Substation secondary system modeling method and related equipment

Abstract

The invention discloses a transformer substation secondary system modeling method and related equipment, and relates to the field of power system modeling.The method comprises the steps that firstly, feature information, hierarchical relations and connection relations of electrical elements are extracted from a transformer substation secondary system configuration file, and the system structure is comprehensively mastered; generating a historical information time sequence in combination with historical information of the transformer substation; then respectively mining a time influence factor and a space influence factor by using a long short-term memory network and a multiple regression model; and finally, establishing a global simulation model based on a digital twinning technology. According to the scheme, equipment operation data is deeply mined, and the data integration problem is solved; the space-time dimension is fully considered, and the equipment state is accurately simulated; information delay is reduced by means of a real-time data mechanism, and virtual-real synchronization is guaranteed; model lightweight and compatibility are achieved, and the multi-scene requirement is met. Therefore, active operation and maintenance decision is achieved, and the operation and maintenance efficiency and safety of the substation are remarkably improved.

Description

Technical Field

[0001] The present application relates to the field of power system modeling, and more specifically, to a substation secondary system modeling method and related equipment. Background Art

[0002] Amid the rapid development of smart grids, substation secondary equipment is evolving towards integration and complexity. Traditional operations and maintenance (O&M) models rely on manual inspections and paper drawings. Manual inspections, limited by the inspectors' expertise and work habits, are inefficient and subjective, making comprehensive and accurate equipment inspections difficult. Missed and false detections are common. Paper drawings, on the other hand, have long update cycles and are unable to synchronize the equipment's real-time operating status and parameter changes. This results in delayed equipment status monitoring and slow fault response. Once a device fails, O&M personnel struggle to obtain accurate information, quickly locate the fault point, and take effective measures. Configuration parameter verification becomes challenging, making full lifecycle management even more difficult.

[0003] While substation secondary system modeling technology has made some progress, enabling three-dimensional visualization of equipment, these technologies have exposed numerous problems in practical applications. From a system analysis perspective, data processing lacks in-depth mining and integration of equipment operating data, making it impossible to fully present a complete picture of equipment operation. Model construction also fails to fully consider the complex operating environment of the substation secondary system and the interactions between equipment, resulting in a deviation between the model's simulation of equipment status and actual conditions. Furthermore, the model suffers from information delays and loss during data updates and transmission, making it difficult to meet real-time operation and maintenance requirements. Furthermore, the model's compatibility across different hardware devices and software platforms is poor, preventing it from operating efficiently in diverse operation and maintenance scenarios, severely hindering the development of intelligent substation secondary system operation and maintenance.

[0004] Therefore, the present application proposes a substation secondary system modeling solution that can circumvent the defects of the prior art. Summary of the Invention

[0005] This application provides a substation secondary system modeling method and related equipment, which solves problems such as insufficient data integration, model simulation deviation, information delay and poor model adaptability, and effectively improves the substation operation and maintenance efficiency and safety.

[0006] A substation secondary system modeling method, comprising:

[0007] Obtaining a configuration file of the substation secondary system, and extracting characteristic information, hierarchical relationships, and connection relationships of each electrical component from the configuration file;

[0008] Acquire historical information of the substation, integrate the historical information according to the characteristic information, the hierarchical relationship, and the connection relationship, and generate a historical information time series, wherein the historical information time series records the integrated historical information arranged in chronological order;

[0009] Inputting the historical information time series into a long short-term memory network to obtain a time impact factor;

[0010] Inputting the feature information, the hierarchical relationship and the connection relationship into a multiple regression model to obtain a spatial impact factor;

[0011] Digital twin technology is used to establish a global simulation model based on the time influence factor, the space influence factor, the feature information, the hierarchical relationship and the connection relationship.

[0012] Optionally, the acquiring of historical information of the substation, integrating the historical information according to the characteristic information, the hierarchical relationship, and the connection relationship, and generating a time series of historical information includes:

[0013] Acquire historical information of the substation, and perform data association with the characteristic information to generate associated historical information;

[0014] Based on the hierarchical relationship and the connection relationship, data integration is performed on the associated historical information to obtain integrated historical information;

[0015] The integrated historical information is arranged in chronological order using the timestamp as an index to generate a historical information time series.

[0016] Optionally, extracting characteristic information, hierarchical relationships, and connection relationships of each electrical component from the configuration file includes:

[0017] Extracting characteristic information of each electrical component from the configuration file according to an XML parsing algorithm and a regular expression matching algorithm;

[0018] extracting the hierarchical relationship of each electrical component from the configuration file according to a tree traversal algorithm;

[0019] The connection relationship of each electrical component is extracted from the configuration file according to a graph search algorithm and an association rule mining algorithm.

[0020] Optionally, extracting characteristic information of each electrical component from the configuration file according to an XML parsing algorithm and a regular expression matching algorithm includes:

[0021] Read the configuration file according to the XML parsing algorithm, and extract structured data in the configuration file by traversing the document tree structure;

[0022] Using a regular expression matching algorithm to match and extract unstructured data in the configuration file;

[0023] The extracted structured data and unstructured data are cleaned and structurally integrated to obtain characteristic information of each electrical component.

[0024] Optionally, extracting the hierarchical relationship of each electrical component from the configuration file according to a tree traversal algorithm includes:

[0025] Parsing the configuration file into a tree data structure, and identifying station-level nodes, interval-level nodes, and device-level nodes through a tree traversal algorithm;

[0026] Based on the parent-child relationship between nodes, a three-level hierarchical structure including stations, intervals and devices is constructed, wherein the station-level node is the root node, the interval-level node is the child node of the station-level node, and the device-level node is the child node of the interval-level node;

[0027] The hierarchical identification and association relationship of each node in the three-level hierarchical structure are stored to generate a hierarchical relationship of electrical components.

[0028] Optionally, extracting the connection relationship of each electrical component from the configuration file according to a graph search algorithm and an association rule mining algorithm includes:

[0029] Mapping the device and connection information in the configuration file into a graph structure, where nodes in the graph structure represent electrical components, edges represent physical connections or logical connections, and recording attribute parameters of the connections;

[0030] Traversing the graph structure using a graph search algorithm, parsing the physical connection paths and logical communication links of each electrical component layer by layer;

[0031] Analyzing the frequent item sets of co-occurrence of devices in the configuration file based on an association rule mining algorithm to determine the potential connection relationship between the electrical components;

[0032] The connection relationship of each electrical component is generated by combining the physical connection path, the logical communication link and the potential connection relationship.

[0033] Optionally, the digital twin technology is used to establish a global simulation model based on the time influence factor, the space influence factor, the feature information, the hierarchical relationship, and the connection relationship, including:

[0034] Establish a BIM model of the substation secondary system;

[0035] Integrating the time impact factor and the space impact factor into the BIM model in a weighted manner to dynamically map the equipment status;

[0036] The BIM model is dynamically evolved according to the feature information, the hierarchical relationship and the connection relationship to generate a global simulation model.

[0037] A substation secondary system modeling device, comprising:

[0038] A configuration file unit is used to obtain a configuration file of the substation secondary system and extract characteristic information, hierarchical relationship and connection relationship of each electrical component from the configuration file;

[0039] a historical information unit, configured to obtain historical information of the substation, integrate the historical information according to the characteristic information, the hierarchical relationship, and the connection relationship, and generate a historical information time series, wherein the historical information time series records the integrated historical information arranged in chronological order;

[0040] A time factor unit, used to input the historical information time series into the long short-term memory network to obtain a time impact factor;

[0041] A spatial factor unit, configured to input the feature information, the hierarchical relationship, and the connection relationship into a multiple regression model to obtain a spatial impact factor;

[0042] A model building unit is used to use digital twin technology to establish a global simulation model based on the time influence factor, the space influence factor, the feature information, the hierarchical relationship and the connection relationship.

[0043] A substation secondary system modeling device includes a memory and a processor;

[0044] The memory is used to store programs;

[0045] The processor is configured to execute the program to implement each step of the substation secondary system modeling method as described in any one of the above items.

[0046] A readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, each step of the substation secondary system modeling method as described in any one of the above items is implemented.

[0047] A computer program product includes a computer program, wherein when the computer program is executed by a processor, each step of the substation secondary system modeling method as described above is executed.

[0048] It can be seen from the above technical solution that the embodiment of the present application provides a substation secondary system modeling method and related equipment, which first extracts the characteristic information, hierarchical relationship and connection relationship of electrical components from the substation secondary system configuration file to fully grasp the system structure; then combines the substation historical information to generate a historical information time series; then uses the long short-term memory network and the multivariate regression model to respectively mine the time influencing factors and the spatial influencing factors; finally, establishes a global simulation model based on digital twin technology.

[0049] This application extracts configuration file information and integrates historical data to generate time series, deeply mines equipment operation data, and comprehensively presents the overall picture of equipment operation, thus solving the problem of insufficient data integration. In terms of model construction, time influencing factors and space influencing factors are used to fully consider the time dimension and spatial relationship of equipment operation, accurately simulate the equipment status, and effectively correct the simulation deviation caused by not considering the complex operating environment and equipment interaction relationship. For the information delay and loss problems in data update and transmission, the mechanism of real-time acquisition and analysis of data ensures the real-time interactivity of the model, greatly reduces information delay, and ensures the synchronization of virtual model and actual equipment. In terms of model adaptability, the optimized global simulation model achieves lightweight and good compatibility, and can be flexibly applied between different hardware devices and software platforms to meet the needs of diverse operation and maintenance scenarios, thereby realizing proactive operation and maintenance decision-making, effectively improving the efficiency and safety of substation operation and maintenance, and providing reliable technical support for the operation and maintenance of smart grid substation secondary systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without any creative work.

[0051] Figure 1 This is a flow chart of a substation secondary system modeling method disclosed in an embodiment of the present application;

[0052] Figure 2 A schematic diagram of a substation secondary system modeling device disclosed in an embodiment of the present application;

[0053] Figure 3 This is a hardware structure block diagram of a substation secondary system modeling device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0055] The present application can be used in a variety of general or special computing device environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multi-processor devices, and distributed computing environments including any of the above devices or devices.

[0056] Next, we will introduce the application scheme. This application proposes the following technical scheme, please see below for details.

[0057] Figure 1 This is a flowchart of a substation secondary system modeling method disclosed in an embodiment of the present application.

[0058] like Figure 1 As shown, the method may include:

[0059] Step S1: Obtain a configuration file of a substation secondary system, and extract characteristic information, hierarchical relationships, and connection relationships of various electrical components from the configuration file.

[0060] Specifically, the configuration file of the substation secondary system is read through the network communication interface or local storage medium. The configuration file usually adopts a standard format, such as the substation configuration language (SCL) file, which contains detailed parameters and structural descriptions of the secondary system. The configuration file is analyzed syntactically and semantically using a parser, and each electrical component, such as relays, protection devices, measurement and control units, etc., is identified based on predefined rules and templates. For each electrical component, its model, rated parameters, functional description and other characteristic information are extracted; by analyzing the logical structure and hierarchical labels in the configuration file, the hierarchical relationship between the components is determined, such as the subordinate relationship between the protection device and the interval layer equipment and the station control layer equipment; at the same time, the description of the electrical connection in the configuration file is parsed to obtain the physical connection and signal transmission connection relationship between the components, so as to fully understand the structural composition of the substation secondary system.

[0061] Step S2: Acquire historical information of the substation, integrate the historical information according to the characteristic information, the hierarchical relationship and the connection relationship, and generate a historical information time series, wherein the historical information time series records the integrated historical information arranged in chronological order.

[0062] Specifically, historical information covering equipment operating status, fault records, operation logs, etc. is obtained from the substation's data storage system, such as a database or historical data server. Based on the electrical component feature information, hierarchical relationships, and connection relationships extracted in step S1, the historical information is screened and classified, and each piece of historical information is matched and associated with the corresponding electrical component. The associated historical information is sorted according to the timestamp. For information involving multiple components at the same time point, it is integrated based on the hierarchical relationships and connection relationships to form a continuous, logically associated time series of historical information. This time series not only records the operating data of each electrical component at different times, but also reflects the mutual influence and collaborative work between components, providing a data basis for subsequent analysis.

[0063] Step S3: Input the historical information time series into the long short-term memory network to obtain the time impact factor.

[0064] Specifically, a long short-term memory (LSTM) network is a special type of recurrent neural network that effectively handles long-term dependencies in time series data. A specific LSTM model is constructed for electrical component time series analysis. The model's input layer receives the time series data constructed in step S2. It contains multiple LSTM hidden layers to learn complex patterns and features in the time series. The output layer outputs a time impact factor. The LSTM model is trained using a large amount of pre-trained electrical component time series data. During training, the model continuously adjusts its internal parameters using a backpropagation algorithm to minimize the error between the predicted results and the actual time series data. Through multiple iterations of training, the model accurately captures the temporal changes in the operating status of electrical components and learns the impact of time factors (such as equipment aging and seasonal changes) on electrical components. The fully trained LSTM model processes new input electrical component time series data and outputs a time impact factor. This factor quantifies the degree of impact of time on the electrical component's status. For example, it reflects the increasing probability of equipment failure with increasing operating time or the fluctuations in equipment performance due to seasonal changes. This factor provides an important basis for evaluating the temporal state of electrical components.

[0065] Step S4: input the feature information, the hierarchical relationship and the connection relationship into a multiple regression model to obtain a spatial impact factor.

[0066] Specifically, a multiple regression model is used to analyze the linear relationship between multiple independent variables and a dependent variable. The multiple regression model is constructed using the electrical component feature information, hierarchical relationships, and connectivity relationships extracted in step S1 as independent variables, and spatially relevant factors (such as equipment operating status indicators and performance parameters) as dependent variables. First, the feature information, hierarchical relationships, and connectivity data used as independent variables are organized and preprocessed. Text data is encoded and converted into numerical data. The data is then standardized or normalized to eliminate the dimensional influence of different variables and improve model training effectiveness and accuracy. The spatial impact factor reflects the combined impact of various factors on electrical components in the spatial dimension. For example, strong electromagnetic interference at the equipment's location or poor heat dissipation due to an unreasonable spatial layout are reflected in the spatial impact factor. This helps comprehensively assess the operating status and potential risks of electrical components within the substation's spatial environment.

[0067] Step S5: Using digital twin technology, a global simulation model is established based on the time impact factor, the spatial impact factor, the feature information, the hierarchical relationship, and the connection relationship.

[0068] Specifically, digital twin technology realizes real-time monitoring, analysis and optimization of physical entities by constructing a virtual model that is highly mapped to the physical entity. Taking the time influence factor, space influence factor, characteristic information, hierarchical relationship and connection relationship obtained in steps S1-S4 as basic data, a virtual electrical component model is constructed according to the physical structure and logical relationship of the actual substation secondary system using three-dimensional modeling software or a professional simulation platform, and assembled and connected according to the hierarchical relationship and connection relationship. The time influence factor and the space influence factor are input as dynamic parameters of the model, and the virtual model is given the changing characteristics of the time dimension and the influencing factors of the space dimension, so that the model can simulate the operating status of the equipment under different time and space conditions. By updating and synchronizing data in real time, a two-way interaction between the virtual model and the actual substation secondary system is realized, and finally a global simulation model that can comprehensively and accurately reflect the operating characteristics of the substation secondary system is established, providing an intuitive and effective tool for equipment operation and maintenance, fault prediction and decision analysis.

[0069] It can be seen from the above technical solution that the embodiment of the present application provides a substation secondary system modeling method and related equipment, which first extracts the characteristic information, hierarchical relationship and connection relationship of electrical components from the substation secondary system configuration file to fully grasp the system structure; then combines the substation historical information to generate a historical information time series; then uses the long short-term memory network and the multivariate regression model to respectively mine the time influencing factors and the spatial influencing factors; finally, establishes a global simulation model based on digital twin technology.

[0070] This application extracts configuration file information and integrates historical data to generate time series, deeply mines equipment operation data, and comprehensively presents the overall picture of equipment operation, thus solving the problem of insufficient data integration. In terms of model construction, time influencing factors and space influencing factors are used to fully consider the time dimension and spatial relationship of equipment operation, accurately simulate the equipment status, and effectively correct the simulation deviation caused by not considering the complex operating environment and equipment interaction relationship. For the information delay and loss problems in data update and transmission, the mechanism of real-time acquisition and analysis of data ensures the real-time interactivity of the model, greatly reduces information delay, and ensures the synchronization of virtual model and actual equipment. In terms of model adaptability, the optimized global simulation model achieves lightweight and good compatibility, and can be flexibly applied between different hardware devices and software platforms to meet the needs of diverse operation and maintenance scenarios, thereby realizing proactive operation and maintenance decision-making, effectively improving the efficiency and safety of substation operation and maintenance, and providing reliable technical support for the operation and maintenance of smart grid substation secondary systems.

[0071] In some embodiments of the present application, the process of obtaining historical information of the substation in step S2, integrating the historical information according to the feature information, the hierarchical relationship, and the connection relationship, and generating a time series of the historical information is introduced, which may specifically include:

[0072] Step S21: Obtain historical information of the substation, and perform data association with the characteristic information to generate associated historical information.

[0073] Specifically, substation historical information comes from a wide range of sources, covering multiple data areas. This includes, but is not limited to, equipment operating status data recorded by the substation monitoring system, such as real-time current, voltage, and power. This data reflects the equipment's electrical operating conditions at different times. Fault records detail key information such as the time, type, and symptoms of equipment failures, providing an important basis for analyzing equipment reliability and causes. Operation logs record various equipment operations, such as switch opening and closing operations and equipment inspection and maintenance, clearly identifying the time, personnel, and content of the operations. Furthermore, there is environmental data, such as substation temperature, humidity, and electromagnetic interference intensity, which can affect equipment performance. This data may be stored in different databases, file systems, or servers and requires access through specific data interfaces and protocols.

[0074] After obtaining the historical information, it is necessary to perform data association with the characteristic information of the electrical components previously extracted from the substation secondary circuit model configuration file. In specific implementation, based on the unique identification of the electrical component, such as the model, number and other characteristic information of the equipment, the data related to the device in the historical information is filtered out and associated. For example, if the number of a certain intelligent electronic device (IED) is "001", all data records related to "001" are searched in the historical information, such as the operating parameters and fault alarm information of the equipment at different time points, and a corresponding relationship is established between these data and the characteristic information of the IED (such as equipment type, rated parameters, etc.), thereby generating associated historical information. In this way, it is ensured that the subsequent analysis of historical information is targeted at specific electrical components, thereby improving the accuracy and pertinence of data processing.

[0075] Step S22: Based on the hierarchical relationship and the connection relationship, data integration is performed on the associated historical information to obtain integrated historical information.

[0076] Specifically, after completing the data association, the associated historical information is integrated based on the hierarchical relationship and connection relationship of the electrical components. The hierarchical relationship of the electrical components constructs a three-level hierarchical structure of station-bay-equipment. This structure clarifies the location and ownership of each device in the substation. For example, at the station level, a substation as a whole has attributes such as the incoming line voltage level and total capacity; the bay level divides the substation into different functional areas, such as the transmission bay and distribution bay, each of which contains a specific set of equipment; the equipment level is specific electrical equipment, such as circuit breakers and relays. The connection relationship describes the physical and logical connections between electrical components. Physical connections, such as cable connections, are responsible for power transmission; logical connections, such as communication links, are used for data transmission and control signal interaction.

[0077] Based on these hierarchical and connectivity relationships, related historical information is integrated. For example, within a transmission bay, devices such as circuit breakers and relays are interconnected via cables and communication links, and all belong to this specific bay. When integrating related historical information, the related historical information for all devices within the bay is aggregated, taking into account their mutual impact. For example, when a cable fault occurs, not only is the fault information for the cable itself recorded, but the impact on connected devices such as circuit breakers and relays is also considered. For example, the circuit breaker may operate due to the fault current, and the relay may issue a corresponding signal. This related information is then integrated to form the integrated historical information for the transmission bay. This data integration approach based on hierarchical and connectivity relationships can more comprehensively reflect the collaborative operation and mutual impact relationships between devices within the substation, providing a more complete data foundation for subsequent analysis.

[0078] Step S23: Arrange the integrated historical information in chronological order using the timestamp as an index to generate a historical information time series.

[0079] Specifically, after data integration yields integrated historical information, this information is sorted chronologically using timestamps as indexes to create a historical information time series. Timestamps are identifiers in historical information that record the time when the data was generated, accurately specifying the specific moment, such as year, month, day, hour, minute, and second. In practice, data processing tools or programming language sorting functions are used to sort the integrated historical information in ascending or descending order based on timestamps.

[0080] For example, using the pandas library in Python, we first store the integrated historical information in a DataFrame. Assuming the timestamp column is named "timestamp," we can call the sort_values(by='timestamp') function to sort the data in the DataFrame chronologically. After sorting, the historical information for each electrical component or device is arranged in chronological order, forming a time series of historical information. In this time series, each data point corresponds to a specific point in time, clearly demonstrating the state changes of the device at different moments. For example, the oil temperature data of a transformer fluctuates over time in a time series. By observing this time series, we can analyze the changing trends of the transformer's oil temperature and determine whether the device is operating abnormally. The data points in the time series can also be used for subsequent data analysis and modeling. For example, using time series analysis methods to predict the future operating status of the device provides a basis for decision-making in equipment maintenance and management.

[0081] In some embodiments of the present application, the process of obtaining a configuration file of the substation secondary system and extracting characteristic information, hierarchical relationships, and connection relationships of each electrical component from the configuration file in step S1 is introduced, which may specifically include:

[0082] Step S11 : extracting characteristic information of each electrical component from the configuration file according to an XML parsing algorithm and a regular expression matching algorithm.

[0083] Further, it may include:

[0084] ① Read the configuration file according to the XML parsing algorithm, and extract the structured data in the configuration file by traversing the document tree structure;

[0085] ② Using a regular expression matching algorithm to match and extract unstructured data in the configuration file;

[0086] ③ Perform data cleaning and structural integration on the extracted structured data and the unstructured data to obtain characteristic information of each electrical component.

[0087] Specifically, XML parsing algorithms are key tools for processing substation secondary system configuration files. For example, the common smart substation configuration file (SCD) uses XML format to describe substation equipment information. The configuration file is loaded using a standard XML parser, such as the xml.etree.ElementTree library in Python or the DOM (Document Object Model) parser in Java. The parser converts the configuration file into a document tree structure, with each XML tag corresponding to a node in the tree.

[0088] When you start traversing the document tree, start from the root node and search according to the depth-first or breadth-first strategy. For example, in an SCD file, there will be <substation>The root node contains multiple <bay>Interval nodes, each <bay>The node contains several <ied>Intelligent electronic device nodes. During the traversal process, for a specific device description node, such as <ied>Node, extract its attributes and child node information. <ied>The name attribute of the node records the device name. <voltage> 、 <current>The other sub-nodes record the electrical parameters of the device and organize this information into a structured data format, such as a dictionary in Python, to facilitate subsequent processing.

[0089] In addition to structured data, configuration files also contain unstructured text information, which is extracted using regular expression matching algorithms. First, the formatting pattern of the unstructured text is analyzed. For example, in cable descriptions, the cable model may follow specific character combination rules, such as "YJV-[0-9]+[AZ]+," which indicates a character beginning with "YJV" followed by a combination of numbers and letters. Regular expression processing functions provided by programming languages, such as Python's re module, are used. The defined regular expression pattern is applied to the text content of the configuration file to search for all strings that match the pattern. The extracted unstructured data is then associated with the corresponding electrical components, such as the cable model with the corresponding cable equipment, allowing the unstructured data to be integrated into the electrical component feature information system.

[0090] The extracted data may contain noise and errors and require data cleaning. For structured data, check data integrity, such as whether device parameters are missing. If missing, supplement them according to the configuration file specifications or default values; check whether the data format is correct, such as whether digital parameters meet the numerical range and format requirements. Otherwise, perform format conversion or correction. For unstructured data, remove irrelevant blank characters, special symbols, etc. After cleaning, integrate the structured and unstructured data. Add the unstructured data as supplementary information to the electrical component records corresponding to the structured data to form a complete set of electrical component feature information, accurately describing the properties and characteristics of each electrical component.

[0091] Step S12: extracting the hierarchical relationship of each electrical component from the configuration file according to a tree traversal algorithm.

[0092] Further, it may include:

[0093] ① Parse the configuration file into a tree data structure, and identify station-level nodes, interval-level nodes, and device-level nodes through a tree traversal algorithm;

[0094] ② Based on the parent-child relationship between nodes, a three-level hierarchical structure including stations, intervals, and devices is constructed, where the station-level node is the root node, the interval-level node is the child node of the station-level node, and the device-level node is the child node of the interval-level node;

[0095] ③Storing the hierarchical identification and association relationship of each node in the three-level hierarchical structure to generate the hierarchical relationship of electrical components.

[0096] Specifically, when using the XML parsing algorithm to parse the configuration file, a tree-like data structure has been initially constructed. The tree traversal algorithm selects depth-first search (DFS) or breadth-first search (BFS). Taking depth-first search as an example, starting from the root node of the tree, explore as deep as possible along a path until it cannot continue or reaches a leaf node, then backtrack to the previous layer node and continue to explore other branches. During the traversal process, nodes at different levels are identified based on the tags and structure definitions of the configuration file. In the SCD file, <substation>The node corresponding to the label is the station-level node. <bay>The labels correspond to interval-level nodes. <ied>The device labels correspond to device-level nodes, marking the level type of each node.

[0097] After identifying the node level, a three-level hierarchical structure is constructed based on the parent-child relationship between nodes. The station-level node serves as the root node and summarizes the key information of the entire substation, such as the name of the substation, voltage level, etc. The bay-level node, as the child node of the station-level node, divides the substation into different functional areas, and each bay has a specific function and equipment set. The equipment-level node, as the child node of the bay-level node, represents a specific electrical equipment. In the SCD file, a <substation>There are multiple nodes under <bay>Node, each <bay>There are multiple nodes under <ied>Nodes, through this parent-child relationship, establish a complete hierarchical architecture, clearly showing the hierarchical relationship between electrical components.

[0098] To facilitate subsequent use of hierarchical relationships, it's necessary to store the hierarchical identifiers and relationships of each node. Use a data structure, such as a Python dictionary, to record each node's name, level (station level, bay level, device level), and parent node name. For example, {"node name 1":{"level":"device level","parent node":"interval node 1"}}. This method fully records the hierarchical relationships of electrical components, providing a crucial basis for subsequent analysis of the device's location and relationships within the substation, as well as for fault impact assessment.

[0099] Step S13: extracting the connection relationship of each electrical component from the configuration file according to a graph search algorithm and an association rule mining algorithm.

[0100] Further, it may include:

[0101] ① Mapping the device and connection information in the configuration file into a graph structure, where nodes represent electrical components, edges represent physical connections or logical connections, and recording the attribute parameters of the connections;

[0102] ② Traversing the graph structure through a graph search algorithm, parsing the physical connection paths and logical communication links of each electrical component layer by layer;

[0103] ③ Based on the association rule mining algorithm, analyze the frequent item sets of co-occurrence of devices in the configuration file to determine the potential connection relationship between the various electrical components;

[0104] ④ Combining the physical connection path, the logical communication link and the potential connection relationship, generate the connection relationship of each electrical component.

[0105] Specifically, when parsing the configuration file, device and connection information is converted into a graph structure. Each electrical component, such as a circuit breaker, relay, or intelligent electronic device (IED), is abstracted as a node in the graph. Node attributes include the device's name, model, and parameters, extracted from the device description portion of the configuration file. Physical cables or logical communication links connecting devices are abstracted as edges, whose attributes record parameters such as the connection type (e.g., cable connection, fiber optic connection), transmission rate (for communication links), and resistance (for cables). In the SCD file, node and edge information is determined by parsing relevant tags and attributes, constructing a graph structure that reflects the connection status of electrical components.

[0106] A graph search algorithm, such as breadth-first search (BFS), is used to traverse the graph structure. Starting from a starting node, all adjacent nodes are visited, followed by their adjacent nodes, exploring the network layer by layer. During the exploration process, the nodes and edges traversed are recorded to parse the physical connection paths and logical communication links between electrical components. Analyzing physical connections reveals the paths of power transmission; analyzing logical connections reveals the hierarchy and scope of signal transmission, identifying the data transmission links between different devices.

[0107] The physical connection paths and logical communication links obtained through the graph search algorithm are integrated with the potential connection relationships determined by the association rule mining algorithm. The potential connection relationships serve as supplementary connection information, along with the physical and logical connection relationships, to fully describe the connections between each electrical component. The resulting connection relationships comprehensively cover both actual and potential connections between electrical components, providing a comprehensive and accurate connection information foundation for analysis, fault diagnosis, and operation and maintenance management of substation secondary systems.

[0108] In some embodiments of the present application, step S5, the process of using digital twin technology to establish a global simulation model based on the time impact factor, the spatial impact factor, the feature information, the hierarchical relationship, and the connection relationship is introduced, which may specifically include:

[0109] Step S51: Establish a BIM model of the substation secondary system.

[0110] Specifically, the size, shape, and location of each electrical component are accurately acquired. This information is typically sourced from substation design drawings, equipment manuals, or on-site survey data. Each electrical component is then presented in a virtual environment as a 3D entity. For example, for a transformer, a 3D model is constructed based on its actual dimensions, including precise modeling of components such as the oil tank, windings, and bushings. These components are then placed according to their actual installation locations within the substation.

[0111] At the same time, detailed attribute information is assigned to each electrical component. These attributes encompass previously extracted characteristic information, such as device model, rated parameters, manufacturer, and device serial number. For example, for intelligent electronic devices (IEDs), not only are technical parameters such as hardware configuration and communication protocol recorded, but management information such as device procurement time and maintenance records can also be added. This approach ensures that BIM models not only have an intuitive visual appearance but also contain rich business data, providing a solid data foundation for subsequent analysis and application.

[0112] Step S52: weighting and integrating the time impact factor and the space impact factor into the BIM model to dynamically map the equipment status.

[0113] Specifically, because the time and space influencing factors have different degrees of influence on device status, their respective weights need to be determined based on actual conditions. There are multiple ways to determine weights. Based on practical experience and professional knowledge, the time and space influences of different types of equipment can be evaluated to determine weights. Alternatively, historical data can be statistically analyzed to collect a large amount of operating data from equipment under different time and space conditions. Statistical methods can be used to analyze the effects of time and space factors on device status and determine weights. Machine learning algorithms, such as neural networks and decision trees, can also be used to learn and train historical data and automatically optimize weight parameters to obtain more accurate weight distribution.

[0114] For example, for devices that are sensitive to time factors, such as capacitors, their performance will gradually decline over time. In this case, the weight of the time impact factor can be appropriately increased. For devices that are significantly affected by spatial layout and electromagnetic interference, such as high-frequency communication equipment, it is more appropriate to increase the weight of the space impact factor. After determining the weights, the time impact factor and the space impact factor are integrated according to the corresponding weights to obtain a comprehensive impact factor.

[0115] Next, this comprehensive influencing factor is associated with each electrical component in the BIM model. The specific implementation method can be to add the comprehensive influencing factor as a new attribute to the attribute information of the electrical component, or to map it to the status parameters of the equipment through a specific algorithm. In the BIM model, dynamic mapping of the equipment status is achieved based on the integrated influencing factor. When the comprehensive influencing factor changes, the status display of the equipment is adjusted in real time. If the comprehensive influencing factor increases, it indicates that the equipment may be in a more dangerous operating state. At this time, the color of the equipment model can be changed, such as changing the green color during normal operation to orange or red; adjusting the transparency of the equipment model to make the equipment in an abnormal state more prominent; or adding warning signs, such as flashing triangle icons, to intuitively display the changes in equipment status. At the same time, the dynamic changes in equipment status are continuously compared and verified with real-time monitoring data, and the mapping relationship is continuously optimized to improve the accuracy and reliability of the model and provide operation and maintenance personnel with more accurate equipment status information.

[0116] Step S53: Dynamically evolve the BIM model according to the feature information, the hierarchical relationship, and the connection relationship to generate a global simulation model.

[0117] Specifically, feature information contains rich attributes of electrical components and is an important basis for driving the dynamic evolution of BIM models. Taking different models of circuit breakers as an example, their breaking capacity, operation time, and other characteristics vary. During the dynamic evolution of the model, these characteristics determine the response characteristics of the circuit breaker in the event of a fault. The unique identifier of the device is used as the node identifier to ensure that each component can be accurately distinguished and located throughout the model. At the same time, the key characteristic parameters of the component are stored as node attributes for calculation and analysis during the dynamic evolution process. For equipment with complex functions, such as protection devices in substations, nodes are further refined according to their protection function modules. For example, a comprehensive protection device includes an overcurrent protection module, a differential protection module, etc. Each module can be used as a child node. They are connected to the main node of the protection device through specific association relationships, together forming a complete functional node system, which more accurately reflects the functional hierarchy and relationships within the device.

[0118] The BIM model is hierarchically managed and dynamically updated based on a three-level hierarchy: station, bay, and equipment. The station level, as the highest level, represents the macroscopic view of the entire substation and summarizes key substation information, such as the total capacity and incoming line voltage level. When changes occur at the station level, such as fluctuations in incoming line voltage, these changes are propagated to the bay and equipment levels according to the hierarchical relationship. The bay level, as an intermediate level, divides the substation into different functional areas. Each bay corresponds to a child node in the model and is connected to the station-level root node. Bay-level nodes store information such as the bay's functional type and the equipment it contains. For example, a transmission bay node records the voltage level it transmits and the connected lines. When equipment within a bay fails or its operating status changes, the bay-level node is promptly updated and the relevant information is fed back to the station level, impacting the equipment level. At the equipment level, as the lowest level, each device corresponds to a leaf node in the model, connected to its bay-level node. Device-level nodes record detailed information about the device's real-time operating parameters, device status, and connections to other devices. Through this hierarchical structure, the architectural changes of the entire substation from macro to micro can be clearly presented, providing an orderly framework for the dynamic evolution of the model.

[0119] Connection relationships include physical and logical connections, which determine how devices in the model interact and influence each other. For physical connections, such as cable connections, edges are created in the model to connect the corresponding device nodes, and parameters such as the cable model, length, resistance, and current carrying capacity are recorded. When a short circuit occurs on a line, the magnitude and propagation path of the fault current are calculated based on the cable's resistance and current carrying capacity, combined with the connection relationships. This in turn affects the status of connected devices, such as causing circuit breakers to trip or protective devices to operate. These changes are reflected in real time in the BIM model. For logical connections, such as communication link connections, edges are similarly created in the model to connect the relevant device nodes, and information such as communication protocol, transmission rate, and latency is recorded. When a communication link fails, these properties are used to simulate the impact of data transmission interruptions or delays on the control and monitoring functions of the relevant devices, enabling the BIM model to accurately demonstrate the impact of logical connection failures on the entire system.

[0120] In addition, the impact of potential connection relationships on the dynamic evolution of the model is taken into account. In the topological structure, potential connection relationships connect corresponding device nodes with edges and give them unique visual identifiers, such as setting potential connection edges as dotted lines. Use numerical values to quantify the closeness of potential associations between devices. By analyzing a large amount of historical data, statistical methods or machine learning algorithms are used to obtain the association strength value. The conditions for the activation of potential connection relationships are recorded in detail. For example, for potential connections formed by spatial heat conduction, the trigger condition may be that the ambient temperature of the device exceeds a certain threshold, or the temperature of the device itself rises sharply in a short period of time. When the corresponding trigger condition is met, the spread of the fault is simulated through the potential connection edge. For example, the heat generated by the overheating fault of the equipment affects nearby equipment through the potential connection relationship of air convection. According to the association strength and trigger conditions recorded by the potential connection edge, the amplitude and time of the temperature increase of the affected equipment are calculated, and then the state parameters of these equipment are updated to realize the propagation simulation of the fault in the BIM model.

[0121] By integrating these characteristic information, hierarchical relationships, and connectivity, the BIM model dynamically evolves, enabling it to reflect real-time operational changes in the substation's secondary system. Ultimately, a global simulation model based on digital twin technology is generated. This model not only offers a high degree of visualization but also accurately simulates system operation under various circumstances, providing powerful support for substation operations and maintenance, fault prediction, and decision-making analysis.

[0122] A substation secondary system modeling device provided in an embodiment of the present application is described below. The substation secondary system modeling device described below and the substation secondary system modeling method described above can refer to each other.

[0123] See also Figure 2 , Figure 2 This is a schematic diagram of a substation secondary system modeling device disclosed in an embodiment of the present application.

[0124] like Figure 2 As shown, the substation secondary system modeling device may include:

[0125] A configuration file unit 110 is used to obtain a configuration file of the substation secondary system and extract characteristic information, hierarchical relationships and connection relationships of each electrical component from the configuration file;

[0126] The historical information unit 120 is configured to obtain historical information of the substation, integrate the historical information according to the characteristic information, the hierarchical relationship, and the connection relationship, and generate a historical information time series, wherein the historical information time series records the integrated historical information arranged in chronological order;

[0127] A time factor unit 130 is used to input the historical information time series into a long short-term memory network to obtain a time impact factor;

[0128] A spatial factor unit 140 is configured to input the feature information, the hierarchical relationship, and the connection relationship into a multiple regression model to obtain a spatial impact factor;

[0129] The model building unit 150 is used to use digital twin technology to establish a global simulation model based on the time influence factor, the space influence factor, the feature information, the hierarchical relationship and the connection relationship.

[0130] It can be seen from the above technical solution that the embodiment of the present application provides a substation secondary system modeling method and related equipment, which first extracts the characteristic information, hierarchical relationship and connection relationship of electrical components from the substation secondary system configuration file to fully grasp the system structure; then combines the substation historical information to generate a historical information time series; then uses the long short-term memory network and the multivariate regression model to respectively mine the time influencing factors and the spatial influencing factors; finally, establishes a global simulation model based on digital twin technology.

[0131] This application extracts configuration file information and integrates historical data to generate time series, deeply mines equipment operation data, and comprehensively presents the overall picture of equipment operation, thus solving the problem of insufficient data integration. In terms of model construction, time influencing factors and space influencing factors are used to fully consider the time dimension and spatial relationship of equipment operation, accurately simulate the equipment status, and effectively correct the simulation deviation caused by not considering the complex operating environment and equipment interaction relationship. For the information delay and loss problems in data update and transmission, the mechanism of real-time acquisition and analysis of data ensures the real-time interactivity of the model, greatly reduces information delay, and ensures the synchronization of virtual model and actual equipment. In terms of model adaptability, the optimized global simulation model achieves lightweight and good compatibility, and can be flexibly applied between different hardware devices and software platforms to meet the needs of diverse operation and maintenance scenarios, thereby realizing proactive operation and maintenance decision-making, effectively improving the efficiency and safety of substation operation and maintenance, and providing reliable technical support for the operation and maintenance of smart grid substation secondary systems.

[0132] Optionally, the acquiring of historical information of the substation, integrating the historical information according to the characteristic information, the hierarchical relationship, and the connection relationship, and generating a time series of historical information includes:

[0133] Acquire historical information of the substation, and perform data association with the characteristic information to generate associated historical information;

[0134] Based on the hierarchical relationship and the connection relationship, data integration is performed on the associated historical information to obtain integrated historical information;

[0135] The integrated historical information is arranged in chronological order using the timestamp as an index to generate a historical information time series.

[0136] Optionally, extracting characteristic information, hierarchical relationships, and connection relationships of each electrical component from the configuration file includes:

[0137] Extracting characteristic information of each electrical component from the configuration file according to an XML parsing algorithm and a regular expression matching algorithm;

[0138] extracting the hierarchical relationship of each electrical component from the configuration file according to a tree traversal algorithm;

[0139] The connection relationship of each electrical component is extracted from the configuration file according to a graph search algorithm and an association rule mining algorithm.

[0140] Optionally, extracting characteristic information of each electrical component from the configuration file according to an XML parsing algorithm and a regular expression matching algorithm includes:

[0141] Read the configuration file according to the XML parsing algorithm, and extract structured data in the configuration file by traversing the document tree structure;

[0142] Using a regular expression matching algorithm to match and extract unstructured data in the configuration file;

[0143] The extracted structured data and unstructured data are cleaned and structurally integrated to obtain characteristic information of each electrical component.

[0144] Optionally, extracting the hierarchical relationship of each electrical component from the configuration file according to a tree traversal algorithm includes:

[0145] Parsing the configuration file into a tree data structure, and identifying station-level nodes, interval-level nodes, and device-level nodes through a tree traversal algorithm;

[0146] Based on the parent-child relationship between nodes, a three-level hierarchical structure including stations, intervals and devices is constructed, wherein the station-level node is the root node, the interval-level node is the child node of the station-level node, and the device-level node is the child node of the interval-level node;

[0147] The hierarchical identification and association relationship of each node in the three-level hierarchical structure are stored to generate a hierarchical relationship of electrical components.

[0148] Optionally, extracting the connection relationship of each electrical component from the configuration file according to a graph search algorithm and an association rule mining algorithm includes:

[0149] Mapping the device and connection information in the configuration file into a graph structure, where nodes in the graph structure represent electrical components, edges represent physical connections or logical connections, and recording attribute parameters of the connections;

[0150] Traversing the graph structure using a graph search algorithm, parsing the physical connection paths and logical communication links of each electrical component layer by layer;

[0151] Analyzing the frequent item sets of co-occurrence of devices in the configuration file based on an association rule mining algorithm to determine the potential connection relationship between the electrical components;

[0152] The connection relationship of each electrical component is generated by combining the physical connection path, the logical communication link and the potential connection relationship.

[0153] Optionally, the digital twin technology is used to establish a global simulation model based on the time influence factor, the space influence factor, the feature information, the hierarchical relationship, and the connection relationship, including:

[0154] Establish a BIM model of the substation secondary system;

[0155] Integrating the time impact factor and the space impact factor into the BIM model in a weighted manner to dynamically map the equipment status;

[0156] The BIM model is dynamically evolved according to the feature information, the hierarchical relationship and the connection relationship to generate a global simulation model.

[0157] The substation secondary system modeling device provided in the embodiment of the present application can be applied to substation secondary system modeling equipment. Figure 3 The hardware structure diagram of the substation secondary system modeling equipment is shown. Figure 3 ,The hardware structure of the substation secondary system modeling device may include: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4;

[0158] In the embodiment of the present application, the number of the processor 1, the communication interface 2, the memory 3, and the communication bus 4 is at least one, and the processor 1, the communication interface 2, and the memory 3 communicate with each other through the communication bus 4;

[0159] The processor 1 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention;

[0160] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory;

[0161] The memory stores a program, and the processor can call the program stored in the memory, wherein the program is used to:

[0162] Obtaining a configuration file of the substation secondary system, and extracting characteristic information, hierarchical relationships, and connection relationships of each electrical component from the configuration file;

[0163] Acquire historical information of the substation, integrate the historical information according to the characteristic information, the hierarchical relationship, and the connection relationship, and generate a historical information time series, wherein the historical information time series records the integrated historical information arranged in chronological order;

[0164] Inputting the historical information time series into a long short-term memory network to obtain a time impact factor;

[0165] Inputting the feature information, the hierarchical relationship and the connection relationship into a multiple regression model to obtain a spatial impact factor;

[0166] Digital twin technology is used to establish a global simulation model based on the time influence factor, the space influence factor, the feature information, the hierarchical relationship and the connection relationship.

[0167] Optionally, the refined functions and extended functions of the program may refer to the above description.

[0168] The present application also provides a readable storage medium, which may store a program suitable for execution by a processor, wherein the program is used to:

[0169] Obtaining a configuration file of the substation secondary system, and extracting characteristic information, hierarchical relationships, and connection relationships of each electrical component from the configuration file;

[0170] Acquire historical information of the substation, integrate the historical information according to the characteristic information, the hierarchical relationship, and the connection relationship, and generate a historical information time series, wherein the historical information time series records the integrated historical information arranged in chronological order;

[0171] Inputting the historical information time series into a long short-term memory network to obtain a time impact factor;

[0172] Inputting the feature information, the hierarchical relationship and the connection relationship into a multiple regression model to obtain a spatial impact factor;

[0173] Digital twin technology is used to establish a global simulation model based on the time influence factor, the space influence factor, the feature information, the hierarchical relationship and the connection relationship.

[0174] Optionally, the refined functions and extended functions of the program may refer to the above description.

[0175] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprise," "include," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a set of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

[0176] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0177] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.< / ied> < / bay> < / bay> < / substation> < / ied> < / bay> < / substation> < / current> < / voltage> < / ied> < / ied> < / ied> < / bay> < / bay> < / substation>

Claims

1. A substation secondary system modeling method, characterized in that: include: Obtaining a configuration file of the substation secondary system, and extracting characteristic information, hierarchical relationships, and connection relationships of each electrical component from the configuration file; Acquire historical information of the substation, integrate the historical information according to the characteristic information, the hierarchical relationship, and the connection relationship, and generate a historical information time series, wherein the historical information time series records the integrated historical information arranged in chronological order; Inputting the historical information time series into a long short-term memory network to obtain a time impact factor; Inputting the feature information, the hierarchical relationship and the connection relationship into a multiple regression model to obtain a spatial impact factor; Digital twin technology is used to establish a global simulation model based on the time influence factor, the space influence factor, the feature information, the hierarchical relationship and the connection relationship.

2. The method according to claim 1, characterized in that The acquiring of historical information of the substation, integrating the historical information according to the characteristic information, the hierarchical relationship and the connection relationship, and generating a time series of historical information includes: Acquire historical information of the substation, and perform data association with the characteristic information to generate associated historical information; Based on the hierarchical relationship and the connection relationship, data integration is performed on the associated historical information to obtain integrated historical information; The integrated historical information is arranged in chronological order using the timestamp as an index to generate a historical information time series.

3. The method according to claim 1, characterized in that The extracting characteristic information, hierarchical relationship and connection relationship of each electrical component from the configuration file includes: Extracting characteristic information of each electrical component from the configuration file according to an XML parsing algorithm and a regular expression matching algorithm; extracting the hierarchical relationship of each electrical component from the configuration file according to a tree traversal algorithm; The connection relationship of each electrical component is extracted from the configuration file according to a graph search algorithm and an association rule mining algorithm.

4. The method according to claim 3, characterized in that Extracting characteristic information of each electrical component from the configuration file according to the XML parsing algorithm and the regularized expression matching algorithm includes: Read the configuration file according to the XML parsing algorithm, and extract structured data in the configuration file by traversing the document tree structure; Using a regular expression matching algorithm to match and extract unstructured data in the configuration file; The extracted structured data and unstructured data are cleaned and structurally integrated to obtain characteristic information of each electrical component.

5. The method according to claim 3, characterized in that Extracting the hierarchical relationship of each electrical component from the configuration file according to the tree traversal algorithm includes: Parsing the configuration file into a tree data structure, and identifying station-level nodes, interval-level nodes, and device-level nodes through a tree traversal algorithm; Based on the parent-child relationship between nodes, a three-level hierarchical structure including stations, intervals and devices is constructed, wherein the station-level node is the root node, the interval-level node is the child node of the station-level node, and the device-level node is the child node of the interval-level node; The hierarchical identification and association relationship of each node in the three-level hierarchical structure are stored to generate a hierarchical relationship of electrical components.

6. The method according to claim 3, characterized in that The method of extracting the connection relationship of each electrical component from the configuration file according to the graph search algorithm and the association rule mining algorithm includes: Mapping the device and connection information in the configuration file into a graph structure, where nodes in the graph structure represent electrical components, edges represent physical connections or logical connections, and recording attribute parameters of the connections; Traversing the graph structure using a graph search algorithm, parsing the physical connection paths and logical communication links of each electrical component layer by layer; Analyzing the frequent item sets of co-occurrence of devices in the configuration file based on an association rule mining algorithm to determine the potential connection relationship between the electrical components; The connection relationship of each electrical component is generated by combining the physical connection path, the logical communication link and the potential connection relationship.

7. The method according to claim 1, characterized in that The digital twin technology is used to establish a global simulation model based on the time influence factor, the space influence factor, the feature information, the hierarchical relationship and the connection relationship, including: Establish a BIM model of the substation secondary system; Integrating the time impact factor and the space impact factor into the BIM model in a weighted manner to dynamically map the equipment status; The BIM model is dynamically evolved according to the feature information, the hierarchical relationship and the connection relationship to generate a global simulation model.

8. A substation secondary system modeling device, characterized in that: include: A configuration file unit is used to obtain a configuration file of the substation secondary system and extract characteristic information, hierarchical relationship and connection relationship of each electrical component from the configuration file; a historical information unit, configured to obtain historical information of the substation, integrate the historical information according to the characteristic information, the hierarchical relationship, and the connection relationship, and generate a historical information time series, wherein the historical information time series records the integrated historical information arranged in chronological order; A time factor unit, used to input the historical information time series into the long short-term memory network to obtain a time impact factor; A spatial factor unit, configured to input the feature information, the hierarchical relationship, and the connection relationship into a multiple regression model to obtain a spatial impact factor; A model building unit is used to use digital twin technology to establish a global simulation model based on the time influence factor, the space influence factor, the feature information, the hierarchical relationship and the connection relationship.

9. A substation secondary system modeling device, characterized in that: including memory and processor; The memory is used to store programs; The processor is configured to execute the program to implement each step of the substation secondary system modeling method according to any one of claims 1 to 7.

10. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the substation secondary system modeling method according to any one of claims 1 to 7 is implemented.

Images