Coal mine intelligent coal face control system based on digital twinning

Abstract

The invention discloses a coal mine intelligent coal face control system based on digital twinning. The system comprises an underground entity unit, a ground virtual unit and an interaction unit connecting the underground entity unit and the ground virtual unit. The physical unit acquires data through the sensing network module and uploads the data through the communication module; the virtual unit builds a three-dimensional dynamic model through a twinborn body building module, virtual and real consistency is guaranteed through a model dynamic correction module, then an optimal control strategy is generated through simulation optimization of a twinborn data analysis and decision-making module, and finally an instruction is issued to an execution mechanism module through a control module to form closed-loop control; according to the method, the digital twinborn body completely corresponding to the physical working face is constructed, simulation operation and verification can be carried out on the whole process of the coal mining technology and equipment linkage logic in a virtual space in advance, and therefore potential action interference and logic conflicts are recognized and eliminated before an actual control instruction is issued, the effect of pre-judgment in advance is achieved, and the real-time performance of the coal mining technology is improved. And the look-ahead decision-making capability of the system is greatly improved.

Description

Technical Field

[0001] This invention relates to the field of coal mining technology, and in particular to a digital twin-based intelligent coal mining face control system. Background Technology

[0002] Intelligent coal mining faces typically adopt an integrated automation architecture based on industrial bus and sensor network. Data is collected by sensors deployed on the equipment, and the starting, stopping, speed adjustment and basic linkage control of equipment such as coal mining machines, hydraulic supports or scraper conveyors are realized by pre-set control programs or remote intervention by operators.

[0003] Existing systems do not make sufficient use of massive amounts of sensing data, focusing mainly on real-time status display and over-limit alarms. They fail to deeply integrate with the geological environment of the working face and the physical properties of the equipment, resulting in the control system's inability to predict the future state of the equipment under the interaction with the surrounding rock. For example, the system cannot adaptively adjust the height of the coal mining machine drum according to changes in the coal-rock interface, nor can it predict the dynamic relationship between the hydraulic support and the roof pressure and adjust the support strategy in advance. This results in the control behavior always being in a situation of lagging response. Furthermore, the generation and verification of existing control strategies heavily rely on physical entities. Any modification or optimization of control logic must be tested on the field equipment, which not only poses safety risks but also has a long debugging cycle and high costs.

[0004] Therefore, in response to the problems mentioned above, this invention proposes a digital twin-based intelligent coal mining face control system. Summary of the Invention

[0005] To overcome the problems of insufficient coordination and lack of foresight in existing systems, this invention proposes a digital twin-based intelligent coal mining face control system. This system constructs a digital twin that operates synchronously with the physical working face and maps the virtual and real worlds. It then performs full-process simulation, analysis, and decision optimization in virtual space, thereby achieving coordinated and forward-looking control of the physical working face equipment.

[0006] The technical solution of this invention is: a digital twin-based intelligent coal mining face control system, comprising physical units, virtual units, and interactive units, wherein: The entity unit includes: The sensor network module includes sensors deployed on the coal mining machine, hydraulic supports, and scraper conveyors to collect real-time data on equipment attitude, operating parameters, location information, and environmental parameters. These sensors include an inertial navigation unit and UWB positioning tags installed on the coal mining machine to acquire its three-dimensional coordinates and attitude in real time; tilt sensors, pressure sensors, and displacement sensors installed on the hydraulic supports to monitor support attitude, support resistance, and pushing stroke; and gas concentration sensors, dust concentration sensors, and a roof pressure monitoring system installed in the working face and return airway to monitor gas concentration, dust concentration, and roof pressure. The actuator module, including the coal mining machine traction unit, drum height adjustment cylinder, hydraulic support electro-hydraulic control valve group, and scraper conveyor frequency converter driver, is used to receive and execute control commands; The virtual unit includes: The twin construction module integrates 3D seismic and drilling data to build a high-precision 3D geological model that includes coal seam thickness undulations, geological structure, and interbedded rock distribution. At the same time, it imports high-precision CAD models of equipment such as coal mining machines and hydraulic supports, and assigns them kinematic and dynamic properties. Then, the 3D geological model and equipment model are assembled in a unified coordinate system to form a static initial twin. Through real-time data driving, the static initial twin evolves into a dynamic twin that can reflect the real-time state of the physical entity. The model correction module, connected to the sensor network module, is used to compare real-time sensor data with virtual model prediction data through data fusion algorithms. When the deviation exceeds a preset threshold, the parameters in the virtual model are corrected in reverse to make the virtual model consistent with the physical entity. The twin data analysis and decision-making module, connected to the model correction module, is used to simulate the entire coal mining process and verify the equipment linkage logic in virtual space. At the same time, it optimizes the cutting path and the automatic follow-up strategy of the support based on the virtual model, and generates the optimal control strategy containing the equipment action sequence and timing. The interaction unit includes: The communication module adopts a mining industrial ring network and a 5G / WiFi6 converged network to provide a high-bandwidth and low-latency data transmission channel between physical units and virtual units; The control module, connected to the twin data analysis and decision-making module and the actuator module, receives pre-execution control strategies from the twin data analysis and decision-making module. Before issuing control commands to physical devices, the control module first performs command rehearsals in the virtual digital twin unit to verify their safety and feasibility. After the rehearsals are passed, the control commands are packaged and synchronously issued to the relevant actuator modules through the high-speed communication module to achieve the linkage of the coal mining machine, hydraulic support and scraper conveyor. The safety early warning and self-decision-making module is connected to the twin data analysis and decision-making module and the control module. This module analyzes the equipment stress cloud map and roof pressure distribution in the virtual model in real time. When overload or roof collapse risk is predicted, a high-level warning is generated. After receiving the high-level warning, a safety intervention command is generated and executed based on the preset safety rule base. This safety intervention command is executed with the highest priority.

[0007] Preferably, the model correction module uses a Kalman filter algorithm for data fusion. By fusing the actual trajectory and pressure data of the physical entity collected by the sensor network module with the prediction output of the virtual model, the implicit parameters in the virtual model that are difficult to measure directly and accurately are dynamically estimated and corrected.

[0008] Preferably, the twin data analysis and decision-making module includes: The virtual scanning unit is used to calculate and update the distribution of residual coal thickness in the coal seam based on the real-time cutting trajectory of the coal mining machine drum in the virtual model. The collision detection unit is used to pre-simulate the motion relationship between the support side plate and the coal mining machine body, and between the drum and the scraper conveyor scraper in virtual space. When potential interference is detected, the timing of the support action or the trajectory of the coal mining machine is adjusted before the control command is generated. The parameter optimization unit employs optimization algorithms based on genetic algorithms or reinforcement learning to rapidly simulate multiple production cycles in a virtual environment with the goal of "lowest energy consumption per ton of coal" or "highest coal mining efficiency," thereby finding the globally optimal or near-optimal combination of equipment operating parameters and optimizing the matching relationship between the coal mining machine's traction speed and drum speed.

[0009] The beneficial effects of this invention are: 1. By constructing a digital twin that completely corresponds to the physical working face, this invention can simulate and verify the entire coal mining process and equipment linkage logic in virtual space in advance. This allows for the identification and elimination of potential action interference and logical conflicts before the actual control commands are issued, thereby achieving the effect of advance prediction and significantly improving the system's forward-looking decision-making capability and operational safety.

[0010] 2. This invention utilizes a digital twin as a unified collaborative decision-making center. Through the twin data analysis and decision-making module, it generates a globally optimal control strategy and synchronously issues the virtual-verified instructions to all actuators such as the coal mining machine, hydraulic support, and scraper conveyor. This breaks down the information silos between equipment subsystems, achieves precise coordination and linkage between the three machines and supporting equipment at the working face, and significantly improves production efficiency.

[0011] 3. This invention uses a model correction module to continuously calibrate and update the virtual digital twin using real-time sensor data, enabling it to dynamically track and adapt to complex working conditions such as changes in coal seam thickness and geological conditions. This gives the system a strong adaptive capability and allows it to maintain a high-fidelity mapping of the physical entity at all times. Attached Figure Description

[0012] Figure 1 The diagram shown is a system framework diagram of the present invention; Figure 2 The diagram shown illustrates the workflow of this invention. Detailed Implementation

[0013] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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 some embodiments of the present invention, but 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.

[0014] Please see Figure 1 This invention provides an embodiment of a digital twin-based intelligent coal mining face control system: In this embodiment, the physical unit is described in detail: First, let's explain the sensor network module: An inertial navigation unit (IMU) is installed on the coal mining machine body to measure its pitch, roll, and yaw angles in real time. UWB positioning tags are also installed, working in conjunction with UWB base stations deployed at the working face to achieve centimeter-level three-dimensional coordinate positioning of the coal mining machine. Vibration sensors are installed in the drum bearing housings, and current and temperature sensors are installed in the motors to monitor load and health status.

[0015] Tilt sensors are installed on each hydraulic support to monitor its verticality and attitude. Pressure sensors are installed in the lower cavity of the column to monitor support resistance in real time. Displacement sensors are installed to accurately measure the stroke of the push jacks, used to control the curvature of the scraper conveyor.

[0016] Gas concentration sensors and dust concentration sensors are installed at the working face and return airway to monitor the gas and dust concentrations at the working face. A microseismic monitoring system and a roof pressure monitoring system are installed to detect the patterns of mine pressure manifestation.

[0017] Current sensors and tension sensors are installed at the head and tail drive sections of the scraper conveyor to monitor chain tension and load conditions.

[0018] The actuator module is explained below: The coal mining machine is controlled by adjusting its travel speed through the frequency converter of the traction unit and controlling the raising and lowering of the drum through the servo valve of the drum height adjustment cylinder, thus achieving automatic height adjustment.

[0019] The hydraulic support is controlled by the solenoid pilot valve of the support electro-hydraulic control valve group, which controls the lowering, moving, and raising of the support, as well as the extension and retraction of the side guards and telescopic beams.

[0020] The scraper conveyor is controlled by frequency converters at the head and tail to coordinate its operating speed, matching it with the amount of coal dropped by the coal mining machine, thus achieving "coal flow balance".

[0021] In this embodiment, the virtual unit is described in detail as follows: First, let's explain the twin construction module: Based on 3D seismic data, drilling data, and geological data revealed during tunnel excavation provided by geological exploration departments, this module uses geostatistical methods such as Kriging interpolation to construct a high-precision 3D geological model that includes the undulations of the coal seam roof and floor, faults, folds, and the distribution of interbedded gangue layers.

[0022] We obtain high-precision CAD models of coal mining machines, hydraulic supports, and scraper conveyors from equipment manufacturers, and use engines such as Unity3D for lightweight rendering. At the same time, we assign physical properties (such as mass and moment of inertia) and kinematic constraints (such as articulation relationships and degrees of freedom) to these models to form "digital prototypes" of the equipment. Finally, we precisely assemble these digital prototypes into the three-dimensional geological model according to the actual installation positions underground to form static initial twins.

[0023] By receiving real-time data to drive the static model, the static initial twin can be transformed into a dynamic twin that reflects the real-time state of the physical entity. For example, the real-time coordinates and attitude data of the coal mining machine can be assigned to its digital model, allowing it to move synchronously with the physical coal mining machine in virtual space.

[0024] The model correction module is explained below: (1) This module defines the key implicit parameters that need to be corrected in the virtual model as state vector X. For example, the working face can be divided into grids, and the "coal seam cutting resistance coefficient" of each grid point is a state variable.

[0025] (2) Based on the state estimate and system dynamics model of the previous time step, predict the state at the current time step. Covariance .

[0026] (3) Obtain the actual observation value Z of the sensor network module (such as the real-time current of the coal mining machine motor, which is strongly correlated with the cutting resistance), and compare the observation value with the observation value predicted by the model (from the state). The Kalman gain K is calculated by comparing the results obtained from the observation model with the Kalman gain K.

[0027] (4) Using the Kalman gain K, the predicted state is... The system performs a weighted fusion with the observed value Z to obtain the optimal state estimate X at the current moment. This X is the corrected distribution of coal seam cutting resistance coefficient. The system immediately updates the virtual geological model with X to make it closer to the real coal seam situation.

[0028] The twin data analysis and decision-making module will be explained as follows: In the digital twin, the virtual scanning unit calculates the Boolean difference between the coal mining machine drum cutting profile and the coal seam model in real time, and dynamically generates a "residual coal thickness" cloud map. This cloud map can intuitively show which areas of the coal seam are over-cut (cutting the top / bottom) or under-cut (leaving the top / bottom), providing a direct basis for optimizing the cutting path of the next cut.

[0029] In virtual space, the collision detection unit uses AABB (axial bounding box) or OBB (directional bounding box) collision detection algorithms to pre-simulate the relative movements of the support side plates and the coal mining machine body, and the coal mining machine drum and the scraper conveyor scraper blades in the next few support operation cycles. Once a penetration (i.e. collision) of the model mesh is detected, the action delay of the relevant support or the stop sequence of the coal mining machine is immediately adjusted in the control strategy to avoid equipment interference accidents in the physical world from the source.

[0030] The parameter optimization unit employs a genetic algorithm-based optimization method, setting the optimization objective as either "lowest energy consumption per ton of coal" or "highest coal mining efficiency." First, the operating parameters of the equipment to be optimized (coal mining machine traction speed V, drum speed N) are encoded as chromosomes in the genetic algorithm. A set of parameter combinations is randomly generated to form an initial population. Then, a complete coal mining cycle is rapidly simulated for each set of parameters (V, N) in the digital twin. Based on the simulation results, the corresponding energy consumption per ton of coal or coal production is calculated as the fitness value of that chromosome. The algorithm then performs genetic operations such as selection, crossover, and mutation on the population based on the fitness, thereby generating a new generation of parameter populations. This simulation and genetic operation are repeated until the maximum number of iterations is reached or the fitness converges. Finally, the parameter combination represented by the chromosome with the highest fitness is the approximate optimal solution under the current operating conditions and will be output as part of the optimal control strategy.

[0031] The interactive unit will be explained in detail below: First, let's explain the communication module: This module uses industrial Ethernet to form an underground backbone ring network. Near mobile devices (such as coal mining machines), mining 5G / WiFi6 base stations are deployed to utilize their ultra-low latency (<20ms) and high speed characteristics to enable the access of a large number of mobile nodes such as coal mining machines and support controllers.

[0032] The control module is described below: After receiving the pre-execution control strategy from the decision-making module, this module does not immediately issue it. Instead, it first performs a rehearsal in the virtual digital twin. During the rehearsal, the collision detection unit is invoked to ensure the absolute safety of the action sequence. After the rehearsal is successful, the module transforms the strategy into control commands and issues them to the relevant actuator modules through the communication module, ensuring the precise timing of the coordinated actions of the three mechanisms.

[0033] The following explanation is provided for the security early warning and self-decision-making module: This module monitors in-depth state information within the virtual digital twin in real time, such as stress cloud maps of key equipment components and roof pressure distribution cloud maps calculated through finite element analysis. When the virtual model predicts that the support resistance of a certain support is about to exceed the safety threshold, or that the roof pressure concentration coefficient is too high, the module immediately generates a high-level warning. Then, based on a preset safety rule library (such as "if the support resistance of the Nth support behind the coal mining machine exceeds the limit, immediately reduce the traction speed of the coal mining machine by 50%), the module automatically generates a safety intervention command. This command has the highest priority and can be executed directly through the intelligent control module, bypassing conventional control commands, to achieve proactive safety protection.

[0034] Please see Figure 2 Furthermore, the workflow of this invention will be described as follows: The sensor network module deployed in the underground working face continuously collects equipment operating status (such as coal mining machine position, support pressure, and conveyor current) and environmental parameters (such as gas concentration and roof delamination). This real-time data is transmitted to the ground control center in real time through the communication module.

[0035] After receiving data, the virtual unit at the ground control center first uses a Kalman filter algorithm to compare and fuse real-time data with virtual model predictions, dynamically correcting key implicit parameters in the virtual model (such as coal seam hardness distribution and roof pressure intensity) to ensure high-fidelity synchronization between the digital twin and the physical entity. Then, based on the updated high-fidelity twin, the twin data analysis and decision-making module simulates the virtual coal mining process for several future production cycles. In this virtual space, the system performs actions such as cutting path optimization, support following logic verification, and collision interference detection, generating a globally optimal and verified equipment collaborative control strategy.

[0036] The generated optimal control strategy is sent to the control module, which decomposes the strategy into specific and timed equipment control instructions, and then sends them again to the actuator modules of the underground physical entities (such as the frequency converter of the coal mining machine and the electro-hydraulic control valve of the support) through the communication module to drive the physical equipment to execute.

[0037] After the physical device performs an action, the new state data it generates is collected again by the sensor network module, and a new round of "uplink-simulation-decision-downlink" cycle is started. Through this continuously operating closed loop, the system can continuously adapt to changing operating conditions and continuously evolve towards the set optimization goals (such as the highest efficiency and the lowest energy consumption), thus achieving true intelligent adaptive control.

[0038] This invention provides comparative examples: This comparative example simulates the effect of the present invention on a virtual working face through experiments. The experiment is based on the system and a digital twin test platform is built, which includes 150 hydraulic supports, 1 coal mining machine and 1 scraper conveyor. The simulated coal seam is 200 meters long, with an average thickness of 3.5 meters, a normal fault in the middle, and interbedded gangue layers with varying thickness.

[0039] This invention sets up three groups of experimental subjects, specifically including: Comparative Example 1 uses a traditional automated system based on preset program control and local sensor feedback. The coal mining machine cuts according to a fixed memory, and the support executes a fixed follow-up program, without global optimization or look-ahead simulation.

[0040] Comparative Example 2 has the sensor network and centralized control of this system, but lacks a digital twin for model correction and forward-looking decision-making, relying solely on big data analysis for rule-based control.

[0041] The experimental example is a complete system of the present invention.

[0042] This experiment assesses production efficiency by monitoring the total time (in hours) to complete the advance of a standard working face (200 meters), evaluates coal recovery rate by calculating the percentage of actual coal extracted to geological reserves, assesses energy consumption per ton of coal by the ratio of total power consumption to total coal production, reflects the number of interference events by recording collisions between the sidewalls and the coal mining machine, and reflects the roof control quality by the percentage of hydraulic supports with excessive support resistance. The test was first conducted under stable coal seam and favorable working conditions, and the results are as follows.

[0043]

[0044] As shown in the table above, under stable operating conditions, all indicators of the present invention are superior to those of the two comparative examples. Although the advantages are not obvious, they demonstrate its continuous optimization capabilities. In particular, the number of equipment interferences is 0, which proves the effectiveness of the collision detection unit.

[0045] The test was conducted under conditions where a fault was encountered and the coal seam thinned. The results are as follows:

[0046] As shown in the table above, under this operating condition, Comparative Example 1, when encountering a fault, failed to recognize the thinning of the coal seam and continued cutting at the original height, resulting in a large amount of cut bottom rock, a sharp drop in recovery rate, a surge in energy consumption, and frequent vibrations causing multiple equipment interferences. While the system in Comparative Example 2 could sense changes in cutting load through sensors, it lacked an understanding of the overall coal seam morphology, leading to slow adjustments. This invention, through a model correction module, pre-corrects the coal seam model in the virtual model. Based on this, the twin data analysis and decision-making module generates an optimized cutting path that bypasses the fault and adapts to the thin coal seam, thereby maximizing coal recovery, protecting the equipment, and significantly improving adaptability under complex geological conditions.

[0047] The test was conducted under conditions of a sudden increase in roof pressure, and the results are as follows:

[0048] As shown in the table above, under this working condition, Comparative Examples 1 and 2 can only react passively after the support pressure exceeds the limit, resulting in production interruption. However, the safety early warning and self-decision-making module of this invention predicts the area of ​​concentrated roof pressure in advance in the virtual model and automatically generates instructions to reinforce the support in the area in advance and appropriately reduce the speed of the coal mining machine, thereby realizing proactive pressure relief mining, controlling the proportion of support exceeding the limit at a low level, and ensuring the continuity and safety of production.

[0049] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A digital twin-based intelligent coal mining face control system, characterized in that, It includes physical units, virtual units, and interactive units, among which: The entity unit includes: The sensor network module includes sensors deployed on the coal mining machine, hydraulic supports, and scraper conveyors to collect equipment attitude, operating parameters, location information, and environmental parameters in real time. The actuator module, including the coal mining machine traction unit, drum height adjustment cylinder, hydraulic support electro-hydraulic control valve group, and scraper conveyor frequency converter driver, is used to receive and execute control commands; The virtual unit includes: The twin construction module is used to build and drive a full-element three-dimensional dynamic virtual model that is consistent with the geometry, physics and behavior rules of the physical working face, based on geological exploration data, equipment CAD models and real-time sensor data. The model correction module, connected to the sensor network module, is used to compare real-time sensor data with virtual model prediction data through data fusion algorithms. When the deviation exceeds a preset threshold, the parameters in the virtual model are corrected in reverse to make the virtual model consistent with the physical entity. The twin data analysis and decision-making module, connected to the model correction module, is used to simulate the entire coal mining process and verify the equipment linkage logic in virtual space. At the same time, it optimizes the cutting path and the automatic follow-up strategy of the support based on the virtual model, and generates the optimal control strategy containing the equipment action sequence and timing. The interaction unit includes: The communication module is used to provide a data transmission channel; The control module, connected to the twin data analysis and decision-making module and the actuator module, is used to convert the optimal control strategy into equipment control commands and send them to the actuator module through the communication module for controlling the working face equipment.

2. The intelligent coal mining face control system based on digital twin as described in claim 1, characterized in that, The sensors in the sensor network module include: an inertial navigation unit and a UWB positioning tag installed on the coal mining machine for real-time acquisition of the three-dimensional coordinates and attitude of the coal mining machine; tilt sensors, pressure sensors, and displacement sensors installed on the hydraulic supports for monitoring the support attitude, support resistance, and pushing stroke; and gas concentration sensors, dust concentration sensors, and a roof pressure monitoring system installed in the working face and return airway for monitoring gas concentration, dust concentration, and roof pressure.

3. The intelligent coal mining face control system based on digital twin as described in claim 1, characterized in that: The twin construction module is used to: integrate 3D seismic and drilling data to construct a high-precision 3D geological model that includes coal seam thickness undulations, geological structure, and interbedded rock distribution; simultaneously import high-precision CAD models of equipment such as coal mining machines and hydraulic supports, and assign them kinematic and dynamic properties; then assemble the 3D geological model and equipment model in a unified coordinate system to form a static initial twin; and through real-time data driving, the static initial twin evolves into a dynamic twin that can reflect the real-time state of the physical entity.

4. The intelligent coal mining face control system based on digital twin as described in claim 1, characterized in that: The model correction module uses a Kalman filter algorithm for data fusion. By fusing the actual trajectory and pressure data of the physical entity collected by the sensor network module with the prediction output of the virtual model, it dynamically estimates and corrects the implicit parameters in the virtual model that are difficult to measure directly and accurately.

5. The intelligent coal mining face control system based on digital twin as described in claim 1, characterized in that, The twin data analysis and decision-making module includes: The virtual scanning unit is used to calculate and update the distribution of residual coal thickness in the coal seam based on the real-time cutting trajectory of the coal mining machine drum in the virtual model. The collision detection unit is used to pre-simulate the motion relationship between the support side plate and the coal mining machine body, and between the drum and the scraper conveyor scraper in virtual space. When potential interference is detected, the timing of the support action or the trajectory of the coal mining machine is adjusted before the control command is generated. The parameter optimization unit is used to optimize the matching relationship between the coal mining machine traction speed and the drum speed through iterative simulation in a virtual model with the goal of "lowest energy consumption per ton of coal" or "highest coal mining efficiency".

6. The intelligent coal mining face control system based on digital twin as described in claim 5, characterized in that: The parameter optimization unit employs optimization algorithms based on genetic algorithms or reinforcement learning to rapidly simulate multiple production cycles in a virtual environment, thereby finding the globally optimal or near-optimal combination of equipment operating parameters.

7. The intelligent coal mining face control system based on digital twin according to claim 1, characterized in that: The control module receives pre-execution control strategies from the twin data analysis and decision-making module. Before issuing control commands to physical devices, it first performs command rehearsals in the virtual digital twin unit to verify their security and feasibility. After the rehearsals are passed, the control commands are packaged and synchronously issued to the relevant actuator modules through the high-speed communication module to achieve the linkage of the coal mining machine, hydraulic support and scraper conveyor.

8. The intelligent coal mining face control system based on digital twin according to claim 1, characterized in that: The system also includes a security early warning and self-decision-making module, which is connected to the twin data analysis and decision-making module and the control module. The security early warning and self-decision-making module is used to generate high-level early warnings and generate and execute security intervention commands.

9. The intelligent coal mining face control system based on digital twin as described in claim 8, characterized in that: The safety early warning and self-decision-making module analyzes the equipment stress cloud map and roof pressure distribution in the virtual model in real time. When an overload or roof collapse risk is predicted, a high-level early warning is generated. After receiving the high-level early warning, a safety intervention command is generated and executed based on the preset safety rule base. This safety intervention command is executed with the highest priority.

10. The intelligent coal mining face control system based on digital twin according to claim 1, characterized in that: The communication module adopts a mining industrial ring network and a 5G / WiFi6 converged network to provide a high-bandwidth and low-latency data transmission channel between physical units and virtual units.

Images