Method and system for constructing spatial correlation knowledge graph of power transformation equipment
By constructing a spatial association knowledge graph of substation equipment, the problem of low efficiency in traditional substation operation and maintenance services has been solved, and the accuracy of mining multiple types of variables and predicting their status has been improved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-20
- Publication Date
- 2026-04-07
AI Technical Summary
Traditional substation operation and maintenance relies on manual inspection, which is inefficient and easily affected by human factors and the environment. Existing technologies lack multi-sequence data mining methods, resulting in low accuracy in predicting the condition of substation equipment.
A spatial association knowledge graph of substation equipment is constructed. By acquiring the equipment set, determining the state vector, calculating the similarity, and modifying the directed edges, the potential association relationships between the equipment are established.
It enables the mining of multiple types of relevant variables for a single power equipment, improving the accuracy and efficiency of power equipment status prediction.
Smart Images
Figure CN121809609A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of power equipment condition prediction technology, and specifically to a method and system for constructing a spatial association knowledge graph of power equipment. Background Technology
[0002] Traditional substation operation and maintenance (O&M) relies heavily on manual labor, involving extensive on-site inspections and manual data recording. This is not only labor-intensive but also inefficient and susceptible to human error and environmental conditions. As power systems become increasingly complex, the demands for accuracy and efficiency in O&M operations are also rising. In recent years, the development of knowledge graph technology has brought new opportunities to intelligent substation O&M. Knowledge graphs can integrate and organize large amounts of structured and unstructured data, representing the entities, attributes, and relationships of the power system through semantic networks, thereby improving the understandability and operability of the data.
[0003] With the development of artificial intelligence technology, predictive models for forecasting the status of power equipment have emerged in recent years. However, these technologies currently mainly rely on single-type sequence data based on the data from the power equipment itself. Since different power equipment in the same region can influence each other, predictions based on a single type of sequence data often have low accuracy. Training a network model with multi-sequence data requires pre-identifying multiple sequence data that may affect a single power equipment, and current technologies lack relevant data mining methods. Summary of the Invention
[0004] The purpose of this invention is to provide a method and system for constructing a spatial association knowledge graph of substation equipment. This method and system can determine the correlation between different substation equipment by constructing a spatial association knowledge graph of substation equipment.
[0005] To achieve the above objectives, embodiments of the present invention provide a method for constructing a spatial association knowledge graph of power equipment, comprising: Obtain the set of substation equipment to be constructed; Construct an initial directed graph of relationships between every two types of power equipment in the power equipment set based on preset standard component relationships; Determine the state vector of each type of substation based on the state data of the substation equipment; Calculate the similarity between every two state vectors; The state similarity between each pair is determined based on the results of the similarity calculation. Modify the directed edges in the initial relational directed graph based on the state similarity to obtain the spatial association knowledge graph of the power equipment.
[0006] Optionally, an initial directed graph of relationships between every two types of power equipment in the power equipment set is constructed based on preset standard component relationships, including: The power equipment, the functional modules and components in the power equipment are respectively designated as first-level nodes, second-level nodes and third-level nodes; The inclusion relationship and the correlation relationship between different nodes are respectively regarded as the first directed edge and the second directed edge.
[0007] Optionally, a state vector for each type of substation is determined based on the substation's state data, including: For devices capable of outputting status parameters, historical output parameters are read as the status data; For devices that cannot output status parameters, the daily inspection records of the devices that cannot output status parameters are analyzed based on a preset corpus to obtain the corresponding status data.
[0008] Optionally, a state vector for each type of substation is determined based on the substation's state data, including: Each of the aforementioned state data is normalized to obtain standard state data; Determine the minimum granularity of change for the standard state data respectively; The standard state data is extracted according to the corresponding minimum change granularity to obtain a feature data sequence; The feature data sequences are encoded respectively to obtain the corresponding state vectors.
[0009] Optionally, the minimum change granularity of the standard state data is determined, including: Calculate the difference between every two adjacent point values in the standard state data to obtain the corresponding difference sequence; In the difference sequence, determine the length of a sequence where the difference directions are consecutively the same, wherein the sequence length is greater than or equal to 10; The sequence length is used as the minimum change granularity.
[0010] Optionally, a similarity calculation is performed on every two state vectors, including: Calculate the Euclidean distance between every two state vectors to obtain the corresponding similarity.
[0011] Optionally, the state similarity between each pair is determined based on the similarity calculation results, including: The state vector is pre-divided into multiple state vector classes according to the minimum change granularity. The similarity between every two state vectors in each state vector class; The similarity is encoded as the state similarity.
[0012] Optionally, the initial relational directed graph further includes a third directed edge representing a potential association; Modify the directed edges in the initial relational directed graph based on the state similarity to obtain the spatial association knowledge graph of the power equipment, including: Modify the third directed edge in the initial relational directed graph based on the state similarity to obtain the spatial association knowledge graph of the power equipment.
[0013] On the other hand, the present invention also provides a system for constructing a spatial association knowledge graph of power equipment, including a processor configured to execute the construction method as described above.
[0014] In another aspect, the present invention also provides a computer-readable storage medium storing instructions for being read by a machine to cause the machine to perform any of the construction methods described above.
[0015] Through the above technical solutions, the embodiments of the present invention provide a method and system for constructing a spatial association knowledge graph of substation equipment. The method and system construct a spatial association knowledge graph of substation equipment based on the standard component relationships and the correlation of state vectors, while taking into account the inherent standard component relationships and the potential association relationships mined from historical data, thereby realizing the mining of multiple types of related variables of a single substation equipment.
[0016] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description
[0017] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of a method for constructing a spatial association knowledge graph of power equipment according to an embodiment of the present invention; Figure 2 This is a flowchart of a method for generating a state vector according to an embodiment of the present invention; Figure 3 This is a flowchart of a method for determining state similarity according to an embodiment of the present invention. Detailed Implementation
[0018] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.
[0019] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application all comply with relevant laws and regulations. In the embodiments of this application, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this application, and do not imply that the applicant has already used or necessarily used such solutions.
[0020] like Figure 1 The diagram shows a flowchart of a method for constructing a spatial association knowledge graph of power equipment according to an embodiment of the present invention. Figure 1 In this context, the construction method may include the following steps: In step S10, the set of substation equipment to be constructed is obtained; In step S11, an initial directed graph of the relationship between each pair of power equipment in the power equipment set is constructed based on the preset standard accessory relationships; In step S12, the state vector of each type of substation is determined based on the state data of the substation equipment; In step S13, the similarity is calculated for every two state vectors; In step S14, the state similarity between each pair is determined based on the similarity calculation results; In step S15, the directed edges in the initial relational directed graph are modified according to the state similarity to obtain the spatial association knowledge graph of the power equipment.
[0021] In such Figure 1 In the construction method shown, step S10 can be used to obtain the set of substation equipment to be constructed. This set of substation equipment can be the collection of all observable substation equipment currently in operation at the substation.
[0022] Step S11 can be used to construct an initial directed graph of relationships between every two types of power equipment in the power equipment set based on preset standard component relationships. Specifically, in one example of the present invention, the standard component relationship can be a correspondence between power equipment, functional modules within the power equipment, and functional components. Considering this correspondence, in this example, power equipment, functional modules within the power equipment, and functional components can be respectively designated as first-level nodes, second-level nodes, and third-level nodes, thereby achieving the division of power equipment or devices at different levels. Since there is an inclusion relationship between first-level nodes, second-level nodes, and third-level nodes, and there is a physical correlation between nodes at the same level, in this example, a first directed edge and a second directed edge can be added to the generated initial directed graph respectively for the inclusion and correlation relationships between different nodes.
[0023] The standard parts relationship can be determined, for example, based on the correspondence in Table 1 below: Table 1 Static Node Device Relationships
[0024] Step S12 can be used to determine the state vector of each type of substation equipment based on its state data. Considering the differences in state data among different substation equipment, for example, power node-related substation equipment such as sensors, breathers, relays, and radiators, the state data can be directly determined by reading current quantifiable parameters, such as current, voltage, oil pressure, temperature, and speed. Therefore, in this example, for this type of equipment with output state parameters, step S12 can directly read historical output parameters as state data. However, for non-quantifiable equipment, such as operating mechanisms, supports, cable trays, and housings, since these are non-output state parameter devices, the state data cannot be directly determined by reading quantifiable parameters. However, for these non-output state parameter devices, substation inspection personnel have daily inspection records. Therefore, in this example, the daily inspection records of these non-output state parameter devices can be analyzed based on a pre-set corpus to obtain the corresponding state data.
[0025] Furthermore, the units of the state data can be in various forms known to those skilled in the art. In one example of the present invention, at least a portion of the units of the state data can be as shown in Table 2 below: Table 2
[0026] Note: float(n) means to retain n decimal places.
[0027] Furthermore, considering that different state vectors have different quantization indices and corresponding units, step S12 can further include the following when generating the state vector: Figure 2 The method shown in the diagram. Figure 2 In this context, the method for generating a state vector may include the following steps: In step S20, each piece of state data is normalized to obtain standard state data. Specifically, in this example, the normalization operation can be performed, for example, using the following formula (1): (1) in, The value after normalization. This is the minimum value of the corresponding sequence. This represents the maximum value of the corresponding sequence.
[0028] In step S21, the minimum change granularity of the standard state data is determined. This minimum change granularity represents the minimum time interval at which the standard state data changes. The specific calculation method for this minimum change granularity can be of various forms known to those skilled in the art. In one example of the present invention, the minimum change granularity can be achieved by first calculating the difference between every two adjacent point values in the standard state data to obtain a corresponding difference sequence, and then determining the length of a sequence in the difference sequence where the difference directions are consecutive. For data cleaning considerations, this sequence length can be greater than or equal to 10. Finally, this sequence length is used as the minimum change granularity.
[0029] In step S22, standard state data is extracted according to the corresponding minimum change granularity to obtain a feature data sequence.
[0030] In step S23, the feature data sequences are encoded to obtain the corresponding state vectors.
[0031] Step S13 can be used to calculate the similarity between every two state vectors. The specific method for this similarity calculation can be of various forms known to those skilled in the art. In one example of the present invention, the similarity calculation can be determined using Euclidean distance.
[0032] Step S14 can be used to determine the state similarity between two states based on the similarity calculation results. Specifically, in this embodiment, considering the aforementioned process of determining state vectors, in order to simplify and reduce computational requirements, each state vector is generated based on the minimum change granularity. Therefore, only when the minimum change granularity of two state vectors is the same can there be a high state similarity between them. Therefore, in one example of the present invention, the method for determining the state similarity may further include as follows: Figure 3 The steps shown are described in this. Figure 3 In this context, the method for determining the similarity of states can be further divided into the following steps: In step S30, the state vector is pre-divided into multiple state vector classes according to the minimum change granularity; In step S31, the similarity between every two state vectors in each state vector class is calculated. In step S32, the similarity is encoded as state similarity.
[0033] In such Figure 3In the method shown, step S30 can be used to pre-divide the state vector into multiple state vector classes according to the minimum change granularity. Since the same minimum change granularity is the basic condition for high state similarity between two state vectors, step S30 can be used to perform preliminary division of the state vectors, thereby reducing the number of similarity calculations.
[0034] Step S31 can be used to calculate the similarity between every two state vectors in each state vector class. This similarity can be calculated, for example, using Euclidean distance.
[0035] Step S15 can be used to modify the directed edges in the initial directed relation graph based on state similarity to obtain a spatial association knowledge graph of substation equipment. In this embodiment, since the initial directed relation graph already contains elements representing inherent associations (inclusion relationship, correlation relationship), and steps S12 to S15 are used to mine potential associations between different nodes, the directed edge generated in step S15 can be used as a third directed edge, different from the first two directed edges. This third directed edge can be used to represent potential associations. Accordingly, step S15 can be used to modify the third directed edge in the initial directed relation graph (since the initial directed relation graph may be based on a previously constructed knowledge graph, a third directed edge may already exist, and this modification is based on recent historical data for further potential association mining) based on state similarity to obtain a spatial association knowledge graph of substation equipment. Specifically, considering that the higher the similarity value of Euclidean distance, the lower the similarity, in this embodiment, the state similarity can be taken as the reciprocal of the Euclidean distance. This satisfies the subsequent value judgment requirements and avoids the problem of numerical overflow. Step S15 can be as follows: First, determine whether there is a third directed edge between the two corresponding nodes in the initial directed graph; if there is a third directed edge, determine whether the state similarity is greater than or equal to a preset threshold; if the state similarity is greater than or equal to the threshold, no modification is needed; otherwise, if the state similarity is less than the threshold, the third directed edge can be directly deleted; if there is no third directed edge, it is necessary to determine whether the state similarity is greater than or equal to the preset threshold; if the state similarity is greater than or equal to the threshold, a third directed edge needs to be added; otherwise, if the state similarity is less than the threshold, no modification is needed.
[0036] On the other hand, the present invention also provides a system for constructing a spatial association knowledge graph of power equipment, including a processor configured to execute the construction method as described above. Specifically, the construction method may include the following steps: In step S10, the set of substation equipment to be constructed is obtained; In step S11, an initial directed graph of the relationship between each pair of power equipment in the power equipment set is constructed based on the preset standard accessory relationships; In step S12, the state vector of each type of substation is determined based on the state data of the substation equipment; In step S13, the similarity is calculated for every two state vectors; In step S14, the state similarity between each pair is determined based on the similarity calculation results; In step S15, the directed edges in the initial relational directed graph are modified according to the state similarity to obtain the spatial association knowledge graph of the power equipment.
[0037] In such Figure 1 In the construction method shown, step S10 can be used to obtain the set of substation equipment to be constructed. This set of substation equipment can be the collection of all observable substation equipment currently in operation at the substation.
[0038] Step S11 can be used to construct an initial directed graph of relationships between every two types of power equipment in the power equipment set based on preset standard component relationships. Specifically, in one example of the present invention, the standard component relationship can be a correspondence between power equipment, functional modules within the power equipment, and functional components. Considering this correspondence, in this example, power equipment, functional modules within the power equipment, and functional components can be respectively designated as first-level nodes, second-level nodes, and third-level nodes, thereby achieving the division of power equipment or devices at different levels. Since there is an inclusion relationship between first-level nodes, second-level nodes, and third-level nodes, and there is a physical correlation between nodes at the same level, in this example, a first directed edge and a second directed edge can be added to the generated initial directed graph respectively for the inclusion and correlation relationships between different nodes.
[0039] The standard parts relationship can be determined, for example, based on the correspondence in Table 1 below: Table 1 Static Node Device Relationships
[0040] Step S12 can be used to determine the state vector of each type of substation equipment based on its state data. Considering the differences in state data among different substation equipment, for example, power node-related substation equipment such as sensors, breathers, relays, and radiators, the state data can be directly determined by reading current quantifiable parameters, such as current, voltage, oil pressure, temperature, and speed. Therefore, in this example, for this type of equipment with output state parameters, step S12 can directly read historical output parameters as state data. However, for non-quantifiable equipment, such as operating mechanisms, supports, cable trays, and housings, since these are non-output state parameter devices, the state data cannot be directly determined by reading quantifiable parameters. However, for these non-output state parameter devices, substation inspection personnel have daily inspection records. Therefore, in this example, the daily inspection records of these non-output state parameter devices can be analyzed based on a pre-set corpus to obtain the corresponding state data.
[0041] Furthermore, the units of the state data can be in various forms known to those skilled in the art. In one example of the present invention, at least a portion of the units of the state data can be as shown in Table 2 below: Table 2
[0042] Note: float(n) means to retain n decimal places.
[0043] Furthermore, considering that different state vectors have different quantization indices and corresponding units, step S12 can further include the following when generating the state vector: Figure 2 The method shown in the diagram. Figure 2 In this context, the method for generating a state vector may include the following steps: In step S20, each piece of state data is normalized to obtain standard state data. Specifically, in this example, the normalization operation can be performed, for example, using the following formula (1): (1) in, The value after normalization. This is the minimum value of the corresponding sequence. This represents the maximum value of the corresponding sequence.
[0044] In step S21, the minimum change granularity of the standard state data is determined. This minimum change granularity represents the minimum time interval at which the standard state data changes. The specific calculation method for this minimum change granularity can be of various forms known to those skilled in the art. In one example of the present invention, the minimum change granularity can be achieved by first calculating the difference between every two adjacent point values in the standard state data to obtain a corresponding difference sequence, and then determining the length of a sequence in the difference sequence where the difference directions are consecutive. For data cleaning considerations, this sequence length can be greater than or equal to 10. Finally, this sequence length is used as the minimum change granularity.
[0045] In step S22, standard state data is extracted according to the corresponding minimum change granularity to obtain a feature data sequence.
[0046] In step S23, the feature data sequences are encoded to obtain the corresponding state vectors.
[0047] Step S13 can be used to calculate the similarity between every two state vectors. The specific method for this similarity calculation can be of various forms known to those skilled in the art. In one example of the present invention, the similarity calculation can be determined using Euclidean distance.
[0048] Step S14 can be used to determine the state similarity between two states based on the similarity calculation results. Specifically, in this embodiment, considering the aforementioned process of determining state vectors, in order to simplify and reduce computational requirements, each state vector is generated based on the minimum change granularity. Therefore, only when the minimum change granularity of two state vectors is the same can there be a high state similarity between them. Therefore, in one example of the present invention, the method for determining the state similarity may further include as follows: Figure 3 The steps shown are described in this. Figure 3 In this context, the method for determining the similarity of states can be further divided into the following steps: In step S30, the state vector is pre-divided into multiple state vector classes according to the minimum change granularity; In step S31, the similarity between every two state vectors in each state vector class is calculated. In step S32, the similarity is encoded as state similarity.
[0049] In such Figure 3 In the method shown, step S30 can be used to pre-divide the state vector into multiple state vector classes according to the minimum change granularity. Since the same minimum change granularity is the basic condition for high state similarity between two state vectors, step S30 can be used to perform preliminary division of the state vectors, thereby reducing the number of similarity calculations.
[0050] Step S31 can be used to calculate the similarity between every two state vectors in each state vector class. This similarity can be calculated, for example, using Euclidean distance.
[0051] Step S15 can be used to modify the directed edges in the initial directed relation graph based on state similarity to obtain a spatial association knowledge graph of substation equipment. In this embodiment, since the initial directed relation graph already contains elements representing inherent associations (inclusion relationship, correlation relationship), and steps S12 to S15 are used to mine potential associations between different nodes, the directed edge generated in step S15 can be used as a third directed edge, different from the first two directed edges. This third directed edge can be used to represent potential associations. Accordingly, step S15 can be used to modify the third directed edge in the initial directed relation graph (since the initial directed relation graph may be based on a previously constructed knowledge graph, a third directed edge may already exist, and this modification is based on recent historical data for further potential association mining) based on state similarity to obtain a spatial association knowledge graph of substation equipment. Specifically, considering that the higher the similarity value of Euclidean distance, the lower the similarity, in this embodiment, the state similarity can be taken as the reciprocal of the Euclidean distance. This satisfies the subsequent value judgment requirements and avoids the problem of numerical overflow. Step S15 can be as follows: First, determine whether there is a third directed edge between the two corresponding nodes in the initial directed graph; if there is a third directed edge, determine whether the state similarity is greater than or equal to a preset threshold; if the state similarity is greater than or equal to the threshold, no modification is needed; otherwise, if the state similarity is less than the threshold, the third directed edge can be directly deleted; if there is no third directed edge, it is necessary to determine whether the state similarity is greater than or equal to the preset threshold; if the state similarity is greater than or equal to the threshold, a third directed edge needs to be added; otherwise, if the state similarity is less than the threshold, no modification is needed.
[0052] In another aspect, the present invention also provides a computer-readable storage medium storing instructions for being read by a machine to cause the machine to perform any of the construction methods described above.
[0053] Through the above technical solutions, the embodiments of the present invention provide a method and system for constructing a spatial association knowledge graph of substation equipment. The method and system construct a spatial association knowledge graph of substation equipment based on the standard component relationships and the correlation of state vectors, while taking into account the inherent standard component relationships and the potential association relationships mined from historical data, thereby realizing the mining of multiple types of related variables of a single substation equipment.
[0054] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0055] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0056] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0057] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0058] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0059] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0060] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0061] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0062] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A method for constructing a spatial association knowledge graph of power equipment, characterized in that, include: Obtain the set of substation equipment to be constructed; Construct an initial directed graph of relationships between every two types of power equipment in the power equipment set based on preset standard component relationships; Determine the state vector for each type of substation based on its state data. Calculate the similarity between every two state vectors; The state similarity between each pair is determined based on the results of the similarity calculation. Modify the directed edges in the initial relational directed graph based on the state similarity to obtain the spatial association knowledge graph of the power equipment.
2. The construction method according to claim 1, characterized in that, Based on preset standard component relationships, an initial directed graph is constructed for each pair of power equipment in the power equipment set, including: The power equipment, the functional modules and components in the power equipment are respectively designated as first-level nodes, second-level nodes and third-level nodes; The inclusion relationship and the correlation relationship between different nodes are respectively regarded as the first directed edge and the second directed edge.
3. The construction method according to claim 1, characterized in that, Based on the state data of the power equipment, determine the state vector for each type of power equipment, including: For devices capable of outputting status parameters, historical output parameters are read as the status data; For devices that cannot output status parameters, the daily inspection records of the devices that cannot output status parameters are analyzed based on a preset corpus to obtain the corresponding status data.
4. The construction method according to claim 1, characterized in that, Based on the state data of the power equipment, determine the state vector for each type of power equipment, including: Each of the aforementioned state data is normalized to obtain standard state data; Determine the minimum granularity of change for the standard state data respectively; The standard state data is extracted according to the corresponding minimum change granularity to obtain a feature data sequence; The feature data sequences are encoded respectively to obtain the corresponding state vectors.
5. The construction method according to claim 4, characterized in that, Determine the minimum granularity of change for the standard state data, including: Calculate the difference between every two adjacent point values in the standard state data to obtain the corresponding difference sequence; In the difference sequence, determine the length of a sequence where the difference directions are consecutively the same, wherein the sequence length is greater than or equal to 10; The sequence length is used as the minimum change granularity.
6. The construction method according to claim 1, characterized in that, The similarity calculation is performed on every two state vectors, including: Calculate the Euclidean distance between every two state vectors to obtain the corresponding similarity.
7. The construction method according to claim 4, characterized in that, The state similarity between each pair is determined based on the similarity calculation results, including: The state vector is pre-divided into multiple state vector classes according to the minimum change granularity. The similarity between every two state vectors in each state vector class; The similarity is encoded as the state similarity.
8. The construction method according to claim 2, characterized in that, The initial relational directed graph also includes a third directed edge representing a potential association; Modify the directed edges in the initial relational directed graph based on the state similarity to obtain the spatial association knowledge graph of the power equipment, including: Modify the third directed edge in the initial relational directed graph based on the state similarity to obtain the spatial association knowledge graph of the power equipment.
9. A system for constructing a spatial association knowledge graph of power equipment, characterized in that, Includes a processor configured to perform the construction method as described in any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that are read by a machine to cause the machine to perform the construction method as described in any one of claims 1 to 8.