Multi-person cooperative practical training and emergency drill system and method based on virtual reality

Abstract

The present application belongs to the technical field of virtual reality, and particularly relates to a multi-person collaborative practical training and emergency drill system and method based on virtual reality. The multi-person collaborative practical training and emergency drill method based on virtual reality comprises the following steps: constructing a virtual mine space according to a production mine excavation engineering plan and a roadway profile; constructing a digital twin of a mining and transportation device; obtaining user usage mode selection information and real-time state data of the user's collaborative operation of a physical model of the mining and transportation device, wherein the mode selection information comprises a training mode and an assessment mode; updating the digital twin data of the mining and transportation device online according to the real-time state data; driving a corresponding virtual three-dimensional model of the mining and transportation device in the virtual mine space to perform a corresponding action, and adjusting the virtual mine space according to the performed action; and using a machine learning algorithm to evaluate the collaborative operation state and the emergency operation state of the mining and transportation device. The present application can realize collaborative operation training of mining engineering.

Description

Technical Field

[0001] The present invention belongs to the field of virtual reality technology, and in particular relates to a multi-person collaborative training and emergency drill system and method based on virtual reality. Background Art

[0002] At present, the mining talent training provided by colleges and universities or mining companies mainly focuses on technical training for students, trainees and employees, and mainly includes technical training for job types and emergency drills in fixed scenarios. There is a lack of technical means for multi-job collaborative operation training and emergency drills in underground on-site environments. The training effect is not ideal, and therefore cannot fully meet the needs of enterprises and colleges and universities for employees and students' practice. Summary of the Invention

[0003] In view of this, the embodiments of the present invention provide a system and method for multi-person collaborative training and emergency drills based on virtual reality to solve the technical problem that the current multi-trade collaborative operation training and emergency drills are quite different from the on-site conditions.

[0004] The technical solution adopted in the present invention is:

[0005] In a first aspect, the present invention provides a multi-person collaborative training and emergency drill method based on virtual reality, the method comprising:

[0006] S1: Construct a virtual mine space based on the production mine excavation engineering plan and tunnel cross-section;

[0007] S2: Build a digital twin of the mining and transportation equipment based on its physical model;

[0008] S3: Acquire the user's usage mode selection information and real-time status data of the physical model of the mining and transportation equipment operated by the user in collaboration, wherein the mode selection information includes a training mode and an assessment mode;

[0009] S4: updating the digital twin data of the mining and transportation equipment online according to the real-time status data;

[0010] S5: Use the digital twin data to drive the corresponding virtual 3D model of the mining and transportation equipment in the virtual mine space to perform corresponding actions, and adjust the virtual mine space according to the executed actions;

[0011] S6: The machine learning algorithm evaluates the collaborative operation status and emergency operation status of the mining and transportation equipment based on the mode selection information and real-time status data.

[0012] In the second aspect, the present invention also provides a multi-person collaborative training and emergency drill method system based on virtual reality, which applies the teaching method described in the first aspect, including a physical model of mining and transportation equipment, a cloud server, and a digital twin update module. The physical model of the mining and transportation equipment is equipped with sensors, and the digital twin update module is used to update the digital twin according to the data collected by the sensors. The digital twin update module is communicatively connected to the cloud server.

[0013] Beneficial Effects: The virtual reality-based multi-person collaborative training and emergency drill method system and method utilizes mining engineering plan views and tunnel cross-sections of a production mine to construct a virtual mine space that fully replicates the complex environment of underground tunnels, equipment layout, geological structures, and more, allowing trainees to experience mine operations in an immersive way. This virtual mine space allows multiple users to collaborate within the same scene, simulating the multi-task collaborative process in an actual mine, thus addressing the lack of collaborative work training in traditional training. Digital twins of mining and transportation equipment are used to map real-time status data of physical equipment to a virtual 3D model. As users operate equipment in the virtual environment, the digital twin data is updated in real time, ensuring that virtual equipment movements are fully synchronized with the physical equipment. This allows for both virtual training and rehearsal support for real-world equipment operation. Flexible training and assessment modes adapt to diverse needs. The system provides both training and assessment modes. The training mode allows trainees to freely practice equipment operation, collaborative processes, and emergency response. The assessment mode automatically evaluates trainee performance and generates quantitative assessment reports. Flexible switching between these two modes is possible. Using machine learning algorithms, the system can assess collaborative operations and analyze the coordination of multi-user operations. By replacing real-world operations with a virtual environment when assessing emergency operations, it can prevent trainees from experiencing equipment damage or personal injury due to operational errors in a real mine. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work, and these are all within the scope of protection of the present invention.

[0015] Figure 1 Schematic diagram of the process of the virtual reality-based multi-person collaborative training and emergency drill method of the present invention;

[0016] Figure 2 A schematic diagram of a scene in a virtual mine in a training mode under a VR perspective of the present invention;

[0017] Figure 3 This is a schematic diagram of a scene in a virtual mine in the assessment mode under the VR perspective of the present invention;

[0018] Figure 4 Schematic diagram of the process of evaluating the implementation status data in the present invention

[0019] Figure 5 Schematic diagram of the flow of the method for training the support vector machine algorithm model in the present invention;

[0020] Figure 6 Schematic diagram of the flow of the method for evaluating using the support vector machine algorithm in the present invention;

[0021] Figure 7 Schematic diagram of the flow of the training mode in the present invention;

[0022] Figure 8 Interactive interface diagram selected for the training items in the present invention;

[0023] Figure 9 Schematic diagram of the process of the assessment mode in the present invention;

[0024] Figure 10 Schematic diagram of the flow of the exhibition viewing mode in the present invention;

[0025] Figure 11 This is a structural block diagram of the virtual reality-based multi-person collaborative training and emergency drill method in the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. It should be noted that, in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. In the description of the present invention, it should be understood that the orientation or position relationship indicated by the terms "center", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like is based on the orientation or position relationship shown in the drawings, and is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the present invention. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further limitations, elements defined by the phrase "comprising..." do not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising the elements. The embodiments of the present invention and the features thereof may be combined with each other if there is no conflict, and all are within the scope of protection of the present invention.

[0027] Example 1

[0028] like Figure 1 As shown, the present invention provides a multi-person collaborative training and emergency drill method based on virtual reality, the method comprising:

[0029] S1: Construct a virtual mine space based on the production mine excavation engineering plan and tunnel cross-section;

[0030] A mining engineering plan is a plan view of the planar layout of a mine's mining operations, including tunnels, working faces, etc. A tunnel profile is a vertical cross-section of a mine tunnel, showing its shape, dimensions, and geological structure.

[0031] This step uses 3D modeling technology to construct a virtual mine space based on the production mine's mining plan and tunnel cross-sections. This space includes the mine's topography, tunnels, and equipment layout, effectively reflecting the actual mine environment. This virtual mine space allows users to conduct operational training in a safe environment, realistically recreating the actual underground working environment while avoiding the risks of on-site operations.

[0032] S2: Build a digital twin of the mining and transportation equipment based on its physical model;

[0033] Mining and transportation equipment refers to the machinery used to extract, transport, and process ore, coal, and other resources during mining operations. These devices play a crucial role in mining operations, improving production efficiency, reducing labor intensity, and ensuring operational safety. Mining and transportation equipment generally falls into three categories: mining equipment, transportation equipment, and auxiliary equipment.

[0034] Mining equipment is mechanical equipment used directly for coal mining, typically performing tasks such as tunneling, cutting, and crushing. Examples include roadheaders and shearers. Shearers are used in longwall mining operations, cutting the coal seam using rotating cutting drums. Transport equipment, such as face conveyors, transports the coal cut by the shearer to the transfer point in the roadway.

[0035] In mining engineering training, trainees use physical models of mining and transportation equipment placed in the training site for training. The physical models of mining and transportation equipment are models made according to the structure and functional characteristics of actual mining and transportation equipment, and can simulate the main functions of actual mining and transportation equipment. The digital twin is a digital representation of the physical model of mining and transportation equipment used by trainees in virtual space, which can synchronize the status and data of the physical equipment in real time. This embodiment can perform three-dimensional modeling on various types of mining and transportation equipment physical models as needed to obtain a virtual model of the corresponding mining and transportation equipment. The virtual model can serve as a digital twin of the mining and transportation equipment. Through the digital twin, users can operate the equipment in a virtual environment, observe the operating status of the equipment in real time, and improve their operational proficiency.

[0036] S3: Acquire the user's usage mode selection information and real-time status data of the physical model of the mining and transportation equipment operated by the user in collaboration, wherein the mode selection information includes a training mode and an assessment mode;

[0037] The system captures the user's selected usage mode (training mode or assessment mode) and real-time status data of the user's collaborative operation of the physical model of the mining and transportation equipment. The training mode is used for learning and practice, while the assessment mode is used to evaluate the user's operational capabilities.

[0038] Training mode: users learn and practice in this mode, and the system provides operation guidance and feedback, such as Figure 2 As shown,

[0039] Assessment mode: Users perform operation assessment in this mode, and the system evaluates and scores based on the operation results, such as Figure 3 shown.

[0040] The training mode covers operating methods such as centralized control one-button start-up, electro-hydraulic control, coal mining machine operation, centralized control center operation, typical troubleshooting, and emergency procedures, and also generates student learning records. The examination mode includes both individual and team assessments. Team assessments involve a team working collaboratively within a set timeframe. Based on how each position handles a problem, the overall accuracy rate of each position and team is statistically evaluated and graded, generating student assessment results.

[0041] Real-time status data is real-time data generated when users operate equipment, such as the location, speed, and operating status of the equipment.

[0042] Through mode selection, the system can provide different operation scenarios according to user needs to meet different training and assessment requirements.

[0043] The physical model of the mining and transportation equipment in this embodiment is an actual teaching and training device that is made by imitating the structure and function of the mining and transportation equipment, and has substantially the same structure and function as the actual mining and transportation equipment operating in a real mine.

[0044] S4: Update the digital twin data of the mining equipment online based on the real-time model parameters. This step uses the model parameters of the mining equipment's physical model collected in real time to update the digital twin, aligning the model parameters with those of the physical model. This ensures that the state of the digital twin is consistent with that of the physical model. This allows the digital twin's state to accurately and promptly reflect the student's operation of the mining equipment's physical model in various teaching scenarios. By updating the digital twin data in real time, the device state in the virtual environment is synchronized with the physical device, improving the accuracy and real-time nature of operations.

[0045] S5: Use the digital twin data to drive the corresponding virtual 3D model of the mining and transportation equipment in the virtual mine space to perform corresponding actions, and adjust the virtual mine space according to the executed actions;

[0046] The updated digital twin data is used to drive the virtual 3D model of the mining and transportation equipment in the virtual mine space to perform corresponding actions, such as moving, rotating, and digging. When the mining and transportation equipment performs actions in the real mine space, the real mine space will also undergo corresponding changes. For example, after the excavation equipment performs an excavation action, the thickness of the wall in the virtual mine space will decrease accordingly. In this regard, the present application also adjusts the virtual space according to the corresponding actions performed by the virtual 3D model of the mining and transportation equipment. For example, after the virtual 3D model of the excavation equipment performs an excavation action, the thickness of the wall in the virtual space is adjusted, so that the virtual space adapts to the trainee's training progress.

[0047] In this embodiment, the initial virtual 3D model of the mining and transportation equipment can be imported into the virtual mine space generated in the previous step. Then, after the digital twin is updated, the updated digital twin data is promptly used to update the virtual 3D model of the mining and transportation equipment in the virtual mine space. This ensures that the state of the virtual 3D model of the mining and transportation equipment in the virtual mine space is synchronized with the state of the physical model of the mining and transportation equipment being operated by the user. This allows the user to experience the effects of operating the mining and transportation equipment in the virtual mine.

[0048] This step uses sensor data from the physical mining model (such as the inclination of hydraulic supports and the speed of scraper conveyors) to update the virtual model in real time, ensuring that the virtual scene synchronizes with the movements of the physical equipment. By driving virtual equipment with digital twin data, users can operate the equipment in real time within the virtual environment, enhancing the immersive and realistic operation.

[0049] To ensure realism, it is necessary to improve the real-time nature of virtual 3D model updates. However, when the amount of updated data is large, the amount of updated data that needs to be processed is large, the data transmission time is long, and the update speed is slow. Regarding the update of the virtual 3D model of the hydraulic support, in this embodiment, the step S5: using the digital twin data to drive the corresponding virtual 3D model of the mining and transportation equipment in the virtual mine space to perform corresponding actions also includes:

[0050] According to the current digital twin data and the previous digital twin data of the hydraulic support, a set of local changes of the virtual three-dimensional model when the hydraulic support guard plate performs an action is obtained;

[0051] During the deployment and retraction of a hydraulic support guard, the base, top plate, and shield remain unchanged, while one portion of the guard expands and contracts, while another portion rotates. Because the guard's expansion and contraction speed and angular velocity do not change abruptly, the guard's expansion and contraction speed and angular velocity can be estimated based on the current and previous digital twin data. This allows us to estimate the possible states of the hydraulic support guard at the updated time point. This set of possible states serves as the localized variation set of the virtual 3D model as the hydraulic support guard executes its movements.

[0052] Sending the shared iteration data of the relevant parts of the side guard plate in the local change collection to the server according to the local change collection;

[0053] Although there are multiple states of the hydraulic support guard plate within the local change set, when the virtual three-dimensional model is updated according to these states, some data used for updating are possessed by these states. The update data possessed by each of the aforementioned groups is the shared iterative data. For example, during the extension and retraction process of the guard plate, the data of the extension and retraction part of the guard plate determined by a small extension speed can be sent to the server as shared iterative data first.

[0054] When the preset update time node is reached, the shared iterative data is used to replace the data of the corresponding part in the virtual three-dimensional model of the hydraulic support;

[0055] If the shared iterative data has been received before the update time node arrives, it is necessary to wait for the update time node to arrive and then use the data to update. If the shared iterative data is received after the update time node arrives, it can be updated at the same time as it is received.

[0056] Executing a shared iterative data update process, the shared iterative data update process comprising:

[0057] Update the current digital twin data;

[0058] This step continuously obtains the latest digital twin data

[0059] Update the local change set based on the updated digital twin data and the previous digital twin data;

[0060] This step obtains the latest local change set based on the new digital twin data

[0061] Acquire newly added shared iteration data according to the updated local change set, and send the newly added shared iteration data to the server;

[0062] As the guard plate performs actions, the uncertainty of the final state of the guard plate becomes smaller and smaller, so new shared iterative data will continue to appear.

[0063] When the new shared iteration data is determined, it is sent to the server for update.

[0064] When a new preset update time node is reached, the data of the corresponding part in the virtual three-dimensional model of the hydraulic support is replaced by the added shared iterative data;

[0065] Determine whether to send redundant data based on the latest local change set and all shared iterative data that have been sent;

[0066] Redundant data refers to the data that needs to be iteratively replaced in all possible states of the virtual three-dimensional model remaining to receive updated data. The more data that has been updated iteratively, the less redundant data there is. When the amount of redundant data is sufficient to complete sending and receiving before the update time node arrives, all redundant data can be sent to the server.

[0067] If so, the redundant data is sent to the server. The server extracts corresponding data from the redundant data based on the final state of the side guard and replaces the corresponding data in the virtual 3D model of the hydraulic support. If not, the shared iterative data update process is repeated. When the final state of the side guard is determined, the data corresponding to the final state of the side guard can be selected to replace the corresponding data in the virtual 3D model of the hydraulic support.

[0068] This step pre-processes the data used for partial replacement of the model during the execution of the action of the hydraulic support guard plate. Before the update node arrives, the update module can be used to determine a part of the shared data and transmit it to the server, which saves server computing power and improves the efficiency of updating the three-dimensional virtual model.

[0069] S6: The machine learning algorithm evaluates the collaborative operation status and emergency operation status of the mining and transportation equipment based on the mode selection information and real-time status data.

[0070] The collaborative operation state refers to the state when multiple users collaboratively operate a device. This state can be the coordination of operations, the sequence of processes, efficiency, etc.

[0071] Emergency operation status: refers to the state in which multiple users collaboratively operate the equipment in an emergency scenario. This state reflects the emergency response capability.

[0072] Machine learning algorithms evaluate the coordinated and emergency operation status of mining and transportation equipment based on the user-selected usage mode (training mode or assessment mode) and real-time status data. The evaluation results can be used to improve operational processes or provide feedback.

[0073] This embodiment constructs a virtual mine space based on the mining engineering plan and tunnel cross-section of the production mine to completely reproduce the complex environment such as underground tunnels, equipment layout, geological structure, etc., so that students can experience the mine operation scene in an immersive way.

[0074] This embodiment supports collaborative operation among multiple users (such as coal miners, scaffolding workers, and safety officers) in a virtual environment, simulating the multi-task collaborative processes of actual mines (e.g., tunneling, mining, and support), thus addressing the lack of collaborative work training in traditional training. Through digital twins of mining and transportation equipment, real-time status data (such as position, speed, and operating parameters) of physical equipment is mapped to a virtual 3D model. As users operate equipment in the virtual environment, the digital twin data is updated in real time, ensuring that virtual equipment movements are fully synchronized with the physical equipment. This can be used for both virtual training and as a rehearsal for real-world equipment operation. Flexible training and assessment modes adapt to diverse needs. The system provides both training and assessment modes. In training mode, trainees can freely practice equipment operation, collaborative processes, and emergency response. The system provides real-time operational guidance and error notifications (such as equipment over-limit alarms). In assessment mode, the system automatically evaluates trainee performance based on preset scoring criteria (such as operational standardization, collaborative efficiency, and emergency response time), generating a quantitative assessment report. Flexible switching between these two modes meets the needs of the entire process, from basic training to skills certification.

[0075] Through machine learning algorithms, the system can evaluate the status of collaborative operations, analyze the coordination of multi-user operations (such as equipment collision risk, task connection efficiency), and identify bottleneck problems in collaborative operations. Evaluate emergency operation status: In simulated emergency scenarios such as gas leakage and mine pressure, analyze the trainees' response speed, standardization of handling procedures, and teamwork capabilities. Based on historical operation data, provide data support for training course design and emergency plan improvement. The virtual environment replaces on-site operations to avoid equipment damage or personal injury caused by operational errors in real mines. Through highly simulated emergency drills (such as fire escape and gas outburst handling), improve the trainees' emergency psychological quality and handling capabilities in real scenarios, and reduce the risk of accidents in actual operations.

[0076] like Figure 4 As shown, in this embodiment, the S6: machine learning algorithm evaluates the collaborative operation state and emergency operation state of the mining and transportation equipment according to the mode selection information and real-time status data, including:

[0077] S61: Acquiring real-time status data of the physical model of the mining and transportation equipment during the process of the trainees collaboratively operating the physical model of the mining and transportation equipment;

[0078] In this embodiment, the real-time model status data of the coal equipment physical model obtained includes but is not limited to data reflecting the height of the hydraulic support column, the angle of the hydraulic support guard plate, the position of the hydraulic support, the angle of the coal mining machine rocker arm, the position of the coal mining machine, the coal mining machine traction speed, and the speed of the belt conveyor.

[0079] In this embodiment, sensors can be installed at set positions on the physical models of each mining and transportation equipment, and these sensors can be used to collect data reflecting the real-time status of the physical model so as to accurately obtain the real-time status of the physical model of the mining and transportation equipment during user training or assessment. For example, for hydraulic supports, displacement sensors and pressure sensors can be installed on the columns, angle sensors can be installed at the hinges of the side guards, displacement sensors can be installed on the front beams, displacement sensors can be installed on the jacks, etc.; for coal mining machines, angle sensors can be installed on the rocker arms, and speed sensors can be installed on the rollers. Position sensors can also be installed on scraper conveyors. Real-time status data refers to parameters dynamically generated by the equipment during operation, which can reflect the accuracy, efficiency, and safety of the current operation. By comprehensively collecting multi-dimensional data, an objective basis is provided for subsequent evaluation, avoiding the limitations of relying on manual observation in traditional training, and ensuring that the evaluation results truly reflect the trainees' actual operating level.

[0080] S62: Obtaining a support vector machine algorithm model trained with data;

[0081] The support vector machine (SVM) is a supervised learning algorithm that classifies high-dimensional data by finding the optimal classification hyperplane. It is particularly suitable for scenarios with small sample sizes and nonlinear data. Before using the SVM algorithm model for evaluation and analysis, this step first trains the SVM algorithm model using data collected by sensors. This data training optimizes the parameters in the SVM algorithm model.

[0082] S63: The support vector machine algorithm model evaluates the collaborative operation status and emergency operation of the mining and transportation equipment based on the input real-time status data of the mining and transportation equipment.

[0083] The evaluation of the collaborative operation status of mining and transportation equipment can include analyzing the collaborative efficiency of multiple devices (such as whether the material connection between the transport vehicle and the tunnel boring machine is smooth) and detecting collaborative conflicts (such as whether there is a collision risk in the equipment's movement trajectory).

[0084] The assessment of emergency operation status includes: judging the speed of emergency response (e.g., whether the ventilation equipment is activated promptly after a gas alarm) and evaluating the standardization of operation (e.g., whether the cutting arm is reset to a safe position during an emergency shutdown).

[0085] S63: The support vector machine algorithm model evaluates the trainee's coal mining operation based on the input model parameter output. After obtaining the data reflecting the model parameters detected by the sensor, the data is input into the trained machine learning algorithm model. The machine learning algorithm outputs the evaluation results of the trainee's coal mining operation based on the input data. The model parameters can indirectly reflect the trainee's operation of the mining and transportation equipment, but the evaluation of whether the trainee's operation meets the standard operation requirements will be affected by multiple model parameters. Different model parameters will also affect each other. Therefore, there is a relatively complex nonlinear relationship between the model parameters and the evaluation results. This embodiment uses the support vector machine algorithm in the machine learning algorithm to process the data collected by the sensor to obtain the evaluation results of the trainee's coal mining operation.

[0086] The SVM algorithm eliminates the subjectivity of traditional manual scoring through data-driven evaluation, ensuring fair and consistent assessment results. SVM's ability to process nonlinear and high-dimensional data enables it to effectively handle the evaluation of multi-variable coupled operational states in a mine environment (for example, the combined impact of the various states of a coal mining machine and the various states of a hydraulic support on equipment operation). The evaluation results are fed back to the training system, which can dynamically adjust the training difficulty (such as increasing the complexity of emergency scenarios) to achieve personalized training path design. By accurately identifying potential risks in collaborative operations (such as equipment collisions and emergency response delays), the consequences of accidents are simulated in a virtual environment in advance to enhance the trainees' risk prediction capabilities.

[0087] like Figure 5 As shown, in this embodiment, the step S62: obtaining a support vector machine algorithm model trained with data includes:

[0088] S621: Using sensors installed on the mining and transportation equipment to obtain status data of the mining and transportation equipment during the user's operation of the mining and transportation equipment;

[0089] S622: Extracting a device collaborative operation status data set and an emergency operation data set from the status data;

[0090] This embodiment can analyze and evaluate the training effect from two aspects: the equipment collaborative operation status and emergency operation. To this end, this embodiment extracts a device collaborative operation status dataset for evaluating the equipment collaborative operation status and an emergency operation dataset for evaluating emergency operation from the collected status data.

[0091] S623: Acquire an initial model of the equipment collaborative operation state and an initial model of the emergency operation, wherein both the initial model of the equipment collaborative operation state and the initial model of the emergency operation adopt a support vector machine algorithm model;

[0092] S624: Labeling the data in the device collaborative operation status dataset according to the evaluation result corresponding to the device collaborative operation status dataset;

[0093] When this step is implemented, operators can perform collaborative operations on mining and transportation equipment, and then obtain data related to the status of the mining and transportation equipment detected by the sensors during the operation. They can also manually determine whether the operation meets the corresponding requirements according to the operating specifications for collaborative operations of mining and transportation equipment. The judgment result will serve as the evaluation result corresponding to the equipment collaborative operation status data set.

[0094] S625: Labeling the data in the emergency operation dataset according to the evaluation result corresponding to the emergency operation dataset;

[0095] When this step is implemented, operators can collaborate on mining and transportation equipment in emergency situations, obtain data related to the emergency operation status detected by sensors during the operation, and manually determine whether the operation meets the corresponding requirements according to the emergency operation specifications. The judgment result serves as the evaluation result corresponding to the emergency operation data set.

[0096] S626: Training the initial model of the equipment collaborative operation state using the labeled equipment collaborative operation state data to obtain an equipment collaborative operation state evaluation algorithm model;

[0097] S627: The emergency operation initial model is trained using the labeled emergency operation data to obtain an emergency operation evaluation algorithm model.

[0098] This step trains the support vector machine algorithm through the labeled data set, and continuously optimizes the model parameters until the evaluation effect of the machine learning algorithm model meets the requirements.

[0099] like Figure 6 As shown, in this embodiment, the S63: support vector machine algorithm model evaluates the collaborative operation state and emergency operation state of the mining and transportation equipment according to the input real-time status data of the mining and transportation equipment, including:

[0100] S630: Using sensors installed on the mining and transportation equipment to obtain real-time status data of the mining and transportation equipment during the user's operation of the mining and transportation equipment;

[0101] S631: extracting a real-time equipment collaborative operation status data set and a real-time emergency operation data set from the real-time status data;

[0102] S632: Obtaining data category labels corresponding to each data in the device collaborative operation status data set;

[0103] In this step, the data category labels include positive (indicated by a value of +1) and negative (indicated by a value of -1).

[0104] A threshold method can be used to obtain data category labels for each data point in the equipment collaborative operation status dataset. This involves setting a threshold based on the equipment's safety operating specifications and determining the category directly from the sensor data. For example, if the pressure sensor on a hydraulic support column exceeds the rated range, it is labeled as negative; if it does, it is labeled as positive. Alternatively, sensor data can be fed into a deep learning algorithm model, which automatically outputs the corresponding data category labels.

[0105] S633: Inputting the data in the operation status data set and the corresponding data category labels into the equipment collaborative operation status assessment algorithm model;

[0106] S634: The equipment collaborative operation status evaluation algorithm model outputs the evaluation result of the corresponding mining and transportation equipment collaborative operation status based on the input equipment collaborative operation status data, which specifically includes the following steps:

[0107] Obtain support vectors corresponding to device collaborative operation status data;

[0108] Calculating a kernel function value of the support vector;

[0109] Multiply each kernel function value by the corresponding Lagrange multiplier and the category label (+1 if the category label is positive, -1 if the category label is negative), and then add all the multiplied results;

[0110] The calculation result is obtained by adding the bias term to the summation result.

[0111] The evaluation results of the coordinated operation status of mining and transportation equipment can include whether the material handover time between the shearer and the transportation equipment is accurate, whether the shearer starts ventilation synchronously during cutting, etc.

[0112] S635: Obtaining data category labels corresponding to each data in the emergency operation data set;

[0113] Similarly, the data category labels of emergency operation data include positive (indicated by the value +1) and negative (indicated by the value -1).

[0114] The method for obtaining data category labels corresponding to each data point in the emergency operation data can use a threshold method. This method sets a threshold based on the equipment's safe operating specifications and directly determines the category based on the sensor data. For example, if the support resistance of a hydraulic support does not reach the set value, it is marked as a negative category, while if the support resistance of a hydraulic support does not reach the set value, it is marked as a positive category.

[0115] In addition, the sensor data can also be input into the deep learning algorithm model, and the deep learning algorithm model automatically outputs the data category label corresponding to the sensor data.

[0116] S636: Inputting the data in the emergency operation data set and the corresponding data category labels into the emergency operation evaluation algorithm model;

[0117] S637: The emergency operation evaluation algorithm model outputs the corresponding emergency operation evaluation result based on the input emergency operation data, specifically including the following steps:

[0118] Obtain support vectors corresponding to emergency operation data;

[0119] Calculating a kernel function value of the support vector;

[0120] Multiply each kernel function value by the corresponding Lagrange multiplier and the category label (+1 if the category label is positive, -1 if the category label is negative), and then add all the multiplied results;

[0121] The calculation result is obtained by adding the bias term to the summation result.

[0122] The evaluation results of emergency operations can include: whether the emergency stop button is pressed immediately after the alarm is triggered; whether the cutting arm is reset to a safe position after the emergency stop; and whether the cutting head is positioned away from the danger zone (such as interference with the bracket).

[0123] like Figure 7 As shown, in this embodiment, when the acquired mode selection information is a training mode, the method further includes:

[0124] S71: Obtaining a training item selected by the user;

[0125] The user can choose to use the training mode or assessment mode through the system. After the user makes a selection to the system, the system will generate mode selection information. If the generated mode selection information is training mode, the system can also allow the user to select the current training item. Figure 8 As shown, users can select specific training items through a virtual reality interactive interface (such as gesture selection, voice command, or menu click).

[0126] S72: Play the corresponding training video according to the training item;

[0127] Training videos provide detailed demonstrations and explanations of specific operational methods for training items, such as centralized control one-button start, electro-hydraulic control, shearer operation, centralized control center operation, typical troubleshooting methods, and emergency operation procedures. Trainees can select training items based on their skill weaknesses, achieving on-demand training and improving learning efficiency.

[0128] S73: Generate a learning record sheet based on the collaborative operation status and emergency operation status of the mining and transportation equipment.

[0129] During the training process, the system records the trainees' operation data (such as equipment parameters, collaborative action timing) and the evaluation results of the machine learning algorithm in real time, and automatically generates a structured learning record sheet. The record sheet includes: Operation data summary: such as task completion time, equipment utilization rate, and number of incorrect operations. Evaluation results: Collaborative efficiency score based on the SVM algorithm, emergency response level (such as "excellent" and "needs improvement"). Improvement suggestions: Targeted suggestions generated based on error patterns (such as "shortening the loading and unloading interval time of transport vehicles" and "strengthening roof support operation training"). The record sheet can be exported for trainees to review or instructors to review.

[0130] When the acquired mode selection information is a training mode, the method further includes:

[0131] Build a team collaboration capability profile based on the team's historical performance data, including:

[0132] Collect data from the team's past training sessions, including overall team operation accuracy, team task completion, equipment operation proficiency, collaboration time deviation, etc.

[0133] By comparing with historical excellent teams through clustering algorithm, the assistance ability level of the team is determined.

[0134] The team collaboration capability portrait and the spatial environment state of the virtual mine space are used as input to construct a deep Q network to output the optimal fault injection parameters. The fault injection parameters include the fault type and the timing of the fault occurrence.

[0135] To enhance the realism of training, environmental changes in a real mine, such as roof subsidence and rising gas concentrations, can be simulated in the virtual mine space. Different environmental changes are likely to cause different equipment failures. Different levels of team collaboration capabilities can address different faults. This step utilizes a deep Q-network to generate the fault type and timing that best matches the team's capabilities and the virtual mine's spatial environment based on the team collaboration profile and the virtual mine's spatial environment.

[0136] According to the fault injection parameters, the corresponding fault type is injected into the virtual mine space when the fault generation timing conditions are met; for example, if the team's roof support collaboration ability is intermediate, a hydraulic support fault can be injected when the roof pressure is too high.

[0137] Determine, based on the fault type, that the virtual three-dimensional model of each mining and transportation equipment is updated to a state corresponding to the fault type;

[0138] The mining and transportation equipment has different states under different fault types. For example, when a hydraulic support fails, the hydraulic support height drops and the supporting force decreases. This step updates the virtual 3D model to the state when the corresponding fault type occurs.

[0139] determining execution limit parameters of the virtual three-dimensional model according to the fault type and the updated virtual three-dimensional model;

[0140] When a fault occurs, the performance of mining and transportation equipment is affected, and its actions are restricted. The restrictions on actions vary depending on the fault type. The parameters that constrain the actions of mining and transportation equipment are called execution restriction parameters. For example, the hydraulic system pressure of a support is limited to a certain pressure. The output power of a hydraulic support is also limited to a certain value.

[0141] Determine the status of relevant components of the corresponding actual physical model according to the fault type and the updated virtual three-dimensional model;

[0142] Update the actual physical model according to the status of relevant components of the actual physical model;

[0143] This step reversely updates the virtual three-dimensional model under the fault condition to the actual physical model, so that the actual physical model is also in the corresponding state under the fault condition.

[0144] The restriction instructions of the actual physical model are generated according to the fault type and the execution restriction parameters of the virtual three-dimensional model.

[0145] For example, a restriction instruction may be generated based on the execution restriction parameter to keep the hydraulic system pressure of the hydraulic support below a set value.

[0146] This embodiment can reasonably inject equipment faults according to the team's capabilities and environmental conditions, which not only makes the equipment fault handling training process closer to the actual situation, but also makes the fault injection adapt to the team's capabilities, thereby quickly improving the team's assistance capabilities through highly targeted training.

[0147] like Figure 9 As shown, when the acquired mode selection information is the assessment mode, the method further includes:

[0148] S74: Obtaining evaluation results of the coordinated operation status and emergency operation status of the mining and transportation equipment;

[0149] S75: Assigning each evaluation result to each user according to the mining and transportation physical model operated by the user;

[0150] For example, if a certain evaluation result is related to the state of a physical model of a mining and transportation equipment, then the user who operates the physical model of the mining and transportation equipment is found as the user corresponding to the evaluation result.

[0151] S76: Generate single-position assessment performance record data based on the corresponding relationship between the assessment results and the users;

[0152] In assessment mode, the system uses the support vector machine (SVM) algorithm to obtain real-time evaluation results of the collaborative operation status (such as collaborative efficiency score and number of conflicts) and emergency operation status (such as response time and handling standardization score) when trainees operate mining and transportation equipment.

[0153] S77: Get team assessment group information;

[0154] During the team assessment, users are divided into teams. The team assessment grouping information in this step includes which users participating in the training are included in each team. In practice, the system can retrieve team assessment grouping information from a pre-set team database, including team member lists, team types (e.g., mining teams, transport teams), and assessment task assignments (e.g., collaborative excavation tasks, joint emergency drills). Grouping information can also be manually configured by the administrator or automatically matched (e.g., based on trainee department or skill level).

[0155] S78: Obtain the evaluation results corresponding to each group of users according to the team assessment group information as the evaluation result set corresponding to the team;

[0156] This step obtains the evaluation results corresponding to all users in each team.

[0157] S79: Generate team assessment performance record data based on the evaluation result set corresponding to the team.

[0158] This step aggregates the performance of all users within the same team to generate a team assessment score and generates a report. Based on the team assessment results, the system can also generate team assessment score data. This data includes: Overall team score (e.g., collaborative task completion rate, emergency drill compliance rate); Member contribution analysis (e.g., key operational contributors, collaboration bottleneck positions); and Team improvement suggestions (e.g., optimizing team division of labor, strengthening cross-position collaboration training).

[0159] Scientific and effective training requires a gradual and orderly process. However, although current evaluation algorithms can automatically evaluate team performance, they cannot achieve the step-by-step training requirement. In this embodiment, S6: the support vector machine algorithm model evaluates the collaborative operation status and emergency operation of mining and transportation equipment based on the input real-time status data of mining and transportation equipment, including:

[0160] Obtain evaluation indicators of team performance;

[0161] The evaluation indicators can be set as needed, for example, the evaluation indicators can be:

[0162] Task completion: percentage of task progress (e.g. number of completed steps / total number of steps).

[0163] Operation accuracy: the ratio of the number of incorrect operations to the total number of operations.

[0164] Collaborative efficiency: The timing consistency of device collaborative operations (the time synchronization of multiple device actions can be calculated using the DTW algorithm).

[0165] Collaboration efficiency: the time interval from the occurrence of an abnormal event to the team's response.

[0166] Communication effectiveness: response latency to voice commands and accuracy of command execution.

[0167] Each evaluation indicator can be quantified with a corresponding score.

[0168] Determine the team performance score based on the team performance evaluation indicators;

[0169] For example, you can choose four indicators, namely task completion, operation accuracy, coordination efficiency, and emergency response speed, as the basis for scoring. In this case, the team performance score P = w1·task completion score + w2·operation accuracy score + w3·coordination efficiency score + w4·emergency response speed score, where w1 to w4 are the weights assigned to task completion, operation accuracy, coordination efficiency, and emergency response speed, respectively.

[0170] According to the classification comprehensive target value of the support vector machine algorithm model, the historical data of the team performance score and the optimal classification boundary of the support vector machine corresponding to the team performance score are obtained;

[0171] This step can score the team performance during the preliminary experiment and find the optimal classification boundary of the support vector machine for each score. For example, the optimal classification boundary can be selected by minimizing the comprehensive classification target value M, where M = r1·classification accuracy + r2·classification interval + r3·classification error rate, and r1 to r3 are the weights assigned to classification accuracy + r2·classification interval + r3·classification error rate respectively.

[0172] When the sliding window change rate of the team performance score exceeds the threshold, the classification boundary update is triggered;

[0173] This step starts updating the classification boundary when the team performance score changes rapidly. The threshold can be set based on experience.

[0174] When the classification boundary update is triggered, the current team performance score is obtained based on the real-time status data of the mining and transportation equipment;

[0175] Update the kernel function parameters of the support vector machine algorithm model according to the current team performance score and the corresponding relationship; this step predicts the kernel function parameters corresponding to the optimal classification boundary corresponding to the current team score based on the aforementioned corresponding relationship, such as the scale parameter in the kernel function.

[0176] The classification boundary of the support vector machine algorithm model is adjusted according to the updated kernel function parameters.

[0177] After the kernel function parameters are updated, the classification boundary of the support vector machine algorithm model is also updated.

[0178] This embodiment updates the classification boundaries of the assessment model in real time based on the team's performance score during the assessment process, allowing the assessment model to adapt to different performance situations. The classification boundaries can be relaxed when the score is low, reducing the classification error rate, while the classification boundaries can be tightened when the score is high, strengthening the assessment of operational accuracy. The difficulty of the assessment is adapted to the team's performance, thus conforming to the scientific training principle of progressively increasing difficulty. This step first determines the relationship between the team's performance score and the optimal classification boundary through historical data and classification comprehensive target optimization. Then, during the assessment process, the classification boundary is quickly updated based on this corresponding relationship, ensuring accuracy while improving the update response speed.

[0179] like Figure 10 As shown, this embodiment also supports the exhibition viewing mode, which specifically includes the following steps:

[0180] S81: Detecting spectator mode request information;

[0181] The user can send spectator mode request information to the system through the operation interface, and the system will detect the spectator mode request information.

[0182] S82: When a spectator mode request message is detected, a terminal display device for display is determined according to the request message;

[0183] S83: Sending image information for displaying the training process in the virtual mine to the terminal device.

[0184] The image information of the training process allows students and employees to display the operation process of all collaborative personnel through the display screen, and view the error points in each process through the playback function, thereby playing a targeted practical training operation and improving the collaborative operation skills of the team.

[0185] In this embodiment, the method further includes:

[0186] S91: Generate control instructions based on the actions performed by the virtual three-dimensional model of the mining and transportation equipment in the virtual mine space; in the virtual mine space, when the trainee or operator drives the virtual three-dimensional model of the mining and transportation equipment through the digital twin to perform actions (such as coal cutting and support movement), the system converts the virtual actions into control instructions that can be recognized by the physical equipment.

[0187] S92: Sending the control instruction to the corresponding mining and transportation equipment in the actual mine;

[0188] S93: The mining and transportation equipment performs coal mining operations according to the control instructions.

[0189] After receiving and interpreting control commands, mining and transportation equipment in a real mine (such as tunnel boring machines and belt conveyors) uses an embedded control system to drive mechanical actuators to perform corresponding actions. For example, a coal mining machine automatically cuts a coal seam according to a path planned in the virtual environment. During execution, equipment sensors collect real-time status data (such as motor temperature and hydraulic pressure) and feed it back to the virtual mine space, forming a closed-loop control system. This embodiment uses remote control commands generated in the virtual mine space to drive equipment, enabling critical operations (such as shutting down equipment in hazardous areas and selecting escape routes) in extreme environments such as fires and gas leaks, maximizing personnel safety.

[0190] Example 2

[0191] like Figure 11 As shown, this embodiment provides a multi-person collaborative training and emergency drill method system based on virtual reality, which applies the teaching method described in Example 1. The system includes a physical model of mining and transportation equipment, a cloud server, and a digital twin update module. Sensors are installed on the physical model of the mining and transportation equipment. The digital twin update module is used to update the digital twin according to the data collected by the sensors. The digital twin update module is communicatively connected to the cloud server.

[0192] It also includes VR glasses, which are in communication with the cloud server and receive image data sent by the cloud server for displaying the virtual mine space. It also includes a simulation display terminal, which is in communication with the cloud server and is used to receive image information sent by the cloud server for displaying the training process in the virtual mine. When students use this system for learning and training, they watch the virtual space produced by the cloud server by wearing VR glasses. The simulation walking platform is used to simulate the inclination state of the high-angle coal seam tunnel so that the students' body sensation is consistent with the visual sense of the virtual scene. In the spectator mode, the display terminal can show the user the operation process in the virtual mine during the training process.

[0193] The above is a detailed introduction to a virtual reality-based multi-person collaborative training and emergency drill method system and method provided by an embodiment of the present invention.

[0194] It should be understood that the present invention is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted. In the above embodiments, several specific steps are described and illustrated as examples. However, the method of the present invention is not limited to the specific steps described and illustrated. Those skilled in the art may make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present invention.

[0195] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in unit, a function card or the like. When implemented in software, the elements of the present invention are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0196] It should also be noted that the exemplary embodiments described herein describe methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the steps described above. In other words, the steps may be performed in the order described in the embodiments, or in a different order, or several steps may be performed simultaneously.

[0197] The above description is only a specific embodiment of the present invention. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention.

Claims

1. A multi-person collaborative training and emergency drill method based on virtual reality, characterized in that: The method comprises: S1: Construct a virtual mine space based on the production mine excavation engineering plan and tunnel cross-section; S2: Build a digital twin of the mining and transportation equipment based on its physical model; S3: Acquire the user's usage mode selection information and real-time status data of the physical model of the mining and transportation equipment operated by the user in collaboration, wherein the mode selection information includes a training mode and an assessment mode; S4: updating the digital twin data of the mining and transportation equipment online according to the real-time status data; S5: Use the digital twin data to drive the corresponding virtual 3D model of the mining and transportation equipment in the virtual mine space to perform corresponding actions, and adjust the virtual mine space according to the executed actions; S6: The machine learning algorithm evaluates the collaborative operation status and emergency operation status of the mining and transportation equipment based on the mode selection information and the real-time status data; The mining and transportation equipment includes a hydraulic support, and S5 includes: According to the current digital twin data and the previous digital twin data of the hydraulic support, a set of local changes of the virtual three-dimensional model when the hydraulic support guard plate performs an action is obtained; Before a preset update time node, the shared iteration data of the relevant parts of the side guard plate in the local change collection is sent to the server according to the local change collection; When the preset update time node is reached, the shared iterative data is used to replace the data of the corresponding part in the virtual three-dimensional model of the hydraulic support; Executing a shared iterative data update process, the shared iterative data update process comprising: Update the current digital twin data; Update the local change set based on the updated digital twin data and the previous digital twin data; Acquire newly added shared iteration data according to the updated local change set, and send the newly added shared iteration data to the server; When a new preset update time node is reached, the data of the corresponding part in the virtual three-dimensional model of the hydraulic support is replaced by the added shared iterative data; Determine whether to send redundant data based on the latest local change set and all shared iterative data that have been sent; If yes, the redundant data is sent to the server, and the server extracts corresponding data from the redundant data according to the final state of the side guard plate to replace the data of the corresponding part in the virtual three-dimensional model of the hydraulic support. If no, the shared iterative data update process is repeated.

2. The virtual reality-based multi-person collaborative training and emergency drill method according to claim 1, characterized in that: When the acquired mode selection information is an assessment mode, the method further includes: S74: Obtaining evaluation results of the coordinated operation status and emergency operation status of the mining and transportation equipment; S75: Assigning each evaluation result to each user according to the physical model of the mining and transportation equipment operated by the user; S76: Generate single-position assessment performance record data based on the corresponding relationship between the assessment results and the users; S77: Get team assessment group information; S78: Obtain the evaluation results corresponding to each group of users according to the team assessment group information as the evaluation result set corresponding to the team; S79: Generate team assessment performance record data based on the evaluation result set corresponding to the team.

3. The virtual reality-based multi-person collaborative training and emergency drill method according to claim 1, characterized in that: When the acquired mode selection information is a training mode, the method further includes: Build a team collaboration capability profile based on team historical performance data; The deep Q network outputs optimal fault injection parameters based on the input team collaboration capability profile and the spatial environment state of the virtual mine space. The fault injection parameters include the fault type and the timing of the fault occurrence. According to the fault injection parameters, when the conditions of the fault generation timing are met, the corresponding fault type is injected into the virtual mine space; updating the virtual three-dimensional model of each mining and transportation equipment to a state corresponding to the fault type according to the fault type; determining execution limit parameters of the virtual three-dimensional model according to the fault type and the updated virtual three-dimensional model; Determine the status of relevant components of the corresponding actual physical model according to the fault type and the updated virtual three-dimensional model; Update the actual physical model according to the status of relevant components of the actual physical model; The restriction instructions of the actual physical model are generated according to the fault type and the execution restriction parameters of the virtual three-dimensional model.

4. The virtual reality-based multi-person collaborative training and emergency drill method according to claim 1, characterized in that: The S6 includes: S61: Acquiring real-time status data of the physical model of the mining and transportation equipment during the user's operation of the physical model of the mining and transportation equipment; S62: Obtaining a support vector machine algorithm model trained with data; S63: The support vector machine algorithm model evaluates the collaborative operation status and emergency operation of the mining and transportation equipment based on the input real-time status data of the mining and transportation equipment.

5. The virtual reality-based multi-person collaborative training and emergency drill method according to claim 4 is characterized in that: The S63 further includes: Obtain evaluation indicators of team performance; Determine the team performance score based on the team performance evaluation indicators; According to the classification comprehensive target value of the support vector machine algorithm model, the historical data of the team performance score and the optimal classification boundary of the support vector machine corresponding to the team performance score are obtained; Obtaining a correspondence between a team performance score and an optimal classification boundary based on the historical data and the optimal classification boundary; When the sliding window change rate of the team performance score exceeds the threshold, the classification boundary update is triggered; When the classification boundary update is triggered, the current team performance score is obtained based on the real-time status data of the mining and transportation equipment; Update the kernel function parameters of the support vector machine algorithm model according to the current team performance score and the corresponding relationship; The classification boundary of the support vector machine algorithm model is adjusted according to the updated kernel function parameters.

6. The virtual reality-based multi-person collaborative training and emergency drill method according to claim 5, characterized in that: The S62 includes: Utilize sensors installed on the mining and transportation equipment to obtain status data of the mining and transportation equipment during the user's operation of the mining and transportation equipment; Extracting a device collaborative operation status data set and an emergency operation data set from the status data; Acquire an initial model of a coordinated operation state of equipment and an initial model of an emergency operation, wherein both the initial model of the coordinated operation state of equipment and the initial model of the emergency operation adopt a support vector machine algorithm model; Annotate the data in the equipment collaborative operation status dataset according to the evaluation results corresponding to the equipment collaborative operation status dataset; Label the data in the emergency operation dataset according to the evaluation results corresponding to the emergency operation dataset; The equipment collaborative operation status evaluation algorithm model is obtained by training the equipment collaborative operation status initial model through the labeled equipment collaborative operation status data; The emergency operation evaluation algorithm model is obtained by training the initial emergency operation model with labeled emergency operation data.

7. The virtual reality-based multi-person collaborative training and emergency drill method according to claim 5, characterized in that: The S63 includes: Utilize sensors installed on mining and transportation equipment to obtain real-time status data of mining and transportation equipment during user operation; Extracting a real-time equipment collaborative operation status data set and a real-time emergency operation data set from the real-time status data; Obtain the data category label corresponding to each data in the equipment collaborative operation status dataset; Inputting the data in the operation status data set and the corresponding data category labels into the equipment collaborative operation status assessment algorithm model; The equipment collaborative operation status evaluation algorithm model outputs the evaluation results of the corresponding mining and transportation equipment collaborative operation status according to the input equipment collaborative operation status data; Obtain the data category labels corresponding to each data in the emergency operation dataset; Inputting the data in the emergency operation data set and the corresponding data category labels into the emergency operation evaluation algorithm model; The emergency operation evaluation algorithm model outputs the corresponding emergency operation evaluation results based on the input emergency operation data.

8. A multi-person collaborative training and emergency drill system based on virtual reality, applying the multi-person collaborative training and emergency drill method according to any one of claims 1 to 7, characterized in that: It includes a physical model of mining and transportation equipment, a cloud server, and a digital twin update module. The physical model of the mining and transportation equipment is equipped with sensors. The digital twin update module is used to update the digital twin according to the data collected by the sensors. The digital twin update module is communicatively connected to the cloud server.

9. The virtual reality-based multi-person collaborative training and emergency drill system according to claim 8, characterized in that: It also includes VR glasses, which are communicatively connected to the cloud server and receive image data sent by the cloud server for displaying the virtual mine space. It also includes a display terminal, which is communicatively connected to the cloud server and is used to receive image information sent by the cloud server for displaying the training process in the virtual mine.

Images