Intelligent substation virtual loop automatic verification method, system and device and medium

Abstract

The invention discloses an intelligent substation virtual circuit automatic verification method, system and device and a medium, and belongs to the technical field of intelligent substation automation, and the method comprises the steps: defining a unified ontology model to obtain a standard function identifier, generating a virtual circuit verification rule, and constructing a standardized knowledge base; obtaining and analyzing an SCD configuration file of a target substation to obtain an instance virtual loop knowledge graph; performing consistency reasoning to generate a diagnosis report, wherein the diagnosis report comprises a diagnosis result of the item to be confirmed; and the user confirms to perform self-learning updating on the standardized knowledge base. According to the method, a standardized knowledge base and an instance virtual loop knowledge graph are constructed, and a consistency reasoning and self-learning mechanism is combined, so that the conversion from artificial experience verification to full-automatic intelligent verification is realized, the problem that a traditional tool cannot perform functional semantic diagnosis is solved, hidden expert knowledge is converted into a computable and evolutionary structured rule, and the functional semantic diagnosis efficiency is improved. The method improves the verification efficiency, depth and accuracy, and has the capability of continuously adapting to technology development.

Description

Technical Field

[0001] This invention relates to the field of intelligent substation automation technology, and in particular to an automatic verification method, system, equipment and medium for virtual circuits in intelligent substations. Background Technology

[0002] With the widespread adoption of smart substation technology, secondary circuits have been transformed from traditional hard cable connections to virtualized communication connections based on the IEC61850 standard, i.e., virtual circuits. The correctness of virtual circuit configuration is directly related to the safe and stable operation of the substation and even the entire power grid. However, the full-station configuration file, or SCD configuration file for short, which is the final carrier of virtual circuit design, has a complex structure and a huge amount of information. Whether the tens of thousands of virtual terminal connections contained therein are correct in functional logic has become the core challenge and bottleneck in the project implementation and acceptance phase.

[0003] Currently, there are two main methods for verifying SCD configuration files. One method relies on manual review based on the experience of designers and debuggers, which is inefficient and highly dependent on individual skill levels, making it difficult to avoid oversights. The other method uses some simple auxiliary tools for automated checks. However, most existing tools can only perform shallow checks on syntax, communication parameters, or simple connection relationships. They cannot diagnose whether the connections are correct at the semantic level of functional logic. For example, they cannot determine whether a trip signal has been correctly sent to the trip output terminal. In addition, the verification rules of these tools are usually fixed and cannot adapt to new technologies, new equipment, or diverse engineering design schemes. They lack self-learning and evolution capabilities, resulting in low intelligence, insufficient verification depth, and poor flexibility. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides an automatic verification method, system, device, and medium for virtual circuits in intelligent substations to address the problem that existing SCD configuration file verification mainly relies on inefficient and error-prone manual review and can only perform superficial checks, failing to diagnose the correctness of functional logic, and lacking adaptive evolution, resulting in insufficient verification depth and flexibility.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides an automatic verification method for virtual circuits in intelligent substations, comprising: Define a unified ontology model, obtain standard function identifiers through the unified ontology model, generate virtual loop verification rules by combining the unified ontology model and the standard function identifiers, and construct a standardized knowledge base through the unified ontology model, the standard function identifiers and the virtual loop verification rules; Obtain the SCD configuration file of the target substation, and parse the SCD configuration file according to the unified ontology model to obtain the instance virtual circuit knowledge graph; The instance virtual circuit knowledge graph is used to perform consistency reasoning with the virtual circuit verification rules to generate a diagnostic report, which includes the diagnostic results of the items to be confirmed. The user confirms the diagnostic result of the item to be confirmed and receives user feedback. The standardized knowledge base is then updated through self-learning based on the user feedback. The steps to generate a diagnostic report include: The virtual loop verification rules are pre-compiled into a structured query; The structured query is executed in the virtual loop knowledge graph of the instance. Consistency reasoning is performed by locating the virtual terminal node of the receiving end and checking whether the virtual terminal node of the sending end upstream of the virtual terminal node of the receiving end conforms to the function identifier of the virtual loop verification rule, and the reasoning result is obtained. Based on the constraint strength and reasoning result of the virtual loop verification rule, when the reasoning result indicates that the virtual loop verification rule is not met, if the constraint strength is a first-level output, an error diagnosis result is generated; if the constraint strength is a second-level output, a warning diagnosis result is generated. The virtual terminal nodes with empty functional identifiers in the instance virtual loop knowledge graph are identified, and a diagnosis result for unconfirmed items with unknown functional identifiers is generated. A diagnostic report is generated by combining the error diagnosis results, warning diagnosis results, and pending confirmation item diagnosis results.

[0007] As a preferred embodiment of the automatic verification method for virtual circuits in intelligent substations according to the present invention, the step of defining a unified ontology model and obtaining standard function identifiers through the unified ontology model includes: Define the bay ontology model and the unified ontology model used to describe electrical bays; Standardized function definitions are extracted based on industry standards and specifications, and then mapped to the unified ontology model to obtain standard function identifiers.

[0008] The beneficial effects of this preferred technical solution are as follows: by defining a unified ontology model and obtaining standard functional identifiers based on industry standards, the functional description and specific device model are decoupled, laying a solid foundation for subsequent automated semantic verification and improving the accuracy and engineering adaptability of the verification.

[0009] As a preferred embodiment of the automatic virtual loop verification method for intelligent substations described in this invention, the step of generating virtual loop verification rules includes: Based on the primary equipment type and the standard function identifier defined in the interval ontology model, virtual loop verification rules are generated, wherein the virtual loop verification rules include rules constraints within the electrical interval and rules constraints between electrical intervals; The rule constraint within the electrical interval is as follows: when the primary equipment type is type A and the receiving terminal function identifier is identifier B, then the transmitting terminal function identifier for primary output or secondary output is identifier C. The electrical bay rule constraint is as follows: when the primary equipment type of this electrical bay is type A and the function identifier of the receiving terminal of this electrical bay is identifier B, then the primary equipment type of the external electrical bay is identifier D for first-level output or second-level output and the function identifier of the transmitting terminal of the external electrical bay is identifier E for first-level output or second-level output.

[0010] The beneficial effects of this preferred technical solution are as follows: by transforming it into a virtual loop verification rule that includes rules and constraints within and between electrical intervals, the explicit expression and computer-executable nature of the virtual loop functional logic are realized, providing a basis for deep semantic verification. The distinction between the constraint strength of the first-level output and the second-level output in the virtual loop verification rule ensures the accuracy and engineering practicality of the verification, enabling the system to identify critical errors and general warnings, and improving the accuracy and practicality of diagnosis.

[0011] As a preferred embodiment of the automatic verification method for virtual circuits in intelligent substations according to the present invention, the step of obtaining the knowledge graph of example virtual circuits includes: The SCD configuration file is parsed using the unified ontology model to extract intelligent electronic devices and virtual terminal connections between them. The intelligent electronic device is assigned to the corresponding electrical interval to obtain the electrical interval composition and the electrical interval affiliation of each virtual terminal; Based on the electrical interval composition and the electrical interval affiliation of each virtual terminal, an electrical interval node corresponding to each electrical interval, a virtual terminal node corresponding to each virtual terminal, a subordinate edge from the virtual terminal node to its electrical interval node, and a connection edge from the transmitting virtual terminal node to the receiving virtual terminal node are created to obtain an instance virtual circuit knowledge graph.

[0012] The beneficial effects of this preferred technical solution are as follows: it parses the SCD configuration file and constructs an instance virtual loop knowledge graph, realizing a graphical and computer-understandable expression of virtual loop connection relationships. The instance virtual loop knowledge graph clearly defines the subordinate and virtual loop connection relationships, providing a data foundation for subsequent consistent reasoning.

[0013] As a preferred embodiment of the automatic verification method for virtual loops in intelligent substations according to the present invention, the consistency inference further includes: After completing the consistency reasoning of all virtual loop verification rules, scan all the connection edges in the instance virtual loop knowledge graph, and identify the connection edges that do not meet the virtual loop verification rules as redundant connection pending confirmation item diagnostic results. The diagnostic results of the redundant connections to be confirmed and the diagnostic results of the unconfirmed items with unknown function identifiers are combined to form the diagnostic results of the unconfirmed items in the diagnostic report.

[0014] The beneficial effects of this preferred technical solution are as follows: by identifying redundant connections through global scanning, and together with the unknown functional identifiers, it constitutes a complete diagnostic result for the items to be confirmed, thus achieving a comprehensive capture of all non-routine cases in the SCD configuration file. This not only ensures the integrity of the verification and avoids missing potential correct connection patterns, but also provides learning targets and inputs for the system's self-learning mechanism.

[0015] As a preferred embodiment of the automatic verification method for virtual circuits in intelligent substations according to the present invention, the step of self-learning and updating the standardized knowledge base through user feedback includes at least one of the following methods: When the user feedback of the diagnosis result of the pending item is a redundant connection, the receiving end electrical spacing type, receiving end function identifier, transmitting end electrical spacing type and transmitting end function identifier corresponding to the diagnosis result of the pending item of the redundant connection are extracted, a draft virtual loop verification rule is generated, and the draft virtual loop verification rule is added to the virtual loop verification rule of the standardized knowledge base. When the user feedback on the diagnostic result of the pending item is that the function identifier is unknown, the function identifier confirmed by the user will be updated to the standard function identifier in the standardized knowledge base.

[0016] The beneficial effects of this preferred technical solution are as follows: by transforming user feedback on the diagnostic results of the two types of items to be confirmed into the increment of the standardized knowledge base, the self-learning and updating of the verification system is realized, overcoming the rigidity of traditional static verification tools, and improving the system's adaptability to new designs and technologies and its long-term practical value.

[0017] Secondly, the present invention provides an automatic verification system for virtual circuits in intelligent substations, comprising: The knowledge base management module is used to build standardized knowledge bases; A graph construction engine is used to parse the SCD configuration file and construct the virtual circuit knowledge graph of the instance. An inference diagnostic engine is used to perform the consistent inference and generate the diagnostic report; The human-computer interaction module is used to output the diagnostic report and receive the user's confirmation operation on the diagnostic results of the items to be confirmed, thereby generating user feedback; The self-learning module is used to update the standardized knowledge base based on the user feedback.

[0018] Thirdly, the present invention provides an electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of an automatic verification method for virtual circuits in a smart substation.

[0019] Fourthly, the present invention provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the aforementioned automatic verification method for virtual circuits in a smart substation.

[0020] Compared with existing technologies, the beneficial effects of this invention are as follows: by constructing a standardized knowledge base and an instance virtual loop knowledge graph, and combining consistent reasoning and self-learning mechanisms, the transformation from manual experience verification to fully automatic intelligent verification is realized. This not only solves the problem that traditional tools cannot perform functional semantic diagnosis, but also transforms implicit expert knowledge into computable and evolvable structured rules, improving verification efficiency, depth and accuracy, while enabling the system to continuously adapt to technological development. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of the overall process of an automatic verification method for virtual circuits in intelligent substations, provided as an embodiment of the present invention.

[0023] Figure 2 This is a flowchart illustrating the construction example of an automatic verification method for virtual circuits in intelligent substations, provided as an embodiment of the present invention, of a virtual circuit knowledge graph.

[0024] Figure 3 This is a schematic diagram illustrating the process of generating a diagnostic report for an automatic verification method for virtual circuits in intelligent substations, provided as an embodiment of the present invention.

[0025] Figure 4 The flowchart illustrates a self-learning update method based on user feedback for an automatic verification method of virtual circuits in an intelligent substation, as provided in one embodiment of the present invention. Detailed Implementation

[0026] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0027] Example 1, referring to Figures 1-4 As an embodiment of the present invention, an automatic verification method for virtual circuits in intelligent substations is provided, comprising: S100. Define a unified ontology model, obtain standard function identifiers through the unified ontology model, generate virtual loop verification rules by combining the unified ontology model and the standard function identifiers, and construct a standardized knowledge base through the unified ontology model, the standard function identifiers and the virtual loop verification rules.

[0028] S200. Obtain the SCD configuration file of the target substation. Based on the unified ontology model, parse the SCD configuration file to obtain the instance virtual circuit knowledge graph.

[0029] S300. Perform consistency reasoning between the instance virtual circuit knowledge graph and the virtual circuit verification rules to generate a diagnostic report, which includes the diagnostic results of the items to be confirmed.

[0030] S400: The user confirms the diagnostic result of the item to be confirmed and receives user feedback. The standardized knowledge base is then updated through self-learning based on the user feedback.

[0031] It should be noted that with the continuous expansion of the construction scale of smart substations and the acceleration of technological iteration, the complexity of their virtual circuit configuration is increasing exponentially. Traditional manual verification methods are inefficient and prone to errors, while existing automated tools can only perform syntax-level checks and cannot diagnose the correctness of connection logic from the functional semantic level. Moreover, their rule bases are fixed and difficult to adapt to new equipment and diversified engineering solutions. Virtual circuit connection errors will directly affect the safe operation of substations. The lack of in-depth verification and adaptive evolution capabilities of existing technologies for functional logic has become a bottleneck restricting the quality and efficiency of smart substation construction.

[0032] Therefore, to address the aforementioned issues of low verification efficiency, lack of semantic diagnosis, and system rigidity, a standardized knowledge base is constructed through steps S100-S400 to achieve the structured accumulation of expert knowledge. Combined with an instance virtual circuit knowledge graph, the SCD configuration file is transformed into a computable instance virtual circuit knowledge graph, enabling a computer-understandable expression of the virtual circuit configuration. Furthermore, consistent reasoning is performed, achieving a leap from syntax checking to functional semantic diagnosis. Finally, through a user feedback-driven self-learning mechanism, a systematic solution is provided for the efficient, accurate, and adaptive verification of virtual circuits in smart substations.

[0033] Example 2, refer to Figures 1-4 As an embodiment of the present invention, based on the above embodiment, an automatic verification method for virtual circuits in intelligent substations is provided.

[0034] In this embodiment of the application, taking a 220kV intelligent substation line protection system as the application scenario, the specific implementation of the steps for constructing a standardized knowledge base for A1~A3 in S100 is as follows: A1. Define a unified ontology model and obtain standard functional identifiers through the unified ontology model.

[0035] The steps for obtaining the standard functional identifier include A1.1 to A1.2: A1.1 Define the bay ontology model and the unified ontology model used to describe electrical bays.

[0036] Specifically, the bay ontology model is defined as a data template for electrical bays. The attributes of the bay ontology model include voltage level and primary equipment type, such as 220kV, electrical bays of lines and busbars. The bay ontology model describes the functional relationships between electrical bays, such as providing voltage and receiving trip signals. Define a unified ontology model as a data template for virtual terminals. The attributes of the unified ontology model include function identifiers and signal types, such as protection trip, GOOSE input, and IED intelligent electronic device.

[0037] A1.2 Extract standardized function definitions based on industry standards and specifications, and map the standardized function definitions to the unified ontology model to obtain standard function identifiers.

[0038] Specifically, referring to the "Q / CSG110016IEC61850 Engineering Application Model" standard, functional semantics are extracted. For example, the protection tripping function is abstracted into line protection-protection tripping GOOSE output, and then stored in the standard function identifier after being decoupled from the IED intelligent electronic device.

[0039] A2. Combine the unified ontology model with the standard function identifier to generate virtual loop verification rules.

[0040] Specifically, the steps to obtain the virtual loop verification rules include A2.1 to A2.3: A2.1. Based on the primary equipment type and the standard function identifier defined in the interval ontology model, generate virtual loop verification rules, wherein the virtual loop verification rules include rules constraints within the electrical interval and rules constraints between electrical intervals.

[0041] Specifically, domain experts create virtual loop verification rules based on design specifications, using primary equipment types such as lines and standard function identifiers such as smart terminals-trip outputs.

[0042] A2.2 The rule constraint within the electrical interval is: when the primary equipment type is type A and the receiving terminal function identifier is identifier B, then the transmitting terminal function identifier for primary output or secondary output is identifier C.

[0043] Specifically, the constraint strength is divided into primary output and secondary output. Primary output is mandatory, while secondary output is required. When the virtual loop connection is an indispensable core virtual loop connection, involving core safety protection functions such as protection tripping, its absence will cause the intelligent substation line protection system to malfunction or cause a safety accident, then it is a primary output. When the virtual loop connection is an auxiliary virtual loop connection, involving auxiliary functions such as measurement, alarm, and waveform recording, even if it is missing, the intelligent substation line protection system can still operate, but it will affect monitoring or optimized operation, then it is a secondary output. Type A indicates the primary equipment type of this electrical compartment, such as a line; Type B indicates the receiving terminal function of this electrical compartment, such as a smart terminal-trip output GOOSE input; Type C indicates the transmitting terminal function of this electrical compartment, such as a line protection-protection trip output GOOSE output. When the primary device type is line and the receiving terminal function identifier is Smart Terminal - Trip Output GOOSE Input, then the sending terminal function identifier must be Line Protection - Protection Trip GOOSE Output.

[0044] A2.3 The electrical bay rule constraint is as follows: when the primary equipment type of this electrical bay is type A and the receiving terminal function identifier of this electrical bay is identifier B, then the primary equipment type of the external electrical bay is identifier D for first-level output or second-level output and the transmitting terminal function identifier of the external electrical bay is identifier E for first-level output or second-level output.

[0045] Specifically, D indicates the primary equipment type of the external electrical compartment, such as busbar; E indicates the transmitting terminal function of the external electrical compartment, such as busbar protection and control - busbar voltage SV output. If the primary equipment type of this electrical compartment is line and the function identifier of the receiving terminal of this electrical compartment is line protection - bus voltage SV input, then the primary equipment type of the external electrical compartment must be bus and the function identifier of the transmitting terminal of the external electrical compartment must be bus protection measurement and control - bus voltage SV output.

[0046] A3. Construct a standardized knowledge base using the unified ontology model, the standard function identifier, and the virtual loop verification rules.

[0047] Specifically, the defined unified ontology model, the obtained standard functional identifiers, and the generated virtual loop verification rules are integrated to form a standardized knowledge base that is independent of any specific substation instance.

[0048] In an optional implementation, step S100 can also be assisted by a graphical interface for domain experts to input and review virtual loop verification rules. The steps are as follows: provide an editing interface, where experts can generate virtual loop verification rules by selecting the primary equipment type and standard function identifier from the drop-down menu, set the constraint strength, and submit them for review before they can be officially entered into the database.

[0049] In another optional implementation, step S100 can also learn initial virtual loop verification rules in batches from historically correct SCD configuration files. The steps are as follows: parse multiple historically correct SCD configuration files, count frequently occurring virtual terminal connection modes that conform to design specifications, generate initial virtual loop verification rules for expert confirmation, and then batch store them in the database.

[0050] In this embodiment of the application, step S200, the step of obtaining the instance virtual circuit knowledge graph, includes B1~B3: B1. The SCD configuration file is parsed using the unified ontology model to extract the smart electronic devices and the virtual terminal connections between them.

[0051] Specifically, such as Figure 2As shown, an XML parser, such as a DOM parser, is used to parse the SCD configuration file of the target substation. Traversing ` / SCL / IED` indicates that all IED smart electronic device information from the SCD configuration file, including the device name (@name) and device type (@type) attributes, is read from the SCL root node. The ` / SCL / Communication / SubNetwork / ConnectedAP / Inputs / ExtRef` element is also parsed, representing an external reference element (ExtRef) pointing to the virtual terminal connections defined in the SCD configuration file. `Communication` indicates the communication network configuration of the target substation; `SubNetwork` indicates the communication subnet where the IED smart electronic device is located; `ConnectedAP` indicates the specific access point of the IED smart electronic device within the communication subnet; `Inputs` represents the input configuration section of a specific IED smart electronic device; and `ExtRef` indicates the extraction and recording of all virtual loop connections from the transmitter to the receiver from the target substation.

[0052] B2. Assign the intelligent electronic device to the corresponding electrical interval to obtain the electrical interval composition and the electrical interval affiliation of each virtual terminal.

[0053] Specifically, according to the naming convention of IED intelligent electronic devices, the names of IED intelligent electronic devices are parsed using a predefined regular expression rule library. For example, the name of IED intelligent electronic device PC11101X is parsed as: P for protection, C for measurement and control, 1 for main transformer No. 1 / voltage level code, and 1101 for electrical bay number. By comparing with the coding table, it is determined that it belongs to electrical bay 1 of 110kV line. For IED intelligent electronic devices with non-standard naming, the internal logic nodes are analyzed and combined with their signal types to determine the electrical bay affiliation.

[0054] B3. Based on the electrical interval composition and the electrical interval affiliation of each virtual terminal, create an electrical interval node corresponding to each electrical interval, a virtual terminal node corresponding to each virtual terminal, a subordinate edge from the virtual terminal node to its electrical interval node, and a connection edge from the transmitting virtual terminal node to the receiving virtual terminal node, to obtain an instance virtual circuit knowledge graph.

[0055] Specifically, in the graph database, this embodiment uses the Neo4j graph database. For each identified electrical bay, such as the 110kV line 1 electrical bay, an electrical bay node is created, with attributes including a voltage level of 110kV and a primary equipment type of line. A virtual terminal node is created for each parsed virtual terminal. A subordinate edge BELONGS-TO is created from the virtual terminal node to its corresponding electrical bay node. Based on the virtual loop connection relationship extracted from the SCD configuration file, a GOOSE-LINK directed edge or SV-LINK directed edge is created from the sending virtual terminal node to the receiving virtual terminal node, thus obtaining a complete instance virtual loop knowledge graph.

[0056] In an optional implementation, step S200 may also employ a multi-strategy fusion device domaining method, wherein the steps are as follows: when the naming of IED intelligent electronic devices is not standardized and the logical node type is ambiguous, the intelligent substation line protection system combines the electrical bay assignment of its configured signal type and uses graph reasoning algorithm to assist in determining its most likely electrical bay assignment.

[0057] In another optional implementation, step S200 can also implement incremental updates of the knowledge graph. The steps are as follows: when the SCD configuration file undergoes partial changes, the intelligent substation line protection system only parses the changed parts through version comparison and performs incremental updates of the instance knowledge graph to avoid full reconstruction and improve processing efficiency.

[0058] In this embodiment of the application, step S300, the step of generating a diagnostic report, includes C1 to C5: C1. Precompile the virtual loop verification rules into a structured query.

[0059] Specifically, such as Figure 3 As shown, the logical form of each virtual loop verification rule is converted into a specific query statement that can be executed in the graph database. For example, if the primary equipment type of an electrical bay is line and the receiving terminal function identifier is Smart Terminal - Trip Output GOOSE Input, then the sending terminal function identifier must be Line Protection - Protection Trip GOOSE Output. If the primary equipment type of an electrical bay is line, and there is a receiving virtual terminal node in the electrical bay whose function identifier is Smart Terminal - Trip Output GOOSE Input, then the sending virtual terminal node connected to this receiving virtual terminal must have a function identifier of Line Protection - Protection Trip GOOSE Output.

[0060] C2. Execute the structured query in the virtual loop knowledge graph of the instance, and perform consistency reasoning by locating the virtual terminal node of the receiving end and checking whether the virtual terminal node of the sending end upstream of the virtual terminal node of the receiving end conforms to the functional identifier of the virtual loop verification rule, and obtain the reasoning result.

[0061] Specifically, the pre-compiled query statement is executed to locate all eligible receiving virtual terminal nodes in the instance virtual circuit knowledge graph. Then, all upstream connections of each receiving virtual terminal node are traversed, i.e., all GOOSE-LINK directed edges or SV-LINK directed edges pointing to it. The function identifier of the sending virtual terminal node is checked to see if it matches the sending function identifier expected by the virtual circuit verification rule. For example, it checks whether all sending terminals connected to the smart terminal-trip output terminal are line protection-protection trip.

[0062] C3. Based on the constraint strength and reasoning result of the virtual loop verification rule, when the reasoning result indicates that the virtual loop verification rule is not met, if the constraint strength is a first-level output, an error diagnosis result is generated; if the constraint strength is a second-level output, a warning diagnosis result is generated. The virtual terminal nodes with empty function identifiers in the instance virtual loop knowledge graph are identified, and a diagnosis result for unconfirmed items with unknown function identifiers is generated.

[0063] Specifically, when it is found that the transmitting end connected to the intelligent terminal-trip output terminal of the line bay is not the line protection-protection trip, the constraint strength is required, and an error diagnosis result is generated: the necessary connection is missing, and the intelligent terminal-trip output of the line bay has not received the line protection-protection trip signal; at the same time, all virtual terminal nodes with empty function identifiers in the instance virtual circuit knowledge graph are scanned, and a diagnosis result for unconfirmed items with unknown function identifiers is generated.

[0064] C4. A diagnostic report is obtained by combining the error diagnosis results, warning diagnosis results, and pending confirmation item diagnosis results.

[0065] Specifically, the generated diagnostic results, such as error diagnostic results, warning diagnostic results, and diagnostic results for items pending confirmation, are summarized to form a diagnostic report.

[0066] Consistent reasoning further includes steps C4.1 to C4.2: C4.1 After completing the consistency reasoning of all virtual loop verification rules, scan all connection edges in the instance virtual loop knowledge graph, and identify connection edges that do not meet the virtual loop verification rules as redundant connection pending confirmation item diagnostic results.

[0067] Specifically, after the rule check is completed, all GOOSE-LINK directed edges and SV-LINK directed edges in the instance virtual loop knowledge graph are scanned. It is found that a certain GOOSE output of the line protection device is connected to the GOOSE input of the bus protection device. However, the virtual loop verification rule does not support this connection, so it is marked as a redundant connection: a direct GOOSE connection from line protection to bus protection is identified as a diagnostic result of a redundant connection to be confirmed.

[0068] C4.2 The diagnostic results of the redundant connection to be confirmed and the diagnostic results of the function identifier unknown to be confirmed are combined to form the diagnostic results of the to be confirmed items in the diagnostic report.

[0069] Specifically, the diagnostic results of the identified redundant connections to be confirmed are merged with the diagnostic results of the unconfirmed items with unknown function identifiers into a single diagnostic result, which is then displayed uniformly in the diagnostic report for users to confirm.

[0070] In an optional implementation, parallel processing can also be used in step S300 to improve diagnostic efficiency. The steps are as follows: different virtual loop verification rules are pre-compiled into multiple independent queries and executed in parallel in the instance virtual loop knowledge graph, using a multi-core processor architecture to accelerate the diagnostic process.

[0071] In another optional implementation, rule priority processing can also be implemented in step S300, which involves setting priority weights for conflicting virtual loop verification rules, and determining the final diagnostic conclusion according to priority when multiple virtual loop verification rules produce different diagnostic results for the same connection.

[0072] In this embodiment of the application, step S400, which involves self-learning and updating the standardized knowledge base based on user feedback, includes steps D1 to D2: D1. When the user feedback of the diagnosis result of the item to be confirmed is a redundant connection, extract the receiving end electrical interval type, receiving end function identifier, transmitting end electrical interval type and transmitting end function identifier corresponding to the diagnosis result of the item to be confirmed for the redundant connection, generate a draft virtual loop verification rule, and add the draft virtual loop verification rule to the virtual loop verification rule of the standardized knowledge base.

[0073] Specifically, such as Figure 4 As shown, when the user confirms the diagnostic result of the pending confirmation item marked as redundant connection: direct GOOSE connection from line protection to bus protection in the diagnostic report, it is actually the context information of the redundant connection extracted by the intelligent substation line protection system after the correct connection: the receiving end electrical bay type is line, the receiving end function identifier is protection-bus protection remote trip GOOSE input, the sending end electrical bay type is bus, and the sending end function identifier is bus protection-remote trip output GOOSE output. Based on the context information of redundant connections, a new draft rule for virtual loop verification between electrical bays is generated: when the primary equipment type of this electrical bay is line and the function identifier of the receiving terminal of this electrical bay is protection-bus protection remote trip GOOSE input, then the primary equipment type of the external electrical bay must be bus and the function identifier of the transmitting terminal of the external electrical bay must be bus protection-remote trip output GOOSE output. The constraint strength is set to level one output. After being reviewed and approved by experts, it is officially added to the virtual loop verification rules in the standard knowledge base.

[0074] D2. When the user feedback on the diagnostic result of the item to be confirmed is that the function identifier is unknown, the function identifier confirmed by the user will be updated to the standard function identifier in the standardized knowledge base.

[0075] Specifically, when a user confirms the diagnostic result of a pending item with an unknown function identifier in the diagnostic report and determines its function identifier as Auxiliary Equipment - Status Indication, the intelligent substation line protection system updates the function identifier of the virtual terminal node to Auxiliary Equipment - Status Indication. At the same time, it adds the standard function identifier of Auxiliary Equipment - Status Indication and its corresponding signal type to the standard function identifiers in the standardized knowledge base.

[0076] In an optional implementation, step S400 can also realize the automatic review of the draft virtual loop verification rules. The steps are as follows: when the generated draft virtual loop verification rules do not conflict with the existing virtual loop verification rules, the intelligent substation line protection system can automatically pass the review and add it to the standardized knowledge base.

[0077] In another optional implementation, step S400 can also perform progressive learning based on confidence level. The steps are as follows: set an initial confidence level for the newly added virtual loop verification rule, and gradually increase the confidence level until it becomes a formal virtual loop verification rule after it is repeatedly verified to be correct during the verification process.

[0078] In summary, this invention takes a 220kV intelligent substation line protection system as the application scenario. It constructs a standardized knowledge base containing a unified ontology model, standard functional identifiers, and virtual circuit verification rules; parses SCD configuration files to build an instance virtual circuit knowledge graph; performs consistent reasoning in the instance virtual circuit knowledge graph using pre-compiled rules for structured queries to generate diagnostic reports; and finally achieves self-learning updates of the standardized knowledge base based on user feedback. This invention also provides optional methods such as parallel processing and confidence mechanisms, solving problems such as low efficiency, lack of semantic diagnosis, and system rigidity in traditional verification methods, and realizing the transformation of virtual circuit verification in intelligent substations from manual experience-based verification to automated intelligent verification.

[0079] Example 3 illustrates a schematic scheme for an automatic verification method for virtual circuits in intelligent substations. It should be noted that the technical solution of this automatic verification system for virtual circuits in intelligent substations is based on the same concept as the aforementioned automatic verification method for virtual circuits in intelligent substations. Details not described in detail in this embodiment can be found in the description of the aforementioned automatic verification method for virtual circuits in intelligent substations.

[0080] This embodiment also provides an automatic verification system for virtual circuits in intelligent substations, including: The knowledge base management module is used to build standardized knowledge bases; A graph construction engine is used to parse the SCD configuration file and construct the virtual circuit knowledge graph of the instance. An inference diagnostic engine is used to perform the consistent inference and generate the diagnostic report; The human-computer interaction module is used to output the diagnostic report and receive the user's confirmation operation on the diagnostic results of the items to be confirmed, thereby generating user feedback; The self-learning module is used to update the standardized knowledge base based on the user feedback.

[0081] This embodiment also provides an electronic device suitable for automatic verification of virtual circuits in intelligent substations, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the automatic verification method for virtual circuits in intelligent substations as proposed in the above embodiment.

[0082] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements an automatic verification method for virtual circuits in an intelligent substation as proposed in the above embodiments.

[0083] The storage medium proposed in this embodiment belongs to the same inventive concept as the method for automatic verification of virtual circuits in intelligent substations proposed in the above embodiments. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0084] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0085] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An automatic verification method for virtual loops in intelligent substations, characterized in that, include: Define a unified ontology model, obtain standard function identifiers through the unified ontology model, generate virtual loop verification rules by combining the unified ontology model and the standard function identifiers, and construct a standardized knowledge base through the unified ontology model, the standard function identifiers and the virtual loop verification rules; Obtain the SCD configuration file of the target substation, and parse the SCD configuration file according to the unified ontology model to obtain the instance virtual circuit knowledge graph; The instance virtual circuit knowledge graph is used to perform consistency reasoning with the virtual circuit verification rules to generate a diagnostic report, which includes the diagnostic results of the items to be confirmed. The user confirms the diagnostic result of the item to be confirmed and receives user feedback. The standardized knowledge base is then updated through self-learning based on the user feedback. The steps to generate a diagnostic report include: The virtual loop verification rules are pre-compiled into a structured query; The structured query is executed in the virtual loop knowledge graph of the instance. Consistency reasoning is performed by locating the virtual terminal node of the receiving end and checking whether the virtual terminal node of the sending end upstream of the virtual terminal node of the receiving end conforms to the function identifier of the virtual loop verification rule, and the reasoning result is obtained. Based on the constraint strength and reasoning result of the virtual loop verification rule, when the reasoning result indicates that the virtual loop verification rule is not met, if the constraint strength is a first-level output, an error diagnosis result is generated; if the constraint strength is a second-level output, a warning diagnosis result is generated. The virtual terminal nodes with empty functional identifiers in the instance virtual loop knowledge graph are identified, and a diagnosis result for unconfirmed items with unknown functional identifiers is generated. A diagnostic report is generated by combining the error diagnosis results, warning diagnosis results, and pending confirmation item diagnosis results.

2. The automatic verification method for virtual loops in intelligent substations as described in claim 1, characterized in that, The steps of defining a unified ontology model and obtaining standard functional identifiers through the unified ontology model include: Define the bay ontology model and the unified ontology model used to describe electrical bays; Standardized function definitions are extracted based on industry standards and specifications, and then mapped to the unified ontology model to obtain standard function identifiers.

3. The automatic verification method for virtual loops in intelligent substations as described in claim 2, characterized in that, The steps for generating virtual loop verification rules include: Based on the primary equipment type and the standard function identifier defined in the interval ontology model, virtual loop verification rules are generated, wherein the virtual loop verification rules include rules constraints within the electrical interval and rules constraints between electrical intervals; The rule constraint within the electrical interval is as follows: when the primary equipment type is type A and the receiving terminal function identifier is identifier B, then the transmitting terminal function identifier for primary output or secondary output is identifier C. The electrical bay rule constraint is as follows: when the primary equipment type of this electrical bay is type A and the function identifier of the receiving terminal of this electrical bay is identifier B, then the primary equipment type of the external electrical bay is identifier D for first-level output or second-level output and the function identifier of the transmitting terminal of the external electrical bay is identifier E for first-level output or second-level output.

4. The automatic verification method for virtual loops in intelligent substations as described in claim 3, characterized in that, The steps to obtain the instance virtual circuit knowledge graph include: The SCD configuration file is parsed using the unified ontology model to extract intelligent electronic devices and virtual terminal connections between them. The intelligent electronic device is assigned to the corresponding electrical interval to obtain the electrical interval composition and the electrical interval affiliation of each virtual terminal; Based on the electrical interval composition and the electrical interval affiliation of each virtual terminal, an electrical interval node corresponding to each electrical interval, a virtual terminal node corresponding to each virtual terminal, a subordinate edge from the virtual terminal node to its electrical interval node, and a connection edge from the transmitting virtual terminal node to the receiving virtual terminal node are created to obtain an instance virtual circuit knowledge graph.

5. The automatic verification method for virtual loops in intelligent substations as described in claim 4, characterized in that, The consistent reasoning includes: After completing the consistency reasoning of all virtual loop verification rules, scan all the connection edges in the instance virtual loop knowledge graph, and identify the connection edges that do not meet the virtual loop verification rules as redundant connection pending confirmation item diagnostic results. The diagnostic results of the redundant connections to be confirmed and the diagnostic results of the unconfirmed items with unknown function identifiers are combined to form the diagnostic results of the unconfirmed items in the diagnostic report.

6. The automatic verification method for virtual loops in intelligent substations as described in claim 5, characterized in that, The step of self-learning and updating the standardized knowledge base based on user feedback includes at least one of the following methods: When the user feedback of the diagnosis result of the pending item is a redundant connection, the receiving end electrical spacing type, receiving end function identifier, transmitting end electrical spacing type and transmitting end function identifier corresponding to the diagnosis result of the pending item of the redundant connection are extracted, a draft virtual loop verification rule is generated, and the draft virtual loop verification rule is added to the virtual loop verification rule of the standardized knowledge base. When the user feedback on the diagnostic result of the pending item is that the function identifier is unknown, the function identifier confirmed by the user will be updated to the standard function identifier in the standardized knowledge base.

7. An automatic verification system for virtual loops in intelligent substations, employing the method described in any one of claims 1-6, characterized in that, include: The knowledge base management module is used to build standardized knowledge bases; A graph construction engine is used to parse the SCD configuration file and construct the virtual circuit knowledge graph of the instance. An inference diagnostic engine is used to perform the consistent inference and generate the diagnostic report; The human-computer interaction module is used to output the diagnostic report and receive the user's confirmation operation on the diagnostic results of the items to be confirmed, thereby generating user feedback; The self-learning module is used to update the standardized knowledge base based on the user feedback.

8. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the automatic verification method for virtual circuits in an intelligent substation as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the automatic verification method for virtual circuits in an intelligent substation as described in any one of claims 1 to 6.

Images