the fault information and the relationships between the entities.

[0005] Furthermore, the type of entity also includes a fault frequency entity; the relationship between entities also includes a fault frequency relationship between the device type entity and the fault frequency entity for characterizing the fault frequency of the device of this type.

[0006] Furthermore, the device type entity is obtained by extracting the device type from the fault information and performing deduplication processing.

[0007] Furthermore, the fault type entity is obtained by extracting the fault type from the fault information and performing deduplication processing.

[0008] Furthermore, the fault handling suggestion entity is obtained by extracting the fault handling suggestions from the fault information and performing deduplication processing.

[0009] Furthermore, the fault device type, fault type and fault handling suggestion in the fault information are respectively stored in their corresponding fields.

[0010] Furthermore, the fault information is stored in a fault information database in a table format, and the fault device type, fault type and fault handling suggestion in the fault information are stored in different rows of the table according to field types.

[0011] Furthermore, the fault knowledge graph is saved as a file in json format for visualization.

[0012] The present invention is a pioneering invention, and its beneficial effects are as follows: the fault knowledge graph construction method of the substation optical fiber loop of the present invention takes the fault equipment type, fault type and fault handling suggestion of the fault information as entities in the knowledge graph, and determines the relationship between the entities of the knowledge graph, and constructs the knowledge graph based on the entities and the relationship. When a certain equipment type fails, the knowledge graph can be used to determine the corresponding fault type based on the corresponding equipment type entity and its fault type relationship, and determine the fault handling suggestion based on the fault type entity and the suggestion relationship, so that the substation staff can directly and effectively determine the faulty equipment type, fault type and handling method, which improves the analysis efficiency of substation faults, can quickly resolve faults when they occur, and reduce the impact of faults on the normal operation of the substation.

[0013] To solve the above technical problems, the present invention further provides a computer device, including a processor, which implements the method steps described in the method for constructing a fault knowledge graph of a substation optical fiber loop of the present invention when executing a computer program.

[0014] The present invention is a pioneering invention, and its beneficial effects are as follows: when executing a computer program, the processor in the computer device of the present invention takes the faulty device type, fault type and fault handling suggestions of the fault information as entities in the knowledge graph, determines the relationship between the entities of the knowledge graph, and constructs the knowledge graph based on the entities and relationships. When a certain equipment type fails, the knowledge graph can be used to determine the corresponding fault type based on the corresponding equipment type entity and its fault type relationship, and determine the fault handling suggestions based on the fault type entity and the suggested relationship, so that the substation staff can directly and effectively determine the faulty equipment type, fault type and handling method, which improves the efficiency of substation fault analysis, can quickly resolve faults when they occur, and reduce the impact of faults on the normal operation of the substation. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a flow chart of a method for constructing a knowledge graph for a smart substation according to a method embodiment of the present invention; Figure 2 is a knowledge extraction flow chart of a method embodiment of the present invention; Figure 3 is an example diagram of a knowledge graph constructed according to a method embodiment of the present invention; Figure 4 It is a visualization diagram of the processed knowledge graph of the method embodiment of the present invention. DETAILED DESCRIPTION

[0016] The fault knowledge graph construction method and computer device of the substation optical fiber loop of the present invention take the fault equipment type, fault type and fault handling suggestion of the fault information as entities in the knowledge graph, determine the relationship between the entities of the knowledge graph, and construct the knowledge graph according to the entities and the relationship. When a certain equipment type fails, the knowledge graph can be used to determine the corresponding fault type according to the corresponding equipment type entity and its fault type relationship, and determine the fault handling suggestion according to the fault type entity and the opinion relationship, so that the substation staff can directly and effectively determine the faulty equipment type, fault type and handling method, improve the analysis efficiency of the substation fault, and can quickly solve the fault when it occurs, reducing the impact of the fault on the normal operation of the substation.

[0017] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is further described in detail below with reference to the accompanying drawings and embodiments.

[0018] Method Example: The fault knowledge graph construction method of the substation optical fiber loop of this embodiment is as follows: Figure 1 As shown, the following steps are included: Step 1: Establish a fault information database based on the fault information data of the device connected to the optical fiber loop.

[0019] In this embodiment, the fault information data of the device connected to the optical fiber loop is stored and database modeled to obtain a fault information database, which is convenient for subsequent knowledge extraction from the fault information. The fault information in the fault information database is stored in a table format, and the table content is shown in Table 1.

[0020] Table 1 Fault Information Table The constructed models are all stored in the open source database MYSQL. Each fault information includes the fault type, fault content, fault device type, fault handling suggestions, fault time and the connection relationship of the faulty device (name of the opposite device).

[0021] In order to facilitate the extraction of entities in the fault knowledge graph, in this embodiment, different information in the fault information is stored in their respective corresponding fields, and stored in different rows of the table according to the field classification. When extracting the corresponding entity, it can be extracted from the corresponding field of the corresponding row in the table. As other implementation methods, it can also be stored in a table format without dividing the fields, and even without establishing a fault information database, and directly proceed to step 2.

[0022] Step 2: Extract fault knowledge from the fault information database and construct a knowledge graph based on the fault knowledge.

[0023] According to the fault information database established in step 1, entities and relationships are extracted, and the triple data <entity, relationship, entity> of the knowledge graph is established using the extracted entities and relationships. Figure 2 As shown, the specific steps are as follows: 1. Determine the node entities in the knowledge graph.

[0024] According to the fault information ( Figure 2 The four fields of device name, fault type, fault handling suggestion, and fault time in the known data can determine the three types of entities ABC in the knowledge graph. Class A entities are device type entities, Class B entities are fault type entities, and Class C entities are fault handling suggestion entities.

[0025] In this embodiment, in order to more intuitively display the fault frequency of the device, the fault type entity also includes a type D entity: a fault frequency entity.

[0026] In this embodiment, Class A entities represent device classes including switches, which can be obtained by querying the device name field in Table 1 and removing duplicates; Class B entities represent the types of faults that may occur in each device, which can be obtained by querying the fault types in Table 1 and removing duplicates; Class C entities represent fault handling suggestions for solving various types of faults, which can be obtained by querying and removing duplicates in the fault handling suggestion field in Table 1; Class D entities represent the frequency of faults, which can be obtained by querying the number of fault times that occur in the corresponding device.

[0027] In this embodiment, deduplication processing is performed to reduce the degree of duplication of the knowledge graph, reduce the complexity of the knowledge graph without causing knowledge loss, and facilitate the construction of the knowledge graph.

[0028] 2. Determine the relationship between entities in the knowledge graph.

[0029] Device categories include switches, data acquisition devices, and protection devices. The devices are interconnected through optical fibers to form optical fiber loops. Both data acquisition devices and protection devices are directly or indirectly connected to switches through optical fibers. Therefore, there is a connection relationship within the A-type entity, that is, the device category entity whose device category is a switch has a connection relationship with other device category entities. If a certain type of fault occurs in a Class A entity, there is a fault type relationship between the Class A entity and the corresponding fault type entity (Class B entity). Furthermore, in order to resolve the fault that occurs in the device, specific fault handling suggestions need to be given to resolve the fault, so there is a suggestion relationship between the Class B entity and the Class C entity.

[0030] The connection relationship is used to characterize the connection relationship between entities. The fault type relationship is used to characterize the fault type of a certain type of equipment. The suggestion relationship is used to characterize the handling method of a certain type of fault.

[0031] In order to more intuitively display the fault frequency of the equipment, the present embodiment adds a fault frequency node, and accordingly increases the number of faults that occur in the A-type entity, which represents that there is a fault frequency relationship between the A-type entity and the D-type entity. The fault frequency relationship is used to characterize the fault frequency of the equipment.

[0032] like Figure 3 As shown in the figure, by extracting four types of entities, ABCD, from the fault information database through the above steps and determining the relationship between the entities, a knowledge graph about fiber loop fault information can be defined. In the figure, the dark blue nodes are type A entities, the light blue nodes are type D entities, the red ones are type B entities, and the green ones are type C entities.

[0033] Step 3: Store the completed knowledge graph.

[0034] The entities and relationships required by the knowledge graph are stored in a json file. The specific contents are as follows: {"nodes":[{"id": "0", "name": "A1",},{ "id": "1", "name":"B1",},…,{ "id": "N", "name": "DN",}], "links": [{"source": "1","target": "0",desc: "Link"},{"source":"2","target": "1",desc: "Link"},…,{"source": "N","target": "M",desc: "Failure frequency"}]} Nodes mainly store all entities in the knowledge graph, and the id and name of the nodes need to be recorded; links mainly store source entities, target entities, and the relationship between source entities and target entities. Based on the data stored in the json file, the echarts open source framework can be used to visualize the knowledge graph, such as Figure 4 As shown in the figure, it is convenient for the operation and maintenance personnel of the smart substation to view and analyze faults, thus improving the efficiency of fault analysis.

[0035] Computer equipment example: A computer device of the present invention includes a processor, and the processor implements the steps of the method for constructing a fault knowledge graph of a substation optical fiber loop as described in the method embodiment when executing a computer program. The specific process and principle of the method have been described in detail in the method embodiment, and will not be repeated in this embodiment.

[0036] The processor may be a microprocessor MCU, a programmable logic device FPGA or other processing device.

[0037] The method and computer device for constructing the fault knowledge graph of the optical fiber loop of the smart substation of the present invention, through the three steps described in the method embodiment, stores and displays the fault information of the optical fiber loop in the form of a knowledge graph, which can conveniently and intuitively display the relationship between the equipment type, fault type, and fault handling suggestions of the optical fiber loop, provide suggestions for operation and maintenance personnel, and help quickly solve the fault of the optical fiber loop and restore the normal operation of the smart substation in time. Further, the equipment type entity, fault type entity, and fault handling suggestion entity in this embodiment are all extracted from the fault information and deduplicated, which reduces the complexity and repetition of the knowledge graph, merges and simplifies the knowledge graph, and facilitates the construction of the knowledge graph. Further, in this embodiment, the equipment type, fault type, and fault handling suggestion are respectively stored in specific fields in the fault information. When constructing the knowledge graph, relevant content can be extracted from the corresponding fields, which is convenient for extracting entities of the knowledge graph and determining the relationship between entities. In this embodiment, the fault information is also stored in the fault information database in the form of a table, and different contents of the fault information are stored in different rows of the table according to the field type, which is convenient for extracting entities and relationships of the fault knowledge graph.

Claims

1. A method for constructing a fault knowledge graph of a substation optical fiber loop, characterized in that: The following steps are involved: 1) Obtain fault information of devices in the optical fiber loop; 2) Extracting entities and relationships between entities in the knowledge graph from fault information; The types of entities include: fault type entities, equipment type entities and fault handling suggestion entities; the relationships between entities include: connection relationships between equipment type entities for characterizing the connection relationship between entities, fault type relationships between equipment type entities and fault type entities for characterizing the fault type to which a fault occurring in a certain type of equipment belongs, and suggestion relationships between fault type entities and fault handling suggestion entities for characterizing the handling method of a certain type of fault; 3) Construct a fault knowledge graph of the substation optical fiber loop based on the entities extracted from the fault information and the relationships between the entities.

2. The method for constructing a fault knowledge graph of a substation optical fiber loop according to claim 1, characterized in that: The types of entities also include fault frequency entities; the relationships between entities also include fault frequency relationships between equipment type entities and fault frequency entities for characterizing the fault frequency of equipment of this type.

3. The method for constructing a fault knowledge graph of a substation optical fiber loop according to claim 1, characterized in that: The device type entity is obtained by extracting the device type from the fault information and performing deduplication processing.

4. The method for constructing a fault knowledge graph of a substation optical fiber loop according to claim 1, characterized in that: The fault type entity is obtained by extracting the fault type from the fault information and performing deduplication processing.

5. The method for constructing a fault knowledge graph of a substation optical fiber loop according to claim 1, characterized in that: The fault handling suggestion entity is obtained by extracting the fault handling suggestions from the fault information and performing deduplication processing.

6. The method for constructing a fault knowledge graph of a substation optical fiber loop according to claim 1, characterized in that: The fault device type, fault type and fault handling suggestion in the fault information are respectively stored in their corresponding fields.

7. The method for constructing a fault knowledge graph of a substation optical fiber loop according to claim 6, characterized in that: The fault information is stored in a fault information database in a table format, and the fault device type, fault type and fault handling suggestion in the fault information are stored in different rows of the table according to field types.

8. The method for constructing a fault knowledge graph of a substation optical fiber loop according to any one of claims 1 to 7, characterized in that: The fault knowledge graph is saved as a file in json format for visualization.

9. A computer device comprising a processor, characterized in that: The processor implements the steps of the method for constructing a fault knowledge graph of a substation optical fiber loop as described in any one of claims 1 to 8 when executing the computer program.

Images