A virtual terminal circuit verification method and device for an intelligent substation configuration description file, a terminal device, and a storage medium

Abstract

This invention discloses a method, apparatus, terminal device, and storage medium for verifying virtual terminal circuits in configuration description files of intelligent substations, belonging to the field of substation technology. The method includes: using a structured model to perform semantic understanding and context association on the configuration description file, identifying the signal configuration information and communication relationships between devices in the configuration description file, mapping the configuration description file into a structured knowledge graph to be verified, extracting the virtual terminal circuits to be verified corresponding to each control function from the knowledge graph to be verified according to each control function of each intelligent device, performing logical configuration verification on each virtual terminal circuit to be verified one by one, and finally generating a logical verification alarm message based on the logical configuration verification failure of any virtual terminal circuit to be verified when any virtual terminal circuit to be verified fails the logical configuration verification. This effectively overcomes the current problem of low efficiency in virtual terminal circuit configuration verification.

Description

Technical Field

[0001] This invention relates to the field of substation technology, and in particular to a method, apparatus, terminal equipment, and storage medium for verifying virtual terminal circuits in a smart substation configuration description file. Background Technology

[0002] Currently, smart substations adopt the IEC 61850 standard, and their configuration information is stored in the Substation Configuration Description (SCD) file. The SCD file records the virtual terminal circuits (VPCs) of all equipment in the substation. These VPCs are the logical connections between devices in a smart substation that transmit signals. Simply put, in a smart substation, each control function of every intelligent device (IED, such as protection devices and monitoring and control devices) typically corresponds to one VPC or a group of interconnected VPCs. Therefore, the configuration verification of VPCs is crucial for the safe operation of the smart substation.

[0003] However, since SCD files are data structured description files that are strictly defined according to a specific XML Schema, their content is complex, the amount of data is large, and the readability is poor. Verifying the virtual terminal circuits of each control function requires strong professional capabilities. It is necessary to sort out the device relationships in the complex XML description, understand the functional logic, and check the signal message configuration one by one. Therefore, the current virtual terminal circuit configuration verification has the problem of low efficiency. Summary of the Invention

[0004] This invention provides a method, apparatus, terminal device, and storage medium for verifying virtual terminal circuit configuration description files in smart substations. The method can solve the problem of low efficiency in virtual terminal circuit configuration verification in the prior art.

[0005] An embodiment of the present invention provides a method for verifying virtual terminal circuits in a smart substation configuration description file, comprising: Obtain the configuration description file for the smart substation; The configuration description file is input into a preset structured model so that the structured model can perform semantic understanding and context association on the configuration description file, and identify the signal configuration information and communication relationships between the devices in the configuration description file; Using devices as entities and communication relationships as edges, edge attributes are defined based on the signal configuration information to generate a knowledge graph to be verified. Based on each control function of each intelligent device in the intelligent substation, extract the virtual terminal circuit corresponding to each control function from the knowledge graph to be verified. Based on the entities, edges, and edge attributes on each virtual terminal circuit to be verified, perform logical configuration verification on each virtual terminal circuit to be verified. If the logic configuration verification of any virtual terminal circuit to be verified fails, a logic verification alarm message is generated based on the virtual terminal circuit to be verified that failed the logic configuration verification.

[0006] Furthermore, the structured model includes: a semantic analysis sub-model and a context association sub-model; The step of inputting the configuration description file into a preset structured model, so that the structured model can perform semantic understanding and contextual association on the configuration description file, and identify the signal configuration information and communication relationships between the devices in the configuration description file, includes: The configuration description file is input into a preset semantic analysis sub-model so that the semantic analysis sub-model performs semantic understanding and word segmentation on the configuration description file, generating device word vectors for each device and signal text vectors for each signal configuration information in the configuration description file; The device word vector and the signal text vector are input into a preset context association sub-model so that the context association sub-model extracts and integrates the context information of the device word vector and the signal text vector; based on the context information, a hidden text vector is calculated to represent the relationship between the device word vector and the signal text vector; based on the hidden text vector, the device word vector and the signal text vector are matched to determine the signal configuration information corresponding to each device; based on the signal configuration information, the communication relationship between each device is determined.

[0007] Furthermore, the step of generating a knowledge graph to be verified, using devices as entities, communication relationships as edges, and defining edge attributes based on the signal configuration information, includes: Obtain device description files and power grid information models; wherein, the device description files record device identifiers for each device in different files, and the power grid information models record device attribute information for each device; Based on the signal configuration information and communication relationship between each device, construct a triplet for two devices that have a communication relationship and the signal configuration information between the two devices; Using devices as entities and communication relationships as edges, edge attributes are defined based on the signal configuration information, and an initial knowledge graph is constructed based on several triples. Traverse each entity in the initial knowledge graph and determine the target device corresponding to the power grid information model of the currently traversed entity based on the device identifier in the device description file; Based on the device attribute information of the target device, define the entity attributes of the currently traversed entity; After traversing all entities in the initial knowledge graph, a knowledge graph to be verified is generated.

[0008] Furthermore, based on each control function of each intelligent device in the intelligent substation, the virtual terminal circuit corresponding to each control function is extracted from the knowledge graph to be verified, including: Based on each control function of each intelligent device, determine the execution device corresponding to each control function; For each control function, the entity corresponding to the intelligent device and the execution device are used as the starting point and the entity corresponding to the execution device is used as the ending point. According to the edge direction in the knowledge graph to be verified, a path search is performed on the knowledge graph to be verified to generate several initial virtual terminal circuits for each control function. For each initial virtual terminal circuit, with the entity corresponding to the intelligent device as the endpoint and the entity corresponding to the execution device as the starting point, a reverse path search is performed according to the edge direction in the initial virtual terminal circuit to select virtual terminal circuits that can perform bidirectional communication from the initial virtual terminal circuits. If any control function does not have a corresponding virtual terminal circuit to be verified, a path verification alarm message is generated.

[0009] Furthermore, the signal configuration information includes: signal type configuration and data configuration; the device attribute information includes: physical port configuration; The step of performing logical configuration verification on each virtual terminal circuit to be verified based on the entities, edges, and edge attributes on each virtual terminal circuit to be verified includes: Traverse the virtual terminal circuits to be verified, take the currently traversed virtual terminal circuit as the target virtual terminal circuit, and determine whether the physical communication link of the target virtual terminal circuit is connected based on the physical port configuration of any two adjacent entities on the target virtual terminal circuit. If the physical communication link of the target virtual terminal circuit is determined to be disconnected, the virtual terminal circuit to be verified in the current traversal will not pass the logical configuration verification. When the physical communication link of the target virtual terminal circuit is confirmed to be connected, the signal type configuration and data configuration are verified according to the control function corresponding to the target virtual terminal circuit to determine whether the operating device can send the correct control signal to the execution device through the target virtual terminal circuit. If so, then the currently traversed virtual terminal circuit to be verified is confirmed to have passed the logic configuration verification. If not, then it is determined that the currently traversed virtual terminal circuit to be verified does not pass the logic configuration verification.

[0010] An embodiment of the present invention also provides a virtual terminal circuit verification device for intelligent substation configuration description files, comprising: The file acquisition module is used to acquire the configuration description file of the smart substation; The file structuring module is used to input the configuration description file into a preset structured model, so that the structured model can perform semantic understanding and context association on the configuration description file, and identify the signal configuration information and communication relationships between the devices in the configuration description file; The graph construction module is used to generate a knowledge graph to be verified by defining edge attributes based on the signal configuration information, with devices as entities and communication relationships as edges. The circuit extraction module is used to extract the virtual terminal circuit to be verified corresponding to each control function from the knowledge graph to be verified based on each control function of each intelligent device in the intelligent substation. The circuit verification module is used to perform logical configuration verification on each virtual terminal circuit to be verified based on the entities, edges, and edge attributes on each virtual terminal circuit to be verified. The verification alarm module is used to generate a logic verification alarm message based on the logic configuration verification failure of any virtual terminal circuit to be verified.

[0011] Furthermore, the structured model includes: a semantic analysis sub-model and a context association sub-model; The file structuring module inputs the configuration description file into a preset structured model, enabling the structured model to perform semantic understanding and contextual association on the configuration description file, and to identify the signal configuration information and communication relationships between devices in the configuration description file, including: The configuration description file is input into a preset semantic analysis sub-model so that the semantic analysis sub-model performs semantic understanding and word segmentation on the configuration description file, generating device word vectors for each device and signal text vectors for each signal configuration information in the configuration description file; The device word vector and the signal text vector are input into a preset context association sub-model so that the context association sub-model extracts and integrates the context information of the device word vector and the signal text vector; based on the context information, a hidden text vector is calculated to represent the relationship between the device word vector and the signal text vector; based on the hidden text vector, the device word vector and the signal text vector are matched to determine the signal configuration information corresponding to each device; based on the signal configuration information, the communication relationship between each device is determined.

[0012] Furthermore, the graph construction module, using devices as entities and communication relationships as edges, defines edge attributes based on the signal configuration information to generate a knowledge graph to be verified, including: Obtain device description files and power grid information models; wherein, the device description files record device identifiers for each device in different files, and the power grid information models record device attribute information for each device; Based on the signal configuration information and communication relationship between each device, construct a triplet for two devices that have a communication relationship and the signal configuration information between the two devices; Using devices as entities and communication relationships as edges, edge attributes are defined based on the signal configuration information, and an initial knowledge graph is constructed based on several triples. Traverse each entity in the initial knowledge graph and determine the target device corresponding to the power grid information model of the currently traversed entity based on the device identifier in the device description file; Based on the device attribute information of the target device, define the entity attributes of the currently traversed entity; After traversing all entities in the initial knowledge graph, a knowledge graph to be verified is generated.

[0013] This application also provides a terminal device, including: One or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement a virtual terminal circuit verification method for a smart substation configuration description file as described in the above embodiments of the invention.

[0014] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a virtual terminal circuit verification method for a smart substation configuration description file as described in the above embodiments.

[0015] The following benefits can be obtained by implementing the present invention: This invention provides a method, apparatus, terminal device, and storage medium for verifying virtual terminal circuits in a configuration description file of an intelligent substation. The method employs a preset structured model to perform semantic understanding and contextual association on the configuration description file, identifying signal configuration information and communication relationships between devices within the file. Then, using devices as entities and communication relationships as edges, edge attributes are defined based on the signal configuration information, mapping the complex configuration description file into a structured knowledge graph to be verified. Next, based on each control function of each intelligent device, the virtual terminal circuits corresponding to each control function are extracted from the knowledge graph. Logical configuration verification is then performed on each virtual terminal circuit based on its entities, edges, and edge attributes defined by the signal configuration information. Finally, if any virtual terminal circuit fails logical configuration verification, a logical verification alarm is generated, effectively overcoming the current problem of low efficiency in virtual terminal circuit configuration verification. Attached Figure Description

[0016] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating a virtual terminal circuit verification method for a smart substation configuration description file according to a certain embodiment of this application; Figure 2 This is a schematic diagram of the structure of a virtual terminal circuit verification device for a smart substation configuration description file provided in a certain embodiment of this application; Figure 3 This is a schematic diagram of the structure of a terminal device provided in a certain embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0020] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0021] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0022] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0023] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0024] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0025] See Figure 1 To address the problems in the prior art, an embodiment of the present invention provides a method for verifying virtual terminal circuits in a smart substation configuration description file, comprising: S1. Obtain the configuration description file of the smart substation; In a preferred embodiment of the present invention, the configuration description file (SCD) is a configuration blueprint for the entire substation. It uses XML to describe in detail the logical relationships of all intelligent devices (IEDs, such as protection devices and monitoring and control devices) within the substation. Before the substation is put into operation, every virtual circuit in the SCD file must be rigorously verified; this is the lifeline for ensuring the safe and stable operation of the power grid.

[0026] S2. Input the configuration description file into a preset structured model so that the structured model can perform semantic understanding and context association on the configuration description file, and identify the signal configuration information and communication relationships between the devices in the configuration description file; Preferably, the structured model includes: a semantic analysis sub-model and a context association sub-model; The step of inputting the configuration description file into a preset structured model, so that the structured model can perform semantic understanding and contextual association on the configuration description file, and identify the signal configuration information and communication relationships between the devices in the configuration description file, includes: The configuration description file is input into a preset semantic analysis sub-model, which performs semantic understanding and word segmentation on the configuration description file to generate device word vectors for each device and signal text vectors for each signal configuration information in the configuration description file. The device word vectors and signal text vectors are then input into a preset context association sub-model, which extracts and integrates the context information of the device word vectors and signal text vectors. Based on the context information, a hidden text vector is calculated to represent the relationship between the device word vectors and signal text vectors. Based on the hidden text vector, the device word vectors and signal text vectors are matched to determine the signal configuration information corresponding to each device. Based on the signal configuration information, the communication relationship between the devices is determined.

[0027] In a preferred embodiment of the present invention, the semantic analysis sub-model is the Power-Roberts model, and the context association sub-model is the BiGRU-CRF model. The Power-Roberts model is based on the Transformer architecture and a dynamic masking strategy. This model can transform SCD text into a high-quality semantic representation containing word vectors, sentence vectors, and position vectors. Specifically, the training process employs a dynamic masking strategy, generating a new masking pattern for each input sequence and dynamically adjusting the masking method of the training data. This mechanism allows the model to learn the features of the SCD text corpus more flexibly.

[0028] In the Power-Roberts pre-training, a Transformer architecture is used to encode the input SCD training text and train it using a self-attention mechanism (SAM). The input to the multi-head attention layer is a matrix, and the input to the SA layer (self-attention mechanism layer) of the Roberta model can be represented as follows: , , ,in These are the weight parameters. SA layer The output is: ; ; in, It is the dimension of the vector. It is a normalization function.

[0029] The Transformer employs a multi-head self-attention mechanism (SAM), and its output moments... The array is calculated as follows: ; in, Indicates the number of heads; , and It is the weight matrix of the m-th head. It is an additional weight matrix; It is a concatenation function.

[0030] The Power-Roberts model transforms device vocabulary from the input SCD training text into word vectors and signal configuration information into text vectors. Both word and text vectors contain the positional information of the corresponding words and information within the file. The model models the input text using a self-attention mechanism (SAM) and fully connected layers, filtering effective information from massive amounts of text to obtain high-quality word vectors.

[0031] The BiGRU-CRF model is used to extract entity relationships. The BiGRU layer generates lexical hidden vectors by integrating contextual information, while the CRF layer considers the dependencies between labels and calculates the optimal label sequence to obtain the final lexical relationships.

[0032] When training the BiGRU-CRF model, the training word vectors generated by Power Roberts are first processed using BiGRU to obtain the hidden vectors of the training word vectors. The values ​​of each dimension of the training word vectors correspond to the label scores of different training word vectors. Subsequently, in the CRF layer, a comprehensive score is calculated based on the individual label scores and the transition scores between labels. Finally, entity relationship recognition and extraction are achieved based on the comprehensive score.

[0033] The Bi-GRU layer is a key feature of GRU networks. It efficiently stores and updates textual context information while maintaining dependencies between data. While unidirectional GRU models can infer subsequent content based on preceding information, relying solely on the preceding context is often insufficient. Bi-GRU models understand contextual information, which enhances their analytical capabilities. By constructing constraint rules based on BiGRU feature learning and combining SCD file data format with a CRF model, the globally optimal label sequence is obtained by analyzing the dependencies between adjacent entity labels. This improves the output mechanism of the BiGRU layer, effectively reducing the probability of the model outputting illegal sequences and avoiding unreasonable label predictions, thus accurately extracting word vector relationships.

[0034] S3. Using devices as entities and communication relationships as edges, define edge attributes based on the signal configuration information to generate a knowledge graph to be verified; Preferably, the step of generating a knowledge graph to be verified, using devices as entities, communication relationships as edges, and defining edge attributes based on the signal configuration information, includes: The process involves: acquiring device description files and a power grid information model; wherein the device description files record device identifiers for each device in different files, and the power grid information model records device attribute information for each device; constructing triples for two devices with communication relationships and their corresponding signal configuration information based on the signal configuration information and the signal configuration information between them; defining edge attributes based on the signal configuration information, using devices as entities and communication relationships as edges, and constructing an initial knowledge graph based on several triples; traversing each entity in the initial knowledge graph, determining the target device corresponding to the currently traversed entity in the power grid information model based on the device identifiers in the device description files; defining entity attributes for the currently traversed entity based on the device attribute information of the target device; and generating a knowledge graph to be verified after traversing all entities in the initial knowledge graph.

[0035] In a preferred embodiment of the present invention, the secondary circuit digital description (SDD) file (device description file) corresponding to the SCD file is associated with the power grid information model (GIM). The SDD file contains the device identifier and device name in different files, while the GIM model contains the physical attributes of the device.

[0036] First, the signal configuration information and communication relationships extracted from BiGRU-CRF in step S2 are structured into "entity-relationship" triples (e.g., [protection device A, send, trip signal] -> [switch device B, receive, trip signal], [protection device B, send, response signal] -> [switch device A, receive, response signal], etc.). A knowledge graph is constructed with devices as entities and communication relationships as edges. Then, the device attribute information of the power grid information model (GIM) is added as entity attributes to the corresponding entities through the SDD file to optimize the knowledge graph.

[0037] Furthermore, to visualize the knowledge graph and improve the readability of the SCD file, geometric element intersection calculation is used to automatically lay out the knowledge graph. Specifically, entities are simulated as particles with the same charge (generating repulsion), and connections are simulated as springs (generating attraction). By continuously calculating the repulsion between particles (i.e., detecting whether "geometric elements" have "intersections" or are too close), overlapping nodes are pushed apart, while attraction is used to bring connected nodes closer. After multiple iterations, the system reaches mechanical equilibrium, ultimately forming a stable layout with uniformly distributed nodes.

[0038] Furthermore, the A* algorithm is employed for intelligent connection finding. The algorithm meshes the canvas and marks nodes as obstacles. Then, it calculates the shortest right-angled path from the start to the end point for each connection line, consisting of horizontal and vertical lines. After the node positions are determined, a smooth, regular, optimal path is found for the connection lines, reducing the connection intersection rate.

[0039] S4. Based on each control function of each intelligent device in the intelligent substation, extract the virtual terminal circuit to be verified corresponding to each control function from the knowledge graph to be verified. Preferably, the step of extracting the virtual terminal circuit to be verified corresponding to each control function from the knowledge graph to be verified based on each control function of each intelligent device in the intelligent substation includes: Based on each control function of each intelligent device, the corresponding execution device for implementing each control function is determined. For each intelligent device and execution device corresponding to a control function, starting from the entity corresponding to the intelligent device and ending at the entity corresponding to the execution device, a path search is performed on the knowledge graph to be verified according to the edge directions in the knowledge graph to be verified, generating several initial virtual terminal circuits for each control function. For each initial virtual terminal circuit, starting from the entity corresponding to the intelligent device and ending at the entity corresponding to the execution device, a reverse path search is performed according to the edge directions in the initial virtual terminal circuit, and virtual terminal circuits capable of bidirectional communication are selected from the initial virtual terminal circuits to be verified. If any control function does not have a corresponding virtual terminal circuit to be verified, a path verification alarm message is generated.

[0040] In a preferred embodiment of the present invention, each control function of the intelligent device corresponds to an execution device that implements the function. For example, in the line protection tripping function, when a line fault occurs, the protection device (intelligent device) sends a tripping signal to the circuit breaker (execution device) on the faulty line to control the circuit breaker to trip and disconnect the faulty line.

[0041] For each control function, the entity corresponding to the intelligent device and the execution device is taken as the starting point and the entity corresponding to the execution device is taken as the ending point. The forward probing and backward tracing search (FBS) algorithm is used to perform bidirectional path search on the knowledge graph to be verified, and virtual terminal circuits that can perform bidirectional communication are found to ensure that the execution device can receive the control signal and the protection device can receive the response signal.

[0042] When there is no virtual terminal circuit capable of bidirectional communication, it is determined that the corresponding control function of the protection device does not have a virtual terminal circuit, and path alarm information is generated for the protection device and the execution device.

[0043] S5. Based on the entities, edges, and edge attributes on each virtual terminal circuit to be verified, perform logical configuration verification on each virtual terminal circuit to be verified. Preferably, the signal configuration information includes: signal type configuration and data configuration; the device attribute information includes: physical port configuration; The step of performing logical configuration verification on each virtual terminal circuit to be verified based on the entities, edges, and edge attributes on each virtual terminal circuit to be verified includes: The process iterates through the virtual terminal circuits to be verified, taking the currently traversed virtual terminal circuit as the target virtual terminal circuit. Based on the physical port configurations of any two adjacent entities on the target virtual terminal circuit, it determines whether the physical communication link of the target virtual terminal circuit is connected. If it is determined that the physical communication link of the target virtual terminal circuit is not connected, the currently traversed virtual terminal circuit fails the logic configuration verification. If it is determined that the physical communication link of the target virtual terminal circuit is connected, based on the control function corresponding to the target virtual terminal circuit, signal configuration verification is performed on the signal type configuration and data configuration to determine whether the operating device can send the correct control signal to the execution device through the target virtual terminal circuit. If it can, the currently traversed virtual terminal circuit passes the logic configuration verification; if it cannot, the currently traversed virtual terminal circuit fails the logic configuration verification.

[0044] In a preferred embodiment of the present invention, to prevent device A from sending a signal to terminal B in the SCD but the connection port between A and B is incorrect, the physical port configuration of the two adjacent entities that are directly connected is first verified. After the physical port configuration verification is passed, the signal configuration is then verified, including signal type matching, determining whether the signal type sent by the signal sending end is the same as the signal type received by the receiving end (trip → trip), switch port configuration, and data attributes (whether the instance number and APPID are correct), etc.

[0045] S6. If the logic configuration verification of any virtual terminal circuit to be verified fails, generate a logic verification alarm message based on the virtual terminal circuit to be verified that failed the logic configuration verification.

[0046] In a preferred embodiment of the present invention, when the logic configuration verification of any virtual terminal circuit to be verified fails, structured logic verification alarm information is generated for the control function, intelligent device, protection device, edge and node corresponding to the virtual terminal circuit to be verified that failed the logic configuration verification, so as to facilitate maintenance personnel to perform maintenance.

[0047] See Figure 2 This invention provides a virtual terminal circuit verification device for a smart substation configuration description file, comprising: The file acquisition module is used to acquire the configuration description file of the smart substation; The file structuring module is used to input the configuration description file into a preset structured model, so that the structured model can perform semantic understanding and context association on the configuration description file, and identify the signal configuration information and communication relationships between the devices in the configuration description file; The graph construction module is used to generate a knowledge graph to be verified by defining edge attributes based on the signal configuration information, with devices as entities and communication relationships as edges. The circuit extraction module is used to extract the virtual terminal circuit to be verified corresponding to each control function from the knowledge graph to be verified based on each control function of each intelligent device in the intelligent substation. The circuit verification module is used to perform logical configuration verification on each virtual terminal circuit to be verified based on the entities, edges, and edge attributes on each virtual terminal circuit to be verified. The verification alarm module is used to generate a logic verification alarm message based on the logic configuration verification failure of any virtual terminal circuit to be verified.

[0048] Furthermore, the structured model includes: a semantic analysis sub-model and a context association sub-model; The file structuring module inputs the configuration description file into a preset structured model, enabling the structured model to perform semantic understanding and contextual association on the configuration description file, and to identify the signal configuration information and communication relationships between devices in the configuration description file, including: The configuration description file is input into a preset semantic analysis sub-model so that the semantic analysis sub-model performs semantic understanding and word segmentation on the configuration description file, generating device word vectors for each device and signal text vectors for each signal configuration information in the configuration description file; The device word vector and the signal text vector are input into a preset context association sub-model so that the context association sub-model extracts and integrates the context information of the device word vector and the signal text vector; based on the context information, a hidden text vector is calculated to represent the relationship between the device word vector and the signal text vector; based on the hidden text vector, the device word vector and the signal text vector are matched to determine the signal configuration information corresponding to each device; based on the signal configuration information, the communication relationship between each device is determined.

[0049] Furthermore, the graph construction module, using devices as entities and communication relationships as edges, defines edge attributes based on the signal configuration information to generate a knowledge graph to be verified, including: Obtain device description files and power grid information models; wherein, the device description files record device identifiers for each device in different files, and the power grid information models record device attribute information for each device; Based on the signal configuration information and communication relationship between each device, construct a triplet for two devices that have a communication relationship and the signal configuration information between the two devices; Using devices as entities and communication relationships as edges, edge attributes are defined based on the signal configuration information, and an initial knowledge graph is constructed based on several triples. Traverse each entity in the initial knowledge graph and determine the target device corresponding to the power grid information model of the currently traversed entity based on the device identifier in the device description file; Based on the device attribute information of the target device, define the entity attributes of the currently traversed entity; After traversing all entities in the initial knowledge graph, a knowledge graph to be verified is generated.

[0050] It is understood that the above-described device embodiments correspond to the method embodiments of the present invention, and can implement the virtual terminal circuit verification method for intelligent substation configuration description files provided by any of the above-described method embodiments of the present invention.

[0051] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0052] See Figure 3 One embodiment of this application also provides a terminal device, including: One or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the virtual terminal circuit verification method for a smart substation configuration description file as described above.

[0053] The processor controls the overall operation of the terminal device to complete all or part of the steps of the virtual terminal circuit verification method for a smart substation configuration description file described above. The memory stores various types of data to support the operation of the terminal device. This data may include, for example, instructions for any application or method used to operate on the terminal device, as well as application-related data. The memory can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0054] In an exemplary embodiment, the terminal device may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute a virtual terminal circuit verification method for a smart substation configuration description file as described in any of the foregoing embodiments, and achieve the same technical effects as the methods described above.

[0055] In another exemplary embodiment, a computer-readable storage medium including a computer program is also provided. When executed by a processor, the computer program implements the steps of a virtual terminal circuit verification method for a smart substation configuration description file as described in any of the foregoing embodiments. For example, the computer-readable storage medium may be the aforementioned memory including the computer program, which can be executed by a processor of a terminal device to complete the virtual terminal circuit verification method for a smart substation configuration description file as described in any of the foregoing embodiments, and achieve the same technical effects as the methods described above.

[0056] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A virtual terminal circuit verification method for a smart substation configuration description file, characterized in that, include: Obtain the configuration description file for the smart substation; The configuration description file is input into a preset structured model so that the structured model can perform semantic understanding and context association on the configuration description file, and identify the signal configuration information and communication relationships between the devices in the configuration description file; Using devices as entities and communication relationships as edges, edge attributes are defined based on the signal configuration information to generate a knowledge graph to be verified. Based on each control function of each intelligent device in the intelligent substation, extract the virtual terminal circuit corresponding to each control function from the knowledge graph to be verified. Based on the entities, edges, and edge attributes on each virtual terminal circuit to be verified, perform logical configuration verification on each virtual terminal circuit to be verified. If the logic configuration verification of any virtual terminal circuit to be verified fails, a logic verification alarm message is generated based on the virtual terminal circuit to be verified that failed the logic configuration verification.

2. The virtual terminal circuit verification method for a smart substation configuration description file as described in claim 1, characterized in that, The structured model includes: a semantic analysis sub-model and a context association sub-model; The step of inputting the configuration description file into a preset structured model, so that the structured model can perform semantic understanding and contextual association on the configuration description file, and identify the signal configuration information and communication relationships between the devices in the configuration description file, includes: The configuration description file is input into a preset semantic analysis sub-model so that the semantic analysis sub-model performs semantic understanding and word segmentation on the configuration description file, generating device word vectors for each device and signal text vectors for each signal configuration information in the configuration description file; The device word vector and the signal text vector are input into a preset context association sub-model so that the context association sub-model extracts and integrates the context information of the device word vector and the signal text vector; based on the context information, a hidden text vector is calculated to represent the relationship between the device word vector and the signal text vector; based on the hidden text vector, the device word vector and the signal text vector are matched to determine the signal configuration information corresponding to each device; based on the signal configuration information, the communication relationship between each device is determined. 3.The virtual terminal circuit verification method for an intelligent substation configuration description file according to claim 2, wherein, The process of generating a knowledge graph to be verified, using devices as entities, communication relationships as edges, and defining edge attributes based on the signal configuration information, includes: Obtain device description files and power grid information models; wherein, the device description files record device identifiers for each device in different files, and the power grid information models record device attribute information for each device; Based on the signal configuration information and communication relationship between each device, construct a triplet for two devices that have a communication relationship and the signal configuration information between the two devices; Using devices as entities and communication relationships as edges, edge attributes are defined based on the signal configuration information, and an initial knowledge graph is constructed based on several triples. Traverse each entity in the initial knowledge graph and determine the target device corresponding to the power grid information model of the currently traversed entity based on the device identifier in the device description file; Based on the device attribute information of the target device, define the entity attributes of the currently traversed entity; After traversing all entities in the initial knowledge graph, a knowledge graph to be verified is generated.

4. The virtual terminal circuit verification method for an intelligent substation configuration description file according to claim 3, characterized in that, The step of extracting the virtual terminal circuit to be verified corresponding to each control function from the knowledge graph to be verified based on each control function of each intelligent device in the intelligent substation includes: Based on each control function of each intelligent device, determine the execution device corresponding to each control function; For each control function, the entity corresponding to the intelligent device and the execution device are used as the starting point and the entity corresponding to the execution device is used as the ending point. According to the edge direction in the knowledge graph to be verified, a path search is performed on the knowledge graph to be verified to generate several initial virtual terminal circuits for each control function. For each initial virtual terminal circuit, with the entity corresponding to the intelligent device as the endpoint and the entity corresponding to the execution device as the starting point, a reverse path search is performed according to the edge direction in the initial virtual terminal circuit to select virtual terminal circuits that can perform bidirectional communication from the initial virtual terminal circuits. If any control function does not have a corresponding virtual terminal circuit to be verified, a path verification alarm message is generated.

5. The virtual terminal circuit verification method for an intelligent substation configuration description file according to claim 4, characterized in that, The signal configuration information includes: signal type configuration and data configuration; the device attribute information includes: physical port configuration. The step of performing logical configuration verification on each virtual terminal circuit to be verified based on the entities, edges, and edge attributes on each virtual terminal circuit to be verified includes: Traverse the virtual terminal circuits to be verified, take the currently traversed virtual terminal circuit as the target virtual terminal circuit, and determine whether the physical communication link of the target virtual terminal circuit is connected based on the physical port configuration of any two adjacent entities on the target virtual terminal circuit. If the physical communication link of the target virtual terminal circuit is determined to be disconnected, the virtual terminal circuit to be verified in the current traversal will not pass the logical configuration verification. When the physical communication link of the target virtual terminal circuit is confirmed to be connected, the signal type configuration and data configuration are verified according to the control function corresponding to the target virtual terminal circuit to determine whether the operating device can send the correct control signal to the execution device through the target virtual terminal circuit. If so, then the currently traversed virtual terminal circuit to be verified is confirmed to have passed the logic configuration verification. If not, then it is determined that the currently traversed virtual terminal circuit to be verified does not pass the logic configuration verification.

6. An apparatus for verifying virtual terminal circuit of a smart substation configuration description file, characterized in that, include: The file acquisition module is used to acquire the configuration description file of the smart substation; The file structuring module is used to input the configuration description file into a preset structured model, so that the structured model can perform semantic understanding and context association on the configuration description file, and identify the signal configuration information and communication relationships between the devices in the configuration description file; The graph construction module is used to generate a knowledge graph to be verified by defining edge attributes based on the signal configuration information, with devices as entities and communication relationships as edges. The circuit extraction module is used to extract the virtual terminal circuit to be verified corresponding to each control function from the knowledge graph to be verified based on each control function of each intelligent device in the intelligent substation. The circuit verification module is used to perform logical configuration verification on each virtual terminal circuit to be verified based on the entities, edges, and edge attributes on each virtual terminal circuit to be verified. The verification alarm module is used to generate logical verification alarm information based on the logical configuration verification failure of any virtual terminal circuit to be verified.

7. The virtual terminal circuit verification apparatus for an intelligent substation configuration description file according to claim 6, wherein, The structured model includes: a semantic analysis sub-model and a context association sub-model; The file structuring module inputs the configuration description file into a preset structured model, enabling the structured model to perform semantic understanding and contextual association on the configuration description file, and to identify the signal configuration information and communication relationships between devices in the configuration description file, including: The configuration description file is input into a preset semantic analysis sub-model so that the semantic analysis sub-model performs semantic understanding and word segmentation on the configuration description file, generating device word vectors for each device and signal text vectors for each signal configuration information in the configuration description file; The device word vector and the signal text vector are input into a preset context association sub-model so that the context association sub-model extracts and integrates the context information of the device word vector and the signal text vector; based on the context information, a hidden text vector is calculated to represent the relationship between the device word vector and the signal text vector; based on the hidden text vector, the device word vector and the signal text vector are matched to determine the signal configuration information corresponding to each device; based on the signal configuration information, the communication relationship between each device is determined.

8. The virtual terminal circuit verification apparatus for an intelligent substation configuration description file according to claim 7, wherein, The graph construction module, using devices as entities and communication relationships as edges, defines edge attributes based on the signal configuration information to generate a knowledge graph to be verified, including: Obtain device description files and power grid information models; wherein, the device description files record device identifiers for each device in different files, and the power grid information models record device attribute information for each device; Based on the signal configuration information and communication relationship between each device, construct a triplet for two devices that have a communication relationship and the signal configuration information between the two devices; Using devices as entities and communication relationships as edges, edge attributes are defined based on the signal configuration information, and an initial knowledge graph is constructed based on several triples. Traverse each entity in the initial knowledge graph and determine the target device corresponding to the power grid information model of the currently traversed entity based on the device identifier in the device description file; Based on the device attribute information of the target device, define the entity attributes of the currently traversed entity; After traversing all entities in the initial knowledge graph, a knowledge graph to be verified is generated.

9. A terminal device, comprising: include: One or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the virtual terminal circuit verification method for a smart substation configuration description file as described in any one of claims 1-5.

10. A storage medium having stored thereon a computer program, characterized in that When the computer program is executed by the processor, it implements a virtual terminal circuit verification method for a smart substation configuration description file as described in any one of claims 1-5.

Images