Multi-scene collaborative simulation mine teaching system and method based on digital twinning

Abstract

The invention relates to the technical field of virtual reality, in particular to a multi-scene collaborative simulation mine teaching system and method based on digital twinning, and the method comprises the steps: generating a virtual mine space containing a large-dip-angle coal seam roadway model according to a mining preparation roadway arrangement form; acquiring a virtual model of the working face equipment as a digital twinborn body of the working face equipment; acquiring real-time model parameters of the working face equipment physical model in different scenes; according to the real-time model parameters, carrying out online updating processing on a digital twinborn body of the working face equipment to obtain an updated digital twinborn body; mapping a virtual three-dimensional model of corresponding working face equipment in a virtual mine space according to the updated digital twin, and controlling the simulation walking platform to incline; and a machine learning algorithm evaluates working face equipment operation according to the real-time model parameters. The experience feeling of students can be improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of virtual reality, and particularly relates to a multi-scenario collaborative simulation mine teaching system and method based on digital twin. Background Art

[0002] The mining of steeply inclined coal seams is a typical operation scenario in coal mines in the western region of China. The layout of the working face and the mining technology are significantly different from those of gently inclined coal seams. Mining engineering teachers generally use various mining and tunneling system models in schools to conduct practical teaching for students and trainees. However, there are the following problems in the existing mining engineering teaching:

[0003] Dispersed physical models: Models such as shearers and hydraulic supports are scattered in different laboratories, and a complete underground operation scenario cannot be constructed;

[0004] Difficult to display steeply inclined: Traditional physical models are difficult to simulate the complex geological conditions of steeply inclined coal seams;

[0005] Restriction of teaching space: The space in the laboratory is limited, and students cannot fully experience the real mine environment. Summary of the Invention

[0006] In view of this, embodiments of the present invention provide a multi-scenario collaborative simulation mine teaching system and method based on digital twin to solve the technical problem that the space in the laboratory is limited and students cannot fully experience the real mine environment.

[0007] The technical solution adopted by the present invention is as follows:

[0008] In a first aspect, the present invention provides a multi-scenario collaborative simulation mine teaching method based on digital twin, and the method includes:

[0009] S1: Generate a virtual mine space containing a steeply inclined coal seam roadway model according to the development and mining roadway layout form of a steeply inclined coal seam mine in actual production;

[0010] S2: Obtain a virtual model of the working face equipment as a digital twin of the working face equipment;

[0011] S3: Obtain the real-time model parameters of multiple physical models of the working face equipment in different scenarios;

[0012] S4: Perform online update processing on the digital twin of the working face equipment according to the real-time model parameters to obtain an updated digital twin;

[0013] S5: Map a corresponding virtual three-dimensional model of the working face equipment in the virtual mine space according to the updated digital twin;

[0014] S6: Use a machine learning algorithm to evaluate the operation of the working face equipment based on the real-time model parameters.

[0015] Preferably, the method further includes:

[0016] S57: Obtain the inclination parameters of the roadway model in the virtual mine space;

[0017] S58: Determine the inclination angle of the simulation walking platform according to the position of the virtual three-dimensional model and the inclination parameters of the roadway model;

[0018] S59: Control the simulation walking platform to tilt in real time according to the inclination angle of the simulation walking platform.

[0019] Preferably, the S4: After performing an online update process on the digital twin of the working face equipment according to the real-time model parameters, the updated digital twin includes;

[0020] S401: Obtain the safety protection range of each working face equipment;

[0021] S402: Determine the safety protection range of the updated digital twin according to the safety protection range of each working face equipment and the corresponding updated digital twin model;

[0022] S403: Judge whether there is mutual interference between the updated virtual three-dimensional models according to the safety protection range of each updated digital twin and the position of the virtual three-dimensional model corresponding to the updated digital twin in the virtual mine space;

[0023] S403: If there is no mutual interference, execute S5;

[0024] S404: If there is mutual interference, suspend the update of the virtual three-dimensional model and send an alarm message according to the interference situation.

[0025] Preferably, the S6: Use a machine learning algorithm to evaluate the operation of the working face equipment based on the real-time model parameters, including:

[0026] S61: Obtain the real-time model parameters during the process of the trainee operating the physical model of the working face equipment in each scenario;

[0027] S62: Obtain the support vector machine algorithm model trained with data;

[0028] S63: The support vector machine algorithm model evaluates the trainee's coal mining operation according to the input model parameters.

[0029] Preferably, the S62: Obtain the support vector machine algorithm model trained with data includes:

[0030] S621: Obtain data of multiple sensors for detecting model parameters when acquiring the equipment on the working face, and divide the sensor data into an independent operation data group and a multi-scenario collaborative operation data group;

[0031] S622: Obtain the support vector machine algorithm model corresponding to the independent operation evaluation item and the support vector machine algorithm model corresponding to the multi-scenario collaborative operation evaluation item respectively as the first support vector machine initial algorithm model and the second support vector machine initial algorithm model;

[0032] S623: Obtain the evaluation results of the evaluation items corresponding to the independent operation data group;

[0033] S624: Obtain the evaluation results of the evaluation items corresponding to the multi-scenario collaborative operation data group;

[0034] S625: Label each group of sensor data according to each evaluation result;

[0035] S626: Train the first support vector machine initial algorithm model with the labeled independent operation data group to obtain an independent operation evaluation algorithm model;

[0036] S627: Train the second support vector machine initial algorithm model with the labeled multi-scenario collaborative operation data group to obtain a multi-scenario collaborative operation evaluation algorithm model.

[0037] Preferably, the S63: The support vector machine algorithm model evaluates the trainee's coal mining operation according to the input model parameters, including:

[0038] S630: Obtain the independent operation data group in the data group generated by detecting the real-time model parameters of the working face equipment;

[0039] S631: Obtain the independent operation evaluation algorithm model;

[0040] S632: Obtain the data category labels corresponding to each data in the independent operation data group;

[0041] S633: Input the data and the corresponding data category labels in the independent operation data group into the independent operation evaluation algorithm model;

[0042] S634: The independent operation evaluation algorithm model outputs the evaluation results of the corresponding independent operation according to the data in the input independent operation data group;

[0043] S635: Obtain the multi-scenario collaborative operation data group in the data group generated by detecting the real-time model parameters of the working face equipment;

[0044] S636: Obtain the multi-scenario collaborative operation evaluation algorithm model;

[0045] S637: Obtain the data category labels corresponding to each data in the multi-scenario collaborative operation data group;

[0046] S638: Input the data and the corresponding data category labels in the multi-scenario collaborative operation group into the multi-scenario collaborative operation evaluation algorithm model;

[0047] S639: The multi-scenario collaborative operation algorithm model outputs the evaluation results of the corresponding multi-scenario collaborative operation according to the data in the input multi-scenario collaborative operation data group.

[0048] Preferably, the evaluation results of the independent operation include whether the hydraulic support is moved in place, whether the protective plate of the hydraulic support is opened, whether the support resistance of the hydraulic support reaches the set value, whether the drum height of the shearer is correct, and whether the oblique cutting feed operation sequence of the shearer is correct; whether the treatment after the occurrence of coal accumulation and material scattering in the scraper conveyor is correct, whether the straightness of the scraper conveyor meets the preset requirements, whether the end operation of the scraper conveyor is correct, whether the installation and evacuation operations of the end support are correct, whether the advanced support matches the mining, and whether the length of the advanced support meets the preset requirements.

[0049] The evaluation results of the multi-scenario collaborative operation include whether the traction speed and position of the shearer match the actions of the hydraulic support, whether the timing sequence of the coal cutting, support moving, and scraper pushing actions is correct, and whether the parallelism of adjacent hydraulic supports meets the preset requirements.

[0050] In a second aspect, the present invention further provides a multi-scenario collaborative simulation mine teaching system based on digital twin, which applies the teaching method described in the first aspect. The method includes a working face equipment physical model, a cloud server, and a digital twin body update module. Sensors are installed on the working face equipment physical model. The digital twin body update module is used to update the digital twin body according to the data collected by the sensors. The digital twin body update module is communicatively connected to the cloud server.

[0051] Preferably, it further includes VR glasses. The VR glasses are communicatively connected to the cloud server, and the VR glasses receive the image data sent by the cloud server for displaying the virtual mine space.

[0052] Preferably, it further includes a simulation walking platform. The simulation walking platform is communicatively connected to the cloud server, and the simulation walking platform is used to receive the data sent by the cloud server for controlling the tilt angle of the simulation walking platform.

[0053] Beneficial effects: In the present invention, the digital-twin-based multi-scenario collaborative simulation mine teaching system and method generate a virtual mine space through the development and preparatory roadway data of an actual mine, accurately reproduce the roadway slope and roof and floor morphology of steeply inclined coal seams, enabling students to intuitively understand the equipment layout logic under complex geological conditions. The virtual model is updated in real time through the sensor data of the physical model to ensure the synchronization of the actions of the virtual scene and the physical equipment. The real-time parameters of equipment such as shearers and hydraulic supports scattered in different laboratories are integrated into a unified virtual scene to construct a complete coal mining operation process chain, breaking through the limitation of physical space fragmentation and presenting the multi-equipment collaborative process completely. By using machine learning algorithms to analyze equipment operation data, evaluation results are generated in real time to guide trainees to correct errors in a timely manner and improve the accuracy of teaching. Description of the Drawings

[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required to be used in the embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings, and all of these are within the protection scope of the present invention.

[0055] Figure 1 It is a schematic flowchart of the digital-twin-based multi-scenario collaborative simulation mine teaching method of the present invention;

[0056] Figure 2 It is a schematic diagram of a partial space in the virtual space from the VR perspective of the present invention;

[0057] Figure 3 It is a schematic diagram of coal mining operations in the virtual space from the VR perspective of the present invention;

[0058] Figure 4 It is a schematic flowchart of the method for controlling the inclination of the simulation platform in the present invention;

[0059] Figure 5 It is a schematic flowchart of the method for updating the digital twin in the present invention;

[0060] Figure 6 It is a schematic flowchart of the method for evaluating the operation of face equipment in the present invention;

[0061] Figure 7 It is a schematic flowchart of the method for training the support vector machine algorithm model in the present invention;

[0062] Figure 8 It is a schematic flowchart of the method for evaluating coal mining operations using the support vector machine algorithm in the present invention;

[0063] Figure 9 It is a structural block diagram of the digital-twin-based multi-scenario collaborative simulation mine teaching method of the present invention. Detailed implementation manners

[0064] To make the objectives, 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 with reference to the accompanying 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 actual relationship or order between these entities or operations. In the description of the present invention, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are 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 operated in a specific orientation, and therefore cannot be construed as a limitation of the present invention. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, the elements defined by the statement "including..." do not exclude the existence of additional identical elements in the process, method, article or device including the said elements. If there is no conflict, the embodiments of the present invention and the various features in the embodiments may be combined with each other, and all are within the protection scope of the present invention.

[0065] Embodiment 1

[0066] As Figure 1 shown, the present invention provides a multi-scenario collaborative simulation mine teaching method based on digital twin, and the method includes:

[0067] S1: Generate a virtual mine space containing a large dip coal seam roadway model according to the development and mining preparation roadway layout form of the large dip coal seam mine in actual production;

[0068] For example, geological exploration data (coal seam dip angle, thickness, roof and floor lithology) and roadway layout drawings (development roadway, mining preparation roadway coordinates) of the actual large dip mine can be obtained; the point cloud data of the underground roadway can also be obtained by 3D laser scanning, and then a virtual mine space can be constructed using a 3D engine based on these data. A 3D roadway grid can also be generated based on the fusion of the BIM model and the point cloud data. The large dip coal seam refers to a coal seam with an inclination angle greater than 35 degrees.

[0069] In this step, a virtual mine space is generated based on the data of the development and preparatory roadways of an actual mine, accurately replicating the roadway gradient and the shapes of the roof and floor of steeply inclined coal seams, enabling students to intuitively understand the equipment layout logic under complex geological conditions.

[0070] S2: Obtain the virtual model of the face equipment as the digital twin of the face equipment;

[0071] Among them, face equipment refers to various mechanical equipment and devices directly involved in coal mining, support, transportation, and safety guarantee operations in a coal mine coal face. These equipment work together to complete the entire process of coal production from coal seam cutting to coal transportation, and are the core components of the mine production system. Face equipment includes face equipment. For example, a shearer is responsible for cutting the coal seam and peeling the coal from the coal wall. Specifically, it includes drum shearers, plough shearers, continuous miners, etc. Different types of shearers are suitable for different coal seam thicknesses and inclinations. For example, steeply inclined coal seams require anti-slip braking devices. Face equipment also includes support equipment, such as hydraulic supports, which are used to support the roof and prevent the roof from caving; hydraulic supports include supported shields suitable for stable roofs, shield supports suitable for broken roofs and providing lateral protection: special steeply inclined supports equipped with anti-tipping and anti-slip devices. Face equipment also includes advanced support equipment, which pre-supports the roadway in front of the coal mining face to prevent the roadway from being damaged by advanced pressure. There are various types of advanced support equipment, such as single hydraulic props, walking-type advanced supports, and unit supports. Face equipment also includes transportation equipment. For example, a scraper conveyor is used to transport the coal cut by the shearer to the roadway transfer point. In this embodiment, 3D models of various types of face equipment can be created as needed to obtain the corresponding virtual models of the face equipment. This virtual model can be used as the digital twin of the face equipment.

[0072] S3: Obtain the real-time model parameters of multiple physical models of face equipment in different scenarios;

[0073] The physical model of the working face equipment in this embodiment is an actual teaching and training equipment made by imitating the structure and function of the working face equipment, and has basically the same structure and function as the actual working face equipment operating in a real mine. Due to the relatively complex coal mining process, a large number of working face equipment are required, and limited by the site, different equipment are often distributed in different teaching scenarios. Therefore, in this step, the model parameters of the working face equipment distributed in different scenarios need to be collected in real time. When the trainees participating in the training operate on the physical models of the working face equipment distributed in different scenarios, the states of the physical models of the working face equipment, such as the postures of the models, the relative position relationships and relative postures between the various components of the working face equipment models, etc., will all change. The parameters reflecting the states of the physical models of the working face equipment, the relative position relationships between the various components of each physical model of the working face equipment, and the relative postures between the various components are the parameters of the aforementioned physical models. This step needs to collect the aforementioned model parameters in real time while the trainees are operating, so as to obtain the model parameters of the physical models of the working face equipment. Since these models are distributed in different scenarios, it is also necessary to maintain the synchronization of data collection in time among the various scenarios during collection.

[0074] S4: Perform an online update process on the digital twin of the working face equipment according to the real-time model parameters to obtain an updated digital twin;

[0075] In this step, the digital twin is updated by using the model parameters of the physical model of the working face equipment collected in real time, so that the model parameters of the digital twin are consistent with those of the physical model, thereby making the state of the digital twin consistent with the state of the physical model of the working face equipment. In this way, the state of the digital twin can accurately and timely reflect the operations of the trainees on the physical models of the working face equipment in various teaching scenarios.

[0076] S5: Map a corresponding virtual 3D model of the working face equipment in the virtual mine space according to the updated digital twin, and control the inclination of the simulation walking platform according to the position of the virtual 3D model in the virtual mine space;

[0077] In this embodiment, the initial virtual 3D model of the working face equipment can be imported into the virtual mine space generated in the previous step in advance. Then, after the digital twin is updated, the virtual 3D model of the working face equipment in the virtual mine space is updated in time by using the updated digital twin, so that the state of the virtual 3D model of the working face equipment in the virtual mine space is synchronized with the state of the physical model of the working face equipment operated by the personnel participating in the training. In this way, the personnel collecting the training can experience the effects generated after operating the working face equipment in the virtual mine, giving the personnel participating in the training in various teaching scenarios an experience similar to that of coal mining operations in the actual mine space. See Figure 2 andFigure 3 As shown in the figure. Since the roadway of the steeply inclined coal seam is generated in the virtual space, when the virtual 3D model of the working face equipment is in the steeply inclined coal seam roadway, the inclination states are different. In this embodiment, a simulation walking platform is used to simulate the inclination scenario of the steeply inclined coal seam roadway.

[0078] In this step, the virtual model is updated in real time through the sensor data of the physical model (such as the inclination angle of the hydraulic support and the cutting depth of the shearer), ensuring the synchronization between the virtual scenario and the actions of the physical equipment. Integrate the real-time parameters of equipment such as shearers and hydraulic supports scattered in different laboratories into a unified virtual scenario, construct a complete coal mine operation process chain, break through the limitation of physical space fragmentation, and fully present the multi-equipment collaborative process.

[0079] S6: Use machine learning algorithms to evaluate the coal mining operation according to the real-time model parameters.

[0080] In this embodiment, while the digital twin can be updated in real time online using the real-time model parameters, and the virtual 3D model of the working face equipment in the virtual mine can be updated in real time, the model parameters of the physical model of the working face equipment collected can be used to timely evaluate the coal mining operations of the personnel in the scenario training. This enables trainees to obtain feedback on the training effects in a timely manner while conducting coal mining operation training in the virtual mine space, which is more conducive for trainees to discover their own deficiencies during the training process and make targeted improvements, significantly improving the training effect.

[0081] In this step, by using the support vector machine algorithm to analyze the equipment operation data, the evaluation results are generated in real time to guide trainees to correct errors in a timely manner and improve the teaching accuracy.

[0082] As Figure 4 shown, in this embodiment, for the multi-scenario collaborative simulation mine teaching method based on digital twin, the method further includes the following steps:

[0083] S57: Obtain the inclination parameters of the roadway model in the virtual mine space;

[0084] The inclination parameters of the roadway model include geometric characteristic parameters such as the slope angle, strike azimuth angle, and radius of curvature of the roadway in the virtual mine space. Among them, the slope angle: the angle between the roadway floor and the horizontal plane, with a range of 0° to 90°, and steeply inclined coal seams are usually defined as 35° to 45°.

[0085] Among them, the strike azimuth angle: the angle between the roadway extension direction and the true north direction, used to determine the spatial orientation of the virtual scenario.

[0086] S58: Determine the inclination angle of the simulation walking platform according to the position of the virtual 3D model and the inclination parameters of the roadway model;

[0087] Among them, the simulation walking platform is a somatosensory simulation device with a dynamically adjustable tilt angle, usually a six-degree-of-freedom (6-DOF) hydraulically driven or electric cylinder driven platform, which can simulate somatosensory feedback such as slopes and vibrations during underground walking.

[0088] S59: Control the tilt of the simulation walking platform according to the tilt angle of the simulation walking platform.

[0089] According to the virtual roadway slope parameters, the pitch angle and roll angle of the simulation walking platform are adjusted in real time through the PID algorithm to keep the somatosensory experience of the trainee consistent with the vision of the virtual scene.

[0090] In this embodiment, through the visual-somatosensory synchronization of the tilt of the simulation platform and the virtual scene, the trainee can personally experience the difficulty of walking in a large dip roadway, solving the problem of "visual and somatosensory disconnection" in traditional VR teaching. When operating on the tilted platform, the trainee needs to synchronously adjust the body posture and the device control strategy to improve the spatial coordination ability in complex environments. This embodiment realizes the deep coupling of the virtual scene and somatosensory feedback through the method of roadway tilt parameter extraction - platform kinematics mapping - high-precision closed-loop control. Compared with traditional fixed platforms or pure VR teaching, it can not only strengthen the teaching immersion through multi-dimensional sensory stimulation, but also make the training safer by simulating extreme working conditions in a controlled environment; and it can also realize three-dimensional evaluation. For example, the operation evaluation dimension can be supplemented through body posture data (such as the center of gravity offset).

[0091] Such as Figure 5 As shown, to solve the problem of interference of working face equipment in different scenarios after multiple scenarios are integrated into the virtual mine space, the S4: After the digital twin of the working face equipment is updated online according to the real-time model parameters, the updated digital twin includes;

[0092] S401: Obtain the safety protection ranges of each working face equipment;

[0093] Among them, the safety protection range of the working face equipment is based on the inherent safety boundary defined by the equipment mechanical structure. For example, the minimum distance between the top beam of the hydraulic support and the shearer drum should be greater than the safety distance.

[0094] S402: Determine the safety protection range of the updated digital twin according to the safety protection ranges of each working face equipment and the corresponding updated digital twin model;

[0095] Among them, the safety protection range of the digital twin is consistent with the safety protection range of the corresponding working face equipment.

[0096] S403: Determine whether there is interference between the updated virtual 3D models based on the security protection scopes of the updated digital twins and the positions of the virtual 3D models corresponding to the updated digital twins in the virtual mine space; the aforementioned interference means that in the virtual mine space, the security protection scopes of two or more devices overlap or intrude, which may lead to the following risks:

[0097] Geometric interference: The collision bodies of the device models are in direct contact, such as the cutting drum of the shearer intruding into the un-shifted support area;

[0098] Process interference: Violating the collaborative operation rules, such as starting the shearer cutting when the advanced support is not completed.

[0099] S403: If there is no mutual interference, then execute S5;

[0100] If there is no mutual interference, then perform normal updates on the 3D models in the virtual mine space, including:

[0101] Obtain the real-time elastic adjustment amount for determining the security protection scope of the virtual 3D model according to the real-time model parameters;

[0102] Determine the elastic boundary of the security protection of the virtual 3D model according to the security protection scope of the digital twin and the dynamic adjustment amount;

[0103] In coal mining operations, the equipment on the working face is often in a constantly changing motion state. If a fixed boundary is used as the security scope, it is difficult to adapt to the dynamic changes of the equipment on the working face in coal mining operations, resulting in its security scope being too conservative and affecting precise operation, or the too small security scope of the equipment on the working face during high-speed movement causing it to be unable to handle emergencies. Therefore, in this embodiment, the static security protection scope is elastically adjusted according to the real-time model parameters reflecting the real-time state of the equipment on the working face (such as the cutting speed of the shearer and the support force of the support), so that it can adapt to the operating state of the equipment on the working face, thus enabling precise operation and avoiding the problem of insufficient emergency handling time. The real-time working face parameters used to determine the dynamic adjustment amount include the cutting speed of the shearer, the drum height, the motor current / temperature; for the hydraulic support: the support pressure, the pushing stroke, the inclination angle; for the conveyor: the chain speed, the load torque, the vibration frequency.

[0104] The specific real-time dynamic adjustment amount can be obtained by multiplying the fixed boundary as the security scope by a correction factor, where the correction factor includes a speed influence factor, a load influence factor, and a geological attenuation influence factor. This can enable the same working face equipment to have different dynamic protection scopes under different dynamic conditions, so that the security protection scope can adapt to the actual operating state of the working face equipment.

[0105] Obtain the dynamic range of the digital twin within a preset future time range according to the real-time model parameters;

[0106] The dynamic range within the preset future time range refers to the possible operating range of the digital twin within a certain period in the future.

[0107] Determine the time-dynamic elastic boundary of the virtual 3D model according to the dynamic range and the elastic boundary;

[0108] For example, pre-calculate the elastic boundary for the next 5s at intervals of 100ms to generate a continuous spatio-temporal body as the time-dynamic elastic boundary. When the operating speed of the working face equipment is relatively fast, the time-dynamic elastic boundary will expand, thus reasonably increasing the safety range. For the case where the model parameters at different moments within the future time range will also change dynamically, the model parameters at a certain future moment can be predicted based on the current real-time model parameters, and the corresponding time-dynamic elastic boundary at that moment can be generated based on the predicted model parameters.

[0109] Judge whether there is mutual interference between the updated virtual 3D models according to the time-dynamic elastic boundary of the virtual 3D model and the position of the virtual 3D model in the virtual mine space;

[0110] Among them, the detection of mutual interference can include hard collision detection. When the safety voxels of two devices appear overlapping in the same spatio-temporal domain, it is judged that a hard collision has occurred;

[0111] Soft conflict detection. When the dynamic elastic boundaries of the virtual 3D models of two working face devices continuously overlap for more than a set duration, it is judged that a soft conflict has occurred;

[0112] Environmental coupling conflict: The intersection of the safety voxels of the equipment and the deformed voxels of the roadway is greater than the set threshold.

[0113] S404: If there is no mutual interference, execute S5;

[0114] S405: If there is mutual interference, suspend the update of the virtual 3D model, roll back the digital twin to a safe state according to the interference situation, and send an alarm message according to the interference situation.

[0115] Among them, the ways of sending alarm messages include:

[0116] Visual warning: Highlight the interference area (red flashing) in the virtual scene;

[0117] Force feedback: Simulate collision vibration through a tactile device;

[0118] Voice prompt: Broadcast the type of violation (such as "E203: The shearer enters an unprotected area")

[0119] S406: Reverse-update the physical model of the working face equipment based on the digital twin in the safe state and initiate the degraded operation mode.

[0120] In this embodiment, after detecting interference, the digital twin is rolled back to the safe state, and the physical model of the working face equipment is reverse-updated using the digital twin in the safe state, so that the physical model of the working face equipment will not continue to operate in the interference state, thus avoiding trainees from training under wrong circumstances. In the degraded operation mode, the operating speed of the physical model is limited within a certain range. In this embodiment, the working face equipment in different scenarios is mapped into the same virtual mine space, and interference caused by unreasonable operations of the actual physical model in different scenarios is avoided through interference detection, making the training environment closer to the real environment.

[0121] As Figure 6 shown, in this embodiment, S6: Use a machine learning algorithm to evaluate the coal mining operation according to the real-time model parameters, including:

[0122] S61: Obtain the real-time model parameters during the process of trainees operating the physical model of the working face equipment in each scenario;

[0123] In this embodiment, the real-time model parameters when obtaining the physical model of the coal equipment include but are not limited to the height of the hydraulic support column, the angle of the hydraulic support rib protection plate, the position of the hydraulic support, the angle of the shearer rocker arm, the position of the shearer, the shearer traction speed, and the speed of the belt conveyor.

[0124] In this embodiment, sensors can be installed at the set positions of each working face equipment physical model, and these sensors are used to collect data reflecting the model parameters so as to accurately obtain the real-time model parameters of the working face equipment physical model during the coal mining operation of the training personnel. For example, for the hydraulic support, displacement sensors and pressure sensors can be installed on the column, an angle sensor can be installed at the hinge of the rib protection plate, a displacement sensor can be installed on the front canopy beam, and a displacement sensor can be installed on the jack; for the shearer, an angle sensor can be installed at the rocker arm, and a rotational speed sensor can be installed on the drum. A position sensor can also be installed on the scraper conveyor.

[0125] S62: Obtain the support vector machine algorithm model trained with data;

[0126] Before using the support vector machine algorithm model for evaluation and analysis, this step first trains the support vector machine algorithm model with the historical data collected by the sensors, and continuously optimizes the parameters in the support vector machine algorithm model through data training, so that it can accurately evaluate the coal mining operation of the trainees according to the data collected by the sensors.

[0127] S63: The support vector machine algorithm model evaluates the coal mining operations of trainees according to the input model parameters. After obtaining the data reflecting the model parameters detected by the sensors, these data are input into the trained machine learning algorithm model, and the machine learning algorithm outputs the evaluation results of the trainees' coal mining operations according to the input data. The model parameters can indirectly reflect the operation of the trainee on the working face equipment. However, the evaluation of whether the trainee's operation meets the standard operation requirements is affected by multiple model parameters, and different model parameters also affect each other. Therefore, there is a relatively complex non-linear relationship between the model parameters and the evaluation results. In this embodiment, the support vector machine algorithm in the machine learning algorithm is used to process the data collected by the sensors to obtain the evaluation results of the trainees' coal mining operations.

[0128] Among them, the S63: The support vector machine algorithm model evaluates the coal mining operations of trainees according to the input model parameters further includes:

[0129] S631: Obtain the historical data of the state vector of the simulation walking platform;

[0130] Among them, the state vector of the simulation walking platform includes state parameters such as the running speed of the conveyor belt of the simulation walking platform, the rotation angle of the turntable, the roll angle of the platform, and the pitch angle of the platform. Specifically, when implementing, data reflecting the foregoing state parameters can be collected.

[0131] S632: Obtain the optimal classification boundary of the support vector machine algorithm model corresponding to the historical data;

[0132] For any set of collected historical data, find the optimal classification boundary of the support vector machine algorithm model corresponding to the generation of this set of data. Among them, the optimal classification boundary can be set as needed. For example, when the platform is stable, the scale parameter of the kernel function is set to a smaller value to keep the classification boundary smooth; when the platform is unstable, the scale parameter of the kernel function is set to a larger value to enhance the flexibility of the classification boundary and adapt to complex data distributions. Among them, the stability degree of the platform can be measured by the change rate of the platform state parameters. When the platform tilt is large, the bias term of the kernel function is set to shift the classification boundary in the tilt direction to adapt to the change of the data distribution.

[0133] S633: Obtain the mapping relationship between the ideal scale parameter and the bias term in the support vector machine and the state vector of the simulation walking platform according to the historical data and the optimal classification boundary;

[0134] Specifically, when implementing, regression analysis can be performed using the historical data of the platform state vector and the scale parameter and bias term under the corresponding optimal classification boundary to obtain the mapping relationship between the ideal scale parameter and the bias term and the state vector of the simulation walking platform.

[0135] S634: Obtain the state vector of the current simulation walking platform when the target state change rate of the simulation walking platform reaches the set threshold;

[0136] The target state of the simulation walking platform can be selected as needed. For example, one or more of the operating speed of the platform conveyor belt, the rotation angle of the turntable, the roll angle of the platform, and the pitch angle of the platform can be selected as the target state. The change amount of the selected target state within a unit time is the target state change rate. When the change rate of one or more of these target states exceeds the set threshold, the dynamic adjustment of the classification boundary can be initiated, and the current state vector of the simulation walking platform at the current moment is obtained.

[0137] S635: Determine the current ideal scale parameter and the current bias term according to the current state vector and the mapping relationship;

[0138] In this step, the optimal scale parameter and bias term corresponding to the current state are found through the mapping relationship based on the current state vector as the current ideal scale parameter and the current bias term.

[0139] S636: Adjust the classification boundary of the support vector machine algorithm model according to the current ideal scale parameter and the bias term.

[0140] In this step, after updating the support vector machine algorithm model with the current ideal scale parameter and the bias term, the classification boundary is adjusted accordingly.

[0141] In this embodiment, the classification boundary of the support vector machine algorithm model is adjusted according to the platform operation state, avoiding misclassification caused by the platform state. Since the platform operation state reflects the environmental state where the user is in the virtual mine space, such an evaluation method can be adaptively adjusted according to the user's environment, making the evaluation method more scientific.

[0142] In this embodiment, S6: Use a machine learning algorithm to evaluate the coal mining operation according to the real-time model parameters, including:

[0143] Such as sticking Figure 7 As shown, in this embodiment, S62: After training the initial support vector machine algorithm model with the training data with labels, the support vector machine algorithm model for evaluation includes:

[0144] S621: Obtain the data of multiple sensors for detecting model parameters when operating the equipment on the working face, and divide the sensor data into independent operation data groups and multi-scenario collaborative operation data groups;

[0145] In this embodiment, sensors installed at the set positions of the equipment on each working face are used to detect and collect model parameters. This embodiment can evaluate the training effect of the trainees from two aspects: the operation standardization of a single working face equipment and the collaborative operation standardization of the working face equipment in multiple different teaching scenarios. For this purpose, in this step, the collected sensor data is divided into an independent operation data group and a multi-scenario collaborative operation data group, which are respectively used to evaluate the operation standardization of a single working face equipment and the collaborative operation standardization of the working face equipment in multiple different teaching scenarios.

[0146] S622: Obtain the support vector machine algorithm models corresponding to the independent operation evaluation items and the support vector machine algorithm models corresponding to the multi-scenario collaborative operation evaluation items as the first support vector machine initial algorithm model and the second support vector machine initial algorithm model respectively;

[0147] Among them, the independent operation evaluation items are used to evaluate the operation standardization of a single working face equipment, and the multi-scenario collaborative operation evaluation items are used to evaluate the collaborative operation standardization of the working face equipment in multiple different teaching scenarios.

[0148] S623: Obtain the evaluation results of the evaluation items corresponding to the independent operation data group;

[0149] When this step is specifically implemented, the operator can be allowed to operate the working face equipment, and then obtain the data of the relevant parameters of the working face equipment detected by the sensor during the operation, and manually determine whether the operation meets the corresponding requirements according to the operation specifications of a single working face equipment. This judgment result is used as the evaluation result of the corresponding sensor data.

[0150] S624: Obtain the evaluation results of the evaluation items corresponding to the multi-scenario collaborative operation data group;

[0151] When this step is specifically implemented, operators in multiple different scenarios can be allowed to operate the working face equipment, and then obtain the data of the relevant parameters of the working face equipment detected by the sensor during the operation, and manually determine whether the operation meets the corresponding requirements according to the collaborative operation specifications of the working face equipment in multiple different teaching scenarios. The judgment result is used as the evaluation result of the corresponding sensor data.

[0152] S625: Label each group of sensor data according to the respective evaluation results;

[0153] S626: Train the first support vector machine initial algorithm model with the labeled independent operation data group to obtain an independent operation evaluation algorithm model;

[0154] S627: Train the second support vector machine initial algorithm model with the labeled multi-scenario collaborative operation data group to obtain a multi-scenario collaborative operation evaluation algorithm model.

[0155] In this step, the support vector machine algorithm is trained with the labeled sensor data, and the parameters of the model are continuously optimized until the evaluation effect of the machine learning algorithm model meets the requirements. Different support vector machines are trained with different data sets.

[0156] As Figure 8 shown, in this embodiment, the step S63: inputting the real-time model parameters into the support vector machine algorithm model to obtain the evaluation result of the coal mining operation includes:

[0157] S630: Obtain the independent operation data set in the data set generated by detecting the real-time model parameters of the working face equipment;

[0158] S631: Obtain the independent operation evaluation algorithm model;

[0159] S632: Obtain the data category labels corresponding to each data in the independent operation data set;

[0160] Among them, the data category labels include the positive class (represented by the value +1) and the negative class (represented by the value -1).

[0161] The method for obtaining the data category label corresponding to the sensor data can adopt the threshold method, that is, set the threshold according to the safe operation specification of the equipment, and directly judge the category through the sensor data. For example, if the data of the pressure sensor on the hydraulic support column exceeds the rated range, it is marked as the negative class, and if it does not exceed the rated range, it is marked as the positive class. 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.

[0162] S633: Input the data and the corresponding data category labels in the independent operation data set into the independent operation evaluation algorithm model;

[0163] S634: The independent operation evaluation algorithm model outputs the evaluation result of the corresponding independent operation according to the data in the input independent operation data set;

[0164] Specifically, it includes the following steps:

[0165] Obtain the support vectors corresponding to the independent operation data;

[0166] Calculate the kernel function values of the support vectors;

[0167] Multiply each kernel function value by the corresponding Lagrange multiplier and category label (if the category label is the positive class, multiply by +1, and if the category label is the negative class, multiply by -1), and then add up all the multiplied results;

[0168] Add a bias term to the added result to obtain the calculation result.

[0169] S635: Obtain the multi-scenario collaborative operation data group in the data group generated by acquiring the real-time model parameters of the detection working face equipment;

[0170] S636: Obtain the multi-scenario collaborative operation evaluation algorithm model;

[0171] S637: Obtain the data category labels corresponding to each data in the multi-scenario collaborative operation data group;

[0172] S638: Input the data and the corresponding data category labels in the multi-scenario collaborative operation group into the multi-scenario collaborative operation evaluation algorithm model;

[0173] S639: The multi-scenario collaborative operation algorithm model outputs the evaluation results of the corresponding multi-scenario collaborative operation according to the data in the input multi-scenario collaborative operation data group, which specifically includes the following steps:

[0174] Obtain the support vectors corresponding to the multi-scenario collaborative operation data;

[0175] Calculate the kernel function values of the support vectors;

[0176] Multiply each kernel function value by the corresponding Lagrange multiplier and class label (multiply by +1 if the class label is a positive class, and multiply by -1 if the class label is a negative class), and then add up all the multiplied results;

[0177] Add a bias term to the added result to obtain the calculation result.

[0178] In this embodiment, the evaluation results of the vertical operation include whether the hydraulic support is moved in place, whether the guard plate of the hydraulic support is opened, whether the support resistance of the hydraulic support reaches the set value, whether the drum height of the shearer is correct, and whether the oblique cutting feed operation sequence of the shearer is correct; whether the treatment after the occurrence of coal accumulation and material scattering in the scraper conveyor is correct, whether the flatness of the scraper conveyor meets the preset requirements, whether the end operation of the scraper conveyor is correct, whether the installation and removal operations of the end support are correct, whether the advanced support matches the mining, and whether the length of the advanced support meets the preset requirements.

[0179] In this embodiment, the evaluation results of the multi-scenario collaborative operation include whether the traction speed and position of the shearer match the actions of the hydraulic support, whether the timing sequence of the coal cutting, support moving, and scraper pushing actions is correct, and whether the parallelism of adjacent hydraulic supports meets the preset requirements.

[0180] In this embodiment, the S5: Mapping the corresponding virtual three-dimensional model of the working face equipment in the virtual mine space according to the updated digital twin also includes:

[0181] S51: Obtain the dynamic incremental change space of the shearer based on the data before and after the update of the digital twin of the shearer;

[0182] In this step, the data before and after the update of the digital twin of the shearer is compared to predict the state of the shearer after performing the action at the next moment. Since only part of the shearer changes when performing an action, and some parts remain unchanged, only the locally changed parts are updated in this embodiment. These locally changed parts are called dynamic increments in this article. And because there are multiple possible states predicted for the shearer, each possible state corresponds to a dynamic increment, and these dynamic increments together form a dynamic incremental change space. For example, after comparing the data before and after, it is found that the left rocker arm of the shearer rotates downward at least, the drums of the left and right rocker arms rotate at a constant speed, and the rest remains unchanged. Since the change amount of the rotation speed of the shearer's rocker arm is limited in a short time, the speed range of the rotation of the shearer's rocker arm within a certain time range can be predicted. The states of the rocker arm and the drum at various rotation speeds within this speed range form the dynamic incremental change space of the shearer.

[0183] S52: The digital twin update module determines the common update data of the shearer according to the dynamic incremental change space;

[0184] Each dynamic increment in the dynamic incremental change space may have the same data that can be used to update the virtual model of the shearer. These data are the intersection of the data of each dynamic increment, and these data are also called common update data in this article. For example, for different rotation angles, the data near the rotation center of the rocker arm is the same, so it can be used as common update data. This step can obtain the common update data in advance at the digital twin update module end through edge computing before the update moment arrives.

[0185] S53: The server updates the corresponding parts of the virtual model of the shearer according to the received common update data;

[0186] Once a part of the common update data is generated, it can be sent to the server first. The server can update the virtual 3D model of the shearer with the common update data according to the pre-set update moment arrangement.

[0187] S54: Determine the data length of the candidate state data of the shearer according to the dynamic incremental change space and the common update data already received by the server;

[0188] Based on the public update data already received by the server, it can be determined which parts of the shearer have had their update data determined, and there are multiple possibilities for the update data of the remaining parts. Each dynamic increment in the dynamic increment change space corresponds to one possibility. In this step, all possible update data for the remaining parts will be obtained as candidate data, and the length of the candidate data will be obtained.

[0189] S55: Determine whether the candidate data processing time meets the requirements based on the candidate data length and the update time point;

[0190] Among them, the candidate data processing time is the time required to send the candidate data to the server. If the candidate data can be processed and sent to the server before the update time point, it meets the requirements; otherwise, it does not meet the requirements.

[0191] S56: If it meets the requirements, the server updates the virtual 3D model based on the end state of the shearer and the candidate data;

[0192] If the candidate data processing time is short enough, the server can receive the candidate data before the update moment, and then select the set of data corresponding to the end state from the candidate data according to the end state of the shearer at the update moment to update the 3D virtual model.

[0193] S57: If not, repeat steps S51 to S56.

[0194] If the candidate data length is long, continue to obtain the public update data to reduce the data length of the candidate data until the candidate data processing time meets the requirements.

[0195] In this embodiment, the public update data is obtained by predicting the motion state of the shearer before the update moment arrives, and the public update data is sent to the server in advance, so that the server can complete the preparation of the data used for the update before the update, thus greatly shortening the time required for the update and significantly increasing the real-time performance of the virtual 3D model update.

[0196] Embodiment 2

[0197] As Figure 9 shown, this embodiment provides a multi-scenario collaborative simulation mine teaching system based on digital twin, which applies the teaching method described in Embodiment 1. The system includes a physical model of working face equipment, a cloud server, and a digital twin update module. Sensors are installed on the physical model of the working face equipment. The digital twin update module is used to update the digital twin according to the data collected by the sensors, and the digital twin update module is communicatively connected to the cloud server.

[0198] Among them, the cloud server generates a virtual mine space containing a large dip angle coal seam roadway model according to the development and drivage roadway layout form of the actual large dip angle coal seam mine. Each sensor installed on the physical model of the working face equipment collects data reflecting the state of the physical model of the working face equipment in real time, and the digital twin update module updates the digital twin online according to the sensor data. The updated digital twin drives the real-time online update of the virtual 3D model of the working face equipment mapped in the virtual mine space.

[0199] The teaching system of this embodiment further includes a VR glasses and a simulation walking platform. The VR glasses are communicatively connected to the cloud server, and the simulation walking platform is communicatively connected to the cloud server. The VR glasses receive the image data for displaying the virtual mine space sent by the cloud server, and the simulation walking platform is used to receive the data for controlling the tilt angle of the simulation walking platform sent by the cloud server. During the process of using this system for learning and training, the trainee views the virtual space generated by the cloud server through the worn VR glasses. The simulation walking platform is used to simulate the tilt state of the large dip angle coal seam roadway, so that the trainee's physical feeling is consistent with the visual of the virtual scene.

[0200] The above is a detailed introduction to a digital twin-based multi-scenario collaborative simulation mine teaching system and method provided by an embodiment of the present invention.

[0201] It should be clear that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, the detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications and additions, or change the order between steps after understanding the spirit of the present invention.

[0202] The functional blocks shown in the above structural block diagrams 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, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments for performing the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted through a data signal carried in a carrier wave on a transmission medium or a communication link. A "machine-readable medium" can include any medium that can store or transmit information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), optical discs, hard disks, fiber optic media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0203] It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps can be executed in the order mentioned in the embodiments, or different from the order in the embodiments, or several steps can be executed simultaneously.

[0204] As mentioned above, the above is only the specific implementation manner of the present invention. Those skilled in the art can 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 foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or replacements, and these modifications or replacements should be covered within the protection scope of the present invention.

Claims

1. A multi-scenario collaborative simulation mine teaching method based on digital twin, characterized in that, The method includes: S1: Generate a virtual mine space containing a large dip coal seam roadway model according to the layout form of the development and preparatory roadways in the actual large dip coal seam mine; S2: Obtain the virtual model of the working face equipment as the digital twin of the working face equipment; S3: Obtain the real-time model parameters of the physical models of the working face equipment in multiple different scenarios; S4: Perform online update processing on the digital twin of the working face equipment according to the real-time model parameters to obtain the updated digital twin; S5: Map the corresponding virtual three-dimensional model of the working face equipment in the virtual mine space according to the updated digital twin, and control the inclination of the simulation walking platform according to the position of the virtual three-dimensional model in the virtual mine space; S6: Use a machine learning algorithm to evaluate the operation of the working face equipment according to the real-time model parameters.

2. The multi-scenario collaborative simulation mine teaching method based on digital twin according to claim 1, wherein, The S5 further includes: S57: Obtain the inclination parameters of the roadway model in the virtual mine space; S58: Determine the inclination angle of the simulation walking platform according to the position of the virtual three-dimensional model and the inclination parameters of the roadway model; S59: Control the real-time inclination of the simulation walking platform according to the inclination angle of the simulation walking platform.

3. The multi-scenario collaborative simulation mine teaching method based on digital twin according to claim 2, characterized in that, The S4 includes; S401: Obtain the safety protection range of each working face equipment; S402: Determine the safety protection range of the updated digital twin according to the safety protection range of each working face equipment and the corresponding updated digital twin model; S403: Judge whether there is mutual interference between the updated virtual three-dimensional models according to the safety protection range of each updated digital twin and the position of the virtual three-dimensional model corresponding to the updated digital twin in the virtual mine space, including: Obtain the dynamic adjustment amount of the safety protection range of the virtual three-dimensional model according to the real-time model parameters; Determine the elastic boundary of the safety protection of the virtual three-dimensional model according to the safety protection range of the digital twin and the dynamic adjustment amount; Obtain the dynamic range of the digital twin within a preset future time according to the real-time model parameters; Determine the time dynamic elastic boundary of the virtual three-dimensional model according to the dynamic range and the elastic boundary; Judge whether there is mutual interference between the updated virtual three-dimensional models according to the time dynamic elastic boundary of the virtual three-dimensional model and the position of the virtual three-dimensional model in the virtual mine space; S404: If there is no mutual interference, execute S5; S405: If there is mutual interference, suspend the update of the virtual three-dimensional model, and roll back the digital twin to a safe state according to the interference situation; S406: Perform reverse update on the physical model of the working face equipment according to the digital twin in the safe state and start the physical model degradation operation mode.

4. The digital-twin-based multi-scenario collaborative simulation mine teaching method according to any one of claims 1 to 3, characterized in that The S6 includes: S61: Obtain the real-time model parameters during the process of the trainees operating the physical model of the working face equipment in each scenario; S62: Obtain the support vector machine algorithm model trained by data; S63: The support vector machine algorithm model evaluates the coal mining operation of the trainees according to the input model parameters.

5. The multi-scenario collaborative simulation mine teaching method based on digital twin according to claim 4, wherein, The S63 further includes: S631: Obtain the historical data of the state vector of the simulation walking platform; S632: Obtain the optimal classification boundary of the support vector machine algorithm model corresponding to the historical data; S633: Obtain the mapping relationship between the ideal scale parameter and the bias term in the support vector machine and the state vector of the simulation walking platform according to the historical data and the optimal classification boundary; S634: Obtain the state vector of the current simulation walking platform when the target state change rate of the simulation walking platform reaches the set threshold; S635: Determine the current ideal scale parameter and the current bias term according to the current state vector and the mapping relationship; S636: Adjust the classification boundary of the support vector machine algorithm model according to the current ideal scale parameter and the bias term.

6. The multi-scenario collaborative simulation mine teaching method based on digital twin according to claim 4, characterized in that, The S62 includes: S621: Obtain the data of multiple sensors for detecting model parameters when operating the working face equipment, and divide the sensor data into an independent operation data group and a multi-scenario collaborative operation data group; S622: Obtain the support vector machine algorithm model corresponding to the independent operation evaluation item and the support vector machine algorithm model corresponding to the multi-scenario collaborative operation evaluation item as the first support vector machine initial algorithm model and the second support vector machine initial algorithm model respectively; S623: Obtain the evaluation results of the evaluation items corresponding to the independent operation data group; S624: Obtain the evaluation results of the evaluation items corresponding to the multi-scenario collaborative operation data group; S625: Label the data in the corresponding independent operation data group and multi-scenario collaborative operation data group according to the evaluation results; S626: Obtain the independent operation evaluation algorithm model after training the first support vector machine initial algorithm model with the labeled independent operation data group; S627: Obtain the multi-scenario collaborative operation evaluation algorithm model after training the second support vector machine initial algorithm model with the labeled multi-scenario collaborative operation data group.

7. The multi-scenario collaborative simulation mine teaching method based on digital twin according to claim 4, characterized in that, The S63 includes: S630: Obtain the independent operation data group in the data group generated by detecting the real-time model parameters of the working face equipment; S631: Obtain the independent operation evaluation algorithm model; S632: Obtain the data category labels corresponding to each data in the independent operation data group; S633: Input the data in the independent operation data group and the corresponding data category labels into the independent operation evaluation algorithm model; S634: The independent operation evaluation algorithm model outputs the corresponding evaluation results of the independent operation according to the data in the input independent operation data group; S635: Obtain the multi-scenario collaborative operation data group in the data group generated by detecting the real-time model parameters of the working face equipment; S636: Obtain the multi-scenario collaborative operation evaluation algorithm model; S637: Obtain the data category labels corresponding to each data in the multi-scenario collaborative operation data group; S638: Input the data in the multi-scenario collaborative operation group and the corresponding data category labels into the multi-scenario collaborative operation evaluation algorithm model; S639: The multi-scenario collaborative operation algorithm model outputs the corresponding evaluation results of the multi-scenario collaborative operation according to the data in the input multi-scenario collaborative operation data group.

8. A multi-scenario collaborative simulation mine teaching system based on digital twins, applying the teaching method according to any one of claims 1 to 7, characterized in that, It includes a physical model of working face equipment, a cloud server, and a digital twin update module. Sensors are installed on the physical model of the working face equipment. The digital twin update module is used to update the digital twin according to the data collected by the sensors, and the digital twin update module is communicatively connected to the cloud server.

9. The digital twin teaching system for simulated mine based on virtual reality technology according to claim 8, characterized in that, It further includes VR glasses. The VR glasses are communicatively connected to the cloud server, and the VR glasses receive image data sent by the cloud server for displaying the virtual mine space.

10. The simulated mine digital twin teaching system based on virtual reality technology according to claim 8, characterized in that, It further includes a simulation walking platform. The simulation walking platform is communicatively connected to the cloud server, and the simulation walking platform is used to receive data sent by the cloud server for controlling the tilt angle of the simulation walking platform.

Images