A multi-source data driven virtual reality simulation method for heavy haul train

Abstract

The application relates to a multi-source data driven heavy haul train virtual reality simulation method. The method comprises the following steps: acquiring three-dimensional modeling data associated with a target heavy haul train, constructing a digital twin model associated with the target heavy haul train by using the three-dimensional modeling data, and displaying the digital twin model on an interface; acquiring multi-source real-time data of the target heavy haul train, obtaining simulation running information of the target heavy haul train by using the multi-source real-time data; importing the simulation running information into the digital twin model to drive the digital twin model, displaying the driving result of the digital twin model on the interface as a virtual reality simulation result of the target heavy haul train. The method can accurately complete simulation and simulation of the heavy haul train by using the three-dimensional modeling data and the multi-source real-time data, and can visually present the simulation result through the digital twin model and construct an immersive virtual reality environment, so that the intelligent degree of the heavy haul train running simulation method is improved.

Description

Technical Field

[0001] This application relates to the field of transportation simulation technology, and in particular to a virtual reality simulation method for heavy-haul trains driven by multi-source data. Background Technology

[0002] With the development of transportation simulation technology, a technology for simulating the operation scenario of heavy-haul trains has emerged. This technology can synchronize the virtual scene of heavy-haul trains, thereby simulating the operation scenario of heavy-haul trains in a virtual scene.

[0003] Currently, simulations of heavy-haul train operation scenarios can typically be achieved through game engines, such as Unity and Unreal Engine, to build a visual interface, or through professional simulation tools, such as MATLAB / Simulink.

[0004] However, simulations based on game engines lack professional train physics simulation capabilities, while simulations using professional simulation tools have poor visualization effects and are difficult to build immersive virtual reality environments. It is evident that current methods for simulating heavy-haul train operation are not intelligent enough. Summary of the Invention

[0005] Therefore, it is necessary to provide a multi-source data-driven virtual reality simulation method, device, computer equipment, computer-readable storage medium, and computer program product for heavy-haul trains that can improve the intelligence of heavy-haul train operation simulation methods, addressing the aforementioned technical problems.

[0006] Firstly, this application provides a multi-source data-driven virtual reality simulation method for heavy-haul trains, including:

[0007] Obtain the 3D modeling data associated with the target heavy-load train, construct the digital twin model associated with the target heavy-load train using the 3D modeling data, and display the digital twin model on the interface;

[0008] Acquire multi-source real-time data of the target heavy-haul train, and use the multi-source real-time data to obtain the simulation operation information of the target heavy-haul train;

[0009] The simulation operation information is imported into the digital twin model to drive the digital twin model, and the driving result of the digital twin model is displayed on the interface as the virtual reality simulation result of the target heavy-haul train.

[0010] In one embodiment, the 3D modeling data includes: 3D model data of the target heavy-haul train, geospatial information data of the railway where the target heavy-haul train is located, and 3D model data of the railway. Constructing a digital twin model associated with the target heavy-haul train using the 3D modeling data includes: performing lightweight processing on the train 3D model data and the railway 3D model data to obtain lightweight train 3D model data and lightweight railway 3D model data; obtaining the visualization simulation visual requirements of the target heavy-haul train; based on the visualization simulation visual requirements, obtaining target train 3D model data, target geospatial information data, and target railway 3D model data from the lightweight train 3D model data, geospatial information data, and lightweight railway 3D model data; and constructing the digital twin model using the target train 3D model data, target geospatial information data, and target railway 3D model data.

[0011] In one embodiment, obtaining the visual simulation requirements of the target heavy-haul train includes: in response to an interaction mode selection request for the digital twin model on the interface, obtaining a target interaction mode selected for the digital twin model; obtaining the visual simulation requirements based on the target interaction mode; and displaying the digital twin model on the interface includes: in response to a display mode selection request for the digital twin model on the interface, obtaining a target display mode selected for the digital twin model; and displaying the digital twin model on the interface according to the target display mode.

[0012] In one embodiment, the multi-source real-time data includes: train dynamics data, traction control data, and air braking system data of the target heavy-haul train; obtaining simulation operation information for the target heavy-haul train using the multi-source real-time data includes: standardizing the train dynamics data, traction control data, and air braking system data to obtain standard train dynamics data, standard traction control data, and standard air braking system data; inputting the standard train dynamics data into a pre-constructed train dynamics calculation model, and outputting longitudinal dynamics system simulation data of the target heavy-haul train through the train dynamics calculation model; inputting the standard traction control data into a pre-constructed multi-mass traction calculation model, and outputting traction transmission system simulation data of the target heavy-haul train through the multi-mass traction calculation model; inputting the air braking system data into a pre-constructed air braking simulation model, and outputting air braking system simulation data of the target heavy-haul train through the air braking simulation model; and using the longitudinal dynamics system simulation data, traction transmission system simulation data, and air braking system simulation data as the simulation operation information of the target heavy-haul train.

[0013] In one embodiment, after obtaining the simulation operation information for the target heavy-haul train using the multi-source real-time data, the method further includes: inputting the simulation operation information into a pre-built train operation trend prediction model, outputting the predicted train operation trend of the target heavy-haul train through the train operation trend prediction model, and displaying the predicted train operation trend on the interface.

[0014] In one embodiment, after obtaining the simulation operation information for the target heavy-load train using the multi-source real-time data, the method further includes: inputting the simulation operation information into a pre-built train equipment health diagnosis model, outputting the train equipment health analysis results of the target heavy-load train through the train equipment health diagnosis model, and displaying the train equipment health analysis results on the interface.

[0015] Secondly, this application also provides a multi-source data-driven virtual reality simulation device for heavy-haul trains, comprising:

[0016] The three-dimensional data acquisition module is used to acquire the three-dimensional modeling data associated with the target heavy-load train, construct a digital twin model associated with the target heavy-load train using the three-dimensional modeling data, and display the digital twin model on the interface.

[0017] The train data simulation module allows users to acquire multi-source real-time data of the target heavy-load train and use the multi-source real-time data to obtain the simulation operation information of the target heavy-load train.

[0018] The digital twin model driving module is used to import the simulation operation information into the digital twin model to drive the digital twin model, and display the driving result of the digital twin model on the interface as the virtual reality simulation result of the target heavy-haul train.

[0019] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in any embodiment of the first aspect.

[0020] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any embodiment of the first aspect.

[0021] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any embodiment of the first aspect.

[0022] The aforementioned multi-source data-driven virtual reality simulation method, device, computer equipment, computer-readable storage medium, and computer program product for heavy-haul trains acquire 3D modeling data associated with the target heavy-haul train, construct a digital twin model associated with the target heavy-haul train using the 3D modeling data, and display the digital twin model on an interface; acquire multi-source real-time data of the target heavy-haul train, obtain simulation operation information of the target heavy-haul train using the multi-source real-time data; import the simulation operation information into the digital twin model to drive the digital twin model, and display the driving result of the digital twin model on the interface as the virtual reality simulation result of the target heavy-haul train. This application constructs and displays a digital twin model of the target heavy-haul train by collecting 3D modeling data associated with the target heavy-haul train to be simulated. It can then collect multi-source real-time data of the target heavy-haul train to perform simulation deduction, thereby obtaining simulation operation information. Finally, the simulation operation information is imported into the digital twin model to drive and display the model, realizing virtual reality simulation of the heavy-haul train. This method not only accurately simulates heavy-haul trains using 3D modeling data and multi-source real-time data, but also visualizes the simulation results through the digital twin model and constructs an immersive virtual reality environment, thus improving the intelligence of the heavy-haul train operation simulation method. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating a multi-source data-driven virtual reality simulation method for heavy-haul trains in one embodiment.

[0025] Figure 2 This is a flowchart illustrating the process of constructing a digital twin model in one embodiment;

[0026] Figure 3 This is a flowchart illustrating the process of obtaining simulation operation information using multi-source real-time data in one embodiment.

[0027] Figure 4 This is a flowchart illustrating a multi-source data-driven virtual reality simulation method for heavy-haul trains in another embodiment.

[0028] Figure 5 This is a schematic diagram of a multi-source data interoperability method in one embodiment;

[0029] Figure 6 This is a schematic diagram of the architecture of a virtual reality simulation tool platform for heavy-duty trains in one embodiment;

[0030] Figure 7 This is a schematic diagram of the data flow of a virtual reality simulation tool platform for heavy-haul trains in one embodiment.

[0031] Figure 8 This is a schematic diagram of a locomotive driver's cab model in one embodiment;

[0032] Figure 9 A schematic diagram of locomotive wheel modeling in one embodiment;

[0033] Figure 10 A schematic diagram of the pantograph raised on the top of the locomotive in one embodiment;

[0034] Figure 11 A schematic diagram illustrating the lowered state of the pantograph on the top of the locomotive in one embodiment;

[0035] Figure 12 This is a schematic diagram of the environment scene setup in one embodiment;

[0036] Figure 13 This is a schematic diagram of the station construction in one embodiment;

[0037] Figure 14 This is a schematic diagram of data-driven coupler movement in one embodiment;

[0038] Figure 15 This is a schematic diagram of the traction drive system data display function in one embodiment;

[0039] Figure 16 This is a schematic diagram illustrating the longitudinal dynamics data display function in one embodiment;

[0040] Figure 17 This is a schematic diagram of the air braking system data display function in one embodiment;

[0041] Figure 18 This is a schematic diagram illustrating the data preprocessing page display function in one embodiment;

[0042] Figure 19 This is a schematic diagram illustrating the model training page display functionality in one embodiment;

[0043] Figure 20 This is a structural block diagram of a multi-source data-driven virtual reality simulation device for heavy-haul trains in one embodiment.

[0044] Figure 21 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0046] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0047] In one embodiment, such as Figure 1 As shown, a multi-source data-driven virtual reality simulation method for heavy-haul trains is provided. This embodiment illustrates the method's application to a terminal. It is understood that this method can also be applied to a server, and further to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0048] Step S101: Obtain the 3D modeling data associated with the target heavy-load train, construct a digital twin model associated with the target heavy-load train using the 3D modeling data, and display the digital twin model on the interface.

[0049] The target heavy-haul train refers to a heavy-haul train that requires virtual reality simulation. The 3D modeling data can refer to the 3D data used to create a digital twin model of the target heavy-haul train. For example, it may include the 3D model data of the target heavy-haul train, the geospatial information data (GIS data) of the railway where the target heavy-haul train is located, and the 3D model data of the railway where the target heavy-haul train is located.

[0050] Specifically, when users conduct virtual reality simulation of a target heavy-haul train, they can first collect the 3D modeling data associated with the target heavy-haul train through the heavy-haul train virtual reality simulation platform installed in the terminal. The platform can also use the 3D modeling data to construct a digital twin model associated with the target heavy-haul train, which may include a digital twin model of the target heavy-haul train or a digital twin model of the railway where the target heavy-haul train is located, etc. Then, the digital twin model can be displayed on the display interface of the heavy-haul train virtual reality simulation platform.

[0051] Step S102: Obtain multi-source real-time data of the target heavy-load train, and use the multi-source real-time data to obtain simulation operation information for the target heavy-load train.

[0052] Simulation operation information refers to the operation information of the target heavy-load train obtained through simulation. Specifically, multi-source real-time data refers to the multi-source data of the train collected by the sensors of the target heavy-load train. This multi-source real-time data may include real-time data such as train dynamics, traction control, and air braking system.

[0053] Specifically, the virtual reality simulation platform for heavy-haul trains can also collect multi-source real-time data of the target heavy-haul train, and then use the multi-source real-time data to perform simulation and deduction. For example, it can complete the simulation and deduction through preset railway industry algorithms to obtain the simulation operation information of the target heavy-haul train, and thus complete the simulation of the operation status of the target heavy-haul train.

[0054] Step S103: Import the simulation operation information into the digital twin model to drive the digital twin model, and display the driving result of the digital twin model on the interface as the virtual reality simulation result of the target heavy-load train.

[0055] After obtaining the simulation operation information of the target heavy-haul train, the simulation operation information can be imported into the digital twin model to complete the driving of the digital twin model. The driving result of the digital twin model can then be displayed on the display interface of the heavy-haul train virtual reality simulation platform, thereby realizing virtual reality simulation of the target heavy-haul train.

[0056] In the aforementioned multi-source data-driven virtual reality simulation method for heavy-haul trains, the method involves acquiring 3D modeling data associated with the target heavy-haul train, constructing a digital twin model associated with the target heavy-haul train using the 3D modeling data, and displaying the digital twin model on the interface; acquiring multi-source real-time data of the target heavy-haul train, and using the multi-source real-time data to obtain the simulation operation information of the target heavy-haul train; importing the simulation operation information into the digital twin model to drive the digital twin model, and displaying the driving result of the digital twin model on the interface as the virtual reality simulation result of the target heavy-haul train. This application constructs and displays a digital twin model of the target heavy-haul train by collecting 3D modeling data associated with the target heavy-haul train to be simulated. It can then collect multi-source real-time data of the target heavy-haul train to perform simulation deduction, thereby obtaining simulation operation information. Finally, the simulation operation information is imported into the digital twin model to drive and display the model, realizing virtual reality simulation of the heavy-haul train. This method not only accurately simulates heavy-haul trains using 3D modeling data and multi-source real-time data, but also visualizes the simulation results through the digital twin model and constructs an immersive virtual reality environment, thus improving the intelligence of the heavy-haul train operation simulation method.

[0057] In one embodiment, the 3D modeling data includes: 3D model data of the target heavy-haul train, geospatial information data of the railway where the target heavy-haul train is located, and 3D model data of the railway; such as Figure 2 As shown, step S101 may further include:

[0058] Step S201: Lightweight processing is performed on the train 3D model data and the railway 3D model data to obtain lightweight train 3D model data and lightweight railway 3D model data.

[0059] In this embodiment, the 3D modeling data may include: the 3D model data of the target heavy-load train, the geospatial information data (GIS data) of the railway where the target heavy-load train is located, and the 3D model data of the railway where the target heavy-load train is located. In order to reduce the storage capacity of the 3D model data, the 3D model data can also be processed by a high proportion of lightweighting, for example, compressing the 3D model data by 5-50 times to obtain lightweight 3D model data.

[0060] Specifically, the train 3D model data and railway 3D model data can be pre-processed to produce lightweight train 3D model data and lightweight railway 3D model data.

[0061] Step S202: Obtain the visual simulation requirements of the target heavy-haul train. Based on the visual simulation requirements, obtain the target train's 3D model data, target geospatial information data, and target railway's 3D model data from the lightweight train's 3D model data, geospatial information data, and lightweight railway's 3D model data.

[0062] Visualization simulation requirements can characterize the rendering requirements of the digital twin model of the target heavy-haul train, while the target train 3D model data, target geospatial information data, and target railway 3D model data refer to the 3D data ultimately used to render the digital twin model associated with the target heavy-haul train.

[0063] Specifically, after completing the lightweight storage of the 3D model data, i.e. obtaining the lightweight train 3D model data and the lightweight railway 3D model data, the heavy-haul train virtual reality simulation platform can also, according to the current visualization simulation visual requirements, select the target train 3D model data, target geospatial information data, and target railway 3D model data that are ultimately needed to render the digital twin model from the lightweight train 3D model data, geospatial information data, and lightweight railway 3D model data.

[0064] Step S203: Construct a digital twin model using the target train 3D model data, target geospatial information data, and target railway 3D model data.

[0065] Finally, the heavy-haul train virtual reality simulation platform can use the selected target train 3D model data, target geospatial information data, and target railway 3D model data to complete the construction of the digital twin model associated with the target heavy-haul train.

[0066] In this embodiment, the 3D model data can also be lightweighted, and the 3D data can be loaded and filtered according to the visual requirements of visualization and simulation. This method can improve the efficiency of digital twin model rendering.

[0067] Furthermore, step S202 may further include: in response to an interaction mode selection request for the digital twin model on the interface, obtaining the target interaction mode selected for the digital twin model; obtaining the visualization simulation visual requirements based on the target interaction mode; step S101 may further include: in response to a display mode selection request for the digital twin model on the interface, obtaining the target display mode selected for the digital twin model; displaying the digital twin model on the interface according to the target display mode.

[0068] In this embodiment, the heavy-haul train virtual reality simulation platform can provide users with a variety of different interaction modes, such as mouse input interaction mode, preset script roaming mode, walking mode, and flight mode. The mouse input interaction mode refers to the interaction mode in which the user controls the movement and rotation of the camera by dragging and scrolling. The preset script roaming mode refers to the automatic roaming mode controlled by pre-edited scripts. The walking mode refers to the interaction mode in which a first-person simulated person walks in the scene. The flight mode is the interaction mode in which the user freely roams from a third-person perspective. The target interaction mode refers to the interaction mode selected by the user.

[0069] Specifically, users can also select an interaction mode on the display interface of the heavy-haul train virtual reality simulation platform. At this time, the heavy-haul train virtual reality simulation platform can take the interaction mode selected by the user as the target interaction mode and obtain the visual simulation requirements based on the target interaction mode.

[0070] Similarly, the heavy-haul train virtual reality simulation platform can also provide users with a variety of different display modes, such as ground navigation mode, transparent mode, macro display mode, and micro display mode. Ground navigation mode refers to the mode of roaming and browsing the ground part of the device area after activation. Transparent mode refers to the display mode of adjusting the ground transparency, which can be used to browse the tunnel section. Macro display mode refers to the display mode of displaying train-related information within the national / regional field of view. Micro display mode supports rapid positioning from macro to micro. Target display mode refers to the display mode selected by the user.

[0071] Specifically, users can also select a display mode on the display interface of the heavy-haul train virtual reality simulation platform. In this case, the heavy-haul train virtual reality simulation platform can use the display mode selected by the user as the target display mode, and then display the digital twin model on the interface according to the target display mode.

[0072] In this embodiment, multiple interaction modes and display modes can be preset and selected by the user on the interface. When the user selects the target interaction mode and the target display mode, the visualization simulation visual requirements can be obtained based on the target interaction mode, and the digital twin model can be displayed according to the target display mode. This method can improve the diversity of digital twin model display methods.

[0073] In one embodiment, the multi-source real-time data includes: train dynamics data, traction control data, and air braking system data of the target heavy-haul train; such as... Figure 3 As shown, step S102 may further include:

[0074] Step S301: Standardize the train dynamics data, traction control data, and air brake system data to obtain standard train dynamics data, standard traction control data, and standard air brake system data.

[0075] In this embodiment, the multi-source real-time data of the target heavy-load train may include the train dynamics data, traction control data, and air brake system data of the target heavy-load train. The standard train dynamics data, standard traction control data, and standard air brake system data are respectively standardized by standardizing the train dynamics data, traction control data, and air brake system data. For example, the standardization process makes the train dynamics data, traction control data, and air brake system data form a unified data format.

[0076] Step S302: Input standard train dynamics data into the pre-constructed train dynamics calculation model, and output the longitudinal dynamic system simulation data of the target heavy-haul train through the train dynamics calculation model.

[0077] Train dynamics calculation model refers to a pre-constructed algorithm model used to simulate the operating data of the longitudinal dynamic system. Specifically, standard train dynamics data can be input into the pre-constructed train dynamics calculation model to simulate the operating data of the longitudinal dynamic system of the target heavy-load train. Then, the simulation data of the longitudinal dynamic system of the target heavy-load train can be output through the train dynamics calculation model.

[0078] Step S303: Input the standard traction control data into the pre-constructed multi-mass traction calculation model, and output the simulation data of the traction transmission system of the target heavy-load train through the multi-mass traction calculation model.

[0079] The multi-mass traction calculation model is a pre-built algorithm model used to simulate the operating data of the traction drive system. Specifically, standard traction control data can be input into the pre-built multi-mass traction calculation model to simulate the operating data of the traction drive system of the target heavy-load train. Then, the simulation data of the traction drive system of the target heavy-load train can be output through the multi-mass traction calculation model.

[0080] Step S304: Input the air brake system data into the pre-constructed air brake simulation model, and output the air brake system simulation data of the target heavy-haul train through the air brake simulation model.

[0081] The air brake simulation model is a pre-built algorithm model used to simulate the operating data of the air brake system. Specifically, the air brake system data can be input into the pre-built air brake simulation model to simulate the operating data of the air brake system of the target heavy-haul train. Then, the air brake simulation model can output the air brake system simulation data of the target heavy-haul train.

[0082] Step S305: The longitudinal power system simulation data, traction transmission system simulation data, and air brake system simulation data are used as the simulation operation information of the target heavy-haul train.

[0083] After obtaining the simulation operation data of the longitudinal power system, traction transmission system and air braking system, the above data, namely the simulation data of the longitudinal power system, traction transmission system and air braking system, can be used as the simulation operation information of the target heavy-haul train.

[0084] In this embodiment, the train dynamics data, traction control data, and air braking system data of the target heavy-load train can also be used to simulate the operation data of the longitudinal power system, traction transmission system, and air braking system of the target heavy-load train, respectively. This method can improve the completeness of the operation simulation of the target heavy-load train.

[0085] In addition, after step S102, the following steps may also be included: inputting simulation operation information into a pre-built train operation trend prediction model, outputting the predicted train operation trend of the target heavy-load train through the train operation trend prediction model, and displaying the predicted train operation trend on the interface.

[0086] The train operation trend prediction model refers to a pre-built neural network model used to predict the trend of heavy-haul train operation data. In this embodiment, the heavy-haul train virtual reality simulation platform can also be equipped with a train operation trend prediction model. After completing the simulation deduction of the target heavy-haul train and obtaining the simulation operation information, the simulation operation information can be input into the pre-built train operation trend prediction model. The train operation trend prediction model outputs the predicted train operation trend of the target heavy-haul train and displays the predicted train operation trend on the display interface of the heavy-haul train virtual reality simulation platform.

[0087] In this embodiment, after obtaining simulation operation information through simulation deduction, the train operation trend prediction model set in the heavy-haul train virtual reality simulation platform can be used to predict the train operation trend of the target heavy-haul train. In this way, the train operation trend prediction of the target heavy-haul train can be completed in the heavy-haul train virtual reality simulation platform, thereby improving the functional diversity of the heavy-haul train virtual reality simulation platform.

[0088] In one embodiment, after step S102, the method may further include: inputting simulation operation information into a pre-built train equipment health diagnosis model, outputting the train equipment health analysis results of the target heavy-load train through the train equipment health diagnosis model, and displaying the train equipment health analysis results on the interface.

[0089] The train equipment health diagnosis model is a pre-built neural network model used to perform health analysis on train equipment on heavy-haul trains. In this embodiment, the heavy-haul train virtual reality simulation platform can also be equipped with a train equipment health diagnosis model. After completing the simulation deduction of the target heavy-haul train and obtaining the simulation operation information, the simulation operation information can be input into the pre-built train equipment health diagnosis model. The train equipment health diagnosis model performs health analysis on the train equipment on the target heavy-haul train, thereby outputting the train equipment health analysis results of the target heavy-haul train, and displaying the train equipment health analysis results on the display interface of the heavy-haul train virtual reality simulation platform.

[0090] In this embodiment, after obtaining simulation operation information through simulation deduction, the train equipment health diagnosis model set in the heavy-haul train virtual reality simulation platform can be used to perform health analysis on the train equipment of the target heavy-haul train. In this way, the equipment health analysis of the target heavy-haul train can be completed in the heavy-haul train virtual reality simulation platform, thereby improving the functional diversity of the heavy-haul train virtual reality simulation platform.

[0091] In one embodiment, a multi-source data-driven virtual reality simulation method for heavy-haul trains is also provided. This method, based on a self-developed rendering engine-driven heavy-haul train operation simulation system, achieves a high-fidelity, interactive virtual reality simulation environment through multi-source data fusion and digital twin technology. The method may specifically include the following steps:

[0092] Step 1: Build an independent virtual reality rendering engine.

[0093] We have independently developed a high-performance 3D rendering engine with ultra-high rendering efficiency in ultra-large and intensive scenes; based on cloud-native visualization architecture design, it has the capabilities of multi-source heterogeneous data integration, massive data carrying, real-scene rendering, abstract rendering and AI visualization; through the complete independent development of the underlying engine framework, we have completely broken away from the dependence on open source or game engines.

[0094] Step 2: 3D data access and processing.

[0095] GIS data access: Supports multiple methods such as local files, databases and online GIS services, seamlessly integrating mainstream static GIS data formats;

[0096] 3D Data Access: Efficiently accesses various mainstream 3D models, large-scale real-world 3D models, and high-precision laser point clouds;

[0097] 3D design data access: Natively supports access to complex 3D engineering model data (such as BIM, PIM), and directly parses design native format files.

[0098] Step 3: Lightweight 3D model load-bearing capacity.

[0099] The 3D model is subjected to high-scale lightweight processing, with a compression ratio of 5-50 times;

[0100] Employ on-demand loading technology: Based on the current perspective requirements, only request the fragmented model resources that need to be loaded from the server;

[0101] Implement a local caching mechanism: When loading, first read the local cache to determine if the requested latest resource is available;

[0102] To ensure data security: the model of server requests is fragmented and encrypted, and local cache files are bound to the device.

[0103] Step 4: Multi-source data fusion processing.

[0104] Construct a multi-source data fusion architecture that couples train dynamics data, traction control data, and air braking system data;

[0105] Establish a millisecond-level data synchronization mechanism to achieve real-time mapping between the physical world and the virtual world;

[0106] Heterogeneous data is standardized to form a unified data format.

[0107] Step 5: Building the intelligent simulation engine.

[0108] Embedded railway-specific algorithms, including train dynamics calculations, operational trend predictions, and equipment health diagnoses;

[0109] Based on the optimization strategy for digital twin generation, simulation and trend prediction are realized;

[0110] It supports real-time interaction and parameter adjustment, and dynamically updates simulation results.

[0111] Step 6: Virtual Reality Scene Construction and Interaction.

[0112] Construct high-fidelity virtual reality scenes, including train bodies, track environments, and weather effects;

[0113] Multiple interaction methods are supported: mouse input interaction, preset script roaming, walking mode, and flight mode;

[0114] Supports multiple display modes: ground navigation mode, transparent mode, macro display, and micro display.

[0115] like Figure 4 As shown, the specific implementation details of this solution are as follows:

[0116] 1. Virtual Reality Simulation Technology Solution:

[0117] 1.1 Core Architecture:

[0118] Self-developed rendering engine: A high-performance 3D rendering engine developed in-house, supporting real-time rendering of scenes with hundreds of millions of pixels;

[0119] Cloud-native architecture: A cloud-native visual architecture that supports the integration of multi-source heterogeneous data and the handling of massive amounts of data.

[0120] 1.2 Data access capability:

[0121] GIS data access: Supports local files, databases and online GIS services, and integrates mainstream static GIS data formats;

[0122] 3D Data Access: Efficiently accesses various mainstream 3D models, large-scale real-world 3D models, and high-precision laser point clouds;

[0123] Design data access: Natively supports access to complex 3D engineering model data (such as BIM, PIM).

[0124] 1.3 Lightweight Model Techniques:

[0125] High compression ratio: Lightweight processing of 3D models, with a compression ratio of 5-50 times;

[0126] On-demand loading: Based on the current perspective requirements, only the fragmented model resources that need to be loaded are requested from the server;

[0127] Local cache: When loading, first read the local cache to determine if the requested latest resource is available;

[0128] Data security: The server request model is fragmented and encrypted, and local cache files are bound to the device.

[0129] 1.4 Interactive and Display Functions:

[0130] (1) Interaction method:

[0131] Mouse input interaction: drag and scroll to control camera movement and rotation;

[0132] Pre-scripted roaming: Supports automatic roaming controlled by pre-edited scripts;

[0133] Walking mode: First-person perspective simulates a person walking within the scene;

[0134] Flight mode: Free roaming in third-person perspective.

[0135] (2) Display mode:

[0136] Ground navigation mode: When enabled, it allows you to roam and browse the ground portion of the device area;

[0137] Transparent mode: Adjust the ground transparency to view the tunnel section;

[0138] Macro view: Displays train-related information across the national / regional field of view;

[0139] Microscopic display: Supports rapid positioning from macroscopic to microscopic levels.

[0140] 1.5 Scene Management Function:

[0141] (1) Layer control: Supports layered management of elements such as terrain, railways, trains, water systems, and equipment.

[0142] (2) Data query:

[0143] Fuzzy search, full-text search, combined search, and exact search;

[0144] Graphical search: Search for points, circles, spheres, and arbitrary polygons.

[0145] (3) Virtual Reality Performance:

[0146] Model texture lighting, partial hidden surface removal, and semi-transparent display;

[0147] It supports immersive devices such as stereoscopic projection and virtual reality headsets.

[0148] (4) Visualization effect:

[0149] Lighting and texture effects, supporting real-time switching (unreal, realistic, and night scene modes);

[0150] Simulates various weather phenomena (rain, snow, and other meteorological effects).

[0151] 2. Multi-source data fusion technology solution:

[0152] 2.1 Data Fusion Architecture:

[0153] Multi-source heterogeneous data preprocessing: preprocessing multi-source heterogeneous data to achieve feature extraction and attribute determination;

[0154] Real-time business data interface: Integrates real-time business data interface with multi-disciplinary data information;

[0155] Joint decision support: Provide data support for joint decision-making.

[0156] 2.2 Data Interconnection Technology:

[0157] like Figure 5 As shown, three different docking methods are employed to improve docking reliability and transmission efficiency:

[0158] (1) RESTful API:

[0159] Used for sample file uploading, data preprocessing, and feature extraction;

[0160] Leveraging standardized HTTP semantics, state visibility, and statelessness;

[0161] Efficiently handle access requests.

[0162] (2) Hybrid mode of RESTful API + WebSocket:

[0163] Used to handle progress status display;

[0164] Task initiation and parameter submission are performed via API.

[0165] Real-time progress is pushed to the client via WebSocket;

[0166] Ensure the reliability of the operation initiation and provide efficient real-time asynchronous feedback.

[0167] (3) WebSocket protocol:

[0168] Data transmission used in real-time simulation processes;

[0169] Enables the server to proactively and efficiently push data;

[0170] Reduce network latency to ensure real-time perception and response to simulation status.

[0171] 2.3 Data Analysis and Simulation:

[0172] (1) Data Analysis Module:

[0173] Build professional visual data analysis capabilities through component drag-and-drop operations;

[0174] Supports access to multiple data sources (relational databases, static data, etc.);

[0175] It supports interface orchestration and allows users to write JavaScript code to encapsulate data.

[0176] (2) Simulation and deduction:

[0177] A highly simulated railway scene was created based on virtual reality technology;

[0178] Simulation and deduction are performed by integrating algorithms from the railway industry.

[0179] Train operation is optimized through simulation and verification in a virtual environment.

[0180] (3) Trend prediction:

[0181] In-depth analysis of railway operation data and trend prediction;

[0182] Using virtual reality to simulate influencing factors, combined with algorithmic data analysis;

[0183] Predict railway operation trends to provide decision support for managers.

[0184] (4) Equipment diagnostics:

[0185] Combining railway industry algorithms within a virtual reality environment;

[0186] Simulate the operation and function of the equipment, and monitor the data in real time;

[0187] Analyze health status and perform fault diagnosis and early warning.

[0188] 2.4 Digital Twin Construction:

[0189] 3D visualization: Enables 3D visualization of various elements;

[0190] Multi-source data-driven: Dynamic evolution of virtual environments driven by multi-source heterogeneous data;

[0191] Spatiotemporal consistency: ensuring consistency with the spacetime of the physical world;

[0192] Professional algorithm library: Embedded in a professional algorithm library in the virtual environment, supporting the generation of diverse emergencies and emergency scenarios.

[0193] 3. Data analysis and simulation methods:

[0194] 3.1 Data Analysis Module:

[0195] (1) Core functions:

[0196] Visualization and Build: Build professional visual data analysis capabilities through drag-and-drop component operations;

[0197] Geographic Information Components: One-stop solution for visual analysis of spatial geographic data;

[0198] A rich component library: provides a visual drag-and-drop interface to enhance data analysis capabilities.

[0199] (2) Data access capability:

[0200] a. Support for multiple data sources:

[0201] Common relational databases;

[0202] Static data files;

[0203] Other data sources can be integrated as needed.

[0204] b. Data Management:

[0205] Users can manage data sources;

[0206] Supports data source configuration and maintenance.

[0207] (3) Data scalability:

[0208] a. Interface Arrangement:

[0209] When the data source does not meet the requirements, the data can be encapsulated again by writing JavaScript code.

[0210] Enhance the decoupling capability between the display layer and the data layer;

[0211] It supports operations such as data format reshaping.

[0212] b. Third-party interface extension:

[0213] When the simulation platform lacks sufficient third-party interfaces, JavaScript code can be written to encapsulate the data again.

[0214] Enhanced decoupling capabilities, supporting operations such as data format reorganization and calculation conversion.

[0215] (4) Configuration flexibility:

[0216] Visual configuration: Adjust component position and size by dragging and dropping;

[0217] Style adjustment: Adjust styles using configuration attributes;

[0218] Lowering the barrier to entry: Lowering the barrier to entry for building visual data analysis.

[0219] 3.2 Simulation and Deduction:

[0220] (1) Core Concepts:

[0221] Digital Twin Scenarios: Constructing highly realistic digital twin scenarios for railways;

[0222] 3D visualization: Enables the 3D visualization of various elements;

[0223] Data-driven: Dynamic evolution of virtual environments driven by multi-source heterogeneous data.

[0224] (2) Key technologies:

[0225] Spatiotemporal consistency: ensuring that the virtual environment is consistent with the physical world in terms of time and space;

[0226] Professional algorithm library: Embed a professional algorithm library in a virtual environment;

[0227] Emergency scenario generation: Supports the generation of diverse emergencies and emergency scenarios.

[0228] 3.3 Trend Forecasting:

[0229] (1) Technical principle:

[0230] Virtual Reality Integration: Leveraging virtual reality technology with railway industry algorithms;

[0231] In-depth analysis: In-depth analysis of railway operation data and prediction of trends;

[0232] Influencing factor simulation: Using virtual reality to simulate influencing factors.

[0233] (2) Implementation method:

[0234] Digital Twin Construction: Constructing a digital twin of the railway operating environment using virtual reality;

[0235] Multi-dimensional factor fusion: Integrating multiple factors for three-dimensional visualization simulation;

[0236] Data fusion analysis: Based on multi-source heterogeneous data fusion analysis;

[0237] Deep learning simulation: Enables deep learning and dynamic simulation of operational status.

[0238] 3.4 Equipment Diagnostics:

[0239] (1) Technical framework

[0240] Virtual Reality Environment: Combining railway industry algorithms within a virtual reality environment;

[0241] Equipment simulation: Simulates the operation and function of equipment;

[0242] Real-time monitoring: Monitor data in real time and analyze health status.

[0243] (2) Diagnostic methods

[0244] Digital Twin Construction: Constructing digital twins of railway equipment in a virtual reality environment;

[0245] Multi-source data fusion: fusing heterogeneous data from multiple sources;

[0246] Collaborative computing: Enables equipment status simulation and health assessment through collaborative computing.

[0247] (3) Technical implementation:

[0248] Multiphysics coupling: The system is simulated using a multiphysics coupling engine;

[0249] Performance analysis: Combining model analysis with fault characteristics;

[0250] Prediction output: Generates a probability matrix and a lifetime prediction curve.

[0251] Using the aforementioned technologies, a virtual reality simulation tool platform for heavy-haul trains can be constructed. The platform architecture of this platform can be as follows: Figure 6 As shown, it is divided into an infrastructure layer, a basic service layer, a data management layer, a scheduling and orchestration layer, and an application layer. The data flow of this architecture can be seen as follows: Figure 7 As shown.

[0252] For the development of virtual reality simulation scenarios for heavy-haul trains, this embodiment constructs a layered collaborative simulation architecture:

[0253] (1) Design a multi-system solution engine. The backend uses a modular interface to solve the longitudinal dynamics of the train, the traction transmission system and the air braking system in parallel, and establishes a data coupling mechanism for the three systems to form a closed-loop calculation logic.

[0254] (2) Using heterogeneous data stream synchronization technology, a dedicated data channel protocol was designed to normalize the heterogeneous data calculated by the back end and push it to the front end in real time. Data joint debugging and verification showed that the system can achieve millisecond-level synchronization of data from the three systems.

[0255] (3) Using the dynamic visualization mapping method, the front-end component design realizes multi-view collaborative rendering. Each view shares a unified time reference coordinate system, dynamically maps the vehicle body movement trajectory, displays the force change of the coupler in real time, presents the motor torque-speed curve, and synchronously updates the air pressure fluctuation trend.

[0256] The specific implementation interface can be seen as follows:

[0257] 1. 3D visual function debugging:

[0258] The debugging of the 3D visual function includes three parts: modeling the train's 3D model, building the train's operating environment, and data-driven 3D model, thereby realizing the 3D visualization virtual simulation presentation of heavy-haul train operation.

[0259] Train 3D modeling can include, for example: Figure 8 The locomotive cockpit model shown is as follows: Figure 9 The locomotive wheel model shown is as follows: Figure 10 The model shown depicts the pantograph on the top of the locomotive in its raised state, and as shown... Figure 11 The model shows the locomotive with the pantograph on top lowered.

[0260] The setup of the train operating environment can include, for example, Figure 12 The environmental scene setup shown, and as Figure 13 The station setup shown.

[0261] Data-driven 3D models can include data-driven coupler movement, such as... Figure 14 As shown.

[0262] 2. Simulation page presentation:

[0263] The virtual reality simulation platform for heavy-haul trains can have the following data display functions, namely: Figure 15 The traction drive system data display function shown is as follows: Figure 16 The longitudinal dynamic data shown, and as follows Figure 17 The data for the air braking system is shown below.

[0264] 3. Intelligent analysis function page presentation:

[0265] The heavy-haul train virtual reality simulation platform also has the following data display functions, namely: Figure 18 The data preprocessing page shown here displays the functionality, and as... Figure 19 The model training page shown here displays the functionality.

[0266] This embodiment demonstrates how a fully independent virtual reality rendering engine can be developed, eliminating reliance on open-source or commercial game engines and enabling real-time rendering of scenes with hundreds of millions of pixels. A multi-source data fusion architecture is constructed, coupling real-time data from train dynamics, traction control, and air braking systems, and establishing a millisecond-level synchronization mechanism to achieve efficient multi-source data fusion. Furthermore, lightweight processing and dynamic loading technologies support high-fidelity rendering of large-scale train formations and track environments. Physically-level lighting and weather effects are integrated to accurately simulate physical phenomena such as coupler stress and wheel-rail friction, improving simulation performance and visual effects. Simultaneously, an innovative intelligent simulation engine is built, embedding railway-specific algorithms to achieve simulation deduction, operational trend prediction, and equipment health diagnosis, realizing intelligent simulation deduction.

[0267] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0268] Based on the same inventive concept, this application also provides a multi-source data-driven virtual reality simulation device for heavy-haul trains to implement the multi-source data-driven virtual reality simulation method for heavy-haul trains described above. The solution provided by this device is similar to the implementation scheme described in the above method. Therefore, the specific limitations of one or more multi-source data-driven virtual reality simulation device embodiments provided below can be found in the limitations of the multi-source data-driven virtual reality simulation method for heavy-haul trains described above, and will not be repeated here.

[0269] In one embodiment, such as Figure 20 As shown, a multi-source data-driven virtual reality simulation device for heavy-haul trains is provided, comprising: a 3D data acquisition module 2001, a train data simulation module 2002, and a twin model driving module 2003, wherein:

[0270] The 3D data acquisition module 2001 is used to acquire the 3D modeling data associated with the target heavy-load train, construct a digital twin model associated with the target heavy-load train using the 3D modeling data, and display the digital twin model on the interface.

[0271] The train data simulation module 2002 is used to acquire multi-source real-time data of the target heavy-load train and use the multi-source real-time data to obtain the simulation operation information of the target heavy-load train.

[0272] The Twin Model Driving Module 2003 is used to import simulation running information into the digital twin model to drive the digital twin model and display the driving results of the digital twin model on the interface as the virtual reality simulation results of the target heavy-load train.

[0273] In one embodiment, the 3D modeling data includes: 3D model data of the target heavy-haul train, geospatial information data of the railway where the target heavy-haul train is located, and 3D model data of the railway; the 3D data acquisition module 2001 is further used to perform lightweight processing on the train 3D model data and the railway 3D model data to obtain lightweight train 3D model data and lightweight railway 3D model data; to obtain the visualization simulation visual requirements of the target heavy-haul train, and based on the visualization simulation visual requirements, to obtain the target train 3D model data, target geospatial information data, and target railway 3D model data from the lightweight train 3D model data, geospatial information data, and lightweight railway 3D model data; and to construct a digital twin model using the target train 3D model data, target geospatial information data, and target railway 3D model data.

[0274] In one embodiment, the 3D data acquisition module 2001 is further configured to, in response to an interaction mode selection request for the digital twin model on the interface, acquire the target interaction mode selected for the digital twin model; obtain the visualization simulation visual requirements based on the target interaction mode; in response to a display mode selection request for the digital twin model on the interface, acquire the target display mode selected for the digital twin model; and display the digital twin model on the interface according to the target display mode.

[0275] In one embodiment, the multi-source real-time data includes: train dynamics data, traction control data, and air braking system data of the target heavy-load train; the train data simulation module 2002 is further used to standardize the train dynamics data, traction control data, and air braking system data to obtain standard train dynamics data, standard traction control data, and standard air braking system data; the standard train dynamics data is input into a pre-constructed train dynamics calculation model, and the longitudinal dynamics system simulation data of the target heavy-load train is output through the train dynamics calculation model; the standard traction control data is input into a pre-constructed multi-mass traction calculation model, and the traction transmission system simulation data of the target heavy-load train is output through the multi-mass traction calculation model; the air braking system data is input into a pre-constructed air braking simulation model, and the air braking system simulation data of the target heavy-load train is output through the air braking simulation model; the longitudinal dynamics system simulation data, traction transmission system simulation data, and air braking system simulation data are used as the simulation operation information of the target heavy-load train.

[0276] In one embodiment, the multi-source data-driven virtual reality simulation device for heavy-haul trains further includes: an operation trend prediction module, which is used to input simulation operation information into a pre-built train operation trend prediction model, output the predicted train operation trend of the target heavy-haul train through the train operation trend prediction model, and display the predicted train operation trend on the interface.

[0277] In one embodiment, the multi-source data-driven virtual reality simulation device for heavy-haul trains further includes: an equipment health analysis module, which is used to input simulation operation information into a pre-built train equipment health diagnosis model, output the train equipment health analysis results of the target heavy-haul train through the train equipment health diagnosis model, and display the train equipment health analysis results on the interface.

[0278] The modules in the aforementioned multi-source data-driven virtual reality simulation device for heavy-haul trains can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0279] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 21As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a multi-source data-driven virtual reality simulation method for heavy-duty trains. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0280] Those skilled in the art will understand that Figure 21 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0281] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0282] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0283] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0284] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0285] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0286] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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 application.

[0287] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A virtual reality simulation method for heavy-haul trains driven by multi-source data, characterized in that, The method includes: Obtain the 3D modeling data associated with the target heavy-load train, construct the digital twin model associated with the target heavy-load train using the 3D modeling data, and display the digital twin model on the interface; Acquire multi-source real-time data of the target heavy-haul train, and use the multi-source real-time data to obtain the simulation operation information of the target heavy-haul train; The simulation operation information is imported into the digital twin model to drive the digital twin model, and the driving result of the digital twin model is displayed on the interface as the virtual reality simulation result of the target heavy-haul train.

2. The method according to claim 1, characterized in that, The 3D modeling data includes: 3D model data of the target heavy-haul train, geospatial information data of the railway where the target heavy-haul train is located, and 3D model data of the railway; the step of constructing a digital twin model associated with the target heavy-haul train using the 3D modeling data includes: The train 3D model data and the railway 3D model data are subjected to lightweight processing to obtain lightweight train 3D model data and lightweight railway 3D model data. Obtain the visual simulation requirements of the target heavy-haul train. Based on the visual simulation requirements, obtain the target train 3D model data, target geospatial information data, and target railway 3D model data from the lightweight train 3D model data, geospatial information data, and lightweight railway 3D model data. The digital twin model is constructed using the target train 3D model data, target geospatial information data, and target railway 3D model data.

3. The method according to claim 2, characterized in that, The visual requirements for obtaining the target heavy-haul train's visualization simulation include: In response to a request to select an interaction mode for the digital twin model on the interface, the target interaction mode selected for the digital twin model is obtained; the visualization simulation visual requirements are obtained based on the target interaction mode. The process of displaying the digital twin model on the interface includes: In response to a request to select a display mode for the digital twin model on the interface, the target display mode selected for the digital twin model is obtained; the digital twin model is then displayed on the interface according to the target display mode.

4. The method according to claim 1, characterized in that, The multi-source real-time data includes: train dynamics data, traction control data, and air braking system data of the target heavy-haul train; obtaining simulation operation information for the target heavy-haul train using the multi-source real-time data includes: The train dynamics data, traction control data, and air brake system data are standardized to obtain standard train dynamics data, standard traction control data, and standard air brake system data. The standard train dynamics data is input into a pre-constructed train dynamics calculation model, and the longitudinal dynamics system simulation data of the target heavy-haul train is output through the train dynamics calculation model. The standard traction control data is input into a pre-constructed multi-mass traction calculation model, and the simulation data of the traction transmission system of the target heavy-load train is output through the multi-mass traction calculation model. The air braking system data is input into a pre-constructed air braking simulation model, and the air braking system simulation data of the target heavy-haul train is output through the air braking simulation model. The simulation data of the longitudinal power system, the simulation data of the traction transmission system, and the simulation data of the air brake system are used as the simulation operation information of the target heavy-haul train.

5. The method according to claim 4, characterized in that, After obtaining the simulation operation information for the target heavy-haul train using the multi-source real-time data, the method further includes: The simulation operation information is input into a pre-built train operation trend prediction model, and the predicted train operation trend of the target heavy-haul train is output through the train operation trend prediction model. The predicted train operation trend is displayed on the interface.

6. The method according to claim 4, characterized in that, After obtaining the simulation operation information for the target heavy-haul train using the multi-source real-time data, the method further includes: The simulation operation information is input into a pre-built train equipment health diagnosis model, and the train equipment health analysis results of the target heavy-haul train are output through the train equipment health diagnosis model. The health analysis results of the train equipment are displayed on the interface.

7. A virtual reality simulation device for heavy-haul trains driven by multi-source data, characterized in that, The device includes: The three-dimensional data acquisition module is used to acquire the three-dimensional modeling data associated with the target heavy-load train, construct a digital twin model associated with the target heavy-load train using the three-dimensional modeling data, and display the digital twin model on the interface. The train data simulation module allows users to acquire multi-source real-time data of the target heavy-load train and use the multi-source real-time data to obtain the simulation operation information of the target heavy-load train. The digital twin model driving module is used to import the simulation operation information into the digital twin model to drive the digital twin model, and display the driving result of the digital twin model on the interface as the virtual reality simulation result of the target heavy-haul train.

8. 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, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images