Train operation safety testing method and system based on virtual-real combination

Abstract

The present invention discloses a train operation safety test method and system based on the combination of virtual and real, and relates to the field of safety testing. The method includes: importing the information to be tested into the platform access layer for demand analysis, and determining the test scenario demand information; matching in the scenario library to obtain a virtual test scenario, and building a test channel in combination with the real test scenario; based on the test tasks received by the management layer, performing simulation tests in the test channel in turn, and performing intelligent evaluation on the simulation test results; and inputting the test evaluation results into the application layer for visual display. This method solves the technical problems in the prior art that due to limited test scenarios, high-risk and high-complexity scenarios cannot be covered, resulting in poor generalization ability of test results, long test cycles and high costs. By increasing the number of test scenarios, the accuracy of the test results is improved, and the technical effect of reducing the test cycle time and cost is achieved through a simulation method that combines virtual and real.

Description

Technical Field

[0001] The present application relates to the field of safety testing technology, and in particular to the field of train safety testing, and specifically to a train operation safety testing method and system based on a combination of virtual and real. Background Art

[0002] Before the railway train operating environment safety detection and monitoring system is put into use, it needs to undergo a lot of testing to meet the application requirements. At present, the train operating environment safety detection and monitoring equipment and system testing are mainly based on the actual test environment, which has the problems of long test cycle, high cost, limited test coverage, and difficulty in covering high-risk, extreme, and high-complexity boundary scenarios, and cannot meet the testing requirements of algorithms, software, hardware, and systems at different levels. With the application of artificial intelligence technology, the results of train operating environment safety detection and monitoring are more dependent on the complexity of the test environment and the completeness of the test data. Hardware-in-the-loop testing based on real environments is difficult to meet the testing requirements. It is necessary to study train operating environment safety detection and monitoring equipment, system testing technology and methods based on complex scenarios and virtual and real combined.

[0003] In summary, the existing technology has technical problems such as limited test scenarios, which make it impossible to cover high-risk and high-complexity scenarios, resulting in poor generalization ability of test results, long test cycles and high costs. Summary of the invention

[0004] Based on this, it is necessary to provide a train operation safety testing method and system based on the combination of virtual and real, which can increase the number of test scenarios and reduce the test cycle time and cost in response to the above technical problems.

[0005] On the first aspect, a train operation safety testing method based on the combination of virtual and real is provided, and the method includes: importing the information to be tested into the platform access layer for demand analysis to determine the test scenario demand information; transferring the test scenario demand information to the basic layer, matching in the scenario library based on the virtual test scenario demand to obtain the virtual test scenario, and building a test channel in combination with the real test scenario; performing simulation tests in the test channel in turn based on the test tasks received by the management layer, and performing intelligent evaluation on the simulation test results; and inputting the test evaluation results into the application layer for visual display.

[0006] On the second aspect, a train operation safety test system based on the combination of virtual and real is provided, and the system includes: a test scenario requirement information determination module, the test scenario requirement information determination module is used to import the information to be tested into the platform access layer for requirement analysis, and determine the test scenario requirement information; a test channel construction module, the test channel construction module is used to transfer the test scenario requirement information to the basic layer, match the virtual test scenario requirements in the scene library, obtain the virtual test scene, and build a test channel in combination with the real test scene; an intelligent evaluation module, the intelligent evaluation module is used to perform simulation tests in the test channel in sequence based on the test tasks received by the management level, and perform intelligent evaluation on the simulation test results; a visualization display module, the visualization display module is used to input the test evaluation results into the application layer for visualization.

[0007] According to a third aspect, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps according to the first aspect when executing the computer program.

[0008] According to a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps described in the first aspect are implemented.

[0009] The above-mentioned train operation safety testing method and system based on the combination of virtual and real solves the technical problems in the prior art that the test scenarios are limited, resulting in the inability to cover high-risk and high-complexity scenarios, resulting in poor generalization ability of the test results, long test cycles and high costs. By increasing the number of test scenarios, the accuracy of the test results is improved, and through the simulation method that combines virtual and real, the technical effect of reducing the test cycle time and cost is achieved.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a flow chart of a train operation safety testing method based on a combination of virtual and real in one embodiment;

[0012] Figure 2 It is a flow chart of an application platform of a train operation safety testing method based on a combination of virtual and real in one embodiment;

[0013] Figure 3 It is a structural block diagram of a train operation safety test system based on virtual-real combination in one embodiment;

[0014] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment.

[0015] Explanation of the reference numerals: test scenario requirement information determination module 11, test channel construction module 12, intelligent evaluation module 13, visualization display module 14. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0017] like Figure 1 As shown, the present application provides a train operation safety testing method based on a combination of virtual and real, the method comprising:

[0018] Import the information to be tested into the platform access layer for demand analysis and determine the test scenario demand information;

[0019] The combination of virtual and real is a comprehensive method or technology that combines the characteristics and advantages of virtual and real environments to provide a more comprehensive, efficient and accurate solution. This application combines the advantages of virtual testing and real testing to evaluate the safety of train operation. It uses a combination of virtual test scenarios and real test scenarios to simulate the operation of trains in different environments and conditions, thereby comprehensively and accurately evaluating the safety performance of trains. The application of the combination of virtual and real in train operation safety testing aims to combine the advantages of virtual testing and real testing to provide a more comprehensive, efficient and accurate testing method. This method helps to improve the safety of train operation, reduce the risk of accidents, and promote the sustainable development of the railway transportation industry.

[0020] like Figure 2As shown, a test platform combining virtuality and reality is developed to meet the requirements of train operation environment safety assurance detection, monitoring algorithms, hardware, software and system testing. The information to be tested includes the model algorithm, software, hardware and system to be tested, which is the target information that needs to be tested. The platform consists of an access layer, a basic layer, a management layer and an application layer. The platform access layer is used to receive the information to be tested. When the information to be tested meets the conditions for access to the model algorithm, software, hardware and system testing, the information to be tested is connected to the platform through the middleware. Based on the purpose and requirements of the test of the information to be tested, a demand analysis is performed; the basic layer includes real test scenarios and virtual test scenarios. The real test scenarios include environments with different working conditions such as railway roadbeds, tunnels, slopes, etc., and are equipped with detection equipment such as video cameras and radars. The basic layer includes different weather conditions such as strong winds, heavy rains, and heavy fogs, and simulation conditions of different intrusion categories such as mudslides, foreign body intrusions and perimeter intrusions. The scenario library under dangerous working conditions is generated through simulation and historical data; the management layer includes test task management, test management, data management, test evaluation and platform management. Task management is the management of tasks to be tested, and test management is the process management of a specific test task. Data management is the recording of test data, etc. Test evaluation gives test results. Platform management includes user management, platform maintenance, etc.; the application layer provides a visual display of test results according to user needs to meet the needs of model algorithms, software, hardware and system testing. Test scenarios refer to real test scenarios and virtual test scenarios that combine virtual and real. Based on the demand analysis, the test scenarios of the information to be tested are determined, such as different weather conditions, track types, selected models, load conditions, etc. The determined test scenarios are converted into specific test scenario requirement information, such as a specific description of the test scenario, required data sets, test steps, etc. By determining the test scenario requirement information of the information to be tested, a clear direction and data are provided for subsequent virtual and real tests to ensure the effectiveness and pertinence of the test.

[0021] Performing test attribute identification on the information to be tested to determine the attributes of the object to be tested;

[0022] Based on the attributes of the object to be tested, feature extraction is performed on the information to be tested according to preset attribute dimensions to obtain test features of the object to be tested;

[0023] A cluster center is set, the cluster center corresponds to a preset test scenario requirement feature, and the test features of the object to be tested are clustered based on the cluster center to obtain the test scenario requirement information.

[0024] Test attribute identification refers to analyzing the information to be tested and obtaining the specific situation of the information to be tested, such as obtaining the information to be tested and identifying the test attributes of the information to be tested. The test attributes include algorithms, software, hardware and systems, and determining the attributes of the object to be tested, such as algorithms; the attribute preset dimension is the data required when testing the information to be tested, which refers to the data set by the staff, such as the application scenario, target and security requirements of the information to be tested. For the information to be tested, the corresponding features of the application scenario, operating environment, security and accuracy of the information to be tested are determined, and the corresponding features of the information to be tested are extracted to obtain the test features of the object to be tested; the cluster center is pre-set by the staff according to the test scenario requirement characteristics, representing different test scenarios and conditions, such as different environments for train operation, different operating conditions, specific safety requirements, etc.; after setting the cluster center, it is necessary to use a clustering algorithm to cluster the test features of the object to be tested, analyze the distance or similarity between the test features of the object to be tested and the cluster center for clustering, obtain information corresponding to the preset test scenario requirement characteristics through cluster analysis, and determine the test scenario requirement information according to the information. By setting cluster centers and performing cluster analysis based on the cluster centers, the test characteristics of the object to be tested can be matched with the preset test scenario requirement characteristics, thereby determining information corresponding to the test scenario requirements, providing strong support for subsequent testing work.

[0025] Collecting a record data set of train operation, classifying the record data set through a decision tree model, and constructing a multi-level historical data set, including weather categories, environmental scene categories, and operation safety categories;

[0026] Aggregate multi-category scenes based on the multi-level historical data sets to construct a multi-category scene data set;

[0027] Extracting scene elements from the multi-category scene data set to construct an element extraction set;

[0028] Based on the preset scene elements, the multi-category scene data set and the element extraction set are traversed respectively to determine the missing data description information;

[0029] The scenes and elements are supplemented according to the missing data description information, and the element library is constructed using the supplemented scene-element library data and their mapping relationships.

[0030] Collect a record data set during the operation of the train, the record data set includes relevant information such as weather conditions, environmental scenes and operation safety events, environmental scenes such as railway roadbed, tunnels, slopes and other different working conditions, which can be obtained through the control system of the train, video cameras and other monitoring equipment, and classify the record data set through a decision tree model. The decision tree is a prediction model that represents a mapping relationship between object attributes and object values. In this application, the root node in the decision tree represents the record data set, and the three leaf nodes represent weather categories, environmental scene categories, and operation safety categories, that is, a multi-level historical data set. The classification subsets corresponding to the weather category leaf nodes are such as sunny days, rainy days, snowy days, etc.; the classification subsets corresponding to the environmental scene categories are such as cities, rural areas, mountainous areas, etc.; the classification subsets corresponding to the operation safety categories are such as normal operation, fault warning, emergency braking, etc., and each level contains a corresponding data subset for subsequent scene aggregation and feature extraction; based on the multi-level historical data set, multi-category scene aggregation is performed, that is, the data of weather, environmental scenes and operation safety categories are aggregated together to form a multi-category scene data set, and the multi-category scene data set will contain various different scenes under different scenes. The train operation data includes different weather conditions such as strong wind, heavy rain and heavy fog, simulation conditions of different intrusion categories such as debris flow, foreign body intrusion and perimeter intrusion, and the running status of the train under the above conditions. The scene elements are extracted from the multi-category scene data set, that is, key elements related to train operation safety, such as weather conditions, environmental scene characteristics, train operation status, etc., are extracted from the data set to construct an element extraction set; the scene elements are set by the staff. Based on the preset scene elements, the multi-category scene data set and the element extraction set are traversed to find the missing data that may exist in the data set. The missing data description information refers to the data that is not actually collected and needs to be supplemented and simulated. For example, there has been no debris flow natural disaster in the target scene, and the monitoring device has not monitored relevant information, but it is necessary to simulate the environmental scene where the debris flow occurs to generate the corresponding missing data description information. According to the missing data description information, data supplementation is performed, and the supplemented scene-element library data and its mapping relationship are used to construct the final element library. The element library will contain elements related to train operation safety in various scenarios, providing strong support for subsequent train operation safety tests. By building a complete train operation safety test element library, we can provide strong guarantee for the safe operation of trains.

[0031] According to the missing data description information, data collection is performed, and a quantitative evaluation of the collection results is performed;

[0032] When the data volume evaluation result does not meet the supplementary requirements, obtain the core description information of the missing data description information;

[0033] Perform characteristic genetic derivation based on the core description information to obtain a genetically derived data set, wherein the genetically derived data set is obtained by performing characteristic genetic changes on the core description information according to a preset derivation step length and derivation direction;

[0034] Based on the genetically derived data set, collaboratively changing missing data description information other than the core description information to construct a missing data derivative set;

[0035] Based on the core description information, a historical record data set is collected, a simulation module is constructed, simulation is performed through the simulation module based on the missing data derivative set, and derivative data that meets the scenario simulation results are screened for supplementation.

[0036] According to the specific description information of the missing data, including the type, scope, impact, etc. of the missing data, according to the specific description information, obtain the corresponding data collection plan, including collection methods, collection tools, collection cycles, etc., obtain the corresponding data, that is, the collection results, and perform a quantitative evaluation on the collection results. The quantitative evaluation includes checking whether the amount of data is sufficient and whether the data is evenly distributed. If the data quantity evaluation result does not meet the supplementary requirements, obtain the core description information of the missing data description information. The core description information refers to the description information that has the greatest impact and is the most critical to the missing data, and is the main reason or key factor for the missing data. After obtaining the core description information, use the characteristic genetic derivation method to generate new data. According to the preset derivation step and derivation direction, perform characteristic genetic changes on the core description information to generate new data that is similar to the original data but not completely the same, so as to expand the data set, for example, according to the requirements of the data, The existing collected data is derived for simulation, and the data that meets the scene requirements is obtained for supplementation. In addition to the core description information, the description information including other missing data is obtained. Based on the genetic derivative data set, these description information are synergistically changed to construct a missing data derivative set. Synergistic change means that when considering the relationship between multiple variables or factors, data adjustment or generation is performed at the same time. After obtaining the genetic derivative data set and the missing data derivative set, a simulation module is constructed based on the data. Different scene requirements should have corresponding description features. If the simulation results meet the description features, it means that the derived data is correct and can be used. If it does not meet the data description of this scene and there are abnormalities, it does not meet the requirements of the simulation results, and the derived data is removed; by screening the derived data that meets the scene simulation results, it is supplemented to the original data set, thereby improving the data set and improving the accuracy and reliability of the test. Targeted data collection, evaluation and supplementation based on the description information of the missing data can build a more complete and accurate data set, and can also improve the effectiveness and reliability of the train operation safety test.

[0037] The test scenario requirement information is transferred to the basic layer, and the virtual test scenario is matched in the scenario library based on the virtual test scenario requirement to obtain the virtual test scenario, and the test channel is built in combination with the real test scenario;

[0038] The test scenario requirement information obtained through cluster analysis is passed to the basic layer. In the basic layer, there is a pre-built scenario library containing various virtual test scenarios. The virtual scenario is created through simulation and emulation technology to simulate the actual operating environment. According to the test scenario requirement information, a match is made in the scenario library to find a virtual test scenario that matches the requirement. The virtual test scenario is combined with the real test scenario to build a test channel. The real test scenario is the actual operating environment, such as a specific railway line, station, roadbed, etc. By building a test channel, the test data and results in the virtual scenario can be interacted and verified with the data in the actual scenario. Building a test channel in combination with virtual test scenarios and real test scenarios can effectively carry out safety testing and improve test efficiency and accuracy.

[0039] Based on the test scenario requirement information, modular decoupling of scenario requirements is performed to extract scenario constituent elements of the test scenario;

[0040] Based on the scene constituent elements, traversal matching is performed in the scene library to obtain a matching scene element set, and the intrinsic connection between the scene elements in the matching scene element set is analyzed to establish a modular test scene library and build a test channel.

[0041] Based on the test scenario requirement information, a detailed analysis and modular decoupling are performed, wherein modular decoupling refers to dividing a complex system into independent modules to reduce the complexity of the system and improve the maintainability of the code. In this application, it refers to dividing multiple different scene components to obtain a series of independent and replaceable modules. Each module or sub-scenario should correspond to a specific test requirement or test target; the extracted scene components are traversed and matched with the virtual test scenes in the scene library. The scene library is a pre-built database containing various virtual test scenarios. By traversing each virtual scene in the scene library, virtual test scenes that match the extracted scene components can be found and extracted. The matching virtual scenes are combined into a matching scene element set for subsequent testing work. Obtaining the matching scenario element set and analyzing the internal connections between the scenario elements can provide a more comprehensive understanding of the overall structure and characteristics of the test scenario, thereby more accurately simulating and testing the operational safety performance; establishing a modular test scenario library, which contains multiple independent and manageable modules or sub-scenarios, each of which represents a specific test requirement or test scenario constituent element, and building a test channel, which connects the virtual test scenario with the actual test scenario for transmitting test data, monitoring the test process, and analyzing test results. Based on the test scenario requirement information, modular decoupling is performed to extract the scenario constituent elements, traversal matching and internal connection analysis are performed in the scenario library, and finally a modular test scenario library is established and a test channel is built, which helps to more accurately simulate and test the operational safety performance of the train and improve test efficiency and accuracy.

[0042] Extracting a collaborative real scene based on the virtual test scene requirement, wherein the collaborative real scene is a real scene with the highest similarity to the virtual test scene requirement;

[0043] Perform synergy and difference analysis based on the modular test scenario library and the collaborative real scenario;

[0044] Based on the synergy, the constituent elements of the collaborative real scene are obtained, and the different constituent elements are merged in combination with the differences to obtain the virtual and real scene elements, and build the test channel.

[0045] Clarify the specific requirements of the virtual test scenario, such as weather conditions, track type, train running status, etc., and extract the scenario with the highest similarity to the virtual test scenario requirements from the existing real scenarios, that is, the collaborative real scenario; by comparing the characteristics and parameters of the virtual test scenario with each scenario in the real scenario library, select the real scenario that best meets the requirements as the collaborative scenario; the synergy analysis aims to find out the common characteristics and parameters in the virtual scenario and the collaborative real scenario to ensure that they have similar behavioral performance in the test, and the difference analysis focuses on the differences between the two, which include weather conditions, track characteristics, train performance, etc.; through the synergy analysis, extract the constituent elements of the collaborative real scenario, which are the basic units that constitute the real scenario, and then combine the results of the difference analysis to merge the difference constituent elements in the virtual scenario and the collaborative real scenario. After the difference constituent elements are merged, a virtual-real scenario containing virtual and real scene elements is obtained. The virtual-real scenario combines the controllability of the virtual test scenario and the authenticity of the real scenario, providing a more realistic environment for safety testing, and building a test channel based on the virtual-real scenario. By building a test channel that combines virtual and real scenarios, the accuracy and effectiveness of safety testing are improved.

[0046] Based on the test tasks received by the management, simulation tests are carried out in the test channel in turn, and the simulation test results are intelligently evaluated;

[0047] The test task includes different test scenarios, test objectives and test requirements, that is, the test requirements of the information to be tested. After receiving the test task, the test channel needs to be configured according to the specific requirements of the test task to ensure that the test channel can simulate an environment that meets the requirements of the test task. During the simulation test, it is necessary to record test management, performance indicators, safety performance and other data for subsequent analysis and evaluation. After the simulation test is completed, the test results are analyzed, that is, according to the specific requirements of the test task, the performance indicators, safety performance and other factors are comprehensively considered to evaluate the test results objectively and comprehensively. Obtaining intelligent evaluation of the simulation test results helps to improve the accuracy and effectiveness of security testing.

[0048] Extracting discrete test results and continuous test results according to the simulation test results;

[0049] Building a discrete evaluation module to evaluate the discrete test results and obtain discrete evaluation results;

[0050] Building a continuous evaluation module to evaluate the continuous test results and obtain continuous evaluation results;

[0051] A multi-level evaluation strategy is set, and a test evaluation result is generated according to the strategy correspondence between the discrete evaluation result and the continuous evaluation result.

[0052] After the simulation test is completed, a large amount of test data is obtained, namely, simulation test results. The simulation test results include discrete test results and continuous test results. Discrete test results usually refer to different test data, different test directions or indicators. Discrete refers to the test result of an intermediate indicator or time point. Check whether there is an abnormality. For example, if the target indicator is between 20-40, it is normal. Then 10-20 and 40-50 are the first level of danger. 60-80 belongs to the second level of danger. More than 80 is the third level of danger. The test result of a single parameter is compared with the data of each level to determine whether there is an abnormality. If so, the abnormal risk level is determined. The continuous test result refers to the test result of the train driving cycle to determine whether the continuous test result is intact. If there is a slight abnormality in a discrete parameter, the corresponding evaluation result of the simulation test result is level one. If there is an abnormality in the entire cycle or the overall continuous parameter, the corresponding evaluation result is judged to be a high level of danger. The discrete evaluation module is used to determine whether the test results are within the preset value range, for example, whether the evaluation of different monitoring data is within the normal range, and determine the test results of the discrete test parameters according to the entered range probability or ratio; the continuous evaluation module can evaluate the test results of the cycle by constructing a periodic timing chain, such as a Markov chain model or a neural network prediction model. Set a multi-level evaluation strategy, which is set by the staff based on experience, and combine to generate the final test evaluation results. The multi-level evaluation strategy can include different evaluation levels and weight allocations to reflect the importance of different test scenarios and performance indicators. Conduct in-depth analysis and evaluation of the simulation test results, obtain discrete evaluation results and continuous evaluation results, and generate the final test evaluation results according to the multi-level evaluation strategy. This will provide strong data support and analysis basis for train operation safety and improve overall work efficiency and quality.

[0053] The test evaluation results are input into the application layer for visual display.

[0054] It is necessary to select a suitable visualization tool or platform to input the test evaluation results into a visualization interface, such as using charts, graphs, color coding, etc. to display data so that users can quickly identify performance trends, outliers or potential problems. The test evaluation results are effectively input into the application layer for visualization, thereby providing decision makers with an intuitive and easy-to-understand way to obtain test evaluation results. This method solves the technical problems in the prior art that due to limited test scenarios, high-risk and high-complexity scenarios cannot be covered, resulting in poor generalization ability of test results, long test cycles and high costs. By increasing the number of test scenarios, the accuracy of the test results is improved, and the test cycle time and cost are reduced through a combination of virtual and real simulation methods.

[0055] In summary, the present invention has at least the following beneficial effects:

[0056] 1. Through the virtual test scenario library generation technology, based on the real test environment, simulate the high-risk scenarios such as strong winds, heavy rains, falling rocks, personnel intrusion, etc. that the train may encounter, as well as historical accident data, to generate a test scenario library. Based on the scenario library, conduct virtual tests to improve the coverage of test scenarios.

[0057] 2. Modularize and decouple the virtual-reality fusion test scenarios, extract the components of the test scenarios, analyze the intrinsic connections between different virtual-reality test scenario elements under complex test requirements, establish a modular test scenario library, and provide reconstruction technology for different scenario modules based on the virtual-reality environment and test requirements to cover typical and boundary safety scenarios in the train operation environment.

[0058] 3. Taking into account the dynamic and static elements of the test scenarios such as meteorology, surrounding environment, and human / animal activities, combined with the uncertainty of artificial intelligence algorithms, the train operation environment safety assurance system testing technology is carried out based on the expected functional safety analysis, and an unknown risk scenario prediction and safety assessment method is established to realize the test and evaluation of the railway operation environment safety detection and monitoring system equipment.

[0059] like Figure 3 As shown, the embodiment of the present application includes a train operation safety test system based on a combination of virtual and real, and the system includes:

[0060] A test scenario requirement information determination module 11, wherein the test scenario requirement information determination module 11 is used to import the information to be tested into the platform access layer for requirement analysis and determine the test scenario requirement information;

[0061] A test channel building module 12, which is used to transfer the test scenario requirement information to the basic layer, match the virtual test scenario requirements in the scenario library, obtain the virtual test scenario, and build a test channel in combination with the real test scenario;

[0062] An intelligent evaluation module 13, which is used to perform simulation tests in the test channels in sequence based on the test tasks received by the management layer, and to perform intelligent evaluation on the simulation test results;

[0063] The visualization display module 14 is used to input the test evaluation results into the application layer for visualization display.

[0064] Furthermore, the embodiment of the present application also includes:

[0065] A module for determining properties of an object to be tested, the module for determining properties of an object to be tested being used to identify test properties of the information to be tested and determine properties of the object to be tested;

[0066] A test feature acquisition module, the test feature acquisition module is used to extract features of the information to be tested according to the preset dimension of the attribute based on the attribute of the object to be tested, so as to obtain the test features of the object to be tested;

[0067] A test scenario requirement information acquisition module, the test scenario requirement information acquisition module is used to set a cluster center, the cluster center corresponds to a preset test scenario requirement feature, cluster the test features of the object to be tested based on the cluster center, and obtain the test scenario requirement information.

[0068] Furthermore, the embodiment of the present application also includes:

[0069] A multi-level historical data set construction module, which is used to collect a record data set of train operation, classify the record data set through a decision tree model, and construct a multi-level historical data set, which includes weather categories, environmental scene categories, and operation safety categories;

[0070] A multi-category scene data set construction module, wherein the multi-category scene data set construction module is used to aggregate multi-category scenes based on the multi-level historical data set to construct a multi-category scene data set;

[0071] An element extraction set construction module, wherein the element extraction set construction module is used to extract scene elements from the multi-category scene data set to construct an element extraction set;

[0072] A missing data description information determination module, the missing data description information determination module is used to traverse the multi-category scene data set and the element extraction set respectively based on preset scene elements to determine the missing data description information;

[0073] The element library construction module is used to supplement the scenes and elements according to the missing data description information, and construct the element library using the supplemented scene-element library data and their mapping relationship.

[0074] Furthermore, the embodiment of the present application also includes:

[0075] A quantity evaluation module, the quantity evaluation module is used to collect data according to the missing data description information and perform a quantity evaluation on the collection results;

[0076] A core description information acquisition module, wherein the core description information acquisition module is used to acquire the core description information of the missing data description information when the data volume evaluation result does not meet the supplementary requirements;

[0077] A genetically derived data set acquisition module, the genetically derived data set acquisition module is used to perform characteristic genetic derivation based on the core description information to obtain a genetically derived data set, wherein the genetically derived data set is obtained by performing characteristic genetic changes on the core description information according to a preset derivation step length and derivation direction;

[0078] A missing data derivative set construction module, wherein the missing data derivative set construction module is used to collaboratively change the missing data description information other than the core description information based on the genetic derived data set to construct a missing data derivative set;

[0079] A derivative data supplementation module is used to collect historical record data sets based on the core description information, construct a simulation module, perform simulation through the simulation module based on the missing data derivative set, and screen the derivative data that meets the scenario simulation results for supplementation.

[0080] Furthermore, the embodiment of the present application also includes:

[0081] A scenario component extraction module, the scenario component extraction module is used to perform modular decoupling of scenario requirements based on the test scenario requirement information, and extract scenario components of the test scenario;

[0082] A test channel building module is used to traverse and match the scene library based on the scene constituent elements, obtain a set of matching scene elements, and analyze the intrinsic connections between the scene elements in the matching scene element set, establish a modular test scene library, and build a test channel.

[0083] Furthermore, the embodiment of the present application also includes:

[0084] A collaborative real scene extraction module, the collaborative real scene extraction module is used to extract a collaborative real scene based on the virtual test scene requirements, the collaborative real scene is a real scene with the highest similarity to the virtual test scene requirements;

[0085] A collaborative difference analysis module, the collaborative difference analysis module is used to perform collaborative and difference analysis based on the modular test scenario library and the collaborative real scenario;

[0086] A difference constituent element fusion module is used to obtain constituent elements of a collaborative real scene based on the synergy, and to fuse the difference constituent elements in combination with the differences to obtain virtual and real scene elements and build the test channel.

[0087] Furthermore, the embodiment of the present application also includes:

[0088] A test result extraction module, the test result extraction module is used to extract discrete test results and continuous test results according to the simulation test results;

[0089] A discrete evaluation result acquisition module, which is used to build a discrete evaluation module, evaluate the discrete test results, and obtain discrete evaluation results;

[0090] A continuous evaluation result acquisition module, which is used to build a continuous evaluation module, evaluate the continuous test results, and obtain continuous evaluation results;

[0091] A test evaluation result generation module is used to set a multi-level evaluation strategy and generate a test evaluation result according to the strategy correspondence between the discrete evaluation results and the continuous evaluation results.

[0092] For the specific implementation of the train operation safety test system based on the combination of virtual and real, please refer to the implementation of the train operation safety test method based on the combination of virtual and real above, which will not be repeated here. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0093] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store news data and data such as time attenuation factors. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement a train operation safety test method based on a combination of virtual and real.

[0094] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0095] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of a train operation safety testing method based on a combination of virtual and real are implemented.

[0096] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of a train operation safety testing method based on a combination of virtual and real are implemented.

[0097] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0098] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A train operation safety testing method based on a combination of virtual and real, characterized in that: The method comprises: Import the information to be tested into the platform access layer for demand analysis and determine the test scenario demand information; The test scenario requirement information is transferred to the basic layer, and the virtual test scenario is matched in the scenario library based on the virtual test scenario requirement to obtain the virtual test scenario, and the test channel is built in combination with the real test scenario; Based on the test tasks received by the management, simulation tests are carried out in the test channel in turn, and the simulation test results are intelligently evaluated; Input the test evaluation results into the application layer for visual display; Among them, before matching in the element library based on the virtual test scenario requirements, it includes: Collecting a record data set of train operation, classifying the record data set through a decision tree model, and constructing a multi-level historical data set, including weather categories, environmental scene categories, and operation safety categories; Aggregate multi-category scenes based on the multi-level historical data sets to construct a multi-category scene data set; Extracting scene elements from the multi-category scene data set to construct an element extraction set; Based on the preset scene elements, the multi-category scene data set and the element extraction set are traversed respectively to determine the missing data description information; Supplementing scenes and elements according to the missing data description information, and constructing the element library using the supplemented scene-element library data and their mapping relationships; Supplement the scene and elements according to the missing data description information, including: According to the missing data description information, data collection is performed, and a quantitative evaluation of the collection results is performed; When the data volume evaluation result does not meet the supplementary requirements, obtain the core description information of the missing data description information; Perform characteristic genetic derivation based on the core description information to obtain a genetically derived data set, wherein the genetically derived data set is obtained by performing characteristic genetic changes on the core description information according to a preset derivation step length and derivation direction; Based on the genetically derived data set, collaboratively changing missing data description information other than the core description information to construct a missing data derivative set; Based on the core description information, a historical record data set is collected, a simulation module is constructed, simulation is performed through the simulation module based on the missing data derivative set, and derivative data that meets the scenario simulation results are screened for supplementation.

2. The method according to claim 1, characterized in that Import the information to be tested into the platform access layer for demand analysis and determine the test scenario demand information, including: Performing test attribute identification on the information to be tested to determine the attributes of the object to be tested; Based on the attributes of the object to be tested, feature extraction is performed on the information to be tested according to preset attribute dimensions to obtain test features of the object to be tested; A cluster center is set, the cluster center corresponds to a preset test scenario requirement feature, and the test features of the object to be tested are clustered based on the cluster center to obtain the test scenario requirement information.

3. The method according to claim 1, characterized in that The test scenario requirement information is transferred to the basic layer, and the virtual test scenario is matched in the scenario library based on the virtual test scenario requirement to obtain the virtual test scenario, and the test channel is built in combination with the real test scenario, including: Based on the test scenario requirement information, modular decoupling of scenario requirements is performed to extract scenario constituent elements of the test scenario; Based on the scene constituent elements, traversal matching is performed in the scene library to obtain a matching scene element set, and the intrinsic connection between the scene elements in the matching scene element set is analyzed to establish a modular test scene library and build a test channel.

4. The method according to claim 3, characterized in that The establishment of a modular test scenario library and construction of a test channel includes: Extracting a collaborative real scene based on the virtual test scene requirement, wherein the collaborative real scene is a real scene with the highest similarity to the virtual test scene requirement; Perform synergy and difference analysis based on the modular test scenario library and the collaborative real scenario; Based on the synergy, the constituent elements of the collaborative real scene are obtained, and the different constituent elements are merged in combination with the differences to obtain the virtual and real scene elements, and build the test channel.

5. The method according to claim 1, characterized in that The intelligent evaluation of the simulation test results includes: Extracting discrete test results and continuous test results according to the simulation test results; Building a discrete evaluation module to evaluate the discrete test results and obtain discrete evaluation results; Building a continuous evaluation module to evaluate the continuous test results and obtain continuous evaluation results; A multi-level evaluation strategy is set, and a test evaluation result is generated according to the strategy correspondence between the discrete evaluation result and the continuous evaluation result.

6. The train operation safety test system based on the combination of virtual and real is characterized by: The system comprises: A test scenario requirement information determination module, which is used to import the information to be tested into the platform access layer for requirement analysis and determine the test scenario requirement information; A test channel building module, which is used to transfer the test scenario requirement information to the basic layer, match the virtual test scenario requirements in the scenario library, obtain the virtual test scenario, and build a test channel in combination with the real test scenario; An intelligent evaluation module, which is used to perform simulation tests in the test channels in sequence based on the test tasks received by the management layer, and to perform intelligent evaluation on the simulation test results; A visualization module, which is used to input the test evaluation results into the application layer for visualization; The system further comprises: A multi-level historical data set construction module, which is used to collect a record data set of train operation, classify the record data set through a decision tree model, and construct a multi-level historical data set, which includes weather categories, environmental scene categories, and operation safety categories; A multi-category scene data set construction module, wherein the multi-category scene data set construction module is used to aggregate multi-category scenes based on the multi-level historical data set to construct a multi-category scene data set; An element extraction set construction module, wherein the element extraction set construction module is used to extract scene elements from the multi-category scene data set to construct an element extraction set; A missing data description information determination module, the missing data description information determination module is used to traverse the multi-category scene data set and the element extraction set respectively based on preset scene elements to determine the missing data description information; An element library construction module, the element library construction module is used to supplement scenes and elements according to the missing data description information, and construct the element library using the supplemented scene-element library data and their mapping relationship; A quantity evaluation module, the quantity evaluation module is used to collect data according to the missing data description information and perform a quantity evaluation on the collection results; A core description information acquisition module, wherein the core description information acquisition module is used to acquire the core description information of the missing data description information when the data volume evaluation result does not meet the supplementary requirements; A genetically derived data set acquisition module, the genetically derived data set acquisition module is used to perform characteristic genetic derivation based on the core description information to obtain a genetically derived data set, wherein the genetically derived data set is obtained by performing characteristic genetic changes on the core description information according to a preset derivation step length and derivation direction; A missing data derivative set construction module, wherein the missing data derivative set construction module is used to collaboratively change the missing data description information other than the core description information based on the genetic derived data set to construct a missing data derivative set; A derivative data supplementation module is used to collect historical record data sets based on the core description information, construct a simulation module, perform simulation through the simulation module based on the missing data derivative set, and screen the derivative data that meets the scenario simulation results for supplementation.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images