SCADA system label generation method and system based on structured multi-source information fusion

Abstract

The present invention provides a SCADA system label generation method and system based on structured multi-source information fusion, relating to the field of industrial automation and control technology. The method and system first generate an initial information modeling framework containing label names, data types and device association relationships based on the SCADA system architecture; then, a multi-level constraint rule library is established according to the characteristics of the engineering field, and the information modeling framework is parsed through a large language model, and semantic verification is performed in combination with the domain knowledge graph to generate a structured label file that conforms to the SCADA system used; finally, through the application platform of the SCADA system or the construction of a digital twin verification platform including a simulation test environment, the generated labels are injected and tested to verify the field integrity, logical consistency and system compatibility of the label file. This method enables the large language model to adapt to specific industrial control scenarios when processing SCADA system label generation.

Description

Technical Field

[0001] The present invention relates to the field of industrial automation and control technology, and in particular to a SCADA system label generation method and system based on structured multi-source information fusion. Background Art

[0002] As a core component of the industrial control field, the SCADA system (Supervisory Control and Data Acquisition) is widely used for monitoring and controlling critical infrastructure such as power generation and water treatment. The system has basic control functions for controlling predefined settings and is implemented by a distributed database. The database contains data elements called "tags" or "points", each of which represents a single input or output value that is controlled or adjusted in the system. Therefore, tags (points) play a core role in the data flow of the SCADA system. It is not only used to represent the status of each device and sensor in the system, but also for the transmission of alarm, monitoring and control signals. It is an important data structure to ensure stable operation and real-time response of the system. However, the existing SCADA system tag configuration method has the following shortcomings and disadvantages:

[0003] 1. Manual input and batch import are prone to configuration errors: Traditional SCADA system tag configuration methods rely on manual input or batch import of data. While this improves efficiency, it is prone to configuration errors, affecting tag accuracy. Especially in large-scale and complex systems, the risk of manual errors is higher, potentially leading to unstable system operation. Therefore, existing methods lack accuracy and reliability.

[0004] 2. Inability to adapt to complex control logic and large-scale system requirements: With the continuous development of industrial automation technology, the control logic and requirements of SCADA systems are becoming increasingly complex. Traditional tag configuration methods often struggle to quickly adapt to system changes and expansion. While they can meet some basic control requirements, traditional methods lack flexibility and adaptability in complex industrial scenarios, making them difficult to meet the needs of large-scale systems.

[0005] 3. Limitations of the large language model approach: In recent years, generative artificial intelligence models based on natural language processing, such as large language models, have been widely used in tasks such as code generation. However, these large language models face certain challenges when processing complex industrial control instructions. The basic training data of existing large language models is mostly concentrated in general scenarios, and there is still a lack of specialized training for industrial control logic. At the same time, studies have shown that the output results of large language models in specific fields perform poorly and are prone to inaccurate results. The process of configuring SCADA tags through large language models involves complex conditional logic, strict industrial standards, and the relationship between equipment, which puts higher requirements on the training and application of large language models.

[0006] Therefore, the existing technology still has significant deficiencies in the accuracy, adaptability and ability to cope with complex demands of tag configuration. An innovative method is urgently needed to improve the efficiency and flexibility of tag configuration and meet the high standards of tag configuration in modern industrial control systems. Summary of the Invention

[0007] The technical problem to be solved by the present invention is to address the deficiencies of the above-mentioned existing technologies and provide a SCADA system label generation method and system based on structured multi-source information fusion. By constructing an information modeling framework with engineering semantics, introducing multi-dimensional constraints based on domain knowledge, and combining semantic parsing and simulation verification mechanisms, the automation, structuring and verification closed loop of industrial label configuration are realized, thereby improving the overall configuration efficiency and system compatibility.

[0008] To solve the above technical problems, the technical solution adopted by the present invention is as follows: On the one hand, the present invention provides a SCADA system label generation method based on structured multi-source information fusion, comprising:

[0009] Analyze device communication protocols, control logic topology, and data collection frequency based on the SCADA system architecture, and generate an initial information modeling framework that includes tag names, data types, and device associations.

[0010] Establish a multi-level constraint rule base based on engineering domain characteristics. The rule base includes process safety constraints, equipment linkage constraints, and multi-threshold alarm priority constraints. The multi-threshold alarm priority constraints support nonlinear segmented threshold settings.

[0011] The information modeling framework is parsed through a large language model, and semantic verification is performed in combination with a domain knowledge graph to generate a structured tag file that conforms to the SCADA system used. The tag file includes an extensible metadata description layer;

[0012] Through the application platform of the SCADA system or by building a digital twin verification platform that includes a simulation test environment, the generated tags are injected and tested to verify the field integrity, logical consistency and system compatibility of the tag files.

[0013] Furthermore, the method further includes: optimizing the generated information modeling framework through a feedback mechanism, and correcting defects in the information modeling framework until the generated label file meets the requirements.

[0014] Furthermore, the generation of the initial information modeling framework includes:

[0015] Establish a standard tag information modeling framework that includes a device type ontology library. The information modeling framework integrates an automatic data type matching algorithm and supports dynamic precision configuration of floating-point numbers, Boolean quantities, and timestamps.

[0016] The device relationship map construction module is introduced to automatically generate a device association matrix by parsing the P&ID diagram or electrical single-line diagram. The matrix supports the pre-definition of the device fault propagation path;

[0017] The alarm rule configuration interface allows users to define the alarm delay time, confirmation mechanism and notification level through a visual interface. The multi-threshold alarm uses a sliding window algorithm for dynamic baseline calculation.

[0018] Furthermore, the multi-level constraint rule library established according to the characteristics of the engineering field includes:

[0019] Process safety constraints: Establish parameter boundary conditions based on HAZOP analysis results and automatically associate logical nodes of the safety instrumented system (SIS);

[0020] Equipment linkage constraints: Generate linkage rule tables by analyzing equipment interlocking logic, supporting cascade alarm settings across control loops;

[0021] Alarm priority constraint: Fuzzy logic algorithm is used to automatically adjust the alarm level according to process impact and frequency of occurrence to generate a dynamic priority queue.

[0022] Furthermore, the structured tag file generation process includes:

[0023] Domain knowledge injection: Integrate industry-specific terminology libraries and engineering standards, and enhance the large language model's understanding of professional terminology through the attention mechanism;

[0024] Automatic verification: Use the abstract syntax tree (AST) to perform syntax checking on the generated tags, and combine it with the data dictionary to verify semantic consistency;

[0025] Version control: Hash verification is performed on each generated tag file, supporting multi-version comparison and rollback operations.

[0026] Furthermore, the injection test of the generated tags to verify the field integrity, logical consistency and system compatibility of the tag file includes:

[0027] Digital simulation verification: Verify and stress test tag files by simulating the SCADA system application platform or establishing a simulation environment that runs synchronously with the physical SCADA system;

[0028] Compatibility testing: Automatically check the compatibility between the tag and the configuration software, historical database and human-machine interface interface;

[0029] Intelligent feedback: Dynamically adjust the prompt word weights of the large language model based on verification results, and optimize the label generation strategy through reinforcement learning.

[0030] On the other hand, the present invention also provides a SCADA system label generation system based on structured multi-source information fusion, comprising:

[0031] Information modeling unit, used to generate a structured information modeling framework based on the SCADA system architecture and equipment characteristics;

[0032] Constraint rule configuration unit, supporting the regular expression and storage of multi-domain expert knowledge;

[0033] Intelligent generation unit, integrating large language models with domain knowledge graphs for collaborative reasoning and generating SCADA system labels;

[0034] Verify and optimize the unit and build a closed-loop test environment to achieve automatic verification and iterative optimization of tags.

[0035] Furthermore, the intelligent generation unit further includes:

[0036] Context-aware module, used to parse device context and automatically complete associated tags;

[0037] Multimodal output module supports the generation of label formats that meet the requirements of different SCADA systems;

[0038] Security enhancement module with built-in data desensitization algorithm to ensure the secure processing of sensitive information.

[0039] In a third aspect, the present invention further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the SCADA system label generation method based on structured multi-source information fusion.

[0040] In a fourth aspect, the present invention further provides a SCADA system engineering implementation system, which integrates a SCADA device that includes the SCADA system label generation method based on structured multi-source information fusion, and is configured with:

[0041] Engineering configuration interface supports multi-user collaborative label design;

[0042] The label lifecycle management module records the label version iteration and verification history;

[0043] System compatibility database, storing technical specifications and interface documents of different SCADA systems.

[0044] The beneficial effects of adopting the above-mentioned technical solution are as follows: the SCADA system label generation method and system based on structured multi-source information fusion provided by the present invention reduces errors caused by manual operation by combining structured information modeling with a large language model to generate label files; the guidance of the structured information modeling framework makes the label generation process more standardized and automated, thereby improving the accuracy of generated labels. Through the structured information modeling framework, complex control logic and device relationships are incorporated into the label generation process, allowing the label generation process to be customized and adjusted according to actual needs, thereby better adapting to system changes and expansion requirements when faced with complex control logic and large-scale systems.

[0045] By optimizing the information modeling framework, the large language model can adapt to specific industrial control scenarios when processing SCADA system label generation. The structured information modeling framework helps the large language model better understand and handle complex conditional logic, strict industrial standards, and inter-device relationships. This overcomes the limitations of existing large language models in specific application areas and improves the accuracy and professionalism of label generation.

[0046] This invention provides new insights into the practical application of large language models in industrial control systems and lays a solid foundation for the future development of industrial intelligence driven by large language models. By optimizing prompting strategies, this invention promotes the application of large language models in specific industrial fields, demonstrates their potential to improve the efficiency and accuracy of SCADA tag generation, and opens a new path for the development of industrial intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a flowchart of the SCADA system label generation method based on structured multi-source information fusion provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0048] The following embodiments of the present invention are described in further detail with reference to the accompanying drawings and examples. The following examples are used to illustrate the present invention but are not intended to limit the scope of the present invention.

[0049] Example 1:

[0050] In this embodiment, a SCADA system label generation method based on structured multi-source information fusion is described. Figure 1 Shown, including:

[0051] Step S1: Analyze the device communication protocol, control logic topology, and data acquisition frequency based on the SCADA system architecture to generate an initial information modeling framework containing tag names, data types, and device association relationships, specifically including:

[0052] Establish a standard tag information modeling framework that includes a device type ontology library. The information modeling framework integrates an automatic data type matching algorithm and supports dynamic precision configuration of floating-point numbers, Boolean quantities, and timestamps.

[0053] The device relationship map construction module is introduced to automatically generate a device association matrix by parsing the P&ID diagram or electrical single-line diagram. The matrix supports the pre-definition of the device fault propagation path;

[0054] The alarm rule configuration interface allows users to define the alarm delay time, confirmation mechanism and notification level through a visual interface. The multi-threshold alarm uses a sliding window algorithm for dynamic baseline calculation.

[0055] In this embodiment, the generation of an information modeling framework first requires clarifying the basic requirements for SCADA system tag generation. Based on the specific SCADA system requirements, the necessary specifications for tag generation are provided. At this point, the information modeling framework will include core tag attributes, such as tag name and data type. The goal of this requirements analysis is to ensure that the foundational content of the information modeling framework covers the most basic information required for tag generation.

[0056] Step S2: Establish a multi-level constraint rule base based on engineering domain characteristics, the rule base includes process safety constraints, equipment linkage constraints and multi-threshold alarm priority constraints, wherein the multi-threshold alarm priority constraints support nonlinear segmented threshold setting;

[0057] Among them, process safety constraints: establish parameter boundary conditions based on HAZOP analysis results and automatically associate logical nodes of the safety instrumented system SIS;

[0058] Equipment linkage constraints: Generate linkage rule tables by analyzing equipment interlocking logic, supporting cascade alarm settings across control loops;

[0059] Alarm priority constraint: Fuzzy logic algorithm is used to automatically adjust the alarm level according to process impact and frequency of occurrence to generate a dynamic priority queue.

[0060] The establishment of a multi-level constraint rule base ensures that the generated tags meet the specific control requirements of the SCADA system, such as joint control of multiple devices or setting complex alarm logic. By introducing these constraints, the generated tags are guaranteed to reflect the complex control requirements of the SCADA system.

[0061] Step S3: parse the information modeling framework through a large language model, perform semantic verification in combination with the domain knowledge graph, and generate a structured tag file that conforms to the SCADA system used. The tag file contains an extensible metadata description layer, specifically including:

[0062] Domain knowledge injection: Integrate industry-specific terminology libraries and engineering standards, and enhance the large language model's understanding of professional terminology through the attention mechanism;

[0063] Automatic verification: Use the abstract syntax tree (AST) to perform syntax checking on the generated tags, and combine it with the data dictionary to verify semantic consistency;

[0064] Version control: Hash verification is performed on each generated tag file, supporting multi-version comparison and rollback operations.

[0065] Step S4: Perform an injection test on the generated tags through the SCADA system application platform or by building a digital twin verification platform that includes a simulation test environment to verify the field integrity, logical consistency, and system compatibility of the tag file, including:

[0066] Digital simulation verification: Verify and stress test tag files by using the simulation test function of the SCADA system application platform or by establishing a simulation environment that runs synchronously with the physical SCADA system;

[0067] Compatibility testing: Automatically check the interface compatibility between the tag and the configuration software, historical database and human-machine interface (HMI);

[0068] Intelligent feedback: Dynamically adjust the prompt word weights of the large language model based on verification results, and optimize the label generation strategy through reinforcement learning.

[0069] Through simulation testing, we can ensure that the generated tags can correctly respond to the control requirements of the system, such as alarm triggering or device linkage operation. If the verification results meet the predetermined goals, the tag generation is completed; if the results do not meet the requirements, prompt optimization;

[0070] Step S5: Optimize the generated information modeling framework through a feedback mechanism and correct defects in the information modeling framework until the generated label file meets the requirements.

[0071] After label generation and verification, if any issues are found (such as inaccurate labels, logical errors, or discrepancies with initial requirements), the generated prompt content is optimized through a feedback mechanism. This feedback is used to adjust the specific content of the information modeling framework and correct any vulnerabilities or errors. This optimization process aims to gradually refine label generation through iterative optimization, ensuring that subsequently generated labels fully meet expectations.

[0072] Example 2:

[0073] In this embodiment, the SCADA system label generation system based on structured multi-source information fusion includes:

[0074] An information modeling generation unit, used to generate a structured information modeling framework based on the SCADA system architecture and equipment characteristics;

[0075] Constraint rule configuration unit, supporting the regular expression and storage of multi-domain expert knowledge;

[0076] Intelligent generation unit, integrating large language models with domain knowledge graphs for collaborative reasoning and generating SCADA system labels;

[0077] Verify and optimize the unit and build a closed-loop test environment to achieve automatic verification and iterative optimization of tags.

[0078] Wherein, the intelligent generation unit further includes:

[0079] Context-aware module, used to parse device context and automatically complete associated tags;

[0080] Multimodal output module supports the generation of label formats that meet the requirements of different SCADA systems;

[0081] Security enhancement module with built-in data desensitization algorithm to ensure the secure processing of sensitive information.

[0082] Example 3:

[0083] This embodiment provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the method for generating labels for a SCADA system based on structured multi-source information fusion is implemented.

[0084] Example 4:

[0085] This embodiment provides a SCADA system engineering implementation system, which integrates the SCADA device for generating SCADA system labels based on structured multi-source information fusion, and is configured with:

[0086] Engineering configuration interface supports multi-user collaborative label design;

[0087] The label lifecycle management module records the label version iteration and verification history;

[0088] System compatibility database, storing technical specifications and interface documents of different SCADA systems.

[0089] Example 5:

[0090] This example is based on the task of building labels for a SCADA system in a power automation plant. It demonstrates the application process of the SCADA system label generation method based on structured multi-source information fusion proposed in this invention in engineering. Specifically, it includes:

[0091] 1. Information modeling framework generation stage;

[0092] First, the OPC communication identifiers, update frequencies, and naming conventions of the plant equipment are extracted to provide a brief description for the large language model, laying the foundation for subsequent tag generation and ensuring that the generated tag files have basic structure and functionality. Then, by importing the plant's P&ID drawings and calling the Equipment Relationship Graph Builder module, an equipment association matrix is ​​automatically generated, showing the relationships between boilers, sensors, and valves.

[0093] During this phase, the specific requirements of the SCADA system need to be determined, the basic information for generating tags needs to be defined, and a preliminary information modeling framework needs to be established. For example, "Ensure that file field names use camelCase format and field values ​​use PascalCase format."

[0094] 2. Multi-level constraint rule library construction stage;

[0095] At this stage, it is necessary to further provide more complex control logic and constraints for the large language model based on the actual operating logic of the plant to ensure that the generated tags can accurately reflect the control needs of the SCADA system and meet the control logic and alarm requirements of the SCADA system.

[0096] Additional constraints are added to the information modeling framework at this stage.

[0097] Specifically, based on the information modeling framework constructed in the demand clarification stage, constraints such as multi-threshold alarms, relationships between devices, and complex control logic are introduced.

[0098] For example, based on alarm frequency analysis and combined with logical rules to set dynamic changes in alarm levels, and give priority to responding to variables with high process impact, an alarm constraint can be added to the information modeling framework: "The alarm is triggered only when the temperature of device A exceeds the set threshold and the temperature of device B exceeds the set threshold."

[0099] By introducing these logics and constraints, we ensure that the generated tags not only meet basic requirements but also adapt to the complex control relationships and alarm requirements involved in the SCADA system.

[0100] 3. Semantic generation and label construction stage;

[0101] In this phase, the information modeling framework, combined with natural language templates, is fed into the Qwen 2.5 large language model deployed on a local server. After receiving the content, the model generates a preliminary tag structure, outputting it in a JSON format. Each tag record contains basic elements such as field name, type, unit, alarm condition, and threshold.

[0102] Through the operations in this stage, the tags required by the SCADA system can be automatically generated through structured prompts and model assistance, providing a usable initial file basis for the subsequent verification and analysis stage.

[0103] 4. Verification and analysis phase;

[0104] At this stage, the generated tags are tested through format checking + SCADA simulation to verify whether the generated tags can accurately respond to control requirements.

[0105] If the verification results meet the predetermined requirements, it is considered that an information modeling framework that meets the needs is obtained; if problems occur, the optimization phase is entered.

[0106] This embodiment uses a large language model combined with an information modeling framework to generate SCADA tag files. The generated tag files are then inspected and semantically verified to determine if the generated tag fields are accurate, such as whether the data type and alarm conditions meet the requirements. The tag files are then imported into the SCADA system for simulation testing to verify whether the generated tags can accurately respond to control requirements, such as triggering alarms and executing device linkage functions. If the verification results meet the predetermined requirements, the information modeling framework is considered to have been obtained; if any problems arise, the feedback optimization phase begins.

[0107] 5. Feedback optimization stage;

[0108] The feedback optimization phase mainly uses the feedback mechanism to optimize the information modeling framework and correct problems in the label generation process. The specific steps include:

[0109] First, analyze the gap between the generated labels and the actual requirements to find out the missing fields or logical errors in the labels;

[0110] Secondly, modify the constraints or tag definitions in the information modeling framework to ensure that the generated tags fully meet the requirements of the SCADA system;

[0111] Finally, multiple rounds of iterative optimization are performed. After each optimization, defects in the information modeling framework are corrected through feedback until the generated label file fully meets the requirements.

[0112] The goal of this phase is to gradually improve the information modeling framework through repeated iterations, thereby ensuring that the labels generated by the large language model can accurately meet the actual needs of the SCADA system.

[0113] In this embodiment, the information modeling framework is optimized and iterated by using a SCADA system label generation method based on structured multi-source information fusion. Each round of optimization and adjustment enables the information modeling framework to be continuously improved. The final information modeling framework can efficiently generate label files that meet industrial needs by combining natural language with a large language model.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some or all of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope defined by the claims of the present invention.

Claims

1. A SCADA system label generation method based on structured multi-source information fusion, characterized by: include: Analyze device communication protocols, control logic topology, and data collection frequency based on the SCADA system architecture, and generate an information modeling framework that includes tag names, data types, and device associations. A multi-level constraint rule base is established based on the characteristics of the engineering field, and additional constraints are added to the information modeling framework to provide control logic and constraints for the large language model. The rule base includes process safety constraints, equipment linkage constraints, and multi-threshold alarm priority constraints, where the multi-threshold alarm priority constraints support nonlinear segmented threshold settings. The information modeling framework is parsed through a large language model, and semantic verification is performed in combination with a domain knowledge graph to generate a structured tag file that conforms to the SCADA system used. The tag file includes an extensible metadata description layer; Domain knowledge injection: Integrate industry-specific terminology libraries and engineering standards, and enhance the large language model's understanding of professional terminology through the attention mechanism. The information modeling framework is combined with natural language templates and input into the large language model. After the model receives the content, it generates a preliminary tag structure. Automatic verification: Use the abstract syntax tree (AST) to perform syntax checking on the generated tags, and combine it with the data dictionary to verify semantic consistency; Version control: Hash verification is performed on each generated tag file, supporting multi-version comparison and rollback operations; Through the application platform of the SCADA system or by building a digital twin verification platform that includes a simulation test environment, the generated tags are injected and tested to verify the field integrity, logical consistency and system compatibility of the tag files.

2. The SCADA system label generation method based on structured multi-source information fusion according to claim 1, characterized in that: The method further includes: optimizing the generated information modeling framework through a feedback mechanism, and correcting defects in the information modeling framework until the generated label file meets the requirements.

3. The SCADA system label generation method based on structured multi-source information fusion according to claim 2, characterized in that: The generation of the information modeling framework includes: Establish a standard tag information modeling framework that includes a device type ontology library. The information modeling framework integrates an automatic data type matching algorithm and supports dynamic precision configuration of floating-point numbers, Boolean quantities, and timestamps. The device relationship map construction module is introduced to automatically generate a device association matrix by parsing the P&ID diagram or electrical single-line diagram. The matrix supports the pre-definition of the device fault propagation path; The alarm rule configuration interface allows users to define the alarm delay time, confirmation mechanism and notification level through a visual interface. The multi-threshold alarm uses a sliding window algorithm for dynamic baseline calculation.

4. The SCADA system label generation method based on structured multi-source information fusion according to claim 3 is characterized in that: The multi-level constraint rule library established according to the characteristics of the engineering field includes: Process safety constraints: Establish parameter boundary conditions based on HAZOP analysis results and automatically associate logical nodes of the safety instrumented system (SIS); Equipment linkage constraints: Generate linkage rule tables by analyzing equipment interlocking logic, supporting cascade alarm settings across control loops; Alarm priority constraint: Fuzzy logic algorithm is used to automatically adjust the alarm level according to process impact and frequency of occurrence to generate a dynamic priority queue.

5. The SCADA system label generation method based on structured multi-source information fusion according to claim 4 is characterized in that: The injection test of the generated tags to verify the field integrity, logical consistency and system compatibility of the tag file includes: Digital simulation verification: Verify and stress test tag files by simulating the SCADA system application platform or establishing a simulation environment that runs synchronously with the physical SCADA system; Compatibility testing: Automatically check the compatibility between the tag and the configuration software, historical database and human-machine interface interface; Intelligent feedback: Dynamically adjust the prompt word weights of the large language model based on verification results, and optimize the label generation strategy through reinforcement learning.

6. A SCADA system label generation system based on structured multi-source information fusion, implemented based on the SCADA system label generation method based on structured multi-source information fusion according to claim 1, characterized in that: include: Information modeling unit, used to generate a structured information modeling framework based on the SCADA system architecture and equipment characteristics; Constraint rule configuration unit, supporting the regular expression and storage of multi-domain expert knowledge; Intelligent generation unit, integrating large language models with domain knowledge graphs for collaborative reasoning and generating SCADA system labels; Verify and optimize the unit and build a closed-loop test environment to achieve automatic verification and iterative optimization of tags.

7. The SCADA system label generation system based on structured multi-source information fusion according to claim 6, characterized in that: The intelligent generation unit further comprises: Context-aware module, used to parse device context and automatically complete associated tags; Multimodal output module supports the generation of label formats that meet the requirements of different SCADA systems; Security enhancement module with built-in data desensitization algorithm to ensure the secure processing of sensitive information.

8. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the method for generating labels for a SCADA system based on structured multi-source information fusion according to claim 1 is implemented.

9. A SCADA system engineering implementation system, integrating a SCADA device of the SCADA system label generation method based on structured multi-source information fusion according to claim 1, and configured with: Engineering configuration interface supports multi-user collaborative label design; The tag lifecycle management module records the tag version iteration and verification history; System compatibility database, storing technical specifications and interface documents of different SCADA systems.

Images