A coal mine intelligent mining operation training method and system based on virtual display

Abstract

The application discloses a kind of coal mine intelligent mining operation training method and system based on virtual display, it is related to coal mine intelligent training technical field;The present application builds intelligent mining working face twin scene by virtual display and digital twin, collects underground temperature and humidity data to establish exclusive somatic temperature difference mapping model, builds multi-role collaborative operation virtual-real linkage framework and sets up collaborative time sequence locking mechanism, using somatic parameter and collaborative operation parameter fusion operation formula, realize the deep linkage of virtual scene, somatic reproduction and collaborative training.System according to the spatial position of role and the dynamic output of intelligent mining operation intensity somatic control parameter, synchronous locking collaborative operation threshold, improve training fit and operation standardization.The present application forms the training system that virtual display, somatic adaptation, collaborative training, linkage control and evaluation closed loop are integrated, enhances training immersion and practicality, adapts the efficient and safe training needs of coal mine intelligent mining operation.

Description

Technical Field

[0001] This invention relates to the field of intelligent coal mine training technology, specifically to a training method and system for intelligent coal mining operations based on virtual display. Background Technology

[0002] Intelligent mining operations have been widely adopted in coal mines. Multi-position coordinated operation of equipment such as underground coal mining machines, hydraulic supports, and scraper conveyors has become commonplace. The underground environment presents significant challenges, including extreme temperatures and humidity, as well as low temperatures and wind chill, placing stringent demands on operators' teamwork, environmental adaptability, and adherence to operational procedures. Traditional offline training suffers from high risks underground, high training costs, difficulty in replicating extreme working conditions, and the inability to conduct collaborative training, thus failing to meet the large-scale, standardized, and highly safe training needs of intelligent mining operations.

[0003] Existing virtual display training technology only enables audiovisual simulation of single-position operations, without linking and controlling the actual temperature difference felt underground with multi-role collaborative operations. It cannot simulate the impact of environmental sensation on collaborative operations, resulting in a disconnect between the training scenario and actual underground working conditions. Trainees can operate smoothly in the virtual environment, but in real underground environments, discomfort and coordination errors can easily lead to operational deviations and safety hazards, making it difficult to effectively transform virtual training into underground practical operation.

[0004] In view of the above, this application is hereby submitted. Summary of the Invention

[0005] The purpose of this invention is to provide a training method and system for intelligent coal mining operations based on virtual display, so as to solve the problems mentioned in the background art.

[0006] To address the aforementioned technical problems, this invention provides a training method for intelligent coal mining operations based on virtual display, comprising the following steps: S1 constructing a virtual twin scene of the intelligent mining face; S2 collecting temperature and humidity data across the entire underground area to establish a body temperature difference mapping model; S3 building a multi-role collaborative operation virtual-real linkage framework; S4 executing linkage control of body temperature difference and collaborative operation; in S4, based on the spatial position of the roles in the virtual display scene and the intensity of the intelligent mining operation, dynamically outputting body temperature control parameters and simultaneously locking the collaborative operation threshold, the body temperature control parameters satisfying the formula... , Represents the somatosensory output parameters. Represents the baseline haptic parameters of the scene. Represents the spatial location parameters of the collaborative roles. This represents the intensity parameter of intelligent mining operations. and To fix the calibration coefficient; through unique body temperature difference and collaborative operation linkage control methods, it is different from the existing single virtual training or body simulation solutions, and realizes the integrated control of virtual display, intelligent mining collaboration and body adaptation. It not only ensures that the training scenario is close to the real underground working conditions, but also avoids collaborative operation errors caused by body discomfort, and builds a complete closed-loop training logic.

[0007] Furthermore, S1 includes the following sub-steps: S11 collecting equipment parameters and geological data of the intelligent mining face; S12 establishing a twin modeling system of equipment and geology; and S13 rendering and outputting a highly realistic operation scene through a virtual display terminal. The construction process of the virtual display twin scene is refined to ensure the matching degree between the scene and the real intelligent mining operation, consolidate the foundation for subsequent collaborative training and somatosensory simulation, and improve the realism of the training scene.

[0008] Furthermore, S3 includes the following sub-steps: S31 configuring multi-role operation terminals, S32 setting intelligent mining collaborative operation sequence, and S33 establishing a virtual-real data interaction channel between the virtual scene and the actual operation terminal; improving the underlying architecture of multi-role collaborative training, clarifying the collaborative sequence and data interaction method of each position, standardizing the intelligent mining collaborative operation process, and solving the problem of insufficient collaboration in existing training.

[0009] A training system for intelligent coal mining operations based on virtual display includes a virtual display scene construction module, a body temperature difference replication module, a multi-role collaborative training module, and a linkage control module. The virtual display scene construction module generates a virtual twin scene of the intelligent mining face; the body temperature difference replication module simulates underground body temperature differences; the multi-role collaborative training module conducts multi-position collaborative operation training; and the linkage control module implements linked control of body temperature and collaborative operation. The linkage control module includes a built-in feature calculation unit for executing formulas. Parameter calculation, Represents the somatosensory output parameters. Represents the baseline haptic parameters of the scene. Represents the spatial location parameters of the collaborative roles. This represents the intensity parameter of intelligent mining operations. and To fix the calibration coefficients, a systematic hardware architecture is constructed. Through the coordinated operation of four modules, the core functions of virtual display, motion simulation, and collaborative training are implemented. The modular design facilitates deployment and maintenance, and the unique feature calculation unit enables precise linkage control, which is different from existing training systems.

[0010] Furthermore, the virtual display scene construction module includes a data acquisition submodule, a twin modeling submodule, and a scene rendering submodule; the data acquisition submodule is used to collect mining equipment and geological data, the twin modeling submodule is used to construct a scene twin model, and the scene rendering submodule is used to output virtual display images; the hierarchical structure of the scene construction module is refined, the functional division of each submodule is clarified, the construction accuracy and rendering efficiency of the virtual display scene are ensured, and the scene visualization effect is improved.

[0011] Furthermore, the body temperature difference replication module includes a data storage submodule and a body temperature control submodule; the data storage submodule is used to store downhole temperature and humidity data, and the body temperature control submodule is used to output body temperature adjustment signals; by separating the core functions of the body temperature replication module, the storage and control of body temperature data are separated, ensuring the stability and real-time performance of body temperature simulation, and accurately reproducing the body temperature difference sensation downhole.

[0012] Furthermore, the multi-role collaborative training module includes a terminal adaptation submodule, a timing control submodule, and a data interaction submodule. The terminal adaptation submodule is used to connect multi-role operation terminals, the timing control submodule is used to control the timing of collaborative operations, and the data interaction submodule is used to realize virtual and real data transmission. By improving the submodule configuration of the collaborative training module, multi-terminal adaptation, collaborative timing control, and data interoperability are achieved, ensuring the orderly conduct of multi-role collaborative operation training and improving the standardization of collaborative training.

[0013] Furthermore, the linkage control module includes a parameter parsing unit and a threshold locking unit; the parameter parsing unit is used to parse and calculate the somatosensory control parameters, and the threshold locking unit is used to execute collaborative operation threshold locking control; refining the unit structure of the linkage control module enables accurate parameter parsing and operation threshold locking, enhances the linkage effect between somatosensory perception and collaborative operation, and further reduces the probability of operation errors caused by somatosensory discomfort.

[0014] Compared with the prior art, the beneficial effects of the present invention are: 1. This invention constructs an intelligent twin scene of mining face through virtual display and digital twin technology, and simultaneously establishes an underground exclusive body temperature difference mapping model, which can completely restore the real working environment and body temperature changes, significantly improve the realism and immersion of the training scene, effectively improve the problem of the disconnect between traditional virtual training and on-site practice, and reduce the operational risks caused by environmental discomfort.

[0015] 2. This invention establishes a virtual-real linkage framework for multi-role collaborative operations. It standardizes the entire process operation through collaborative timing lock and job permission control. It also adopts an original formula for the fusion calculation of motion parameters and collaborative operation parameters to achieve deep linkage between virtual scenes, motion replication and collaborative training. It can dynamically adjust motion output and lock collaborative operation thresholds according to the role position and operation intensity, which greatly improves the stability and standardization of multi-role cooperation.

[0016] 3. This invention integrates virtual display, body temperature difference replication, multi-role collaborative training and linkage control into an integrated training system, and constructs a multi-dimensional closed-loop evaluation mechanism, which can accurately locate skill gaps and achieve personalized reinforcement, significantly improve training efficiency and skill conversion speed, and comprehensively improve the training quality and safety assurance level of intelligent mining operations in coal mines. Attached Figure Description

[0017] Figure 1 A flowchart of a training method for intelligent coal mining operations based on virtual display; Figure 2 This is a schematic diagram of a training system for intelligent coal mining operations based on virtual display. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Please see Figures 1 to 2 This invention provides a technical solution: a training method and system for intelligent coal mining operations based on virtual display. This specific embodiment focuses on a virtual display training scenario for routine multi-role collaborative operations in intelligent mining faces, and elaborates on the training method and system for intelligent coal mining operations based on virtual display. The disclosed technologies referenced in this invention include basic modeling technology for coal mine virtual simulation training, underground environment data acquisition technology, multi-terminal collaborative interaction technology, and haptic feedback control technology. However, these disclosed technologies only achieve basic applications with single functions and do not form a closed-loop system integrating multiple technologies. This technical solution innovatively integrates and improves upon the disclosed technologies to form a unique training control logic.

[0020] I. System Overall Architecture and Composition: This system is built upon virtual display technology, digital twin technology, intelligent sensing technology, and edge computing technology. It is divided into four core modules: virtual display scene construction module, body temperature difference replication module, multi-role collaborative training module, and linkage control module. These four modules are interconnected and share data, jointly realizing virtual display training for normalized multi-role collaborative operations in intelligent mining faces, solving the problems of insufficient collaboration, lack of body sensation, and disconnect between training and practice in existing virtual training.

[0021] 1.1 Virtual Display Scene Construction Module: The virtual display scene construction module includes a data acquisition submodule, a twin modeling submodule, and a scene rendering submodule. Its core function is to collect basic data from a real intelligent mining face, construct a 1:1 digital twin scene, and complete scene rendering output through a virtual display terminal, providing a basic carrier for subsequent training. The data acquisition submodule is responsible for collecting operating parameters of intelligent mining equipment, underground geological environment parameters, and working face spatial layout parameters; the twin modeling submodule constructs a twin model that integrates the equipment and geology based on the collected data, ensuring the consistency between the model and the real scene; the scene rendering submodule interfaces with VR headsets, virtual display screens, and control console display terminals to complete high-definition scene rendering and real-time output.

[0022] 1.2 Perceived Temperature Difference Replication Module: The perceived temperature difference replication module includes a data storage submodule and a perceived temperature control submodule. Its core function is to store temperature and humidity data for the entire downhole area and adjust the perceived temperature output in real time according to changes in the scene, thus reproducing the real downhole temperature difference perception. The data storage submodule has a built-in perceived temperature database that stores downhole temperature and humidity calibration data for different areas and different work intensities. The perceived temperature control submodule connects to a wearable temperature sensing module and a wind simulation module, receives control commands, and outputs corresponding perceived temperature adjustment signals to achieve dynamic replication of temperature difference perception.

[0023] 1.3 Multi-role Collaborative Training Module: The multi-role collaborative training module includes a terminal adaptation submodule, a timing control submodule, and a data interaction submodule. Its core function is to adapt to multiple role-operated terminals, control the timing of collaborative operations, and realize two-way data interaction between the virtual scene and the actual operating terminal. The terminal adaptation submodule is compatible with VR control terminals, physical mining control consoles, and AR wearable terminals, meeting the needs of simultaneous access for multiple roles; the timing control submodule presets an intelligent mining collaborative operation process, locking the order of operations for each position to avoid confusion in the collaborative process; the data interaction submodule establishes a data transmission channel to realize two-way transmission of virtual scene data, operation command data, and work status feedback data.

[0024] 1.4 Linkage Control Module: The linkage control module includes a parameter parsing unit, a threshold locking unit, and a feature calculation unit. Its core function is to calculate the somatosensory control parameters, realizing the linkage control of somatosensory temperature difference and coordinated operation. It is the core innovative module of this system. The feature calculation unit has built-in core calculation formulas to complete the fusion calculation of somatosensory parameters and coordinated parameters; the parameter parsing unit parses the calculation results and generates corresponding somatosensory control and coordinated operation commands; the threshold locking unit locks the coordinated operation threshold based on the parsing results to avoid operational errors caused by somatosensory discomfort.

[0025] II. Specific implementation methods and steps: Step S1, the virtual display scene construction module, performs scene building operations: The core of this step is to complete the construction of a virtual display twin scene for the intelligent mining face, providing a basic simulation environment for subsequent multi-role collaborative training and motion temperature difference replication. In existing publicly available technologies, the construction of virtual training scenes in coal mines often uses single-device modeling or simplified environment modeling, which can only achieve basic visual display and cannot accurately reflect the equipment layout, geological conditions, and operational logic of the intelligent mining face, resulting in a disconnect between the training scene and actual operations. Therefore, this step constructs a highly realistic virtual display scene through multi-dimensional data collection, high-precision twin modeling, and real-time rendering output, ensuring the authenticity and practicality of subsequent training. Specific technical methods are as follows: The S11 data acquisition submodule collects basic data. Through underground sensing equipment and the intelligent coal mine management and control platform, it collects model parameters, spatial location parameters, and operating logic parameters of intelligent mining core equipment such as coal mining machines, hydraulic supports, and scraper conveyors. At the same time, it collects geological structure parameters of the working face, roadway layout parameters, and ventilation equipment layout parameters. After the collected data is preprocessed by the edge computing node, it is transmitted to the twin modeling submodule.

[0026] The S12 twin modeling submodule constructs a twin model using a lightweight digital twin modeling algorithm. Based on the collected basic data, it builds an integrated twin model of equipment, geology, and environment. During the modeling process, the operating logic, action response mechanism, and collaborative linkage of the intelligent mining equipment are preserved, redundant model data is eliminated, and the model accuracy and rendering efficiency are balanced. After the modeling is completed, the model data is transferred to the scene rendering submodule.

[0027] The S13 scene rendering submodule performs rendering output, adopts a real-time rendering algorithm, connects to various virtual display terminals, and adaptively adjusts the rendering precision according to the terminal performance to ensure that the scene picture is smooth and lag-free. It also loads the basic sound effects of intelligent mining operations in sync to enhance the immersive experience of the scene.

[0028] This step employs a lightweight twin modeling accuracy control algorithm, the formula of which is: ,in Represents the final modeling accuracy. Represents the original modeling accuracy. This represents the lightweight factor, the value of which is determined by the terminal rendering performance. It is based on publicly available digital twin modeling technology, optimizing the lightweight factor for underground coal mine scenes to reduce rendering load while ensuring the integrity of the model's core features.

[0029] Example: For an intelligent fully mechanized mining face in a mine, the data acquisition submodule collects data such as the cutting parameters of the coal mining machine, the support spacing of the hydraulic supports, the conveying inclination angle of the scraper conveyor, the coal seam thickness, and the location of the ventilation fans in the roadway, completing the basic data collection; the twin modeling submodule starts the lightweight digital twin modeling algorithm and executes the calculation according to the formula application process: the first step is to determine the original modeling accuracy. The values ​​are set to 100% full-precision modeling parameters. The second step is to calibrate the lightweight coefficient based on whether the access terminal is a VR headset or a conventional large display screen. The value is taken as 0.75, and in the third step, it is substituted into the formula. The calculation yields the final modeling accuracy. With a precision of 75%, the fourth step involves constructing an integrated twin model of equipment, geology, and environment based on this precision. This model retains the core logic of the coal mining machine's inclined cutting, the hydraulic support's follow-up movement, and the coordinated operation of the scraper conveyor, while eliminating redundant texture data. The scene rendering submodule uses a VR headset and a large-screen terminal to simultaneously render and output a virtual working face scene with a precision of 75%, clearly presenting the location of each piece of equipment, the working space, and the environmental layout without any lag or delay. This provides a foundational scenario for the subsequent collaborative training of the four roles: coal mining machine driver, support worker, conveyor driver, and control operator.

[0030] The unique approach of this technical solution lies in integrating the entire intelligent mining process logic into virtual scene modeling, rather than merely building visual models of equipment and the environment. This differs from publicly available virtual modeling technologies that only focus on visual reproduction. It significantly improves the alignment between the virtual scene and actual operations, reduces training bias caused by scene distortion, lowers the difficulty of subsequent collaborative training adaptation, and enhances overall training efficiency.

[0031] Step S2: Constructing a Perceived Temperature Difference Mapping System: The core of this step is to collect temperature and humidity data across the entire underground area and establish a perceived temperature difference mapping model to provide data support for subsequent dynamic perception replication. In existing publicly available technologies, virtual training in coal mines only achieves audiovisual simulation and does not involve environmental perception simulation. Some perception technologies are only applied to general VR scenarios and do not have customized mapping logic for the temperature differences in underground coal mines, thus failing to reproduce the realistic perception of high temperature and humidity, and low temperature and cold air underground. Therefore, this step establishes a perception mapping system specifically for intelligent underground mining scenarios through data collection, model construction, and parameter calibration, filling the gap in perception during virtual training. Specific technical methods are as follows: S21 collects temperature and humidity data across the entire underground area. By deploying temperature and humidity sensors in the mining face, roadways, and air intakes, it collects temperature and humidity values ​​for different areas and different working periods, simultaneously records the correlation data between work intensity and temperature and humidity, and transmits the collected data to the data storage submodule.

[0032] The S22 data storage submodule categorizes and stores the collected data, classifies and organizes temperature and humidity data according to region type and operation intensity level, and establishes an underground somatic perception database to provide data support for the somatic perception mapping model.

[0033] S23 constructs a somatosensory temperature difference mapping model. Based on stored temperature and humidity data, it uses a linear regression fitting algorithm to establish a mapping relationship between the scene environment and somatosensory output, calibrates the benchmark parameters and adjustment coefficients for somatosensory control, and ensures that the somatosensory output is consistent with the real underground environment.

[0034] This step uses a motion-sensory mapping linear fitting algorithm, the formula of which is: ,in Represents the somatosensory mapping coefficient. Represents the ambient humidity parameter. Represents the ambient temperature parameter. , This represents the calibration coefficient for the underground environment. It is based on publicly available environmental motion-sensory fitting technology, and the coefficient values ​​are optimized to improve mapping accuracy, taking into account the high humidity and large temperature differences characteristic of underground coal mines.

[0035] Example: Continuing from the example scenario in step S1, the first step involves collecting data through temperature and humidity sensors to determine the temperature parameters during operation at the longwall mining face. The value is 38, humidity parameter The value is 88%, which is the temperature parameter in the air inlet area. Value is 16, humidity parameter The value was set at 62%; the second step involved calibrating the environmental calibration coefficient based on the characteristics of the high-humidity downhole environment. The value is 0.3. The value is set to 0.7; the third step is to perform the calculation according to the formula application process, substituting the values ​​into the formula for the fully mechanized mining face. The somatosensory mapping coefficients are obtained. The value is 62.6. Substituting this value into the formula for the air intake area, we obtain the body perception mapping coefficient. The value is 28.6; the fourth step data storage submodule classifies and stores the temperature and humidity data and the body sensation mapping coefficient of the two types of areas, and establishes an exclusive body sensation database; the fifth step body sensation temperature difference replication module constructs a body sensation temperature difference mapping model based on the calculated mapping coefficient, calibrates the body sensation output benchmark of different areas, and ensures that the subsequent wearable temperature sensing module can accurately replicate the body sensation of the corresponding area and fit the body sensation characteristics of normal operation on the work surface.

[0036] The unique technical approach of this solution lies in its customized motion mapping model tailored to the specific temperature and humidity environment of intelligent coal mining faces, rather than directly applying general motion fitting technology. This distinguishes it from existing motion sensing technologies that are not adapted to underground scenarios. It accurately reproduces the real temperature differences and sensations experienced underground, enhancing the immersion of virtual training, reducing operational errors caused by discomfort after trainees begin their work, and strengthening the practicality of the training.

[0037] Step S3: Building a Multi-Role Collaborative Training Module and Establishing a Collaborative Operation Framework: The core of this step is to build a virtual-physical linkage framework for multi-role collaborative operations, clarifying the operational permissions, collaborative timing, and data interaction rules for each position. In existing publicly available technologies, virtual training in coal mines is mostly single-person, single-machine operation, and a few collaborative training programs only achieve simple online connections, failing to incorporate the collaborative timing and control logic of intelligent mining operations, which easily leads to operational confusion and coordination errors. Therefore, this step constructs a standardized multi-role collaborative training system through terminal adaptation, timing control, and data interaction, aligning with the collaborative needs of routine intelligent mining operations. Specific technical means are as follows: The S31 terminal adapter submodule adapts to multi-role operating terminals, connecting to the VR control terminal of the coal mining machine driver, the physical control console of the support worker, the operating panel of the transport machine driver, and the monitoring terminal of the central control operator, respectively, to complete the identity authentication and permission allocation of each terminal, ensuring that each role can only execute the operation instructions of the corresponding position.

[0038] The S32 timing control submodule sets the collaborative operation timing, sorts out the routine operation process of intelligent mining, sets the order of operation for starting the coal mining machine, moving the support along with the machine, and transporting the conveyor in conjunction with the machine, and sets timing lock rules. Subsequent actions cannot be triggered if the preceding standardized operation is not completed.

[0039] The S33 data interaction submodule establishes a two-way data channel, connecting the virtual display scene with each operation terminal, enabling bidirectional transmission of operation commands uploading and operation status feedback downloading, ensuring that the actions of the virtual scene and the operations of the actual operation terminal respond synchronously.

[0040] This step employs a collaborative timing control algorithm, the formula of which is: ,in This represents the currently executable operation instructions. This indicates that the preceding operation instruction has been completed. This represents the current operational instructions for the assigned position. It is based on publicly available industrial collaborative management and control technology, optimizing the timing logic for intelligent coal mining operations to ensure the standardization of collaborative operations.

[0041] Example: Continuing from the above example, the first step, the terminal adaptation submodule, completes the access and permission allocation for the four roles of the terminal: the coal mining machine operator is responsible for equipment start / stop and cutting control; the support worker is responsible for support movement operations; the transport machine operator is responsible for transport start / stop control; and the central control operator is responsible for overall operating condition monitoring and command issuance. The second step is to streamline the intelligent mining collaborative operation process and determine the preceding operation instructions. This is the instruction for the support to be in place; the current operational instruction for the current position. This is the start command for the coal mining machine's cutting process; the third step is to substitute the values ​​into the formula. Execution timing determination, only when and When instructions match and overlap, output the currently executable operation instructions. The first step is to unlock the coal mining machine's start-up permission; the fourth step, the timing control submodule, is based on this calculation logic to set a timing lock rule that the support must be in place before the coal mining machine can start cutting, and finally the conveyor can start transporting; the fifth step, the data interaction submodule, builds a two-way data channel to synchronize the operation of each terminal with the actions of the virtual scene. If any position violates the operation or fails to meet the timing judgment requirements, the virtual scene will trigger an alarm prompt simultaneously to ensure the standardization of the four-role collaborative operation process.

[0042] The unique technical approach of this solution lies in integrating intelligent mining-specific collaborative timing lock-in rules into a multi-terminal training framework, rather than simply achieving multi-terminal connectivity. This distinguishes it from existing collaborative training technologies that lack process control. It standardizes multi-role collaborative operation procedures, reduces coordination errors, strengthens trainees' awareness of job coordination, and aligns with the actual needs of routine underground collaborative operations.

[0043] Step S4, the linkage control module, executes haptic and collaborative linkage control: The core of this step is to achieve linkage control between haptic temperature difference and multi-role collaborative operation. This is the core innovative step of this invention and a key difference from all publicly available technologies. In existing publicly available technologies, virtual scenes, haptic simulation, and collaborative training operate independently, without forming a linkage control system, thus failing to solve the problem of haptic changes interfering with collaborative operation. Therefore, this step achieves deep linkage among the three through parameter calculation, instruction parsing, and threshold locking, improving the realism and effectiveness of training. Specific technical means are as follows: The S41 feature calculation unit acquires real-time parameters, collects spatial position parameters of collaborative roles in the virtual display scene and intelligent mining operation intensity parameters, retrieves scene baseline somatosensory parameters, and calls core formulas to complete parameter calculations.

[0044] The S42 parameter parsing unit analyzes the calculation results, converts the calculated motion output parameters into motion control commands, and simultaneously combines the task intensity and role position to generate collaborative operation threshold control commands.

[0045] The S43 threshold locking unit performs linkage control, transmitting motion control commands to the motion control submodule to achieve dynamic motion adjustment; at the same time, according to the collaborative threshold command, it locks the operation threshold of the corresponding position. When the trainee's operation deviates from the threshold due to motion discomfort, the violation operation is suspended and the standard prompt is triggered.

[0046] This step uses a core linkage calculation formula, which is a core innovative formula for invention. The formula is as follows: ,in Represents the somatosensory output parameters. Represents the baseline haptic parameters of the scene. Represents the spatial location parameters of the collaborative roles. This represents the intensity parameter of intelligent mining operations. and The calibration coefficients are fixed. The method is based on publicly available parameter fusion calculation technology. This solution features a unique formula structure specifically designed for coal mine training scenarios, enabling the fusion calculation of haptic and collaborative parameters. No existing publicly available literature discloses this formula or its application logic.

[0047] Example: Following all the examples above, four roles conduct routine collaborative operations in a virtual scenario. The first step, the feature calculation unit, collects real-time parameters. The coal mining machine operator and the support worker are located in the high-temperature and high-humidity zone of the working face. The spatial position parameters of the collaborative roles are... The value is 1.2, which is the intensity parameter for intelligent mining operations. The value is 0.9, which is the baseline motion perception parameter for the scene. The value is 36, and the calibration is a fixed coefficient. The value is 2. The value is set to 5; the second step is to substitute it into the core formula. The calculation yields the motion-sensing output parameters. The value is 42.9. The third step, the parameter parsing unit, parses this parameter and converts it into a high-temperature and high-humidity body-feeling control command, simultaneously generating a collaborative operation threshold relaxation command. The fourth step, the body-feeling control submodule, receives the command and adjusts the wearable temperature sensing module's output to correspond to the body-feeling sensation. The threshold locking unit simultaneously adjusts the operation threshold to prevent students from being misjudged for minor deviations due to discomfort. When the character moves to the low-temperature zone of the air inlet, the first step updates the parameters, coordinating with the character's spatial position parameters. The value is 0.5, which is the intensity parameter for intelligent mining operations. The value is 0.3, which is the baseline motion parameter for the scene. The value is set to 16; in the second step, the values ​​are substituted into the core formula again to obtain the motion-sensing output parameters. The value is 17.9; the third step, the somatosensory control submodule, quickly adjusts the output low-temperature somatosensory sensation, and the threshold locking unit simultaneously tightens the operation threshold to ensure the stability of the coordinated operation.

[0048] The unique technical approach of this solution lies in the fusion calculation formula of haptic parameters and intelligent mining collaboration parameters, which enables deep linkage between virtual display scenarios, haptic temperature difference replication, and multi-role collaborative training, unlike the independent operation mode of existing publicly available technologies. This significantly reduces collaborative operation errors caused by haptic discomfort, improves the stability of multi-role collaborative training, strengthens the fit between training scenarios and real underground working conditions, and achieves a qualitative improvement in training quality.

[0049] Step S5: Training Process Monitoring and Effectiveness Evaluation: The core of this step is to monitor the entire training process data, evaluate the training effectiveness, and form a closed-loop training system. Existing publicly available technologies for evaluating virtual training in coal mines only statistically analyze operational completion rates, failing to consider factors such as experiential adaptation and collaborative quality for a comprehensive assessment. This results in a one-sided evaluation that cannot accurately pinpoint trainees' weaknesses. Therefore, this step achieves precise quantification of training effectiveness through multi-dimensional data collection and comprehensive evaluation calculations, providing a basis for subsequent training optimization. Specific technical methods are as follows: The S51 collects training data throughout the entire process, including real-time collection of trainees' operation instructions, sensory adaptation data, collaborative data, and data on violations, and transmits the data to the assessment unit.

[0050] S52 constructs a comprehensive evaluation model and uses a weighted scoring algorithm to perform weighted calculations on operational standardization, tactile adaptability, and teamwork, generating a comprehensive training score.

[0051] S53 outputs an assessment report and optimization suggestions, identifies trainees' skill gaps based on the scoring results, and pushes targeted remedial training content to complete the training loop.

[0052] This step uses a comprehensive evaluation weighted algorithm, the formula of which is: ,in Represents the overall training score. The score represents the standard operating procedure score. Represents the somatosensory adaptation score. The score represents the team's collaborative efforts. , , This represents the weighting coefficients, and the sum of the weighting coefficients is 1. The method is based on publicly available comprehensive evaluation techniques, and the weighting coefficients are optimized in conjunction with the training characteristics of this invention to improve evaluation accuracy.

[0053] Example: Following the example above, the first step is for the system to collect training data from four roles of trainees throughout the entire process, including a scoring system for the operating procedures of a coal mining machine operator. The score is 85 points, representing the sensory adaptation score. The score is 70 points, and the evaluation is based on teamwork. The score is set at 75 points; the second step involves determining the weighting coefficients based on the core training needs. The value is 0.4. The value is 0.3. The value is 0.3, and the sum of the three coefficients is 1; the third step is to substitute the values ​​into the formula. The calculation yields a comprehensive training score. The score was 77.5. The fourth step was to analyze the scoring results and identify the trainee's weaknesses as poor teamwork and insufficient adaptability to high temperatures. The fifth step was to push two types of remedial training content: high-temperature collaborative work and extreme physical operation adaptation, to help the trainee make up for the skill deficiencies and form a complete closed loop of "training-assessment-remediation".

[0054] The unique approach of this technical solution lies in incorporating sensory adaptation into the training evaluation system. It combines operational procedures and collaborative teamwork to conduct a multi-dimensional comprehensive assessment, unlike existing training evaluations that only focus on operational completion. This accurately identifies trainees' skill gaps, enhances the comprehensiveness of training evaluation, enables personalized training reinforcement, and further improves overall training effectiveness.

[0055] III. In summary: The specific implementation process of this invention is as follows: First, a virtual display scene construction module is used to build a twin scene of an intelligent mining face. Then, a body temperature difference replication module is used to build an underground body sensation mapping system. Subsequently, a multi-role collaborative training module is used to build a collaborative operation framework. Finally, a linkage control module executes core linkage control, combined with training, monitoring, and evaluation stages, to form a complete training closed loop. The publicly available documents and technologies cited in this technical solution include coal mine digital twin virtual modeling technology, underground environment sensing and acquisition technology, multi-terminal industrial collaboration technology, body sensation feedback control technology, and comprehensive evaluation weighting technology. The above-mentioned publicly available technologies are all basic applications with single functions, and have not achieved the integration and linkage of multiple technologies. Furthermore, they have not built a linkage calculation system and collaborative control logic for intelligent coal mine mining scenarios, and have not disclosed the core linkage formula and application process of this invention.

[0056] This technical solution employs unique techniques throughout the entire process. First, it integrates intelligent mining operation logic into virtual scene modeling, using lightweight modeling formulas to achieve adaptive precision control. Second, it customizes a unique underground tactile temperature difference mapping model, adapting to the specific temperature and humidity environment underground through linear fitting formulas. Third, it establishes a multi-role collaborative framework with time-sequence locking, standardizing the operation process based on collaborative time-sequence formulas. Fourth, it integrates tactile feedback and collaborative parameters into calculation formulas, achieving deep, full-function linkage, with clear and reproducible formula application processes. Fifth, it constructs a multi-dimensional training evaluation system, achieving accurate evaluation through weighted scoring formulas. These unique techniques work together to produce technical effects that cannot be achieved by a single publicly available technology, and the overall technical solution is not obvious to those skilled in the art. Compared to existing publicly available technologies, this invention significantly improves the alignment between virtual training and real-world operations, significantly reduces the error rate of trainees' collaborative operations, greatly enhances tactile adaptability, and simultaneously optimizes training efficiency and quality. It fully meets the training needs of routine multi-role collaborative operations in intelligent coal mining faces, possessing strong practical application prospects and promotional value.

Claims

1. A training method for intelligent coal mining operations based on virtual display, characterized in that: Includes the following steps: S1 constructs a virtual twin scene of intelligent mining face display; S2 collects temperature and humidity data of the entire underground area to establish a body temperature difference mapping model; S3 builds a virtual-real linkage framework for multi-role collaborative operation; S4 executes linkage control of body temperature difference and collaborative operation. In S4, based on the spatial position of the role in the virtual display scene and the intensity of intelligent mining operations, the motion control parameters are dynamically output and the collaborative operation threshold is locked simultaneously. The motion control parameters satisfy the formula. , Represents the somatosensory output parameters. Represents the baseline haptic parameters of the scene. Represents the spatial location parameters of the collaborative roles. This represents the intensity parameter of intelligent mining operations. and For fixed calibration coefficients.

2. The training method for intelligent coal mining operations based on virtual display as described in claim 1, characterized in that: S1 includes the following sub-steps: S11 collecting intelligent mining face equipment parameters and geological data, S12 establishing a twin modeling system of equipment and geology, and S13 rendering and outputting a highly realistic operation scene through a virtual display terminal.

3. The training method for intelligent coal mining operations based on virtual display as described in claim 2, characterized in that: S3 includes the following sub-steps: S31 Configure multi-role operation terminals, S32 Set intelligent mining collaborative operation sequence, S33 Establish virtual and real data interaction channel between virtual scene and actual operation terminal.

4. A training system for intelligent coal mining operations based on virtual display, characterized in that: The system includes a virtual display scene construction module, a body temperature difference replication module, a multi-role collaborative training module, and a linkage control module. The virtual display scene construction module generates a virtual twin scene of the intelligent mining face; the body temperature difference replication module simulates underground body temperature differences; the multi-role collaborative training module conducts multi-position collaborative operation training; and the linkage control module enables the linkage control of body temperature and collaborative operation. The linkage control module includes a built-in feature calculation unit, which executes formulas... Parameter calculation, Represents the somatosensory output parameters. Represents the baseline haptic parameters of the scene. Represents the spatial location parameters of the collaborative roles. This represents the intensity parameter of intelligent mining operations. and For fixed calibration coefficients.

5. The intelligent coal mining operation training system based on virtual display as described in claim 4, characterized in that: The virtual display scene construction module includes a data acquisition submodule, a twin modeling submodule, and a scene rendering submodule. The data acquisition submodule is used to collect mining equipment and geological data, the twin modeling submodule is used to construct a scene twin model, and the scene rendering submodule is used to output virtual display images.

6. The intelligent coal mining operation training system based on virtual display as described in claim 5, characterized in that: The body temperature difference replication module includes a data storage submodule and a body temperature control submodule; the data storage submodule is used to store downhole temperature and humidity data, and the body temperature control submodule is used to output body temperature adjustment signals.

7. The intelligent coal mining operation training system based on virtual display as described in claim 6, characterized in that: The multi-role collaborative training module includes a terminal adaptation submodule, a timing control submodule, and a data interaction submodule. The terminal adaptation submodule is used to connect multi-role operation terminals, the timing control submodule is used to control the timing of collaborative operations, and the data interaction submodule is used to realize virtual and real data transmission.

8. The intelligent coal mining operation training system based on virtual display as described in claim 7, characterized in that: The linkage control module includes a parameter parsing unit and a threshold locking unit; the parameter parsing unit is used to parse and calculate the somatosensory control parameters, and the threshold locking unit is used to perform collaborative operation threshold locking control.

Images