High-speed rail electromagnetic compatibility intelligent analysis system and construction method thereof
Through deep learning and knowledge graphs and other technologies, an intelligent analysis system for high-speed rail electromagnetic compatibility was built, which solved the systematization problem of electromagnetic compatibility research in high-speed rail system, improved analysis efficiency and accuracy, improved electromagnetic compatibility performance, and ensured the safety of high-speed rail system Sex and stability.
Patent Information
- Application Number
- CN202410908208.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-08
- Publication Date
- 2024-11-15
AI Technical Summary
The existing technology lacks systematic overall analysis in the electromagnetic compatibility research of high-speed rail systems, and it is difficult to effectively deal with complex electromagnetic disturbance sources and transmission coupling methods, which affects the safety and stability of high-speed rail systems.
Deep learning and neural networks combine knowledge graphs and expert systems to build a high-speed rail electromagnetic compatibility intelligent analysis system. Through the knowledge graph construction module, expert knowledge base and decision analysis module, we systematically deal with electromagnetic compatibility problems, identify and position electromagnetic compatibility problems, Output systematized prediction analysis results.
It significantly improves the efficiency and accuracy of electromagnetic compatibility analysis, provides a comprehensive analysis of electromagnetic compatibility performance of high-speed rail system, ensures the flexibility and scalability of the system, improves electromagnetic compatibility performance, and ensures the normal operation of high-speed rail system.
Smart Images

Figure CN118965948A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a high-speed rail electromagnetic compatibility intelligent analysis system and a construction method thereof. Background Art
[0002] With the continuous construction and development of high-speed railways, it has become one of the safest, most efficient and environmentally friendly modes of transportation. Among all the technologies related to high-speed railways, the safety of high-speed railways is the basic principle of their development, and one of the core technologies closely related to the safety of high-speed railway systems is their electromagnetic compatibility performance. High-speed trains will experience complex and dynamically changing electromagnetic environments during cross-line operation, facing the influence of various electromagnetic interference sources from inside and outside the system, and there are many sensitive devices in the high-speed railway system, and the electromagnetic transmission coupling path is complex. Therefore, in order to ensure the safe operation of the high-speed railway system, it is necessary to conduct a systematic study and analysis of its electromagnetic compatibility. Although there are many research results related to the electromagnetic compatibility of high-speed railway systems, most of them are related studies based on a certain device, a certain electromagnetic interference source or a certain subsystem, and there are relatively few studies and analyses on the electromagnetic compatibility of the high-speed railway system as a whole. Summary of the invention
[0003] In order to solve the above technical problems, the present invention provides a high-speed rail electromagnetic compatibility intelligent analysis system and a construction method thereof. By making use of various modeling methods in machine learning, such as deep learning, neural networks and expert systems, and making full use of existing research results in various aspects such as theoretical analysis, practical testing and modeling simulation related to high-speed rail electromagnetic compatibility, it can achieve rapid positioning of high-speed rail electromagnetic compatibility problems and intelligent system analysis, provide an effective way to systematically solve actual high-speed rail electromagnetic compatibility problems, and help improve the overall electromagnetic compatibility performance of the high-speed rail system, thereby providing a guarantee for its normal operation.
[0004] The present invention provides a high-speed rail electromagnetic compatibility intelligent analysis system, which specifically includes:
[0005] A knowledge graph construction module, wherein the knowledge graph construction module takes the electromagnetic disturbance sources, transmission coupling paths and sensitive equipment of the high-speed rail operation system as modules, and constructs a knowledge graph of the mutual correlation between the modules and within them;
[0006] An expert knowledge base, which is based on the knowledge graph and classifies and organizes research results related to electromagnetic compatibility elements of high-speed rail systems through different electromagnetic compatibility analysis methods;
[0007] A decision analysis module is used to build a deep learning semantic recognition and classification network, and to identify and locate the input electromagnetic compatibility problem through the deep learning semantic recognition and classification network to obtain an identification result. According to the identification result, the corresponding sub-module in the expert knowledge base is called, and the research results of multiple sub-modules are integrated to output the systematic prediction and analysis results of the electromagnetic compatibility problem through comparative analysis.
[0008] In one embodiment of the present invention, the expert knowledge base includes four sub-modules: an electromagnetic modeling simulation module, an electromagnetic test analysis module, an electromagnetic theory derivation module and an electromagnetic standard verification module.
[0009] In one embodiment of the present invention, the submodule is used to store research data related to the corresponding electromagnetic compatibility analysis method and classify and organize the research data, wherein the research data includes the category of research results, parameter settings, and comparative analysis results of simulation or test results.
[0010] In one embodiment of the present invention, the method for obtaining the recognition result includes: using the deep learning semantic recognition classification network to extract key electromagnetic compatibility element vocabulary in the input question, and obtaining the recognition result through combined analysis of the association relationship of the knowledge graph.
[0011] In one embodiment of the present invention, the electromagnetic disturbance sources include off-line disturbance of the bow network and traction current harmonic disturbance; the transmission coupling paths include radiation reflection, line crosstalk and conduction coupling; the sensitive equipment includes vehicle-mounted antennas, communication cables and signal equipment.
[0012] The present invention also provides a method for constructing a high-speed rail electromagnetic compatibility intelligent analysis system, which is used to construct the high-speed rail electromagnetic compatibility intelligent analysis system. The method comprises the following steps:
[0013] S1: The electromagnetic disturbance sources, transmission coupling paths and sensitive devices of the high-speed rail operation system are set as modules, and a knowledge graph of the interrelationships between and within each module is constructed;
[0014] S2: Based on different types of electromagnetic disturbance sources, a corresponding expert knowledge base is constructed, and research results related to the electromagnetic compatibility elements of the high-speed rail system are classified and sorted out through different electromagnetic compatibility analysis methods;
[0015] S3: Optimizing the expert knowledge base, including: for each submodule in the expert knowledge base, recording and improving relevant simulation test settings, model building methods and analysis results according to the types of problems and research methods involved;
[0016] S4: Building a deep learning semantic recognition and classification network, identifying and locating input electromagnetic compatibility issues through the deep learning semantic recognition and classification network, and obtaining recognition results, which are key electromagnetic compatibility elements;
[0017] S5: Based on the identification result, the corresponding sub-module in the expert knowledge base is called, the research results of multiple sub-modules are integrated, and the systematic prediction and analysis results of the electromagnetic compatibility problem are output through comparative analysis.
[0018] In one embodiment of the present invention, the expert knowledge base includes four sub-modules: an electromagnetic modeling simulation module, an electromagnetic test analysis module, an electromagnetic theory derivation module and an electromagnetic standard verification module.
[0019] In one embodiment of the present invention, the submodule is used to store research data related to the corresponding electromagnetic compatibility analysis method and classify and organize the research data, wherein the research data includes the category of research results, parameter settings, and comparative analysis results of simulation or test results.
[0020] In one embodiment of the present invention, the method for obtaining the recognition result includes: using the deep learning semantic recognition classification network to extract key electromagnetic compatibility element vocabulary in the input question, and obtaining the recognition result through combined analysis of the association relationship of the knowledge graph.
[0021] In one embodiment of the present invention, the electromagnetic disturbance sources include off-line disturbance of the bow network and traction current harmonic disturbance; the transmission coupling paths include radiation reflection, line crosstalk and conduction coupling; the sensitive equipment includes vehicle-mounted antennas, communication cables and signal equipment.
[0022] The above technical solution of the present invention has the following advantages compared with the prior art:
[0023] By constructing a knowledge graph and an expert knowledge base, the present invention can systematically handle the electromagnetic compatibility problems of high-speed railways, and use deep learning technology for intelligent identification and analysis, which significantly improves the efficiency and accuracy of electromagnetic compatibility analysis; the electromagnetic disturbance source, transmission coupling path, and sensitive equipment are divided into different modules, and the relationship between modules is constructed to make the system easy to expand and maintain. At the same time, the expert knowledge base is also divided into multiple sub-modules, which can be added, reduced or updated as needed, improving the flexibility and scalability of the system; it integrates multiple analysis methods such as electromagnetic modeling simulation, electromagnetic test analysis, electromagnetic theory derivation, and electromagnetic standard verification, and can comprehensively analyze electromagnetic compatibility problems from multiple dimensions to ensure the comprehensiveness and accuracy of the analysis results. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] In order to make the content of the present invention more clearly understood, the present invention is further described in detail below according to specific embodiments of the present invention in conjunction with the accompanying drawings, wherein
[0025] Figure 1 It is a structural schematic diagram of a high-speed rail electromagnetic compatibility intelligent analysis system provided by an embodiment of the present invention;
[0026] Figure 2 It is a specific structural diagram of a high-speed rail electromagnetic compatibility intelligent analysis system provided by an embodiment of the present invention;
[0027] Figure 3 It is a flow chart of a method for constructing a high-speed rail electromagnetic compatibility intelligent analysis system provided by an embodiment of the present invention;
[0028] Figure 4 This is a flow chart for analyzing the impact of bow-net offline interference on vehicle-mounted antennas when the electromagnetic compatibility problem is bow-net offline interference;
[0029] Explanation of the reference numerals in the specification: 100, knowledge graph construction module; 200, expert knowledge base; 300, decision analysis module. DETAILED DESCRIPTION
[0030] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention.
[0031] Embodiment 1
[0032] Reference Figures 1-2 As shown, the present invention provides a high-speed rail electromagnetic compatibility intelligent analysis system, which specifically includes:
[0033] A knowledge graph construction module 100, wherein the knowledge graph construction module 100 takes the electromagnetic disturbance sources, transmission coupling paths and sensitive equipment of the high-speed rail operation system as modules to construct a knowledge graph of the mutual correlation between the modules and within the modules;
[0034] An expert knowledge base 200, which is based on the knowledge graph and classifies and organizes research results related to electromagnetic compatibility elements of high-speed rail systems through different electromagnetic compatibility analysis methods;
[0035] A decision analysis module 300, which is used to build a deep learning semantic recognition and classification network, identify and locate the input electromagnetic compatibility problem through the deep learning semantic recognition and classification network, and obtain an identification result. According to the identification result, the corresponding sub-module in the expert knowledge base is called, and the research results of multiple sub-modules are integrated to output the systematic prediction and analysis results of the electromagnetic compatibility problem through comparative analysis;
[0036] Among them, the electromagnetic interference sources include off-line disturbance of the bow network and traction current harmonic disturbance; the transmission coupling paths include radiation reflection, line crosstalk and conduction coupling; the sensitive equipment includes vehicle-mounted antennas, communication cables and signal equipment.
[0037] In this embodiment, based on the main electromagnetic compatibility elements involved in the high-speed rail system obtained from the previous analysis, namely, electromagnetic disturbance sources, transmission coupling paths and sensitive equipment, the existing research results related to the main electromagnetic compatibility elements are classified and sorted according to different applied analysis methods to build an electromagnetic compatibility expert knowledge base for the high-speed rail system.
[0038] like Figure 2 As shown, according to different electromagnetic analysis methods adopted, the expert knowledge base 200 is divided into four sub-modules: an electromagnetic modeling simulation module, an electromagnetic test analysis module, an electromagnetic theory derivation module and an electromagnetic standard verification module.
[0039] Furthermore, the submodule is used to store research data related to the corresponding electromagnetic compatibility analysis method and classify and organize the research data, wherein the research data includes the category of research results, parameter settings, and comparative analysis results of simulation or test results.
[0040] For example, the electromagnetic modeling and simulation module mainly stores the existing related research on the electromagnetic compatibility of high-speed rail systems based on equivalent modeling and simulation methods, including research results categories, parameter settings of equivalent simulation models, comparative analysis of simulation results, etc. When different electromagnetic compatibility problems are input, the corresponding expert knowledge base submodule can be located through methods such as semantic recognition in deep learning, and the preliminary prediction and analysis of electromagnetic compatibility problems can be achieved by referring to the existing related research results in the submodule.
[0041] The decision analysis module 300 is used to build a deep learning semantic recognition and classification network, and the input electromagnetic compatibility problem is identified and located through the deep learning semantic recognition and classification network to obtain a recognition result. Specifically, the method for obtaining the recognition result includes: using the deep learning semantic recognition and classification network to extract key electromagnetic compatibility element vocabulary in the input problem, and combining and analyzing the association relationship of the knowledge graph to obtain the recognition result.
[0042] Embodiment 2
[0043] The present invention also provides a method for constructing a high-speed rail electromagnetic compatibility intelligent analysis system, which is used to construct the high-speed rail electromagnetic compatibility intelligent analysis system described in Example 1. Figure 3 As shown, the construction method comprises the following steps:
[0044] S1: The electromagnetic disturbance sources, transmission coupling paths and sensitive devices of the high-speed rail operation system are set as modules, and a knowledge graph of the interrelationships between and within each module is constructed;
[0045] S2: Based on different types of electromagnetic disturbance sources, a corresponding expert knowledge base is constructed, and research results related to the electromagnetic compatibility elements of the high-speed rail system are classified and sorted out through different electromagnetic compatibility analysis methods;
[0046] S3: Optimizing the expert knowledge base, including: for each submodule in the expert knowledge base, recording and improving relevant simulation test settings, model building methods and analysis results according to the types of problems and research methods involved;
[0047] S4: Building a deep learning semantic recognition and classification network, identifying and locating input electromagnetic compatibility issues through the deep learning semantic recognition and classification network, and obtaining recognition results, which are key electromagnetic compatibility elements;
[0048] S5: according to the identification result, calling the corresponding submodule in the expert knowledge base, integrating the research results of multiple submodules, and outputting the systematic prediction and analysis results of the electromagnetic compatibility problem through comparative analysis;
[0049] Among them, the electromagnetic interference sources include off-line disturbance of the bow network and traction current harmonic disturbance; the transmission coupling paths include radiation reflection, line crosstalk and conduction coupling; the sensitive equipment includes vehicle-mounted antennas, communication cables and signal equipment.
[0050] Furthermore, according to the different electromagnetic analysis methods adopted, the expert knowledge base is divided into four sub-modules: electromagnetic modeling simulation module, electromagnetic test analysis module, electromagnetic theory derivation module and electromagnetic standard verification module. The sub-modules are used to store research data related to the corresponding electromagnetic compatibility analysis method and classify and organize the research data, which includes the category of research results, parameter settings and comparative analysis results of simulation or test results.
[0051] For example, the electromagnetic modeling and simulation module mainly stores the existing related research on the electromagnetic compatibility of high-speed rail systems based on equivalent modeling and simulation methods, including research results categories, parameter settings of equivalent simulation models, comparative analysis of simulation results, etc. When different electromagnetic compatibility problems are input, the corresponding expert knowledge base submodule can be located through methods such as semantic recognition in deep learning, and the preliminary prediction and analysis of electromagnetic compatibility problems can be achieved by referring to the existing related research results in the submodule.
[0052] For step S3: optimizing the expert knowledge base, including: for each sub-module in the expert knowledge base, according to the type of problems and research methods involved, recording and improving relevant simulation test settings, model building methods and analysis results.
[0053] Furthermore, according to the types of problems involved in each sub-module in the expert knowledge base and the different research methods applied, the relevant parameter settings and result analysis should be given as comprehensively as possible to achieve continuous refinement and improvement of each sub-module, thereby outputting more accurate predictive analysis results.
[0054] For example, if we build an expert knowledge base related to bow-net offline disturbance, the existing research related to bow-net offline disturbance may involve multiple research methods such as electromagnetic modeling simulation, electromagnetic testing and theoretical analysis. When improving the corresponding expert knowledge base, we need to provide as detailed as possible the parameter settings and simulation results in the equivalent simulation model, the test process design and result analysis in the actual electromagnetic test and simulation test, the theoretical analysis method and result verification used in the theoretical analysis model, and other relatively complete parameter settings and result analysis based on all the relevant research results. When building the electromagnetic compatibility expert knowledge base of the high-speed rail system, refining and improving each part of the knowledge base as much as possible will help to better realize the prediction and analysis of actual electromagnetic compatibility problems.
[0055] In step S4, a deep learning semantic recognition and classification network is built, and the input electromagnetic compatibility problem is recognized and located by the deep learning semantic recognition and classification network to obtain a recognition result. The method for obtaining the recognition result includes: when a description of an actual problem is given, the deep learning semantic recognition and classification network is used to extract the key electromagnetic compatibility element vocabulary in the input problem, and the recognition result is obtained by combining and analyzing the association relationship of the knowledge graph.
[0056] Furthermore, according to the electromagnetic compatibility elements involved in actual problems, different modules in the expert knowledge base can be called, and finally a comprehensive analysis result can be formed to achieve systematic predictive analysis of electromagnetic compatibility problems and their related influencing factors.
[0057] For example, if the actual electromagnetic compatibility problem encountered is offline interference from the bow and catenary, the process of analyzing the impact of offline interference from the bow and catenary on the vehicle antenna is as follows: Figure 4 First, intelligent modeling methods such as semantic recognition can be used to accurately locate the electromagnetic compatibility problems encountered, that is, through intelligent semantic recognition, key information in the problem can be extracted, such as offline interference of the bow network and the vehicle-mounted antenna, and then the main electromagnetic compatibility elements involved can be preliminarily located, and through the analysis of the knowledge graph association relationship between different electromagnetic compatibility elements, all electromagnetic elements that may be involved can be accurately located.
[0058] Furthermore, the relevant expert knowledge base modules are called according to the electromagnetic compatibility elements pointed out in the previous positioning. For example, the existing research related to the offline disturbance of the bow network may involve multiple research methods such as electromagnetic modeling simulation, electromagnetic testing and theoretical analysis, so the research results in multiple relevant expert knowledge bases will be considered at the same time, and through comparative analysis, a comprehensive prediction result will be given in the end, so as to provide analysis and reference for the electromagnetic compatibility problems encountered.
[0059] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0060] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0061] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0062] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0063] Obviously, the above embodiments are merely examples for clear explanation and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived from these are still within the protection scope of the invention.
Claims
1. A high-speed rail electromagnetic compatibility intelligent analysis system, characterized in that: Includes the following modules: A knowledge graph construction module, wherein the knowledge graph construction module takes the electromagnetic disturbance sources, transmission coupling paths and sensitive equipment of the high-speed rail operation system as modules, and constructs a knowledge graph of the mutual correlation between the modules and within them; An expert knowledge base, which is based on the knowledge graph and classifies and organizes research results related to electromagnetic compatibility elements of high-speed rail systems through different electromagnetic compatibility analysis methods; A decision analysis module is used to build a deep learning semantic recognition and classification network, and to identify and locate the input electromagnetic compatibility problem through the deep learning semantic recognition and classification network to obtain an identification result. According to the identification result, the corresponding sub-module in the expert knowledge base is called, and the research results of multiple sub-modules are integrated to output the systematic prediction and analysis results of the electromagnetic compatibility problem through comparative analysis.
2. The high-speed rail electromagnetic compatibility intelligent analysis system according to claim 1 is characterized by: The expert knowledge base includes four submodules: an electromagnetic modeling and simulation module, an electromagnetic test and analysis module, an electromagnetic theory derivation module and an electromagnetic standard verification module.
3. The high-speed rail electromagnetic compatibility intelligent analysis system according to claim 2 is characterized by: The submodule is used to store research data related to the corresponding electromagnetic compatibility analysis method and classify and organize the research data, wherein the research data includes the category of research results, parameter settings, and comparative analysis results of simulation or test results.
4. The high-speed rail electromagnetic compatibility intelligent analysis system according to claim 1 is characterized by: The method for obtaining the recognition result includes: using the deep learning semantic recognition classification network to extract key electromagnetic compatibility element vocabulary in the input question, and obtaining the recognition result through combined analysis of the association relationship of the knowledge graph.
5. The high-speed rail electromagnetic compatibility intelligent analysis system according to claim 1 is characterized by: The electromagnetic disturbance sources include off-line disturbance of the bow network and traction current harmonic disturbance; the transmission coupling paths include radiation reflection, line crosstalk and conduction coupling; the sensitive equipment includes vehicle-mounted antennas, communication cables and signal equipment.
6. A method for constructing a high-speed rail electromagnetic compatibility intelligent analysis system, characterized in that: Used to construct the high-speed rail electromagnetic compatibility intelligent analysis system as described in any one of claims 1 to 5, the construction method comprises the following steps: S1: The electromagnetic disturbance sources, transmission coupling paths and sensitive equipment of the high-speed rail operation system are set as modules, and a knowledge graph of the interrelationships between and within each module is constructed; S2: Based on different types of electromagnetic disturbance sources, a corresponding expert knowledge base is constructed, and research results related to the electromagnetic compatibility elements of the high-speed rail system are classified and sorted out through different electromagnetic compatibility analysis methods; S3: Optimizing the expert knowledge base, including: for each submodule in the expert knowledge base, recording and improving relevant simulation test settings, model building methods and analysis results according to the types of problems and research methods involved; S4: Building a deep learning semantic recognition and classification network, identifying and locating input electromagnetic compatibility issues through the deep learning semantic recognition and classification network, and obtaining recognition results, which are key electromagnetic compatibility elements; S5: Based on the identification result, the corresponding sub-module in the expert knowledge base is called, the research results of multiple sub-modules are integrated, and the systematic prediction and analysis results of the electromagnetic compatibility problem are output through comparative analysis.
7. The method for constructing a high-speed rail electromagnetic compatibility intelligent analysis system according to claim 6, characterized in that: The expert knowledge base includes four submodules: an electromagnetic modeling and simulation module, an electromagnetic test and analysis module, an electromagnetic theory derivation module and an electromagnetic standard verification module.
8. The method for constructing a high-speed rail electromagnetic compatibility intelligent analysis system according to claim 7 is characterized in that: The submodule is used to store research data related to the corresponding electromagnetic compatibility analysis method and classify and organize the research data, wherein the research data includes the category of research results, parameter settings, and comparative analysis results of simulation or test results.
9. The method for constructing a high-speed rail electromagnetic compatibility intelligent analysis system according to claim 6, characterized in that: The method for obtaining the recognition result includes: using the deep learning semantic recognition classification network to extract key electromagnetic compatibility element vocabulary in the input question, and obtaining the recognition result through combined analysis of the association relationship of the knowledge graph.
10. The method for constructing a high-speed rail electromagnetic compatibility intelligent analysis system according to claim 6, characterized in that: The electromagnetic disturbance sources include off-line disturbance of the bow network and traction current harmonic disturbance; the transmission coupling paths include radiation reflection, line crosstalk and conduction coupling; the sensitive equipment includes vehicle-mounted antennas, communication cables and signal equipment.
