Brand-new intelligent dedusting and ventilation control system for tunneling roadway based on remote control

Abstract

The invention, which relates to the technical field of tunneling roadways, discloses a brand-new tunneling roadway dust removal and ventilation intelligent control system based on remote control, comprising an intelligent control system main body, the intelligent control system main body comprises a remote control center, a multi-dimensional sensing module, an intelligent prediction module, a multi-system cooperative control module and a remote control module; the multi-dimensional sensing module collects gas concentration, dust concentration, airflow speed, temperature and tunneling operation parameters in a tunneling roadway in real time, through the multi-system cooperative control module and the energy efficiency optimization module, cooperative linkage of a ventilation system, a dust removal system and a spraying dust reduction system is achieved, airflow conflicts and system interference are avoided, the dust removal efficiency is improved, and meanwhile, the energy efficiency of the system is improved. Operation parameters are dynamically adjusted based on the frequency conversion fan and the energy efficiency database, energy consumption is optimized on the premise that safety is guaranteed, the problems of energy waste and low energy efficiency of a traditional system are solved, and green and energy-saving operation is achieved.

Description

Technical Field

[0001] This invention relates to the field of tunneling, specifically to a novel intelligent control system for dust removal and ventilation in tunneling based on remote control. Background Technology

[0002] In underground coal mine tunneling operations, dust and gas are two major hazards: high concentrations of dust can not only cause occupational diseases such as pneumoconiosis, but may also lead to coal dust explosions; while gas accumulation can easily cause gas explosions, seriously threatening the lives of miners and the normal operation of equipment. Therefore, efficient dust removal and ventilation control at the tunneling face have become the core aspects of safe coal mine production.

[0003] Reference patent (CN117988910B) discloses a dust control device and method for changing the airflow direction in the tunnel face. The device uses an intelligent air distribution device to divide the airflow in the compressed air duct into radial airflow and axial airflow. The radial airflow forms a positive pressure chamber at the front end of the tunnel to block the dust-laden circulating airflow, and the axial airflow forms a dust-laden vortex at the tunnel face. The dust is then drawn in by a dust removal fan.

[0004] Based on the aforementioned patents, although the device can effectively suppress circulating air, its airflow regulation mainly relies on mechanical structures, such as self-contracting rings and contracting wind deflectors. It lacks intelligent prediction and dynamic response capabilities for gas concentration and dust diffusion trends, and it does not achieve multi-system collaborative control. Furthermore, ventilation, dust removal, and spraying systems often operate independently without collaborative control, which can easily lead to airflow conflicts and low dust removal efficiency. At the same time, since it cannot dynamically adjust the air volume according to actual needs, traditional systems often maintain a high air volume output during tunneling, resulting in energy waste. The lack of intelligent control strategies also prevents the system from achieving the optimal energy efficiency ratio under different working conditions. Therefore, this invention provides a new intelligent control system for dust removal and ventilation in tunneling roadways based on remote control. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a novel intelligent control system for dust removal and ventilation in tunneling roadways based on remote control. This system solves the problems of lacking intelligent prediction and dynamic response capabilities for gas concentration and dust diffusion trends, failing to achieve multi-system collaborative control, and the fact that ventilation, dust removal, and spraying systems often operate independently without collaborative control, easily leading to airflow conflicts and low dust removal efficiency. Furthermore, because traditional systems cannot dynamically adjust airflow according to actual needs, they often maintain high airflow output during tunneling, resulting in energy waste. The lack of intelligent control strategies also prevents the system from achieving optimal energy efficiency ratios under different operating conditions.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a novel intelligent control system for dust removal and ventilation in tunneling roadways based on remote control, comprising a main body of the intelligent control system, which includes a remote control center, a multi-dimensional sensing module, an intelligent prediction module, a multi-system collaborative control module, and a remote control module; the multi-dimensional sensing module collects real-time data on methane concentration, dust concentration, airflow velocity, temperature, and tunneling operation parameters within the tunneling roadway; the intelligent prediction module, based on machine learning algorithms and combining historical data with real-time collected data, predicts methane accumulation trends and dust diffusion paths; the multi-system collaborative control module dynamically and collaboratively regulates the operating parameters of the ventilation system, dust removal system, and spray dust suppression system according to the prediction results and preset safety thresholds, achieving coordinated linkage of airflow, dust removal, and dust suppression.

[0007] Preferably, the multi-dimensional sensing module includes a distributed array of gas sensors, laser dust sensors, ultrasonic wind speed sensors, and tunneling machine operation status sensors. The gas sensors and dust sensors are arranged in groups every 5-8 meters, and are densely arranged at the tunneling face to ensure the comprehensiveness and real-time nature of data acquisition.

[0008] Preferably, the intelligent prediction module incorporates a gas accumulation prediction model and a dust diffusion prediction model. The gas accumulation prediction model is based on an LSTM neural network, which takes into account the gas concentration change rate, airflow velocity, and roadway cross-sectional parameters, and outputs the gas concentration distribution prediction results for the next 10-30 minutes. The dust diffusion prediction model combines fluid dynamics simulation and random forest algorithm to predict the diffusion range of dust under different airflow conditions.

[0009] Preferably, the multi-system collaborative control module is configured with airflow-dust removal-dust suppression collaborative logic. When the predicted dust diffusion range expands, the airflow direction is first optimized by adjusting the angle of the air guide plate of the ventilation system, then the fan speed of the dust removal system is increased, and finally the spray dust suppression system is activated according to the dust concentration.

[0010] Preferably, the ventilation system is equipped with a variable frequency fan, and the collaborative control module dynamically adjusts the fan frequency to change the air volume based on the predicted results of gas concentration, dust concentration and tunneling operation intensity; when the concentration is below the safety threshold and there is no risk of accumulation and diffusion, the air volume is automatically reduced to an energy-saving operating state.

[0011] Preferably, the main body of the intelligent control system also includes an emergency response submodule. When the multi-dimensional sensing module detects that the gas concentration or dust concentration exceeds the emergency threshold, or the intelligent prediction module predicts that it is about to exceed the standard, the emergency response submodule immediately triggers a linkage emergency mode that enables the ventilation system to operate at full load, the dust removal system to efficiently extract, and the spray system to be activated across the entire area. It also sends an alarm signal to the remote control center and locks the tunneling machine's operating permissions.

[0012] Preferably, the remote control module has real-time monitoring, parameter configuration, historical data tracing and fault diagnosis functions, and supports staff to view various monitoring data, system operation status and prediction results in the roadway through a visual interface. It can also remotely modify safety thresholds, collaborative control logic and equipment operating parameters.

[0013] Preferably, the main body of the intelligent control system also includes an energy efficiency optimization module. The energy efficiency optimization module establishes an energy efficiency database based on different tunneling conditions, including rock tunneling, coal tunneling, and tunneling speed. By comparing the energy consumption and dust removal and ventilation effects under different combinations of operating parameters, the optimal parameter combination is automatically selected.

[0014] Beneficial effects

[0015] This invention provides a novel intelligent control system for dust removal and ventilation in tunnel boring machines based on remote control. Compared with existing technologies, it has the following advantages: (1) The new intelligent control system for dust removal and ventilation in tunneling roadways based on remote control collects environmental parameters in the roadway in real time through a multi-dimensional sensing module, and uses an intelligent prediction module to accurately predict the gas accumulation trend and dust diffusion path based on machine learning technologies such as LSTM neural network and random forest algorithm. This achieves intelligent early warning and dynamic response to risks, overcomes the problems of lack of prediction ability and response lag in traditional systems, and significantly improves safety and automation level.

[0016] (2) The new intelligent control system for dust removal and ventilation in tunneling roadways based on remote control realizes the coordinated linkage of ventilation, dust removal and spray dust suppression systems through multi-system collaborative control module and energy efficiency optimization module, avoids airflow conflict and system interference, and improves dust removal efficiency. At the same time, based on the variable frequency fan and energy efficiency database, the operating parameters are dynamically adjusted to optimize energy consumption under the premise of ensuring safety, solve the problems of energy waste and low energy efficiency in traditional systems, and realize green and energy-saving operation. Attached Figure Description

[0017] Figure 1 This is a block diagram illustrating the main principle of the intelligent control system of the present invention; Figure 2 This is a block diagram illustrating the principle of the multi-dimensional sensing module of the present invention. Figure 3 This is a block diagram illustrating the principle of the intelligent prediction module of the present invention. Figure 4 This is a block diagram illustrating the principle of the multi-system collaborative control module of the present invention. Figure 5 This is a block diagram illustrating the principle of the remote control module of the present invention. 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 Figure 1 and Figure 5 This invention provides a technical solution: a novel intelligent control system for dust removal and ventilation in tunneling roadways based on remote control, comprising an intelligent control system body, which includes a remote control center, a multi-dimensional sensing module, an intelligent prediction module, a multi-system collaborative control module, and a remote control module; the multi-dimensional sensing module collects real-time data on methane concentration, dust concentration, airflow velocity, temperature, and tunneling operation parameters within the tunneling roadway; the intelligent prediction module, based on machine learning algorithms and combining historical data with real-time collected data, predicts methane accumulation trends and dust diffusion paths; the multi-system collaborative control module dynamically and collaboratively regulates the operating parameters of the ventilation system, dust removal system, and spray dust suppression system according to the prediction results and preset safety thresholds, achieving coordinated linkage of airflow, dust removal, and dust suppression.

[0020] The aforementioned system uses a multi-dimensional sensing module to collect real-time data on methane concentration, dust concentration, airflow velocity, temperature, and tunneling operation parameters within the tunnel. An intelligent prediction module, based on machine learning algorithms (such as LSTM neural networks and random forest algorithms) and combining historical and real-time data, predicts methane accumulation trends and dust diffusion paths. A multi-system collaborative control module dynamically and collaboratively adjusts the operating parameters of the ventilation system, dust removal system, and spray dust suppression system based on the prediction results and preset safety thresholds, achieving coordinated operation of airflow, dust removal, and dust suppression. A remote control module provides overall monitoring and remote operation support, enabling intelligent prediction and dynamic response to methane and dust risks. This solves the inefficiency problem caused by the independent operation of subsystems in traditional systems. Through multi-system collaborative control, the overall efficiency and safety of dust removal and ventilation are improved, human intervention is reduced, and the level of automation is enhanced.

[0021] Machine learning algorithms are the core support of the intelligent prediction module. The system follows a closed-loop process of "data input - model training - real-time inference - result output". The system first collects massive amounts of historical data (including time-series data such as gas concentration, dust diffusion, and airflow parameters) through a multi-dimensional perception module. After cleaning and normalization preprocessing, the data is input into the corresponding prediction model for training. After training, the model receives real-time collected data, quickly infers and outputs prediction results, providing decision-making basis for multi-system collaborative control. The entire process requires no manual intervention, realizing intelligent linkage of "data-prediction-control".

[0022] In a preferred embodiment, the multi-dimensional sensing module includes a distributed array of gas sensors, laser dust sensors, ultrasonic wind speed sensors, and tunneling machine operating status sensors. The gas and dust sensors are arranged in groups of 5-8 meters, with denser arrangement at the tunneling face to ensure comprehensive and real-time data acquisition. Sensor data is transmitted to a remote control center for processing in real time. By densely arranging the sensors, blind spots are avoided, improving the accuracy and reliability of data acquisition. Dense monitoring at the tunneling face can promptly capture abnormal situations, providing a solid data foundation for intelligent prediction and collaborative control.

[0023] In a preferred embodiment, the intelligent prediction module incorporates a gas accumulation prediction model and a dust diffusion prediction model. The gas accumulation prediction model is based on an LSTM neural network, taking into account the gas concentration change rate, airflow velocity, and roadway cross-sectional parameters, and outputs a prediction of the gas concentration distribution over the next 10-30 minutes. The dust diffusion prediction model combines fluid dynamics simulation and a random forest algorithm to predict the diffusion range of dust under different airflow conditions. The two models operate in parallel, synchronizing the prediction results to the multi-system collaborative control module and the remote control center. By utilizing advanced machine learning models, the accuracy and timeliness of the predictions are improved, enabling the system to identify gas accumulation and dust diffusion risks in advance. This provides a scientific basis for collaborative control and reduces the likelihood of accidents.

[0024] Among them, the LSTM neural network is good at processing long-term time-dependent data and can accurately capture the dynamic pattern of gas concentration changes with time and airflow, solving the problem that traditional models are difficult to predict accumulation trends. In addition to gas concentration change rate, airflow velocity, and roadway cross-section parameters, the input parameters are supplemented with tunneling operation intensity (such as tunneling machine cutting power) and roadway ventilation resistance coefficient as auxiliary inputs to improve the comprehensiveness of prediction.

[0025] Additional explanation: The tunneling operation parameters (such as cutting speed and pitch angle) and the roadway ventilation resistance coefficient are not simply used as input data, but are deeply integrated into a multi-system collaborative control and dynamic wind resistance compensation model. The system acquires the tunneling machine's pose and cutting parameters in real time through the tunneling machine's operating status sensors, and combines this with three-dimensional roadway scanning data (such as LiDAR or structured light scanning) to dynamically construct a geometry-wind resistance mapping table for the tunneling face area. This table not only includes static roadway cross-sectional parameters, but also reflects in real time the changes in local wind resistance distribution caused by changes in the tunneling machine's position. This process is implemented through an embedded wind resistance calculation submodule, whose algorithm is based on computational fluid dynamics (CFD). D) The simplified model is integrated with empirical formulas. The wind resistance distribution map is updated every 5 seconds, and the results are fed back to the variable frequency fan control logic of the ventilation system in real time. In the multi-system collaborative control module, tunneling operation parameters and ventilation resistance coefficients jointly participate in airflow-dust removal collaborative decision-making. In the gas accumulation prediction model (LSTM) and dust diffusion prediction model (random forest + CFD), tunneling operation parameters are used as time-series feature inputs, while the roadway ventilation resistance coefficient is embedded as an environmental constraint in the model inference process. This integration method makes the prediction results not only dependent on historical data, but also respond to changes in tunneling technology in real time, improving the real-time performance and scenario adaptability of the prediction.

[0026] Fluid dynamics simulation fundamentals: Using computational fluid dynamics (CFD) methods based on the Navier-Stokes governing equations, the initial diffusion trajectory of dust under different airflow velocities and directions is simulated, outputting basic diffusion field data. The role of the random forest algorithm: To address the issue of simulation results being affected by nonlinear factors such as turbulence and roadway obstacles, the random forest algorithm (constructing 100-150 decision trees) is introduced. Using simulation data, real-time dust concentration, and dust generation at the tunnel face as inputs, the algorithm corrects the predicted diffusion range. First, the macroscopic diffusion trend is obtained through fluid dynamics simulation, and then the random forest algorithm is used to optimize local accuracy, balancing prediction efficiency and accuracy.

[0027] In a preferred embodiment, the multi-system collaborative control module sets up airflow-dust removal-dust suppression collaborative logic. When the predicted dust diffusion range expands, the airflow direction is first optimized by adjusting the angle of the air guide plate of the ventilation system, then the fan speed of the dust removal system is increased, and finally the spray dust suppression system is started according to the dust concentration. This avoids airflow conflicts and interference between systems, optimizes the dust removal process, improves dust removal efficiency, reduces energy waste by starting sequentially, and ensures rapid and effective control of pollution when dust diffuses.

[0028] In a preferred embodiment, the ventilation system is equipped with a variable frequency fan. The collaborative control module dynamically adjusts the fan frequency to change the air volume based on the predicted gas concentration, dust concentration, and tunneling operation intensity. When the concentration is below the safety threshold and there is no risk of accumulation or diffusion, the air volume is automatically reduced to an energy-saving operating state, realizing intelligent air volume adjustment. Under the premise of ensuring safety, energy consumption is significantly reduced. The energy-saving operation mode reduces unnecessary energy waste, lowers operating costs, and extends the service life of the equipment.

[0029] In a preferred embodiment, the main body of the intelligent control system further includes an emergency response submodule. When the multi-dimensional sensing module detects that the gas concentration or dust concentration exceeds the emergency threshold, or the intelligent prediction module predicts that it is about to exceed the standard, the emergency response submodule immediately triggers a linkage emergency mode that enables the ventilation system to operate at full load, the dust removal system to efficiently extract dust, and the spray system to be activated across the entire area. It also sends an alarm signal to the remote control center and locks the tunneling machine's operating permissions to prevent further risks. This provides a rapid emergency response mechanism, prevents the accident from escalating, and automatically locks the tunneling machine's permissions to avoid delays caused by human operation, ensuring the safety of miners and the integrity of equipment, and improving the reliability of the system.

[0030] In a preferred embodiment, the remote control module has real-time monitoring, parameter configuration, historical data tracing and fault diagnosis functions. It allows staff to view various monitoring data, system operating status and prediction results in the roadway through a visual interface. It can remotely modify safety thresholds, collaborative control logic and equipment operating parameters, which improves the operability and flexibility of the system, allows remote management and real-time adjustment, reduces the risk to on-site staff, improves fault handling efficiency, and supports data-driven decision optimization.

[0031] In a preferred embodiment, the intelligent control system further includes an energy efficiency optimization module. This module establishes an energy efficiency database based on different tunneling conditions, including rock tunneling, coal tunneling, and tunneling speed. By comparing energy consumption and dust removal / ventilation effects under different combinations of operating parameters, it automatically selects the optimal parameter combination, optimizing system energy efficiency and minimizing energy consumption while ensuring effective dust removal and ventilation. This achieves green and energy-saving operation, reduces long-term operating costs, and adapts to changing needs under different operating conditions.

[0032] The establishment of the energy efficiency database begins with the data acquisition phase. In the early stages of operation, the system collects the operating parameters (such as fan frequency, air guide plate angle, spray pressure, etc.) and corresponding energy consumption data (obtained in real time by the power monitoring module) of the ventilation, dust removal, and spraying systems under different working conditions (rock tunnels / coal tunnels, different tunneling speeds, and different gas and dust concentration ranges) through the multi-dimensional sensing module. Then, the system sets a comprehensive evaluation function for the effect evaluation index: "dust removal efficiency - ventilation effect - energy consumption ratio". The dust removal efficiency is based on the dust concentration reduction rate, the ventilation effect is based on the stability of gas concentration control, and the energy consumption ratio is the electrical energy consumption per unit time. Finally, the data storage structure uses a time-series database (such as InfluxDB) to store each record. Each record includes fields such as: operating condition label, operating parameter combination, real-time energy consumption, dust removal efficiency score, ventilation effect score, and timestamp. When the system detects the current operating condition (such as coal roadway excavation or medium excavation speed), the energy efficiency optimization module retrieves historical operating records under the same or similar conditions from the database. It then uses the Pareto frontier search algorithm (multi-objective optimization) to filter the retrieved parameter combinations, identifying the several sets of parameters with the lowest energy consumption under the premise that "dust removal efficiency ≥ set threshold and ventilation effect meets standards." The system automatically applies the optimal parameter combination and continuously monitors the actual effect during operation. If the actual energy consumption is higher than expected or the dust removal effect decreases, the system triggers an online learning mechanism, storing the data from this operation as a new sample in the database and fine-tuning the selection strategy to form a closed-loop optimization.

[0033] Additional information: The gas sensor is model KGQ7, the laser dust sensor is model GCG1000, the ultrasonic wind speed sensor is model FC-2A, and the tunneling machine operating status sensor is model GY-69.

[0034] Furthermore, any content not described in detail in this specification is existing technology known to those skilled in the art.

[0035] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0036] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A novel intelligent control system for dust removal and ventilation in tunneling roadways based on remote control, comprising the main body of the intelligent control system, characterized in that: The main body of the intelligent control system includes a remote control center, a multi-dimensional sensing module, an intelligent prediction module, a multi-system collaborative control module, and a remote control module. The multi-dimensional sensing module collects real-time data on gas concentration, dust concentration, airflow velocity, temperature, and tunneling operation parameters in the tunnel. The intelligent prediction module, based on machine learning algorithms and combining historical data with real-time collected data, predicts gas accumulation trends and dust diffusion paths. The multi-system collaborative control module dynamically and collaboratively adjusts the operating parameters of the ventilation system, dust removal system, and spray dust suppression system according to the prediction results and preset safety thresholds, achieving coordinated linkage of airflow, dust removal, and dust suppression.

2. The novel intelligent control system for dust removal and ventilation in tunneling roads based on remote control as described in claim 1, characterized in that: The multi-dimensional sensing module includes distributed gas sensors, laser dust sensors, ultrasonic wind speed sensors, and tunneling machine operation status sensors. The gas sensors and dust sensors are arranged in groups of 5-8 meters, and are densely arranged at the tunneling face to ensure the comprehensiveness and real-time nature of data acquisition.

3. The novel intelligent control system for dust removal and ventilation in tunneling roads based on remote control as described in claim 1, characterized in that: The intelligent prediction module incorporates a gas accumulation prediction model and a dust diffusion prediction model. The gas accumulation prediction model is based on an LSTM neural network. It takes gas concentration change rate, airflow velocity and roadway cross-sectional parameters as input and outputs the gas concentration distribution prediction results for the next 10-30 minutes. The dust diffusion prediction model combines fluid dynamics simulation and random forest algorithm to predict the diffusion range of dust under different airflow conditions.

4. The novel intelligent control system for dust removal and ventilation in tunneling roads based on remote control as described in claim 1, characterized in that: The multi-system collaborative control module is configured with airflow-dust removal-dust suppression collaborative logic. When the predicted dust diffusion range expands, the airflow direction is first optimized by adjusting the angle of the air guide plate of the ventilation system, then the fan speed of the dust removal system is increased, and finally the spray dust suppression system is activated according to the dust concentration.

5. The novel intelligent control system for dust removal and ventilation in tunneling roads based on remote control as described in claim 1, characterized in that: The ventilation system is equipped with a variable frequency fan. The collaborative control module dynamically adjusts the fan frequency to change the air volume based on the predicted gas concentration, dust concentration and tunneling operation intensity. When the concentration is below the safety threshold and there is no risk of accumulation and diffusion, the air volume is automatically reduced to an energy-saving operating state.

6. The novel intelligent control system for dust removal and ventilation in tunneling roads based on remote control as described in claim 1, characterized in that: The main body of the intelligent control system also includes an emergency response submodule. When the multi-dimensional sensing module detects that the gas concentration or dust concentration exceeds the emergency threshold, or the intelligent prediction module predicts that it is about to exceed the standard, the emergency response submodule immediately triggers a linkage emergency mode that enables the ventilation system to operate at full load, the dust removal system to efficiently extract, and the spray system to be activated across the entire area. It also sends an alarm signal to the remote control center and locks the tunneling machine's operating permissions.

7. The novel intelligent control system for dust removal and ventilation in tunneling roads based on remote control as described in claim 1, characterized in that: The remote control module has real-time monitoring, parameter configuration, historical data tracing and fault diagnosis functions. It allows staff to view various monitoring data, system operation status and prediction results in the roadway through a visual interface, and can remotely modify safety thresholds, collaborative control logic and equipment operating parameters.

8. The novel intelligent control system for dust removal and ventilation in tunneling roads based on remote control as described in claim 1, characterized in that: The main body of the intelligent control system also includes an energy efficiency optimization module. Based on different tunneling conditions, including rock tunneling, coal tunneling and tunneling speed, the energy efficiency optimization module establishes an energy efficiency database and automatically selects the optimal parameter combination by comparing the energy consumption and dust removal and ventilation effects under different combinations of operating parameters.

Images