Intelligent control method and device for mine dust removal, control equipment and storage medium

Abstract

The invention relates to an intelligent control method and device for mine dust removal, control equipment and a storage medium, and belongs to the technical field of mine environmental protection. The intelligent control method for mine dust removal comprises the steps that real-time monitoring data of a multi-mode sensor is acquired; inputting the preprocessed real-time monitoring data into a dust concentration prediction model to obtain a dust concentration prediction result output by the dust concentration prediction model; a control instruction is generated based on the real-time monitoring data and the dust concentration prediction result, the control instruction is used for adjusting working parameters of spraying dust removal equipment, and the spraying dust removal equipment comprises fixed spraying equipment, a vehicle-mounted spraying dust reduction vehicle and a movable spraying gun. The dust removal cost is effectively reduced while the dust removal efficiency of the mine is improved.

Description

Technical Field

[0001] This invention relates to the field of environmental protection technology in mining, and in particular to an intelligent control method, device, control equipment, and storage medium for dust removal in mines. Background Technology

[0002] In mining operations, dust pollution poses a serious threat to human health, equipment lifespan, and the ecological environment. Miners exposed to dust for extended periods are at risk of developing pneumoconiosis, leading to irreversible lung damage. Dust also accelerates equipment wear and tear, penetrating components such as bearings and gears, resulting in a 30%-50% increase in maintenance frequency and a 20%-30% reduction in lifespan. Dust dispersion also causes persistently high levels of particulate matter (PM) in surrounding areas, leading to a 20%-30% reduction in crop yields, a 15% decrease in vegetation cover, and contributing to soil acidification and regional smog.

[0003] Existing mine dust control systems suffer from a disconnect between monitoring and dust suppression. Dust monitoring systems and spray dust suppression systems are largely independent, lacking an effective linkage mechanism. They also lack adaptability to complex environments. Mine operating environments are diverse and complex, influenced by geological conditions, climate factors, mining processes, and other factors, making it difficult for existing dust control technologies to adapt to such complex and changing environments. Furthermore, existing mine dust control systems generally have low levels of intelligence, relying primarily on manual operation and experience-based judgment.

[0004] Therefore, how to improve the efficiency of dust removal in mines and reduce dust removal costs has become an urgent technical problem to be solved. Summary of the Invention

[0005] In view of this, it is necessary to provide an intelligent control method, device, control equipment and storage medium for mine dust removal, so as to solve the problems of low efficiency and high cost of existing mine dust removal solutions.

[0006] To address the aforementioned problems, in a first aspect, the present invention provides an intelligent control method for dust removal in mines, comprising: Acquire real-time monitoring data from multimodal sensors, including dust concentration sensors, wind speed and direction sensors, temperature and humidity sensors, and cameras; The preprocessed real-time monitoring data is input into the dust concentration prediction model to obtain the dust concentration prediction result output by the dust concentration prediction model. The dust concentration prediction model is composed of cascaded LSTM network and CNN network, and is trained using the preprocessed historical monitoring data of multimodal sensors as samples and the historical dust concentration data as sample labels. Control commands are generated based on real-time monitoring data and dust concentration prediction results. These commands are used to adjust the operating parameters of the spray dust suppression equipment, which includes fixed spray equipment, vehicle-mounted spray dust suppression vehicles, and mobile spray cannons.

[0007] In one possible implementation, the generation of control commands based on real-time monitoring data and dust concentration prediction results includes: A dust removal strategy model is constructed with the objective function of minimizing dust concentration and water consumption, the decision variables of the operating parameters of the spray dust removal equipment, the constraints of mine operation safety and the operating limitations of the spray dust removal equipment, and the state variables of real-time monitoring data and dust concentration prediction results. The dust removal strategy model is solved, and control commands are generated based on the solution results.

[0008] In one possible implementation, solving the dust removal strategy model includes: The dust removal strategy model is solved based on the PSO algorithm or the GA algorithm.

[0009] In one possible implementation, the method further includes: Based on the dust concentration prediction results and real-time dust concentration, the spray dust removal equipment that needs to be scheduled is determined.

[0010] In one possible implementation, acquiring the real-time monitoring data from the multimodal sensor includes: Real-time monitoring data from multimodal sensors is acquired using 5G and / or LoRa wireless networks.

[0011] In one possible implementation, the method further includes: After generating control commands based on real-time monitoring data and dust concentration prediction results, the control commands are sent to the spray dust removal equipment via 5G wireless network and / or LoRa wireless network.

[0012] In one possible implementation, the method further includes: After the control command is sent to the spray dust removal equipment, it is adjusted and resent based on the real-time changes in dust concentration.

[0013] On the other hand, the present invention also provides an intelligent control device for dust removal in mines, comprising: The acquisition module is used to acquire real-time monitoring data from multimodal sensors, including dust concentration sensors, wind speed and direction sensors, temperature and humidity sensors, and cameras. The prediction module is used to input the preprocessed real-time monitoring data into the dust concentration prediction model to obtain the dust concentration prediction result output by the dust concentration prediction model. The dust concentration prediction model is composed of cascaded LSTM network and CNN network, and is trained using the preprocessed historical monitoring data of multimodal sensors as samples and the historical dust concentration data as sample labels. The generation module is used to generate control commands based on real-time monitoring data and dust concentration prediction results. The control commands are used to adjust the operating parameters of the spray dust suppression equipment, which includes fixed spray equipment, vehicle-mounted spray dust suppression vehicles, and mobile spray cannons.

[0014] Secondly, the present invention also provides a control device, including a memory and a processor, wherein, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the intelligent control method for mine dust removal described in any of the above implementations.

[0015] Thirdly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instruction, which, when executed by a processor, can implement the steps of the intelligent control method for mine dust removal described in any of the above implementations.

[0016] The beneficial effects of this invention are as follows: The intelligent control method, device, control equipment, and storage medium for mine dust removal provided by this invention first acquire real-time monitoring data from multimodal sensors to provide a comprehensive and reliable data foundation for subsequent data processing and intelligent decision-making. Then, a dust concentration prediction model composed of LSTM and CNN networks is used to predict the dust concentration over a future period. Finally, based on the real-time monitoring data and the dust concentration prediction results, a spray dust suppression strategy is determined and control commands are generated. These control commands are used to adjust the operating parameters of spray dust removal equipment, including fixed spray equipment, vehicle-mounted spray dust suppression vehicles, and mobile spray cannons. This achieves adaptive mine dust removal control based on multimodal sensor monitoring data, avoiding the complex manual dust removal control process and effectively reducing dust removal costs while improving mine dust removal efficiency. Attached Figure Description

[0017] Figure 1 A schematic flowchart of an embodiment of the intelligent control method for dust removal in mines provided by the present invention; Figure 2 A schematic flowchart of an embodiment of the closed-loop control process for dust removal in mines provided by the present invention; Figure 3 This is a schematic flowchart of an embodiment of the sensor raw data processing procedure provided by the present invention; Figure 4 A schematic flowchart of an embodiment of the control process of the spray dust removal equipment provided by the present invention; Figure 5 A schematic diagram of an embodiment of the intelligent control device for dust removal in mines provided by the present invention; Figure 6 A schematic diagram of an embodiment of the control device provided by 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 a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0019] In the description of the embodiments of the present invention, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0020] The terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0021] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0022] In mining operations, dust pollution poses a serious threat to worker health, equipment lifespan, and the ecological environment. According to the National Occupational Disease Report, pneumoconiosis accounts for 71.7% of occupational diseases nationwide, with miners suffering irreversible lung damage due to long-term exposure to PM2.5 / PM10. Dust also accelerates equipment wear and tear: it penetrates bearings, gears, and other components, increasing maintenance frequency by 30%-50% and shortening lifespan by 20%-30%. For example, in transport vehicles, clogged filters cause a 10%-15% decrease in engine power and an 8%-12% increase in fuel consumption, resulting in annual losses exceeding 100 million yuan. Ecologically, dust dispersion leads to persistently high PM levels in surrounding areas, resulting in a 20%-30% reduction in crop yields, a 15% decrease in vegetation cover, and inducing soil acidification and regional smog. There is an urgent need to implement source control through intelligent dust removal technology to ensure miner safety, reduce operating costs, and restore the ecological environment.

[0023] However, existing technologies have significant shortcomings. First, there is a disconnect between monitoring and dust suppression. Mine dust monitoring systems and spray dust suppression systems are mostly independent, lacking an effective linkage mechanism. Data acquired by the dust monitoring system is not promptly and accurately fed back to the spray dust suppression system, resulting in spray dust suppression operations being unable to be precisely controlled based on the actual dust pollution situation. For example, when the dust monitoring system detects an increase in dust concentration in a certain area, due to the lack of real-time communication and linkage between the two, the spray dust suppression system may be unable to adjust spray parameters or activate spray equipment in time, thus missing the optimal dust suppression opportunity and further exacerbating dust pollution.

[0024] Secondly, there is a lack of adaptability to complex environments. Mining operations are complex and diverse, influenced by geological conditions, climate, mining processes, and many other factors. Existing dust control technologies often struggle to adapt to this complex and ever-changing environment. For example, in open-pit mines, during windy weather, the water mist from traditional spray dust suppression technology is easily dispersed, failing to effectively settle dust. In underground mines, ventilation conditions are complex, and the dispersion patterns of dust are difficult to predict, making existing monitoring and dust suppression technologies inadequate for practical needs. Furthermore, different mines have varying ore properties, mining methods, and production scales, and current dust control technologies lack flexibility and customizability, failing to optimize configurations for the specific characteristics of different mines.

[0025] Finally, the level of automation is low. Existing mine dust control systems generally have a low level of automation, relying mainly on manual operation and experience-based judgment. For example, the start-up, shutdown, and adjustment of spray parameters in spray dust suppression systems are mostly done manually, which is not only inefficient but also prone to errors. Regarding dust monitoring, although some systems can collect data in real time, they lack in-depth data analysis and intelligent processing capabilities, making it impossible to predict dust concentration trends based on historical data and real-time monitoring, thus failing to provide a basis for taking proactive dust control measures. With the trend of intelligent development in mines, this low-automation dust control technology is no longer sufficient to meet the requirements of safe production and efficient environmental protection in mines.

[0026] To address the aforementioned problems, this invention provides an intelligent control method, apparatus, control equipment, and storage medium for dust removal in mines, which will be described in detail below.

[0027] Figure 1 A schematic flowchart of an embodiment of the intelligent control method for dust removal in mines provided by the present invention is shown below. Figure 1 As shown, the intelligent control method for dust removal in mines includes: S101. Acquire real-time monitoring data from multimodal sensors, including dust concentration sensors, wind speed and direction sensors, temperature and humidity sensors, and cameras.

[0028] It should be noted that the intelligent control method for dust removal in mines provided by this invention can be applied to industrial dust removal scenarios, especially dust removal scenarios in mines.

[0029] When implementing intelligent control for dust removal in mines, control equipment (such as portable or desktop computers) can first acquire real-time monitoring data from multimodal sensors, including dust concentration sensors, wind speed and direction sensors, temperature and humidity sensors, and cameras. This enables real-time and accurate monitoring of environmental parameters such as dust concentration, wind speed and direction, temperature and humidity, and dust generation and diffusion, providing a comprehensive and reliable data foundation for subsequent data processing and intelligent decision-making.

[0030] S102. Input the preprocessed real-time monitoring data into the dust concentration prediction model to obtain the dust concentration prediction result output by the dust concentration prediction model. The dust concentration prediction model is composed of cascaded LSTM network and CNN network, and is trained using the preprocessed historical monitoring data of the multimodal sensor as samples and the historical dust concentration data as sample labels.

[0031] It should be noted that after acquiring real-time monitoring data from the multimodal sensors, the data can be preprocessed, such as through data cleaning, calibration, and fusion. This preprocessed data can then be input into a dust concentration prediction model to obtain the predicted dust concentration. The dust concentration prediction model consists of a cascaded Long Short-Term Memory (LSTM) network and a Convolutional Neural Network (CNN). The LSTM network learns the time-series characteristics of dust concentration, capturing its trend over time, while the CNN network extracts features from video images to identify dust diffusion patterns. The dust concentration prediction model can be trained by using preprocessed historical monitoring data from the multimodal sensors as samples and historical dust concentration data as sample labels. This allows it to capture the complex relationship between dust concentration and various influencing factors and predict the dust concentration trends in different areas of the mine over a future period (e.g., the next 1-2 hours).

[0032] S103. Based on real-time monitoring data and dust concentration prediction results, control commands are generated. The control commands are used to adjust the working parameters of the spray dust suppression equipment, which includes fixed spray equipment, vehicle-mounted spray dust suppression vehicles, and mobile spray cannons.

[0033] It should be noted that after obtaining the dust concentration prediction results, a spray dust suppression strategy can be determined and control commands can be generated based on real-time monitoring data and dust concentration prediction results. These control commands are then used to adjust the operating parameters of spray dust suppression equipment, including fixed spray equipment, vehicle-mounted spray dust suppression vehicles, and mobile spray cannons. Specific operating parameters of the spray dust suppression equipment may include spray volume, spray pressure, spray angle, and spray time.

[0034] In summary, the intelligent control method for mine dust control provided by this invention first acquires real-time monitoring data from multimodal sensors to provide a comprehensive and reliable data foundation for subsequent data processing and intelligent decision-making. Then, it predicts the dust concentration over a future period using a dust concentration prediction model composed of LSTM and CNN networks. Finally, it determines a spray dust suppression strategy and generates control commands based on the real-time monitoring data and dust concentration prediction results. These control commands are used to adjust the operating parameters of spray dust suppression equipment, including fixed spray equipment, vehicle-mounted spray dust suppression vehicles, and mobile spray cannons. This achieves adaptive mine dust control based on multimodal sensor monitoring data, avoiding complex manual dust control processes and effectively reducing dust control costs while improving mine dust control efficiency.

[0035] In some embodiments of the present invention, the generation of control commands based on real-time monitoring data and dust concentration prediction results includes: A dust removal strategy model is constructed with the objective function of minimizing dust concentration and water consumption, the decision variables of the operating parameters of the spray dust removal equipment, the constraints of mine operation safety and the operating limitations of the spray dust removal equipment, and the state variables of real-time monitoring data and dust concentration prediction results. The dust removal strategy model is solved, and control commands are generated based on the solution results.

[0036] It should be noted that when generating control commands based on real-time monitoring data and dust concentration prediction results, the objective function is to minimize dust concentration and water consumption, the decision variables are the operating parameters of the spray dust suppression equipment, the constraints are mine operation safety and the operating limitations of the spray dust suppression equipment, and the state variables are the real-time monitoring data and dust concentration prediction results to construct the dust suppression strategy model. The dust suppression strategy model is then solved, and control commands are generated based on the solution results.

[0037] In some embodiments of the present invention, solving the dust removal strategy model includes: The dust removal strategy model is solved based on the PSO algorithm or the GA algorithm.

[0038] It should be noted that when solving the dust removal strategy model, either the Particle Swarm Optimization (PSO) algorithm or the Genetic Algorithm (GA) algorithm can be used.

[0039] In some embodiments of the present invention, the method further includes: Based on the dust concentration prediction results and real-time dust concentration, the spray dust removal equipment that needs to be scheduled is determined.

[0040] It should be noted that the real-time dust height can be calculated based on the real-time monitoring data from the multimodal sensor. When determining which spray dust suppression equipment needs to be scheduled based on the dust concentration prediction results and the real-time dust concentration, a dust pollution index can be determined based on the dust concentration prediction results and the real-time dust concentration, and then the spray dust suppression equipment to be scheduled can be determined in combination with the preset pollution index threshold.

[0041] In some embodiments of the present invention, acquiring real-time monitoring data from the multimodal sensor includes: Real-time monitoring data from multimodal sensors is acquired using 5G and / or LoRa wireless networks.

[0042] It should be noted that when acquiring real-time monitoring data from multimodal sensors, this data can be obtained via 5G wireless networks and / or Long Range Radio (LoRa) wireless networks. The wireless communication network employs a dynamic routing protocol (such as AODV) to automatically select the optimal transmission path based on base station load and signal strength. When communication signals weaken in a certain area, the system can automatically switch to a backup frequency band (such as switching from the 5G band to the LoRa band) to ensure continuous data transmission. Data can be encrypted using the AES-256 encryption algorithm during transmission to prevent data leakage and tampering.

[0043] In some embodiments of the present invention, the method further includes: After generating control commands based on real-time monitoring data and dust concentration prediction results, the control commands are sent to the spray dust removal equipment via 5G wireless network and / or LoRa wireless network.

[0044] It should be noted that control commands can also be sent to the spray dust removal equipment via 5G wireless network and / or LoRa wireless network.

[0045] In some embodiments of the present invention, the method further includes: After the control command is sent to the spray dust removal equipment, it is adjusted and resent based on the real-time changes in dust concentration.

[0046] It should be noted that after the control command is issued, the control equipment can continuously monitor the dust suppression effect. By comparing the dust concentration data before and after dust suppression, and the changes in dust concentration in video images, the dust suppression efficiency can be evaluated. If the dust suppression efficiency does not meet expectations (e.g., below 80%), the spray dust suppression strategy can be optimized, for example, by adjusting the spray parameters or adding more dust suppression equipment, thus forming a closed-loop control.

[0047] To address the disconnect between monitoring and dust suppression in existing technologies, this invention constructs a multimodal sensor network to collect real-time data on dust concentration, wind speed and direction, temperature and humidity, and video. This data is then transmitted to a data processing center for fusion processing, breaking down the barriers of independent system operation and achieving closed-loop linkage between monitoring and dust suppression. To address poor adaptability to complex environments, a multimodal data fusion and adaptive spray equipment design is employed. Combining fluid dynamics models and machine learning algorithms, spray parameters are dynamically adjusted based on environmental changes, effectively improving adaptability to complex environments. To address low intelligence, a dust concentration prediction model is built using a deep learning architecture integrating LSTM and CNN. An intelligent decision optimization algorithm solves for the optimal spray parameters, and automated, precise control and fault diagnosis are achieved through PID control algorithms and equipment health status assessment models, significantly improving the system's intelligence level. Practical application cases in open-pit and underground mines have verified significant results in improving dust suppression efficiency, saving resources, and increasing economic benefits.

[0048] Combination Figure 2 The intelligent control process for dust removal in mines includes the following steps: 1. Construction of a Multimodal Sensor Network. By deploying various types of dust concentration sensors, such as light scattering and beta-ray absorption sensors, combined with wind speed and direction sensors, temperature and humidity sensors, and high-definition video surveillance cameras, and based on the dust generation characteristics and environmental requirements of different areas of the mine, a comprehensive and multi-layered sensor network is constructed. This enables real-time and accurate monitoring of environmental parameters such as dust concentration, wind speed and direction, temperature and humidity, and dust generation and diffusion in the mine, providing a comprehensive and reliable data foundation for subsequent data processing and intelligent decision-making.

[0049] Dust concentration sensors are deployed using various types, including light scattering dust sensors and beta-ray absorption dust sensors, to achieve accurate measurement of dust concentrations of different particle sizes. In key dust-generating areas of the mine, such as working faces, ore crushing workshops, belt conveyor corridors, and ore stockpiles, dust concentration sensors are strategically placed based on area size, dust generation intensity, and dust diffusion patterns. For example, in working faces, a sensor is installed every 10-15 meters; in large ore crushing workshops, sensors are installed near dust-generating points such as crusher inlets, outlets, and belt conveyor junctions. Simultaneously, sensors are also deployed in the mine's ventilation system, such as ventilation shafts and ventilation tunnels, to monitor dust concentration in the ventilation airflow, enabling timely understanding of dust diffusion throughout the mine's ventilation network.

[0050] To accurately obtain wind speed and direction information in different areas of the mine, wind speed and direction sensors are installed every 50-100 meters in the open-pit mining area, forming a grid layout. In underground mines, wind speed and direction sensors are installed at key locations such as main ventilation roadways, stope inlets, and outlets, based on the direction of the roadways and the structure of the ventilation system. These sensors employ high-precision three-cup anemometers and vane-type wind direction sensors, enabling real-time and accurate measurement of wind speed and direction data, which is then transmitted to the data processing center via wireless communication modules. Analysis of the wind speed and direction data allows for the prediction of the direction and range of dust dispersion, providing crucial information for the precise control of the spray dust suppression system.

[0051] Temperature and humidity have a significant impact on dust generation and dispersion. Temperature and humidity sensors are installed simultaneously in various working areas and monitoring points throughout the mine. In open-pit mines, considering the differences in temperature and humidity in different areas, multiple temperature and humidity sensors are installed in the mining area, transport roads, ore storage yards, etc. In underground mines, while the temperature and humidity in the roadways are relatively stable, differences may exist in different mining areas and working faces; therefore, temperature and humidity sensors are installed near each mining area and main working face. The temperature and humidity sensors are digital sensors, characterized by high accuracy, high reliability, and strong anti-interference capabilities. They can collect environmental temperature and humidity data in real time and transmit the data to the data processing center for subsequent correction of dust monitoring data and formulation of dust suppression strategies.

[0052] High-definition video surveillance cameras are installed at key locations in the mine, such as working faces, ore transport roads, and crushing and screening workshops. These cameras are equipped with infrared night vision, zoom, and pan-tilt control functions, enabling comprehensive, real-time video monitoring of the mining operation. Through video image analysis technology, the generation and diffusion of dust, as well as the operating status of mining equipment and personnel activities, can be observed intuitively. Furthermore, combining video surveillance data with data from other sensors provides more comprehensive information for the integrated analysis and control of dust pollution. For example, video image recognition technology can automatically identify the driving trajectory and loading / unloading operations of mining transport vehicles. Combined with dust concentration sensor data, the amount of dust generated during vehicle movement and loading / unloading can be determined, and the operating parameters of the spray dust suppression equipment can be adjusted accordingly.

[0053] Various types of sensors collect data at set frequencies: the dust concentration sensor collects data once per second, the wind speed and direction sensor collects data once every 2 seconds, the temperature and humidity sensor collects data once every 5 seconds, and the video surveillance camera records high-definition video (1920×1080 resolution) at a frame rate of 25 frames per second. The sensor data is converted from digital to digital (A / D), encapsulated into data packets with timestamps and sensor IDs, and transmitted to the base station via a wireless communication module.

[0054] To ensure data accuracy, the system employs a redundancy verification mechanism. Each sensor node is equipped with dual data acquisition channels. When the difference between the data acquired by the two channels exceeds a set threshold (e.g., a dust concentration difference > 5%), the system automatically initiates a calibration procedure. By comparing data with adjacent sensor data and analyzing historical data trends, the system determines the validity of the data and makes corrections.

[0055] 2. Data Transmission and Processing. A hybrid wireless communication network based on LoRa and 5G is established to ensure efficient and stable transmission of multimodal sensor data; a high-performance server cluster is equipped with a distributed storage architecture and professional data processing software to perform preprocessing such as cleaning, calibration, and fusion on the collected data; and a big data processing platform and algorithm library are used to achieve rapid processing and in-depth analysis of massive amounts of data, providing accurate and valuable information support for intelligent decision-making.

[0056] To achieve rapid and stable transmission of multimodal sensor data, a hybrid communication network based on LoRa and 5G wireless communication technologies is constructed in the mine. LoRa wireless communication technology is used in remote areas or areas with severe signal obstruction. LoRa features low power consumption and long-distance transmission, reaching distances of several kilometers, meeting the sensor data transmission needs of these areas. In the main operating areas and areas with high data traffic, a 5G communication network is deployed. 5G networks offer high speed, low latency, and massive connectivity, ensuring real-time, high-speed transmission of large amounts of sensor data. For example, in the mining face and crushing workshop, the massive amounts of data generated by dust concentration sensors, wind speed and direction sensors, temperature and humidity sensors, and video surveillance cameras can be rapidly uploaded to the data processing center via the 5G network, ensuring data timeliness. Sensor nodes, through their built-in wireless communication modules, package the collected data according to specific communication protocols and then send it to nearby base stations. The base stations then transmit the received data to the server in the data processing center via wired or wireless means.

[0057] The data processing center is equipped with a high-performance server cluster for storing, processing, and analyzing massive amounts of data collected by multimodal sensors. The servers employ a distributed storage architecture, combining the advantages of solid-state drives (SSDs) and hard disk drives (HDDs) to achieve efficient data storage and rapid access. SSDs are used to store sensor data and processing results with high real-time requirements, leveraging their high-speed read / write capabilities to ensure rapid data retrieval and access; HDDs are used to store historical data, reducing long-term storage costs. The server cluster is equipped with professional data processing software and database management systems such as Hadoop, Spark, MySQL, and MongoDB. Hadoop and Spark are used for distributed processing and analysis of massive amounts of data, enabling rapid processing of multimodal sensor data and extraction of valuable information. MySQL is used to store structured sensor data and analysis results, facilitating complex queries and statistical analysis; MongoDB is used to store unstructured video surveillance data and some semi-structured text data, supporting flexible data storage and rapid retrieval.

[0058] After data enters the data processing center, it first undergoes a data preprocessing stage. Data preprocessing algorithms include steps such as data cleaning, data calibration, and data fusion. Data cleaning primarily removes noise, outliers, and duplicate data from sensor-collected data. For example, by setting reasonable threshold ranges, outliers significantly exceeding the normal range in dust concentration sensor data are removed; time series analysis algorithms are used to identify and remove noise interference from wind speed and direction sensor data. Data calibration involves calibrating sensor data based on sensor calibration parameters and the actual measurement environment to improve data accuracy. For example, based on ambient temperature and humidity data measured by temperature and humidity sensors, the measurement results of dust concentration sensors are corrected to eliminate the influence of temperature and humidity on dust concentration measurement. Data fusion combines data from multiple types of sensors about the same monitoring area to obtain more accurate and comprehensive environmental information. For example, data from dust concentration sensors, wind speed and direction sensors, and temperature and humidity sensors are fused to comprehensively assess the dust pollution status of the area and the impact of environmental factors on dust dispersion.

[0059] The wireless communication network employs dynamic routing protocols (such as AODV) to automatically select the optimal transmission path based on base station load and signal strength. When communication signals weaken in a certain area, the system can automatically switch to a backup frequency band (such as switching from the 5G band to the LoRa band) to ensure the continuity of data transmission. Data is encrypted using the AES-256 encryption algorithm during transmission to prevent data leakage and tampering.

[0060] Combination Figure 3As we see, after receiving sensor data, the data processing center first performs data cleaning, using a moving average filtering algorithm to remove high-frequency noise. Then, it uses a Kalman filtering algorithm to calibrate dynamic data such as dust concentration and wind speed in real time. The DS evidence theory is employed to fuse multi-source data, such as combining dust concentration data, wind speed and direction data, and video image analysis results to construct a dust pollution level assessment model and output a comprehensive dust pollution index (ranging from 0 to 100, with higher values ​​indicating more severe pollution).

[0061] 3. Intelligent Decision-Making and Control. Utilizing machine learning and deep learning algorithms, combined with historical data and mine production operation data, a dust concentration prediction model is established to dynamically predict dust concentrations in different areas of the mine. Based on the prediction results and real-time monitoring data, an intelligent optimization algorithm is used to construct a spray dust suppression strategy optimization algorithm to generate the optimal spray dust suppression strategy. Control commands are sent to the spray dust suppression equipment via wireless communication to achieve automatic adjustment of equipment operating parameters. It also has remote manual control functions to cope with emergencies and ensure accurate and efficient dust suppression operations.

[0062] The dust concentration prediction model is established using machine learning and deep learning algorithms, combined with historical sensor data and mine production operation data. A time series prediction model, such as Long Short-Term Memory (LSTM) networks, is employed to dynamically predict dust concentrations in different areas of the mine. The model's input data includes historical dust concentration data, wind speed and direction data, temperature and humidity data, and operational status data of mining equipment (such as crusher start-up time, transport vehicle routes and frequencies). Through learning and training on a large amount of historical data, the model can capture the complex relationship between dust concentration and various influencing factors and predict the trend of dust concentration changes in different areas of the mine over a future period (e.g., the next 1-2 hours). For example, in an open-pit mine, the established dust concentration prediction model predicts that between 2-3 PM, due to increased mining intensity and wind speed, the dust concentration in a certain mining area will rise significantly, allowing the system to take corresponding dust suppression measures in advance.

[0063] The dust suppression spraying strategy optimization algorithm is based on dust concentration prediction results and real-time monitoring data, combined with the actual operation and environmental conditions of the mine. The algorithm aims to minimize dust concentration and water consumption, using the spray volume, spray pressure, spray angle, and spray time of the spraying equipment as decision variables, while also considering constraints such as mine operation safety and equipment operating limitations. Intelligent optimization algorithms such as Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) are employed to optimize the dust suppression spraying strategy. For example, when the dust concentration prediction model predicts an increase in dust concentration in a certain area, the algorithm calculates the optimal spray volume, spray pressure, and spray angle based on real-time wind speed, wind direction, temperature, humidity, and other environmental data for that area, as well as the performance parameters of the spraying equipment, to achieve the best dust suppression effect with minimal water consumption. Simultaneously, the algorithm also rationally schedules the spraying time of the spraying equipment according to the mine's operation plan to avoid impacting normal production operations.

[0064] Combination Figure 4 The intelligent decision-making and control module generates corresponding control commands based on the optimized dust suppression spray strategy and sends them to the controller of the dust suppression spray equipment via a wireless communication network. The dust suppression spray equipment includes fixed spray systems, vehicle-mounted dust suppression spray trucks, and mobile spray cannons. Upon receiving the control commands, the controller automatically adjusts the operating parameters of the spray equipment, such as starting or stopping spraying, adjusting the spray volume, and changing the spray pressure and angle. For example, for a fixed spray system, the controller controls the opening of the electric regulating valve according to the control commands to adjust the water pressure in the spray pipes, thereby adjusting the spray volume; for a vehicle-mounted dust suppression spray truck, the controller connects to the vehicle's control system via a wireless communication module to control the vehicle's speed, spray direction, and spray intensity. Simultaneously, the system also has a remote manual control function, allowing operators to manually send control commands from the monitoring center through a human-machine interface to operate the dust suppression spray equipment in response to emergencies or special operational needs.

[0065] The dust concentration prediction model employs a hybrid deep learning architecture, combining an LSTM network with a convolutional neural network (CNN). The LSTM network learns the time-series features of dust concentration, capturing its trend over time; the CNN network extracts features from video images to identify dust diffusion patterns. Model input also includes mine operation plan data (such as blasting times and equipment start-up / shutdown schedules). Through transfer learning and online training mechanisms, model parameters are continuously optimized, with prediction errors controlled within ±10%.

[0066] The intelligent decision-making module generates a dust suppression strategy based on the predicted dust concentration and real-time comprehensive dust pollution index, combined with preset thresholds (e.g., light pollution: index 30-50; moderate pollution: index 50-70; heavy pollution: index > 70). When heavy pollution is predicted to occur in a certain area, the system automatically initiates a three-level response: firstly, the fixed spray system in and around the area is activated; if the pollution does not subside after 5 minutes, a vehicle-mounted dust suppression spray truck is dispatched to provide support; if the pollution still does not meet the standards after 10 minutes, mobile spray cannons are activated for enhanced dust suppression.

[0067] 4. Dust Suppression Spray Equipment Cluster. This cluster consists of an intelligent fixed spray system, intelligent vehicle-mounted dust suppression spray trucks, and mobile spray cannons. Each device possesses intelligent control and parameter adjustment functions. The intelligent fixed spray system targets fixed dust-generating points, achieving flexible adjustment of spray parameters through modular design and precise electromagnetic control valves. The intelligent vehicle-mounted dust suppression spray truck, based on a new energy chassis, possesses autonomous navigation and obstacle avoidance capabilities, and can dynamically adjust spray parameters according to the needs of different areas. The mobile spray cannons are suitable for large open areas, can automatically identify obstacles, and effectively suppress dust diffusion by intelligently adjusting parameters such as spray angle and pressure. The three systems work together to achieve full-area dust suppression coverage in the mine.

[0068] A smart fixed spray system is deployed at fixed dust-generating points in the mine (such as the entrance and exit of the crushing workshop and the transfer point of the belt conveyor). This system adopts a modular design, with each spray module equipped with an electromagnetic control valve, a pressure sensor, a flow sensor, and an adjustable atomizing nozzle. The electromagnetic control valve can precisely open and close according to control commands, with a response time of less than 0.5 seconds; the pressure sensor monitors the pipeline water pressure in real time with an accuracy of ±0.1MPa; the flow sensor measures the spray water volume with an error rate controlled within ±2%. The nozzle has 360° rotation and angle adjustment functions, and can be driven by a motor to achieve horizontal angle adjustment of 0-360° and vertical angle adjustment of 0-90°. The spray particle size is adjustable within the range of 5-150μm, ensuring effective capture of dust at different heights and distances. Adjacent spray modules are networked via a fieldbus (such as Profibus) to achieve data sharing and collaborative control.

[0069] This vehicle-mounted dust suppression sprayer, modified from a new energy chassis, is equipped with a high-power centrifugal fan (air volume ≥10000m³ / h) and a multi-stage adjustable spray system. The vehicle features a GPS positioning module, inertial navigation system, and millimeter-wave radar, enabling autonomous navigation and obstacle avoidance. The onboard controller receives remote control commands, automatically plans its route to the designated dust suppression area, and dynamically adjusts the spray angle (horizontal 0-270°, vertical -15°-60°), spray volume (0-100L / min), and fan speed (500-2000rpm) based on the dust concentration, wind speed, and wind direction data of that area. The vehicle also features a water purification and recycling device; the recycled spray water is filtered and precipitated for reuse, increasing water resource utilization to over 80%.

[0070] Mobile spray cannons are deployed for large open areas in mines (such as ore yards and open-pit mine faces). The spray cannons are hydraulically driven and feature 360° continuous horizontal rotation and -10° to 60° vertical pitch adjustment, with a maximum spray distance of 80 meters. Built-in ultrasonic ranging sensors and lidar automatically identify surrounding obstacles to prevent collision damage to the spraying device. The spray cannons connect to the control center via a 4G / 5G communication module and can intelligently adjust spray parameters based on multi-modal sensor data. In strong winds, the system can automatically increase the spray pressure to 8MPa and adjust the spray angle to create an air curtain, effectively suppressing dust dispersion.

[0071] After receiving control commands, the spray equipment controller adjusts the actuators using a PID control algorithm. Taking spray volume control as an example, based on the deviation between the target spray volume and the actual flow rate, the opening of the electromagnetic control valve is automatically adjusted to achieve a flow control accuracy of ±3%. Simultaneously, the system calculates the spray coverage area using a fluid dynamics model based on real-time wind speed and direction data, dynamically adjusting the nozzle angle to ensure a high degree of matching between the spray area and the dust diffusion area.

[0072] During the dust suppression process, the system continuously monitors the dust suppression effect. By comparing dust concentration data before and after dust suppression, and changes in dust concentration in video images, the dust suppression efficiency is evaluated. If the dust suppression efficiency does not meet expectations (e.g., below 80%), the system automatically feeds back to the intelligent decision-making module to re-optimize the spray dust suppression strategy, adjust spray parameters, or deploy additional dust suppression equipment, forming a closed-loop control.

[0073] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention achieves comprehensive, real-time, and accurate monitoring of mine dust and environmental parameters by constructing a multimodal sensor network, breaking through the limitations of traditional single-point monitoring. Utilizing advanced data transmission and processing modules, it integrates and deeply analyzes multi-source data, resolving the disconnect between monitoring and dust suppression. Based on an intelligent decision-making and control module, it achieves adaptive dynamic adjustment of spray dust suppression strategies through accurate dust concentration prediction and intelligent optimization algorithms. The intelligent design and collaborative operation of spray dust suppression equipment clusters effectively cope with complex environments. This invention significantly improves the intelligence level of mine dust control, increases dust suppression efficiency, reduces water consumption, reduces equipment wear, and lowers occupational disease risks, achieving efficient, environmentally friendly, and sustainable development in mine production. It fundamentally overcomes the shortcomings of traditional technologies in terms of monitoring comprehensiveness, system linkage, environmental adaptability, and intelligence.

[0074] The following is a specific example of intelligent control for dust removal in a mine: 1. System Deployment and Implementation. During the system deployment and implementation phase, multimodal sensors were scientifically deployed in key dust-generating areas both in the open and underground, based on the actual operating scenarios of the mine. The installation height and spacing were precisely set, and protective measures were implemented. A hybrid communication network consisting of LoRa and 5G was built, and a dedicated communication room for the mine was constructed to ensure data transmission. A high-performance server cluster was equipped, a big data processing platform and database were installed, and a data processing software system was deployed to achieve the end-to-end construction from data acquisition to processing, laying a solid foundation for the stable operation of the system.

[0075] The sensor installation height should be adjusted according to the actual situation: dust concentration sensors should be installed 1.5-2 meters above the ground to avoid obstruction by personnel or equipment; wind speed and direction sensors should be installed at an unobstructed high location, 5-10 meters above the ground; video surveillance cameras should be installed 3-5 meters above the ground to ensure that the field of view covers the target area. All sensors should be encapsulated in a waterproof, dustproof, and impact-resistant protective shell, and lightning protection grounding measures should be implemented.

[0076] At an open-pit iron ore mining site, 20 light-scattering dust concentration sensors were installed every 15 meters at the blasting face. One beta-ray absorption dust concentration sensor was installed at each of the 10 dust-generating points in the ore crushing workshop, including the crusher inlet, outlet, and belt conveyor junction. 15 wind speed and direction sensors were installed in a grid pattern at 80-meter intervals throughout the mining area; 30 sensors were installed every 50 meters in underground tunnels. 20 temperature and humidity sensors were installed in the open-pit stockpile and at each working face in the underground mining area. 30 high-definition video surveillance cameras were installed at key locations such as the mining face, transport roads, and crushing workshop to ensure coverage of all dust-generating areas.

[0077] A dedicated communication equipment room was built for the mine, equipped with core switches, routers, and other network devices to construct an internal communication network. VLAN technology was used to isolate different types of sensor data, ensuring the stability and security of data transmission. Simultaneously, a network firewall and intrusion detection system were installed to prevent external network attacks.

[0078] Three LoRa base stations were built on the edge of the mine, each with a coverage radius of 3 kilometers, ensuring data transmission for sensors in remote areas. 5G micro base stations were deployed in the main operating areas of the mine to achieve full 5G signal coverage. Sensor nodes automatically switch communication modes based on signal strength using built-in LoRa / 5G dual-mode communication modules. For example, deep in underground tunnels, sensors automatically select LoRa mode to communicate with the base station; in open working areas on the surface, they switch to 5G mode to ensure rapid transmission of large amounts of data (such as video data).

[0079] Deploy data processing software systems, including sensor data acquisition programs, data cleaning and calibration modules, data fusion algorithm libraries, dust concentration prediction models, and intelligent decision-making systems. Build data processing workflows using visual programming tools (such as Node-RED) to automate the data acquisition, processing, and decision-making processes.

[0080] The data processing center is equipped with a cluster of four high-performance servers, each configured with an Intel Xeon Gold 6248R processor, 128GB of memory, and 2TB SSD + 12TB HDD storage. It runs the Hadoop big data processing platform, the Spark stream computing framework, a MySQL relational database, and a MongoDB non-relational database.

[0081] 2. System Operation and Debugging. During system operation and debugging, the sensor data acquisition, communication network transmission, and functions of each module are fully integrated and debugged to ensure the normal operation of all parts of the system. In the actual operation and testing phase, system indicators are continuously monitored, the predicted dust concentration values ​​are compared with the actual values ​​to evaluate the accuracy of the model, the working status of the dust suppression equipment is statistically analyzed to calculate the dust suppression efficiency, and sudden situations and equipment failures are simulated to test the system's emergency response and fault handling capabilities, ensuring the reliability and stability of the system in a real production environment.

[0082] System commissioning includes the following: Starting the sensor nodes and checking the data acquisition function to ensure all sensors are collecting data normally at the set frequency. Through the monitoring interface of the data processing center, checking the completeness and accuracy of the data uploaded by the sensors, and verifying that the data timestamps are synchronized with the actual time. Testing the wireless communication network, simulating scenarios such as signal obstruction and base station failure, to verify whether the system can automatically switch communication modes and transmission paths, ensuring continuous data transmission. At the data processing center, checking whether the received data is completely encrypted and whether the decrypted data is consistent with the original data. Performing functional tests on the intelligent decision-making and control module, inputting simulated dust concentration data, wind speed and direction data, etc., to verify the accuracy of the dust concentration prediction model and the effectiveness of the spray dust suppression strategy optimization algorithm. Testing the spray dust suppression equipment's accurate response by manually sending control commands and adjusting operating parameters.

[0083] During the actual operation and testing phase, the dust concentration in a localized area was artificially created to exceed the standard (e.g., by turning on a dust generator in a certain area). The system's ability to detect the anomaly in a timely manner, activate the corresponding dust suppression strategy, and the response time and dust suppression effect of the equipment were observed. Simultaneously, the system's fault diagnosis and emergency handling capabilities in the event of equipment failure (e.g., a malfunction of the solenoid control valve in a spray module) were tested, and its ability to automatically switch to backup equipment or issue alarm information was checked.

[0084] During normal mine production, the system operates continuously for 72 hours, with real-time monitoring of various system indicators. Dust concentration changes in different time periods and areas are recorded, and predicted values ​​are compared with actual measured values ​​to evaluate the accuracy of the dust concentration prediction model. The operating time and water consumption of the spray dust suppression equipment are statistically analyzed, and the dust suppression efficiency is calculated (Dust suppression efficiency = (Dust concentration before dust suppression - Dust concentration after dust suppression) / Dust concentration before dust suppression × 100%).

[0085] 3. System Optimization and Maintenance. Regarding system optimization and maintenance, the dust concentration prediction model and spray dust suppression strategy optimization algorithm are regularly iterated and updated. Model parameters and algorithm weights are adjusted based on new data and actual dust suppression effects to improve the system's intelligent decision-making capabilities. Detailed regular equipment maintenance plans are developed, and sensors, spray dust suppression equipment, communication base stations, and servers are inspected, maintained, and updated. An equipment fault early warning mechanism is established, utilizing machine learning to analyze equipment operating data to predict potential faults, enabling preventative maintenance, extending equipment lifespan, and ensuring long-term efficient system operation. Model iterative optimization is divided into weekly updates and monthly evaluations. The dust concentration prediction model is updated weekly by adding newly collected data from the previous week (including data from normal and special operating conditions) to the training set and retraining the model. An online learning algorithm is used to update model parameters in real time, adapting to changes in dust generation patterns during mining production (such as dust variations caused by adjustments in mining processes or equipment replacements). The optimization algorithm for the spray dust suppression strategy is evaluated monthly. Based on the difference between the actual and expected dust suppression effects, the weights and constraints of the algorithm's objective function are adjusted. For example, if excessive water consumption is found, the weight of water consumption in the objective function is appropriately increased to optimize the spray dust suppression strategy and reduce water waste.

[0086] Equipment maintenance management includes developing a regular maintenance plan and establishing an equipment fault early warning mechanism. The regular maintenance plan includes: daily visual inspection of sensors, cleaning surface dust and debris to ensure normal sensor operation; weekly inspection of mechanical components of the spray dust suppression equipment, such as lubricating rotating parts of the nozzles and checking pipe seals; and monthly hardware testing and software updates of communication base stations and data processing servers to ensure stable system operation. The equipment fault early warning mechanism analyzes equipment operating data collected by sensors (such as spray pump motor current and pipe pressure fluctuations) and uses machine learning algorithms to predict equipment faults. When a potential equipment fault is predicted (e.g., an impending damage to the spray pump bearing), the system issues an early warning, prompting maintenance personnel to perform preventative maintenance and reduce equipment downtime.

[0087] To better implement the intelligent control method for mine dust removal in the embodiments of the present invention, based on the intelligent control method for mine dust removal, correspondingly, as follows: Figure 5 As shown in the figure, this embodiment of the invention also provides an intelligent control device for mine dust removal. The intelligent control device 500 for mine dust removal includes: The acquisition module 501 is used to acquire real-time monitoring data from multimodal sensors, including dust concentration sensors, wind speed and direction sensors, temperature and humidity sensors, and cameras. The prediction module 502 is used to input the preprocessed real-time monitoring data into the dust concentration prediction model to obtain the dust concentration prediction result output by the dust concentration prediction model. The dust concentration prediction model is composed of cascaded LSTM network and CNN network, and is trained using the preprocessed historical monitoring data of the multimodal sensor as samples and the historical dust concentration data as sample labels. The generation module 503 is used to generate control commands based on real-time monitoring data and dust concentration prediction results. The control commands are used to adjust the operating parameters of the spray dust suppression equipment, which includes fixed spray equipment, vehicle-mounted spray dust suppression vehicles, and mobile spray cannons.

[0088] The intelligent control device 500 for mine dust removal provided in the above embodiments can realize the technical solutions described in the embodiments of the intelligent control method for mine dust removal. The specific implementation principles of each module or unit can be found in the corresponding content of the embodiments of the intelligent control method for mine dust removal, which will not be repeated here.

[0089] like Figure 6 As shown, the present invention also provides a control device 600. The control device 600 includes a processor 601, a memory 602, and a display 603. Figure 6 Only some components of the control device 600 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0090] In some embodiments, processor 601 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 602 or process data, such as the intelligent control method for dust removal in mines in this invention.

[0091] In some embodiments, processor 601 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 601 may be local or remote. In some embodiments, processor 601 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-cloud, etc., or any combination thereof.

[0092] In some embodiments, memory 602 may be an internal storage unit of control device 600, such as a hard disk or memory of control device 600. In other embodiments, memory 602 may also be an external storage device of control device 600, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., provided on control device 600.

[0093] Furthermore, the memory 602 may include both internal storage units of the control device 600 and external storage devices. The memory 602 is used to store application software and various types of data for which the control device 600 is installed.

[0094] In some embodiments, display 603 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an organic light-emitting diode (OLED) touchscreen. Display 603 is used to display information from control device 600 and to display a visual user interface. Components 601-603 of control device 600 communicate with each other via a system bus.

[0095] In one embodiment, when the processor 601 executes the intelligent control program for mine dust removal stored in the memory 602, the following steps can be implemented: Acquire real-time monitoring data from multimodal sensors, including dust concentration sensors, wind speed and direction sensors, temperature and humidity sensors, and cameras; The preprocessed real-time monitoring data is input into the dust concentration prediction model to obtain the dust concentration prediction result output by the dust concentration prediction model. The dust concentration prediction model is composed of cascaded LSTM network and CNN network, and is trained using the preprocessed historical monitoring data of multimodal sensors as samples and the historical dust concentration data as sample labels. Control commands are generated based on real-time monitoring data and dust concentration prediction results. These commands are used to adjust the operating parameters of the spray dust suppression equipment, which includes fixed spray equipment, vehicle-mounted spray dust suppression vehicles, and mobile spray cannons.

[0096] It should be understood that when the processor 601 executes the intelligent control program for mine dust removal in the memory 602, in addition to the functions mentioned above, it can also perform other functions, as can be found in the description of the corresponding method embodiments above.

[0097] Furthermore, this embodiment of the invention does not specifically limit the type of control device 600 mentioned. Control device 600 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the invention, control device 600 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0098] Accordingly, this application also provides a computer-readable storage medium for storing computer-readable programs or instructions. When the programs or instructions are executed by a processor, they can implement the steps or functions of the intelligent control method for mine dust removal provided in the above-described method embodiments.

[0099] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0100] The intelligent control method, device, control equipment, and storage medium for dust removal in mines provided by this invention have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.

Claims

1. An intelligent control method for dust removal in mines, characterized in that, include: Acquire real-time monitoring data from multimodal sensors, including dust concentration sensors, wind speed and direction sensors, temperature and humidity sensors, and cameras; The preprocessed real-time monitoring data is input into the dust concentration prediction model to obtain the dust concentration prediction result output by the dust concentration prediction model. The dust concentration prediction model is composed of cascaded LSTM network and CNN network, and is trained using the preprocessed historical monitoring data of multimodal sensors as samples and the historical dust concentration data as sample labels. Control commands are generated based on real-time monitoring data and dust concentration prediction results. These commands are used to adjust the operating parameters of the spray dust suppression equipment, which includes fixed spray equipment, vehicle-mounted spray dust suppression vehicles, and mobile spray cannons.

2. The intelligent control method for mine dust removal according to claim 1, characterized in that, The generation of control commands based on real-time monitoring data and dust concentration prediction results includes: A dust removal strategy model is constructed with the objective function of minimizing dust concentration and water consumption, the decision variables of the operating parameters of the spray dust removal equipment, the constraints of mine operation safety and the operating limitations of the spray dust removal equipment, and the state variables of real-time monitoring data and dust concentration prediction results. The dust removal strategy model is solved, and control commands are generated based on the solution results.

3. The intelligent control method for mine dust removal according to claim 2, characterized in that, Solving the dust removal strategy model includes: The dust removal strategy model is solved based on the PSO algorithm or the GA algorithm.

4. The intelligent control method for mine dust removal according to claim 2, characterized in that, The method further includes: Based on the dust concentration prediction results and real-time dust concentration, the spray dust removal equipment that needs to be scheduled is determined.

5. The intelligent control method for dust removal in mines according to claim 1, characterized in that, The acquisition of real-time monitoring data from the multimodal sensor includes: Real-time monitoring data from multimodal sensors is acquired using 5G and / or LoRa wireless networks.

6. The intelligent control method for dust removal in mines according to claim 1, characterized in that, The method further includes: After generating control commands based on real-time monitoring data and dust concentration prediction results, the control commands are sent to the spray dust removal equipment via 5G wireless network and / or LoRa wireless network.

7. The intelligent control method for dust removal in mines according to claim 6, characterized in that, The method further includes: After the control command is sent to the spray dust removal equipment, it is adjusted and resent based on the real-time changes in dust concentration.

8. An intelligent control device for dust removal in mines, characterized in that, include: The acquisition module is used to acquire real-time monitoring data from multimodal sensors, including dust concentration sensors, wind speed and direction sensors, temperature and humidity sensors, and cameras. The prediction module is used to input the preprocessed real-time monitoring data into the dust concentration prediction model to obtain the dust concentration prediction result output by the dust concentration prediction model. The dust concentration prediction model is composed of cascaded LSTM network and CNN network, and is trained using the preprocessed historical monitoring data of multimodal sensors as samples and the historical dust concentration data as sample labels. The generation module is used to generate control commands based on real-time monitoring data and dust concentration prediction results. The control commands are used to adjust the operating parameters of the spray dust suppression equipment, which includes fixed spray equipment, vehicle-mounted spray dust suppression vehicles, and mobile spray cannons.

9. A control device, characterized in that, Including memory and processor, among which, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the intelligent control method for mine dust removal according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the intelligent control method for mine dust removal as described in any one of claims 1 to 7.

Images