Intelligent regulation and control method and system for dust removal and air control of underground high-gas heading face

Abstract

The invention discloses an intelligent regulation and control method and system for dust removal and air control of an underground high-gas heading face, and relates to the field of intelligent control. Firstly, an environment parameter set and an equipment parameter set are obtained in real time; constructing a digital twinborn model of the tunneling face and the ventilation system based on the environmental parameter set and the equipment parameter set, and simulating gas concentration and dust concentration under different working conditions; the prediction model predicts the gas emission amount trend and the dust concentration trend; and inputting the environment parameter set, the equipment parameter set and the risk level into an optimization model, and generating a target decision instruction by the optimization model. The operation parameters in the ventilation system can be timely regulated and controlled in real time based on the monitored environment parameter set of the tunneling face and the equipment parameter set in the ventilation system, so that the ventilation and dust removal efficiency of the ventilation system is improved. Moreover, the decision instruction is generated by referring to the trend of the gas emission amount and the dust concentration in the future, so that the accuracy of the decision instruction of the ventilation system is further improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control, and more specifically, to an intelligent regulation method and system for dust removal and air control in a high-gas heading face underground. Background Art

[0002] At present, the main threats to coal mine safety production include accidents such as gas, water inrush, dust, fire, roof, etc. Among them, gas explosion and dust pollution are the core problems threatening miners' safety and production efficiency. And doing a good job in monitoring ventilation parameters and linkage regulation in the mine heading face can effectively prevent the occurrence of mine accidents.

[0003] The air volume of the traditional ventilation system is fixed or adjusted manually. Therefore, it cannot dynamically respond to the real-time changes of the heading speed, gas emission volume and dust concentration, which is likely to cause local gas accumulation or serious waste of ventilation energy consumption. Moreover, there is a lack of coordinated control between the dust removal fan and the ventilation fan, and conflicts are likely to occur between different devices. For example, the air flow conflict between the dust removal fan and the ventilation fan leads to a reduction in the dust removal efficiency. Summary of the Invention

[0004] In view of this, the present invention provides an intelligent regulation method and system for dust removal and air control in a high-gas heading face underground, which is used to solve the problems of lagging regulation, isolated equipment and excessive energy consumption in the existing dust removal and air control regulation methods for high-gas heading faces underground.

[0005] To achieve the above object, the following solutions are proposed: An intelligent regulation method for dust removal and air control in a high-gas heading face underground, comprising: Obtaining an environmental parameter set and an equipment parameter set in real time; Constructing a digital twin model of the heading face and the ventilation system based on the environmental parameter set and the equipment parameter set, and simulating the gas concentration and dust concentration under different working conditions through the digital twin model; Inputting the environmental parameter set and the influence parameter set into a pre-trained prediction model for the prediction model to predict the gas emission trend and dust concentration trend within a preset future time period; Dividing the risk level based on the gas emission trend and the dust concentration trend; Inputting the environmental parameter set, the equipment parameter set and the risk level into an optimization model for the optimization model to generate a target decision instruction; Performing parameter regulation based on the target decision instruction.

[0006] Preferably, the environmental parameter set includes: gas concentration, dust concentration and wind speed; The equipment parameter set includes: air volume, spray intensity and dust removal power.

[0007] Preferably, the process of constructing the digital twin models of the tunneling face and the ventilation system based on the environmental parameter set and the equipment parameter set includes: Construct the digital twin models of the tunneling face and the ventilation system based on the BIM roadway model, the environmental parameter set and the equipment parameter set; Dynamically calculate the air resistance distribution, simulate the dust diffusion field using the discrete phase model, and load the tunneling machine pose data to real-time correct the boundary conditions of the digital twin models of the tunneling face and the ventilation system.

[0008] Preferably, the influence parameter set includes: historical gas concentration, cutting speed, and geological conditions.

[0009] Preferably, the method further includes: Judge whether the risk level drops after a preset time period; If it does not drop, forcibly lock each device and report the fault.

[0010] An intelligent control system for dust removal and air control in a high-gas underground tunneling face realizes the foregoing intelligent control method for dust removal and air control in a high-gas underground tunneling face. The system includes: A real-time perception layer for obtaining the environmental parameter set and the equipment parameter set in real time; A data processing and decision-making layer constructs the digital twin models of the tunneling face and the ventilation system based on the environmental parameter set and the equipment parameter set, and simulates the gas concentration and dust concentration under different working conditions through the digital twin models; inputs the environmental parameter set and the influence parameter set into a pre-trained prediction model for the prediction model to predict the gas emission trend and dust concentration trend within a preset future time period; divides the risk level based on the gas emission trend and the dust concentration trend; inputs the environmental parameter set, the equipment parameter set, and the risk level into an optimization model for the optimization model to generate a target decision instruction; An execution layer adjusts parameters based on the target decision instruction.

[0011] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects: The intelligent regulation method for dust removal and air control in high-gas heading faces underground provided by the present invention first obtains the environmental parameter set and equipment parameter set in real time; constructs a digital twin model of the heading face and the ventilation system based on the environmental parameter set and the equipment parameter set, and simulates the gas concentration and dust concentration under different working conditions through the digital twin model; inputs the environmental parameter set and influencing parameters into a pre-trained prediction model, and the prediction model predicts the gas emission trend and dust concentration trend within a preset future time period; divides the risk level based on the gas emission trend and dust concentration trend; inputs the environmental parameter set, equipment parameter set and risk level into an optimization model for the optimization model to generate target decision instructions. The present invention can timely and real-time regulate the operating parameters in the ventilation system based on the monitored environmental parameter set of the heading face and the equipment parameter set in the ventilation system, thereby improving the efficiency of ventilation and dust removal in the ventilation system. Moreover, when generating decision instructions, the trend of gas emission and dust concentration within a certain period in the future is referred to, thereby further improving the accuracy of the decision instructions of the ventilation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0013] Figure 1 It is a structural framework diagram of an intelligent regulation system for dust removal and air control in a high-gas heading face underground provided by an embodiment of the present invention; Figure 2 It is a structural schematic diagram of an intelligent regulation system for dust removal and air control in a high-gas heading face underground provided by an embodiment of the present invention; Figure 3 It is a flowchart of an intelligent regulation method for dust removal and air control in a high-gas heading face underground provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0015] First, in combination with Figure 1 introduce the intelligent regulation system for dust removal and air control in a high-gas heading face underground provided by the embodiment of the present invention, as Figure 1As shown in the figure, the system includes: a real-time perception layer 100, a data processing and decision-making layer 200, and an execution layer 300.

[0016] The real-time perception layer 100 includes a multi-parameter sensor network and a device status monitoring module. The device status monitoring module includes a local ventilator speed acquisition module, a dust removal fan negative pressure acquisition module, a spray system water pressure acquisition module, etc. The multi-parameter sensor network includes a laser methane sensor, a light scattering dust sensor, and a temperature and humidity sensor. Among them, the laser methane sensor (accuracy ±0.1%, sampling frequency 1Hz) is deployed at the heading face and the return airway to monitor the change of methane concentration at the heading face and the return airway in real time; the light scattering dust sensor (range 0-1000mg / m³, resolution 0.1mg / m³) is deployed at the cutting point, the transfer point and the return side to monitor the change of dust concentration in the heading roadway in real time; the ultrasonic anemometer (accuracy ±0.1m / s) is used to monitor the air velocity in the main airway and the working face; the temperature and humidity sensor (accuracy ±0.5℃).

[0017] The layout of the multi-parameter sensor network is as follows: One laser methane sensor can be installed every 3m along the heading face (1.2m from the floor, inclination angle 15°), and one every 5m in the return airway (0.8m from the roof) to monitor the change of methane concentration at the heading face and the return airway in real time. Three scattering sensors can be distributed in a 120° ring 2m in front of the cutting point, with a height of 1.5m, and a binocular vision system is installed above the transfer point. The pitch angle of the binocular vision system is -30° to form a three-dimensional monitoring network to monitor the change of dust concentration in the heading roadway in real time. One ultrasonic anemometer is arranged at the entrance of the main airway, the working face and the return airway respectively. The range of the ultrasonic anemometer is 0-15m / s, and the sampling rate is 10Hz, which is used to monitor the air velocity in the main airway and the working face. The temperature and humidity sensor is deployed at the heading face to monitor the temperature and humidity change in the heading roadway, which is used to assist in evaluating the ventilation efficiency.

[0018] The layout of the device status monitoring module is as follows: The device status monitoring module includes a local ventilator speed acquisition module, a dust removal fan negative pressure acquisition module, a spray system water pressure acquisition module, etc., which are respectively installed on the corresponding devices in the execution layer to collect the operating parameters of the devices under different working conditions, and are used for visual dust removal and air control intelligent regulation.

[0019] The data processing and decision-making layer 200 includes edge computing nodes, a prediction model, and an optimization model. The edge computing nodes are deployed in the underground explosion-proof box and are built with a data processing unit for providing data transmission, processing, calculation, and storage services, etc., and performing abnormal data cleaning, feature extraction, and local decision-making. The prediction model can be a time series prediction model constructed based on the LSTM neural network. The prediction model can output the trends of gas emission and dust concentration in a future period by inputting influencing parameters such as historical gas concentration, cutting speed, and geological conditions. The optimization model includes a reinforcement learning framework, a Q-learning algorithm, and a multi-objective genetic algorithm. Among them, the reinforcement learning framework includes a state space (gas concentration, dust concentration, wind speed), an action space (air volume, spray intensity, dust removal power), and a reward function (safety weight 60%, energy consumption weight 30%, efficiency weight 10%); the Q-learning algorithm is used to iteratively optimize the control strategy; the multi-objective genetic algorithm can be the NSGA-II algorithm, which is used to solve the Pareto optimal solution set of air volume - energy consumption - dust removal efficiency. The optimization process is executed every 5 minutes. After outputting the Pareto front solution set, the TOPSIS method can be used to select the solution with the highest comprehensive score.

[0020] The execution layer 300 is a ventilation system, including a ventilator, a spray system, and a dust removal fan. Among them, the ventilator can be a variable frequency speed regulation local ventilator, the spray system can be a high-pressure spray system, and the dust removal fan is a dry dust removal fan. The rated power of the variable frequency speed regulation local ventilator can be 55kW, and the adjustment range is 30% - 100%. The variable frequency speed regulation local ventilator receives the air volume instruction in the target decision-making instruction through the RS485 bus. The pressure range of the high-pressure spray system can be 10 - 20MPa, the adjustable angle of the nozzle array is ±30°, it is deployed at the heading face, and the electromagnetic valve and stepper motor are used to control the spray particle size (10 - 50μm) and the coverage area. The filtration efficiency of the dry dust removal fan is greater than or equal to 95%, and the adjustable range of negative pressure is 500 - 2000Pa, which can cooperate with the wet filtration device to achieve secondary dust removal.

[0021] Next, in combination with Figure 3 An intelligent regulation method for dust removal and air control in a high-gas heading face underground provided by an embodiment of the present invention will be introduced. This regulation method can be implemented based on the aforementioned regulation system. As Figure 3 shown, the method includes: Step S01, obtain the environmental parameter set and the device parameter set in real time.

[0022] Specifically, the laser methane sensor, light scattering dust meter and ultrasonic anemometer in the multi-parameter sensor network are used to collect the three-dimensional vector data of gas concentration, respirable dust concentration and wind speed at the excavation face in real time to obtain a set of environmental parameters. The operating parameters such as the fan frequency, dust removal fan negative pressure, spray water pressure and so on in the ventilation system are obtained through the equipment status monitoring module to obtain a set of equipment parameters.

[0023] The sliding window Tukey algorithm (window width 30s) is used to remove abnormal data points in the environmental parameter set and the device parameter set. The data frames of different sensors can also be matched by timestamp to compensate for transmission delay (≤50ms).

[0024] Step S02: construct a digital twin model of the excavation face and ventilation system based on the environmental parameter set and the equipment parameter set, and simulate the gas concentration and dust concentration under different working conditions through the digital twin model.

[0025] Specifically, based on the environmental parameter set and equipment parameter set collected by the real-time perception layer, a digital twin model is constructed to simulate the ventilation and dust removal effects under different working conditions. A three-dimensional digital twin model of the excavation face and ventilation system is constructed based on the BIM tunnel model, environmental parameter set and equipment parameter set; then, the wind resistance distribution is dynamically calculated, the discrete phase model (DPM) is used to simulate the dust diffusion field, and the tunnel boring machine posture data (cutting speed, pitch angle) is loaded to correct the boundary conditions of the digital twin model of the excavation face and ventilation system in real time. Based on the three-dimensional structure of the tunnel (BIM model), real-time sensor data (gas concentration, dust distribution, wind speed, etc.) and tunnel boring machine posture parameters, the wind resistance distribution and dust diffusion field of the ventilation system are dynamically simulated. The digital twin model not only includes the operating status of the ventilation system, but also covers the environmental characteristics of the excavation face, and can comprehensively map the gas, dust and wind flow dynamics of the physical space. Among them, the three-dimensional structure (BIM model) of the tunnel is based on BIM or point cloud scanning technology to build a high-precision (±5cm) three-dimensional geometric model of the tunnel, including cross-sectional shape, branch structure, support form, etc. The unstructured grid division method is used to spatially discretize the tunnel (such as tetrahedral or hexahedral grids) to ensure a higher grid density in key areas (such as excavation faces and turns).

[0026] The ventilation and dust removal effects of the excavation face and ventilation system can be quantitatively analyzed through the digital twin model of the excavation face and ventilation system. The ventilation and dust removal effects can be quantitatively analyzed through parameters such as gas concentration, respirable dust concentration; tunnel wind speed, air volume, temperature and humidity; fan frequency, dust removal power, spray pressure and coverage angle; energy consumption, equipment operation efficiency, etc.

[0027] The calculation process of each parameter is as follows: 1. Dynamic calculation of wind resistance distribution: Frictional resistance: Calculated by the Darcy-Weisbach formula: , where f is the friction coefficient, L is the roadway length, is the hydraulic diameter, is the air density, v is the average wind speed.

[0028] Local resistance: For areas such as turns, branches, and sudden cross-section changes, the local resistance coefficient method is used for calculation: , where K is the local resistance coefficient.

[0029] Dynamic wind resistance compensation: Combining real-time monitoring data (such as the cross-section wind speed distribution collected by ultrasonic anemometers and the data of temperature and humidity sensors), the adaptive Kalman filtering algorithm is used to correct the friction coefficient and local resistance coefficient. The actual wind pressure loss is monitored through a pressure gradient sensor (such as a differential pressure gauge deployed in the ventilation duct), and compared with the theoretical value to dynamically update the resistance model parameters.

[0030] Ventilation network solution: Construct a ventilation network equation set, and based on the principles of mass conservation and energy conservation, the Newton-Raphson iteration method is used to solve the air volume and wind pressure distribution of each branch.

[0031] Output results: The wind speed, wind pressure, and wind resistance heat maps of each section of the roadway are used to guide the optimization of the ventilation fan frequency.

[0032] 2. Simulate the dust diffusion field: Dust generation source intensity: Based on the cutting speed of the roadheader (0 - 5 m / min) and the physical properties of coal and rock (such as hardness, moisture content), the instantaneous dust generation amount is calculated through an empirical formula: , where k is the dust generation coefficient, is the cutting speed, S is the cutting area, is the density of coal and rock.

[0033] According to the pose data of the roadheader (pitch angle, cutting head coordinates), the dust injection position and direction are corrected in real time.

[0034] Coupled solution of the air flow field: Based on the calculated wind speed field (from the wind resistance distribution model), the air flow is regarded as the continuous phase and the dust as the discrete phase, and the coupled motion of the two is solved. The governing equations are: Continuous phase: Navier-Stokes equation; Discrete phase: Particle motion equation: , where u p is the particle velocity, is the dynamic viscosity of the fluid, is the particle density, is the particle diameter, u f is the fluid velocity, C D is the drag coefficient, Re is the Reynolds number and g is the acceleration due to gravity.

[0035] Numerical solution: CFD software is used for transient solution, the time step is set to 0.1 second, and the dust concentration cloud map is updated every 5 seconds.

[0036] Output results: dust mass concentration distribution (mg / m³), diffusion path heat map, and concentration peaks in key areas (such as transfer points and return air lanes).

[0037] Step S03, inputting the environmental parameter set and the influencing parameter set into the pre-trained prediction model, so that the prediction model can predict the gas emission trend and dust concentration trend in a future preset time period.

[0038] Specifically, the LSTM prediction model is used to predict the gas emission and respirable dust concentration trends in the future. The LSTM prediction model predicts the gas emission and dust concentration trends in the future preset time period through the gas concentration, dust concentration, wind speed at the current moment in the environmental parameter set, and the historical gas concentration, cutting speed, geological conditions and other influencing parameters in the influencing parameter set. The LSTM prediction model predicts the gas emission and dust concentration at different times in the future preset time period, and reflects the overall trend through the time series changes of the values.

[0039] The warning is triggered directly based on whether the predicted value exceeds the preset threshold or if the predicted value shows continuous growth and the slope exceeds the set threshold, even if it is not exceeded at present, the system will determine it as "trend exceeding the limit" and trigger advance control.

[0040] Step S04, classifying the risk levels based on the gas emission trend and the dust concentration trend.

[0041] Specifically, risk levels are divided according to the trends of gas emission and dust concentration: low risk maintains the current control strategy; medium risk triggers feedforward control; high risk initiates advance control.

[0042]

[0043] Step S05, inputting the environmental parameter set, the equipment parameter set and the risk level into the optimization model so that the optimization model can generate a target decision instruction.

[0044] Specifically, the environmental parameter set, equipment parameter set, and risk level are input into the reinforcement learning framework to generate decision instructions. The optimization model generates decision instructions based on the real-time sensing data such as gas concentration, respirable dust concentration, roadway air velocity, temperature and humidity in the currently monitored environmental parameter set; the equipment operation parameters such as the rotation speed of the ventilation fan, the negative pressure of the dust removal fan, the water pressure of the spray system, and the nozzle angle in the equipment parameter set; and the gas emission trend and dust concentration trend output by the prediction model.

[0045] The decision instructions include the air volume set value, spray intensity level, and dust removal power instruction. Then, the NSGA-II algorithm is used to balance the energy consumption and efficiency of the decision instructions, the NSGA-II algorithm is used to solve the Pareto optimal solution set, and the entropy weight TOPSIS method is used to select the target decision instruction from the non-dominated solution set. For example: an early warning is triggered based on whether the predicted value exceeds the preset threshold, or when the predicted value shows a continuous increase and the slope exceeds the set threshold, even if it does not exceed the limit currently, the system will determine it as "trend overrun" and trigger early regulation.

[0046] Different risk levels correspond to different control strategies and decision instructions. For example: 1. Low-risk control strategy: Maintain the current safe state and optimize energy efficiency.

[0047] Specific measures: Ventilation system: Keep the fan frequency at 80%-100% of the rated value and dynamically fine-tune it according to the wind resistance model (±2 Hz).

[0048] Spray system: Turn on the basic spray mode (pressure 10 MPa, particle size 50 μm) to cover the main dust generation points (such as the cutting head).

[0049] Dust removal system: The dust removal fan operates at 60% of the rated power, and the filter unit works in the conventional mode.

[0050] Monitoring frequency: Update the environmental parameters every 30 seconds without active intervention.

[0051] 2. Medium-risk control strategy: Suppress potential risks in advance to prevent the concentration from deteriorating further.

[0052] Specific measures: Ventilation enhancement: Increase the fan frequency to 110%-120% of the rated value, and preferentially increase the air supply volume in the driving face (the air volume is increased by 15%-20%).

[0053] Start the local air duct deflector to optimize the air flow path and reduce the accumulation of gas in the eddy current area.

[0054] Spray Upgrade: Switch to the high-pressure spray mode (pressure 15 MPa, particle size 30 μm) to expand the coverage area to high-risk areas. Activate the coordinated injection of multiple nozzles (such as adding a temporary fog curtain 2 m in front of the cutting point).

[0055] Dust Removal Enhancement: Increase the power of the dust removal fan to 80%, and turn on the standby filter unit. Start the pulse backwashing mechanism (interval shortened to 10 seconds) to maintain a filtration efficiency of ≥95%.

[0056] Dynamic Monitoring: Update data every 10 seconds. If it does not degrade to a low risk within 30 minutes, trigger manual intervention for inspection.

[0057] 3. High-Risk Control Strategy: Rapidly contain the overlimit risk to ensure the safety of personnel and equipment.

[0058] Specific Measures: Emergency Ventilation: Increase the fan frequency to 150% of the rated value (short-term overload mode), open the bypass air duct, and forcefully dilute the gas. Activate the local pressurization system to ensure that the evacuation path wind speed ≥ 1.5 m / s.

[0059] Dust Suppression: Start the high-pressure spray at full power (pressure 20 MPa, particle size ≤ 20μm) to form a three-dimensional surrounding fog curtain. Deploy dry-wet combined dust removal: The dry dust removal fan operates at 100% power, and the wet filtration device (water film dust removal) is started synchronously.

[0060] Production Interruption and Evacuation: Immediately cut off the power supply of the cutting motor and trigger an audible and visual alarm. Broadcast the evacuation instructions through the personnel positioning system and dynamically plan the shortest safe path (avoiding high-concentration areas).

[0061] Step S06, perform parameter regulation based on the target decision instruction.

[0062] Specifically, transmit the optimized decision instruction to devices such as the variable-frequency speed regulation local ventilator, high-pressure spray system, and dry dust removal fan at the execution layer through the RS485 bus, and adjust their working parameters according to the target decision instruction. Among them, the adjustment rate of the local ventilator frequency is less than or equal to 1 Hz / s to prevent air flow impact, and the spray particle size matches the pressure.

[0063] Control the ventilation system through hierarchical response. If the gas concentration is less than 0.8%, the target decision instruction is the current decision instruction; if the gas concentration is between 0.8% and 1.0% or the predicted trend exceeds the preset limit, the target decision instruction is to increase the air volume by 10%, switch the spray system to the high-pressure mode, adjust the spray particle size to be less than or equal to 20 μm, increase the dust removal power of the dry dust collector to 80% of the rated power, and activate the standby wet filtration device. Among them, the maximum increase in air volume does not exceed 120% of the rated value. If the gas concentration is greater than or equal to 1.0%, the target decision instruction is to cut off the power supply of the cutting motor, start the audible and visual alarm, open the bypass air duct, start emergency ventilation (air volume 150% of the rated value), and turn off the cutting power supply. It may also include broadcasting evacuation instructions through the positioning system.

[0064] The intelligent regulation method for dust removal and air control in high-gas heading faces underground provided by the embodiments of the present invention. First, obtain the environmental parameter set and equipment parameter set in real time; construct a digital twin model of the heading face and the ventilation system based on the environmental parameter set and the equipment parameter set, and simulate the gas concentration and dust concentration under different working conditions through the digital twin model; input the environmental parameter set and influence parameters into the pre-trained prediction model, and the prediction model predicts the gas emission trend and dust concentration trend within a preset future time period; divide the risk level based on the gas emission trend and dust concentration trend; input the environmental parameter set, equipment parameter set and risk level into the optimization model for the optimization model to generate target decision instructions. The embodiments of the present invention can timely adjust the operating parameters in the ventilation system based on the monitored environmental parameter set of the heading face and the equipment parameter set in the ventilation system, thereby improving the efficiency of ventilation and dust removal in the ventilation system. Moreover, when generating the decision instruction, the trend of gas emission and dust concentration in the future period of time is referred to, thereby further improving the accuracy of the decision instruction of the ventilation system.

[0065] The intelligent regulation method for dust removal and air control in high-gas heading faces underground in the embodiments of the present invention triggers the hierarchical response mechanism in advance by predicting the sudden increase in gas emission or the over-limit of dust concentration; seeks the optimal balance among safety (suppressing gas and dust), energy consumption (reducing operating costs) and efficiency (prolonging equipment life) through a multi-objective optimization algorithm; adjusts the collaborative strategy of ventilation and dust removal equipment in real time according to dynamic working conditions such as heading speed and geological condition changes to avoid local gas accumulation or a decrease in dust removal efficiency; uses the digital twin model for virtual commissioning and pre-plan deduction to verify the system robustness and the effectiveness of emergency measures under extreme working conditions.

[0066] In addition, in order to better ensure the accuracy of the regulation scheme of the present invention in different situations, based on the intelligent regulation method for dust removal and air control in high-gas heading faces underground in the foregoing embodiments, the regulation method of the embodiments of the present invention may further include: At every preset time period, compare the prediction trend output by the prediction model with the set of real-time collected environmental parameters; if the error is greater than 15%, retrain the prediction model online.

[0067] In addition, the regulation method of the embodiment of the present invention can also perform fault diagnosis, and the process is as follows: To avoid sensor redundancy, a "two-out-of-three" voting logic is adopted for key parameters. When 2 / 3 of the sensor data is consistent, it is adopted; if there is no 2 / 3 sensor data consistency, a fault mark is made to rule out the possibility of false alarms.

[0068] If the risk has not been downgraded after a period of time, each device can be forcibly locked and the fault can be reported to the central monitoring system.

[0069] When the ventilation duct pressure gradient ΔPa > 50 Pa, start the air leakage location algorithm, and at the same time combine the digital twin model to invert the coordinates of the leakage point (accuracy ±1 m).

[0070] After the communication is interrupted, it can be switched to local PLC control, and 80% of the target decision instruction is executed. At the same time, activate the spray full coverage mode, that is, the nozzle angle is locked at 45°.

[0071] Finally, it should also 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. 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 elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0072] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts among the various embodiments can be referred to each other.

[0073] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent control method for dust removal and air control in a high-gas heading face underground, characterized in that, It includes: Obtaining the environmental parameter set and the device parameter set in real time; Constructing a digital twin model of the tunneling face and the ventilation system based on the environmental parameter set and the device parameter set, and simulating the gas concentration and dust concentration under different working conditions through the digital twin model; Inputting the environmental parameter set and the influence parameter set into a pre-trained prediction model for the prediction model to predict the gas emission trend and dust concentration trend within a preset future time period; Dividing the risk level based on the gas emission trend and the dust concentration trend; Inputting the environmental parameter set, the device parameter set, and the risk level into an optimization model for the optimization model to generate target decision instructions; Conducting parameter regulation based on the target decision instructions.

2. The intelligent regulation method for dust removal and air control in the underground high-gas heading face according to claim 1, characterized in that, The environmental parameter set includes: gas concentration, dust concentration, and wind speed; The device parameter set includes: air volume, spray intensity, and dust removal power.

3. The intelligent regulation method for dust removal and air control in the underground high-gas heading face according to claim 2, characterized in that, The process of constructing a digital twin model of the tunneling face and the ventilation system based on the environmental parameter set and the device parameter set includes: Constructing a digital twin model of the ventilation system based on the BIM roadway model, the environmental parameter set, and the device parameter set; Dynamically calculating the wind resistance distribution, simulating the dust diffusion field using the discrete phase model, and loading the tunneling machine pose data to correct the boundary conditions of the digital twin model of the ventilation system in real time.

4. The intelligent regulation method for dust removal and air control in the underground high-gas heading face according to claim 3, wherein, The influence parameter set includes: historical gas concentration, cutting speed, and geological conditions.

5. The intelligent regulation method for dust removal and air control in the underground high-gas heading face according to claim 1, characterized in that, The method further includes: Judging whether the risk level drops after a preset duration; If it does not drop, forcibly lock each device and report a fault.

6. An intelligent control system for dust removal and air control in a high-gas heading face underground, characterized in that, To implement the intelligent regulation method for dust removal and air control in the high-gas tunneling face underground described in claim 1, the system includes: A real-time perception layer for obtaining the environmental parameter set and the device parameter set in real time; A data processing and decision-making layer that constructs a digital twin model of the tunneling face and the ventilation system based on the environmental parameter set and the device parameter set, and simulates the gas concentration and dust concentration under different working conditions through the digital twin model; inputs the environmental parameter set and the influence parameter set into a pre-trained prediction model for the prediction model to predict the gas emission trend and dust concentration trend within a preset future time period; divides the risk level based on the gas emission trend and the dust concentration trend; inputs the environmental parameter set, the device parameter set, and the risk level into an optimization model for the optimization model to generate target decision instructions; An execution layer for conducting parameter regulation based on the target decision instructions.

Images