Coal mine ventilation optimization and air quality regulation and control method based on adaptive learning

Abstract

The invention discloses a coal mine ventilation optimization and air quality regulation and control method based on adaptive learning, and relates to the technical field of coal mine ventilation optimization, and the method comprises the following steps: arranging a plurality of sensors in a mine, carrying out the real-time collection and monitoring of key environment parameters, and uploading the collected data to a central control system; and comparing the collected real-time data with historical data, and dividing the collected real-time data into conventional working condition data and abnormal working condition data according to environment states. Through real-time monitoring of various sensors and a deep learning algorithm, accurate ventilation control is achieved, a problem area is rapidly positioned in an emergency, airflow is dynamically adjusted, and safety of miners is guaranteed. According to the system, an LSTM model is adopted to predict an event trend in advance, preventive regulation and control measures are taken in time, real-time adjustment is supported, and the strain capacity is improved. Through a multi-stage ventilation mode, the system optimizes energy consumption and equipment operation efficiency, reduces unnecessary energy waste and maintenance cost, and realizes balance between safety and economy.

Description

Technical Field

[0001] The present invention relates to the technical field of coal mine ventilation optimization, and in particular to a method for coal mine ventilation optimization and air quality control based on adaptive learning. Background Art

[0002] Coal mine ventilation optimization and air quality control based on adaptive learning aims to dynamically adjust the ventilation system in coal mines through intelligent technology to achieve efficient ventilation and air quality management. This method relies on adaptive learning algorithms to automatically identify and predict the best ventilation strategies under different environmental conditions by real-time monitoring of gas composition, temperature, humidity and other data in the mine. The system continuously learns from historical data and changes in the mine environment, and gradually optimizes the ventilation mode to ensure the safety of mine workers, improve energy efficiency, and reduce the accumulation and emission of harmful gases, thereby reducing ventilation costs and improving mine production efficiency while ensuring mine safety.

[0003] The prior art has the following deficiencies:

[0004] In the optimization of coal mine ventilation and air quality control based on adaptive learning, the adaptive learning algorithm of the existing technology may experience "overfitting" under extreme working conditions. When the mine system operates under a certain condition for a long time (such as stable climate or constant production load), the adaptive learning system may mistakenly regard this state as a "standard condition" and optimize the ventilation strategy based on this. However, when an emergency occurs (such as a sudden increase in gas, fire, or equipment failure), the system may not be able to quickly identify the anomaly and adapt to the new environmental requirements, resulting in delayed or failed ventilation response. This may aggravate the increase in harmful gas concentrations, the spread of fire, and even directly endanger the safety of miners. The seriousness of this problem lies in the fact that if the system prediction and emergency ventilation strategy are insufficient, critical rescue time will be missed, resulting in catastrophic consequences.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a method for optimizing coal mine ventilation and controlling air quality based on adaptive learning, which realizes precise ventilation control and event emergency management through a combination of multiple sensors, deep learning and reinforcement learning algorithms. When emergencies such as gas leakage or fire occur, the system quickly detects and locates the problem area, dynamically adjusts the airflow to concentrate in the affected area, avoids the shutdown of the entire mine, improves safety and prevents secondary disasters. At the same time, the system predicts the development trend of events through the LSTM model, takes preventive control in advance, reduces the occurrence of risks, and supports real-time adjustment strategies to improve resilience. A multi-stage ventilation mode is adopted to reduce fan power consumption and airflow waste while ensuring safety, continuously optimize energy consumption levels, effectively reduce operating costs and improve the economy and sustainability of the system to solve the problems in the above-mentioned background technology.

[0007] In order to achieve the above object, the present invention provides the following technical solution: a method for optimizing coal mine ventilation and controlling air quality based on adaptive learning, comprising the following steps:

[0008] Various sensors are deployed in the mine to collect and monitor key environmental parameters in real time, and the collected data is uploaded to the central control system;

[0009] Compare the collected real-time data with historical data, and divide them into normal working condition data and abnormal working condition data according to the environmental status. Use K-means clustering classification algorithm to identify potential extreme conditions to ensure that subsequent algorithm optimization can cover the control needs under different working conditions.

[0010] Based on the mine's historical abnormal events, a library of multiple ventilation plans and emergency response strategies is established, including multi-layer ventilation modes to deal with gas surges, fires and equipment failures, and the plan library is regularly updated based on new data;

[0011] Using reinforcement learning algorithms, we generate preliminary ventilation strategies based on real-time data and suggestions from the plan library, continuously optimize through interactive feedback with historical data, and simulate the adjustment effects in the airflow and air quality model within the mine to obtain the optimal preliminary strategy;

[0012] Use multiple anomaly detection algorithms to analyze real-time mine data in parallel. Once a data pattern deviates from the normal state, an alarm is triggered, the current preliminary ventilation strategy is interrupted, and emergency response mode is entered;

[0013] After an emergency occurs, a deep learning algorithm is activated to re-evaluate the current status and predict the development trend of the incident based on historical abnormal data. Based on the prediction results, the ventilation mode is adjusted dynamically in real time to ensure that the air quality in the mine is restored to a safe range in the shortest time possible while minimizing energy consumption.

[0014] Preferably, the specific steps of using the K-means clustering algorithm to classify the mine environment data are as follows:

[0015] Extract key features from the real-time data collected by sensors, perform outlier detection and noise filtering on sensor data, and eliminate data anomalies caused by sensor false alarms or failures; normalize the preprocessed data to map data of different units and dimensions to a unified scale to ensure that the weights of various parameters are balanced in cluster analysis. Finally, merge the processed data with historical data to form a complete data set;

[0016] Divide the data set into K clusters. After determining the K value, select the initial cluster center point through random initialization or K-means++ algorithm to reduce the risk of the algorithm falling into the local optimal solution.

[0017] Assign each piece of data to the nearest cluster center according to the Euclidean distance, and then recalculate the cluster center position based on all the data points assigned to the cluster. Repeat the process of data assignment and cluster center update until the position of the cluster center no longer changes significantly or reaches the set number of iterations.

[0018] After clustering is completed, different labels are assigned to each cluster, and the characteristic centers of each cluster are analyzed. Isolated data that cannot be classified into regular clusters are marked as abnormal conditions, triggering further detection and alarm.

[0019] Preferably, the specific steps for establishing a library of multiple ventilation plans and emergency response strategies are as follows:

[0020] Collect data on various abnormal events that have occurred in the mine in the past;

[0021] Different abnormal events are classified into multiple levels according to their severity and impact scope;

[0022] In the process of building the emergency plan library, all ventilation modes and emergency response measures are encoded in the form of rules to form a modular strategy library;

[0023] To ensure that the plan library can respond to the ever-changing mine environment, new data and the latest safety incident feedback are regularly incorporated into the analysis and existing plans are optimized.

[0024] Preferably, the specific steps of generating a preliminary ventilation strategy using a reinforcement learning algorithm are as follows:

[0025] In the reinforcement learning framework, the state space, action space and reward mechanism are first defined. The state space contains the environmental parameters in the mine, the action space refers to the control instructions that can be executed by the ventilation system, and the reward mechanism is designed according to the ventilation effect and safety of the system.

[0026] Based on the current real-time data, the reinforcement learning algorithm is used to read the historical cases and emergency plans that are closest to the current environment from the plan library as a reference for generating preliminary strategies;

[0027] After generating the preliminary strategy, we conducted virtual tests in the mine’s airflow and air quality simulation model to verify the effectiveness of the strategy in various extreme scenarios by simulating different working conditions.

[0028] When the preliminary strategy passes the simulation test, it will be deployed to the actual mine ventilation system and the execution effect will be monitored in real time. If the ventilation effect meets expectations and meets safety standards, the strategy will be marked as qualified and recorded in the plan library for reference in similar scenarios in the future. If deviations occur during execution, the algorithm will adjust the strategy based on the new data to ensure that the ventilation system always remains in the optimal state.

[0029] Preferably, the specific steps of using multiple anomaly detection algorithms to analyze real-time mine data in parallel are as follows:

[0030] In the process of anomaly detection, the mine environment parameters X collected from the sensor are i}={x1,x2,…,x n} is input into the algorithm module, where x i Represents the real-time data of the i-th sensor. In order to ensure the stability and efficiency of the algorithm, the collected data is feature extracted and standardized. Let X∈R m×n Represents the data matrix, where m is the number of samples and n is the dimension of the monitored environmental parameter. The standardized formula is: j = 1, ..., n, where μ j and σ j are the mean and standard deviation of parameter j, and the standardized data z ij It is passed to the subsequent detection algorithm to eliminate the influence of different parameter scales;

[0031] The isolation forest algorithm is used to construct a random tree to evaluate the isolation degree of the sample points. For each sample z i , the isolation forest will generate T random trees, the depth of each tree represents the number of steps required to completely separate the sample points, let sample z i The depth of the t-th tree is H(z i ), then the average depth of all trees is: Combined with the expected tree depth c(n), the anomaly score S(z i ) is calculated as follows:

[0032]

[0033] , by setting the threshold α, such as S(z i)>α, it is marked as abnormal.

[0034] Preferably, a class of support vector machines is used to construct boundaries in high-dimensional space to detect abnormal data points. Given a data set Z = {z1, z2, ..., z m}, SVM separates normal data from abnormal data by finding a hyperplane w·z-ρ=0, and the optimization goal is: subject to:w·z i ≥ρ-ξ i ,ξ i ≥0, where v is the parameter that controls the abnormality rate, ξ i It is a slack variable used to process data points on the soft boundary. When new sample data falls outside the hyperplane, it is marked as an outlier.

[0035] Through parallel analysis of isolation forest and SVM, two independent anomaly scores are calculated for each data, namely S IF (z i ) and S SVM (z i ), in order to achieve multi-algorithm fusion, a weighted anomaly scoring strategy is adopted. The specific expression is: S total (z i )=β·S IF (z i )+(1-β)·S SVM (z i ), where β is the algorithm weight parameter, reflecting the importance of isolation forest and SVM in different scenarios. total (z i )>α, the system immediately triggers an alarm, interrupts the current ventilation strategy, enters the emergency response mode, and executes the corresponding plan.

[0036] Preferably, the specific steps of using a deep learning algorithm to re-evaluate emergencies and dynamically adjust ventilation modes are as follows:

[0037] When an emergency is detected in the mine, the latest real-time data is collected immediately;

[0038] After the initial status assessment, predict the development trend of the emergency through similar cases in historical data;

[0039] Generate and execute real-time ventilation adjustment instructions based on the prediction results;

[0040] After adjusting the ventilation mode, feedback data is continuously collected and analyzed to ensure that the air quality gradually returns to a safe range. If any abnormal changes are detected or the strategy execution does not meet expectations, the situation will be immediately re-evaluated through the deep learning algorithm, and the instructions will be automatically optimized and adjusted to achieve secondary or multiple iterative optimizations. In addition, the data and response process of this emergency will be stored in the historical database for reference for similar events in the future and to improve the model's adaptive capabilities.

[0041] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0042] The present invention uses a variety of sensors to monitor the mine environment in real time, and combines deep learning and reinforcement learning algorithms to achieve precise ventilation control. When an emergency (such as a gas leak or fire) occurs, the system can quickly detect and locate the problem area, and dynamically adjust the ventilation mode to concentrate the main airflow in the affected area. At the same time, through precise control of regional classification, the shutdown of the entire mine or the full evacuation of personnel is avoided, and local problems are quickly resolved. This rapid response capability significantly improves the safety of the mine, reduces the risk of event deterioration and spread, and maximizes the protection of the lives of miners. In addition, the precise control strategy avoids unnecessary airflow disturbances, reduces the diffusion of gas in the mine, and helps prevent the occurrence of secondary disasters.

[0043] By adopting time-series deep learning models such as LSTM, the present invention enables the system to predict the development trend of events in advance and adopt preventive control strategies to reduce the occurrence of potential risks. For example, after detecting a decrease in wind speed and a slow increase in gas concentration, the system can increase the fan power in advance and open the spare damper for ventilation to prevent the gas concentration from further increasing. The combination of prediction and prevention enables the system to take emergency measures before an event occurs, buying more time to deal with potential dangers. In addition, the system also supports real-time adjustment strategies. If the initial prediction deviates, the algorithm can quickly correct and redeploy the best solution. This capability makes the mine's response to emergencies more flexible and efficient, avoiding the limitations of traditional management with delayed reactions.

[0044] The present invention not only ensures the safe operation of the mine through a phased ventilation mode, but also significantly reduces energy consumption. In the early stage of the event, the system runs the ventilation equipment at high power to quickly reduce the concentration of harmful gases; when the air quality gradually recovers, the system will reduce the fan power and close some unnecessary dampers to reduce unnecessary airflow waste. By recording the energy consumption data and response effects of historical events, the energy consumption level of each stage is continuously optimized to achieve the best balance between safety and energy efficiency. Compared with the traditional full-power ventilation solution, this multi-stage mode significantly reduces power consumption and equipment wear, reduces the long-term operating costs of the mine, and improves the economy and sustainability of the ventilation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0046] Figure 1 The present invention is a method flow chart of a method for coal mine ventilation optimization and air quality control based on adaptive learning. DETAILED DESCRIPTION

[0047] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0048] The present invention provides Figure 1 A method for optimizing coal mine ventilation and controlling air quality based on adaptive learning is shown, comprising the following steps:

[0049] Various sensors are deployed in the mine to collect and monitor key environmental parameters in real time, and the collected data is uploaded to the central control system;

[0050] Various sensors are deployed in the mine to collect and monitor key environmental parameters in a comprehensive and real-time manner, and upload the data to the central control system to ensure the safety and efficiency of air quality and ventilation. These sensors mainly include the following categories:

[0051] Gas sensor: used to monitor methane concentration, prevent gas from exceeding the standard, and avoid the risk of explosion caused by gas accumulation.

[0052] Carbon Monoxide Sensor: Detects CO concentration in mines to prevent poisoning risks caused by insufficient ventilation, equipment failure or fire.

[0053] Oxygen sensor: monitors oxygen content to ensure that the oxygen concentration in the mine is within a safe range and prevent the occurrence of hypoxia.

[0054] Temperature and humidity sensor: monitors temperature and humidity changes in the mine to control air comfort and prevent excessive temperatures from overheating equipment or affecting workers' health.

[0055] Dust sensor: monitors dust concentration in the air to prevent excessive dust accumulation from causing explosions or respiratory diseases.

[0056] Wind speed and direction sensors: monitor the speed and direction of airflow within the mine to ensure that the ventilation system operates along the intended path and avoids airflow turbulence.

[0057] Pressure sensor: Detects changes in air pressure in different areas and is used to predict gas leaks or abnormal damper operation.

[0058] Carbon dioxide sensor: monitors carbon dioxide concentration to prevent miners from suffocating or becoming fatigued due to excessive carbon dioxide.

[0059] Hydrogen sulfide sensor: detects the presence of toxic hydrogen sulfide gas to avoid poisoning caused by leakage of the gas in the mine.

[0060] Through the coordinated monitoring of these sensors, the system can fully grasp the environmental conditions within the mine, provide reliable data support for intelligent ventilation and air quality control, and provide timely warnings and adjustments when abnormal operating conditions occur.

[0061] The collected real-time data is compared with historical data, and divided into normal working condition data and abnormal working condition data according to the environmental status. In this process, the K-means clustering classification algorithm is used to identify potential extreme conditions to ensure that the subsequent algorithm optimization can cover the control needs under different working conditions;

[0062] The specific steps of using K-means clustering algorithm to classify mine environment data are as follows:

[0063] The system first extracts key features from the real-time data collected by the sensor, such as gas concentration, carbon monoxide concentration, temperature and humidity, wind speed, etc. To ensure data quality, the system needs to detect outliers and filter noise on the sensor data to eliminate data anomalies caused by sensor false alarms or failures. In addition, some data may be missing, in which case interpolation or mean value substitution is used to supplement it. The preprocessed data also needs to be normalized to map data of different units and dimensions to a unified scale (such as 0 to 1) to ensure that each parameter is weighted equally in the cluster analysis. Finally, the system merges the processed data with the historical data to form a complete data set.

[0064] The core of the K-means algorithm is to divide the data set into K clusters. Therefore, before applying the algorithm, it is necessary to determine a reasonable number of clusters K. Mine managers can estimate the K value based on the historical operation records of the mine and the types of different working conditions (such as normal state, gas increase state, fire precursors, etc.). To further accurately select the K value, the elbow method or silhouette coefficient method can be used to analyze the error under different numbers of clusters to ensure that the clustering results are more representative. After determining the K value, the initial cluster center point is selected through random initialization or K-means++ algorithm to reduce the risk of the algorithm falling into a local optimal solution.

[0065] The execution process of the K-means algorithm includes two main loops: one is to assign each data to the nearest cluster center based on the Euclidean distance, and the other is to recalculate the cluster center position based on all the data points assigned to the cluster. The system repeats the process of data assignment and cluster center update until the location of the cluster center no longer changes significantly or reaches the set number of iterations. When real-time mine data continues to flow into the system, it triggers the online update mechanism of the K-means algorithm, that is, incrementally updating the cluster center based on the new data. This iterative update mechanism helps the system dynamically identify new data patterns and keep them consistent with historical data.

[0066] After clustering, the system assigns different labels to each cluster (such as "normal operating conditions", "abnormal gas concentration", "precursor of equipment failure", etc.), and analyzes the characteristic centers of each cluster. For example, when the center of a cluster shows that the gas concentration is higher than the safety threshold, the system marks the cluster as "gas warning state". For isolated data that cannot be classified into regular clusters, the system marks it as an abnormal operating condition and triggers further detection and alarm. This classification result not only provides a data basis for real-time control strategies, but also enriches historical data sets, so that subsequent algorithm optimization covers a variety of extreme situations, thereby enhancing the system's ability to respond to emergencies.

[0067] Based on the mine's historical abnormal events, a library of multiple ventilation plans and emergency response strategies is established, including multi-layer ventilation modes to deal with gas surges, fires and equipment failures, and the plan library is regularly updated based on new data;

[0068] The specific steps to establish a library of multiple ventilation plans and emergency response strategies are as follows:

[0069] The system first collects data on various abnormal events that have occurred in the mine in the past, including detailed records of cases such as gas surges, fires, and equipment failures. These data sources include sensor logs, manual inspection reports, accident analysis reports, and historical archives in the mine safety management system. The focus of the analysis is to identify the triggering conditions, impact range, duration, and degree of harm of each type of event. Through data analysis and retrospective statistics, the system summarizes the occurrence patterns of various abnormal events (such as specific seasons, equipment aging cycles, etc.), laying the foundation for the design of corresponding plans. The comprehensiveness and accuracy of the data are crucial to ensure that the system can cover all potential risks when facing complex scenarios.

[0070] According to the severity and impact range of different abnormal events, the events are divided into multiple levels, such as "mild abnormality", "moderate abnormality", "serious abnormality" and "critical state". Different levels of events correspond to different ventilation modes. For example, when the gas increases slightly, it may only be necessary to increase the power of the ventilator in the local area, while serious gas leakage requires the dampers of the entire mine to be switched, the ventilator to be started to maximum power, and personnel evacuation instructions to be issued. The system designs multi-layer ventilation modes according to the event level and mine layout to ensure that ventilation control from local to global can be achieved. The plan covers normal ventilation, gas emergency, fire handling and safe ventilation plans after equipment shutdown.

[0071] In the process of building the plan library, the system encodes all ventilation modes and emergency response measures in the form of rules and forms a modular strategy library. These modular plans are managed by a rule engine, which can automatically match applicable plans based on real-time data and historical cases. For example, when the gas concentration in a certain area exceeds the set threshold and the wind speed slows down, the system will select the plan related to gas leakage according to the rules and determine whether it is necessary to enter the second or third level response mode. Each plan includes specific operating instructions, the start-up sequence of ventilation equipment, the opening and closing settings of dampers, personnel evacuation routes and other details to ensure that each emergency measure can be executed efficiently.

[0072] To ensure that the plan library can cope with the ever-changing mine environment, the system regularly incorporates new data and the latest safety incident feedback into the analysis and optimizes existing plans. Through adaptive learning algorithms, the system can identify which plans are most effective in actual events and make adjustments to the insufficient links. For example, if a delayed response to a gas leak causes the danger to escalate, the system will optimize the alarm trigger time and ventilation equipment response sequence in the plan. The data review after each event can prompt the plan library to be dynamically updated and achieve intelligent optimization. Mine managers can also manually adjust the plan according to the latest regulations and management requirements to ensure that the strategy library always remains efficient and compliant.

[0073] Using reinforcement learning algorithms, a preliminary ventilation strategy is generated based on real-time data and the recommendations of the plan library. The algorithm is continuously optimized through interactive feedback with historical data, and the adjustment effects are simulated in the airflow and air quality model in the mine to obtain the optimal preliminary strategy;

[0074] The specific steps for generating a preliminary ventilation strategy using a reinforcement learning algorithm are as follows:

[0075] In the reinforcement learning framework, the system first defines the state space, action space, and reward mechanism. The state space contains the combination of real-time data of various environmental parameters in the mine, such as gas concentration, CO content, temperature and humidity, wind speed, etc. The action space refers to the control instructions that can be executed by the ventilation system, such as adjusting the fan power, opening or closing the damper, changing the direction of regional wind flow, etc. The reward mechanism is designed according to the ventilation effect and safety of the system. For example, positive rewards are given when the gas concentration is reduced and the air quality is improved, and negative rewards are given when the ventilation energy consumption is too high or the response is delayed. This mechanism ensures that the goal of the algorithm is to achieve an efficient and low-cost ventilation strategy while maintaining safety.

[0076] Based on the current real-time data, the reinforcement learning algorithm will read the historical cases and emergency plans that are closest to the current environment from the plan library as a reference for generating preliminary strategies. At this time, the algorithm will select the best initial action combination under the current state, such as increasing the main fan power in advance or opening the backup vents when the gas concentration is high. These preliminary actions are determined by Q-learning or deep Q network (DQN) algorithms. The system will evaluate the short-term and long-term benefits of each action to formulate a preliminary ventilation strategy. The guidance of the plan library can effectively narrow the algorithm exploration space, speed up the strategy generation speed, and ensure a quick response in an emergency.

[0077] After generating the preliminary strategy, the system conducts a virtual test in the mine's airflow and air quality simulation model. By simulating different working conditions (such as changes in wind speed and sudden increases in gas), the system verifies the effectiveness of the strategy in various extreme scenarios. If the simulation results show that the strategy has defects, such as low ventilation efficiency or air quality in some areas that does not meet the standards, the system will adjust the action combination and retest. In this process, the reinforcement learning algorithm is continuously optimized through interactive feedback with historical data, and the simulation results are fed back to the strategy model, so that the next round of strategy generation is closer to the optimal solution.

[0078] When the preliminary strategy passes the simulation test, the system deploys it to the actual mine ventilation system and monitors the execution effect in real time. If the ventilation effect meets expectations and meets safety standards, the strategy is marked as qualified and recorded in the plan library for reference in similar scenarios in the future. If deviations occur during execution, the algorithm will adjust the strategy based on new data to ensure that the ventilation system always maintains the optimal state. This parallel process of "exploration and utilization" enables the system to maintain dynamic learning and adaptability when dealing with changing environments, and achieve safe, efficient, and energy-saving ventilation control.

[0079] Multiple anomaly detection algorithms (such as the isolation forest algorithm and support vector machine) are used to analyze the real-time data of the mine in parallel. Once the data pattern is detected to deviate from the normal state, an alarm is triggered, and the current preliminary ventilation strategy is interrupted to enter the emergency response mode. During this process, the system marks the abnormal situation and stores the data samples for subsequent algorithm optimization;

[0080] The specific steps of using multiple anomaly detection algorithms to analyze real-time mine data in parallel are as follows:

[0081] In the process of anomaly detection, the mine environment parameters X collected from the sensor are i}={x1,x2,…,x n} is input into the algorithm module, where x i Represents the real-time data of the i-th sensor. In order to ensure the stability and efficiency of the algorithm, the system will extract and standardize these data. Let X∈R m×n Represents a data matrix, where m is the number of samples (such as the amount of sensor data collected in the past 5 minutes) and n is the dimension of the monitored environmental parameter (such as gas concentration, wind speed, etc.). The standardized formula is: j = 1, ..., n, where μ j and σ j are the mean and standard deviation of parameter j respectively. The standardized data z ij It is passed to the subsequent detection algorithm to eliminate the impact of different parameter scales.

[0082] The isolation forest algorithm is used to construct a random tree to evaluate the isolation degree of the sample points. i , the isolation forest will generate T random trees, and the depth of each tree represents the number of steps required to completely separate the point. i The depth of the t-th tree is H(z i ), then the average depth of all trees is: Combined with the expected tree depth c(n) (adjusted for the number of samples n in the tree), the anomaly score S(z i ) is calculated as follows:

[0083]

[0084] , if S(z i ) is close to 1, the sample point is highly abnormal; if it is close to 0.5, it is in the normal range. By setting the threshold α, such as S(z i )>α, it is marked as abnormal.

[0085] One-Class SVM is used to construct boundaries in high-dimensional space to detect abnormal data points. Given a data set Z = {z1, z2, ..., zm}, SVM separates normal data from abnormal data by finding an optimal hyperplane w·z-ρ=0. Its goal is to maximize the interval while ensuring that most samples are in the normal area. The optimization goal is: subject to:w·z i ≥ρ-ξ i ,ξ i ≥0, where ν is the parameter that controls the abnormality rate, ξ i is a slack variable used to handle data points on the soft boundary. When new sample data falls outside the hyperplane, it is marked as an outlier.

[0086] Through parallel analysis of isolation forest and SVM, the system calculates two independent anomaly scores for each data, namely S IF (z i ) and S SVM (z i ). In order to achieve multi-algorithm fusion, the system adopts a weighted anomaly scoring strategy, the specific expression is: S total (z i )=β·S IF (z i )+(1-β)·S SVM (z i ), where β is the algorithm weight parameter, reflecting the importance of isolation forest and SVM in different scenarios. total (z i )>α(the set global abnormal threshold), the system immediately triggers an alarm, interrupts the current ventilation strategy, enters the emergency response mode, and executes the corresponding plan. At this time, the system sends instructions to all fans and dampers through the central control system, and issues an evacuation notice in the personnel dispatch system to ensure the safety of miners in the shortest time.

[0087] After an emergency occurs, the system starts a deep learning algorithm to re-evaluate the current status and predict the development trend of the incident in combination with historical abnormal data. Based on the prediction results, the system makes real-time dynamic adjustments to the ventilation mode to ensure that the air quality in the mine is restored to a safe range in the shortest time while minimizing energy consumption. This adjustment includes detailed control of the fan speed, damper opening and closing status, and regional airflow distribution;

[0088] The specific steps to use deep learning algorithms to re-evaluate emergencies and dynamically adjust ventilation modes are as follows:

[0089] When an emergency (such as a sudden increase in gas or a fire) is detected in the mine, the system immediately collects the latest real-time data, including key parameters such as gas concentration, temperature and humidity, wind speed, and oxygen content. These data are input into the deep learning model together with historical abnormal data for status assessment. The system uses time series models such as long short-term memory networks (LSTM) to analyze the changing trend of the current status to ensure that it can understand whether the development of the current event is a continuation, deterioration, or alleviation of the warning state. In addition, the system also compares the environmental differences in different areas to determine whether the problem is localized or may trigger a chain reaction throughout the mine.

[0090] After the initial status assessment, the system predicts the possible development trend of the emergency through similar cases in historical data. The deep learning model will speculate whether the incident will deteriorate (such as gas continues to rise or fire spread) and how long it will take to return to normal based on the rate of change of the current environmental parameters. The system also considers the possibility of equipment failure or human intervention, and simulates multiple possible scenarios based on the effects of historical emergency responses. The risk level of each scenario will be scored, and the model will select the response strategy with the lowest risk and the highest resource utilization efficiency to provide a basis for subsequent adjustments.

[0091] Based on the prediction results, the system generates and executes real-time ventilation adjustment instructions. This includes adjusting the wind speed of the ventilator (such as increasing the fan power to a peak or reducing it to an energy-saving state), the opening and closing state of the damper (such as closing certain ventilation paths to concentrate wind power), and optimizing regional airflow distribution (directing more wind power into the affected area). The system will gradually deploy these adjustments and continuously monitor the feedback effects of various parameters to ensure that the ventilation system can respond quickly to changes in events. At the same time, the control strategy will take into account the optimization of energy consumption and avoid running the fan at high power for a long time, thereby balancing safety and cost.

[0092] After adjusting the ventilation mode, the system continuously collects and analyzes feedback data to ensure that the air quality gradually returns to a safe range. If any abnormal changes are detected or the strategy execution does not meet expectations, the deep learning algorithm will immediately re-evaluate the situation and automatically optimize the adjustment instructions to achieve secondary or multiple iterations of optimization. In addition, the system stores the data and response process of this emergency in a historical database for reference in similar events in the future and to improve the model's adaptive capabilities. The entire process implements closed-loop management from event detection, prediction, adjustment to feedback optimization, ensuring that the mine can quickly return to a stable state in an emergency and minimize unnecessary energy consumption.

[0093] Implementation method 1: Precision ventilation control based on regional classification;

[0094] In the mine, the complexity of the environment and the diversity of risk areas determine the need for precise ventilation control with regional classification. The mine is divided into multiple independent areas, such as production areas, transportation areas, equipment maintenance areas, etc. Each area is equipped with multiple sets of sensors to monitor key environmental parameters (such as gas concentration, CO concentration, temperature, humidity and wind speed). When the system detects a sudden increase in gas concentration in a specific area, the deep learning model will quickly determine the type and risk level of the event based on the matching of real-time data and historical data in the area. For example, if the increase in gas concentration is accompanied by a decrease in wind speed, this may indicate a failure of the regional ventilation equipment or a blockage in the ventilation path.

[0095] Once the type and risk level of the event are identified, the system immediately initiates the response mechanism. The ventilation system will dynamically adjust the damper opening and closing status and the wind speed of the fan in the area to concentrate the main airflow to the affected area. At the same time, to prevent unnecessary energy consumption, the system will reduce the ventilation supply to other non-critical areas. For example, when high gas concentrations appear in the production area, the system will close some dampers leading to the transportation area or maintenance area to ensure that the airflow is concentrated in key areas. In addition, if the event is local and controllable (such as a problem in a branch tunnel), the system will give priority to using local ventilation equipment for processing without affecting the overall ventilation status of the mine.

[0096] The advantage of this implementation is that it can respond quickly to local events without having to shut down the entire mine or evacuate all personnel. This hierarchical control ensures efficient allocation of system resources and avoids energy waste caused by blindly increasing ventilation. At the same time, precise regional control can reduce wind flow disturbances and prevent gas from spreading between regions, effectively improving mine safety and response speed.

[0097] Implementation method 2: Combining dynamic prediction with preventive regulation;

[0098] Emergencies are often hidden and sudden, so predictive control is an important part of ensuring mine safety. This implementation uses time series models such as long short-term memory networks (LSTM) to analyze and predict real-time data and historical cases in the mine. The LSTM model can capture the trend of parameter changes over time and identify possible early signs before abnormal events occur. For example, if the wind speed in a certain area gradually decreases, the temperature rises, and the gas concentration shows a slow upward trend, the system will predict that the fan may fail and issue a warning instruction in advance.

[0099] When the system predicts that an abnormal event may occur, it will automatically trigger a preventive control strategy. In the early stages of a gas leak, the system may increase the power of the ventilator in advance and open the backup damper to increase ventilation in the area. If the model predicts that the risk of fire is increasing, the system will re-plan the wind flow path to prevent gas accumulation or the spread of fire. At the same time, the personnel dispatch system will send an advance evacuation notice to ensure that workers avoid areas where accidents may occur. These preventive measures can effectively reduce the risk of events worsening and buy more time for rescue.

[0100] This implementation also has the ability to dynamically update the course of events. Even if there are errors in the prediction, the deep learning model can continuously correct the judgment based on new real-time data and dynamically adjust the response strategy. For example, the system may find that the initially predicted fire risk has decreased, so it stops emergency measures and switches to regular ventilation mode. This flexible preventive control significantly improves the mine's resilience and management level, avoiding the possibility of events worsening.

[0101] Implementation 3: Energy efficient multi-stage ventilation mode;

[0102] While ensuring mine safety, how to optimize energy consumption is one of the keys to ventilation system design. This implementation method proposes a multi-stage ventilation mode. After an emergency occurs, it gradually reduces the fan power and adjusts the damper state to achieve a balance between safety and energy efficiency. In the early stage of an emergency, in order to ensure that the air quality in the mine quickly returns to a safe range, the system will instruct all main fans and local fans to run at the highest power to maximize air circulation.

[0103] As the air quality gradually improves, the system will analyze the recovery progress of the event based on the prediction results of the deep learning model and enter the second stage of low-power operation mode. In this stage, the system will gradually reduce the operating power of the fan and close some unnecessary dampers to reduce energy consumption. For example, when the gas concentration drops below the critical value and remains stable, the system will switch to using a lower-power backup fan to maintain air circulation in the area instead of continuing to use a high-power fan. At the same time, the system will close dampers that are not related to the main ventilation path to prevent airflow waste.

[0104] This implementation also includes an intelligent energy consumption optimization mechanism. The system records the effect and energy consumption data of each ventilation adjustment, and continuously optimizes the timing and amplitude of fan power adjustment. For example, if the system finds that long-term high-power operation does not improve the event processing effect, it will shorten the high-power operation time. In addition, after the event is over, the system will formulate a more energy-saving ventilation strategy for similar events in the future based on the feedback data.

[0105] This multi-stage ventilation mode ensures the safety of the mine in emergency situations while minimizing long-term energy consumption. By combining safety and energy efficiency, this implementation not only improves the economic efficiency of mine management, but also enhances the intelligence level of the ventilation system.

[0106] The present invention uses a variety of sensors to monitor the mine environment in real time, and combines deep learning and reinforcement learning algorithms to achieve precise ventilation control. When an emergency (such as a gas leak or fire) occurs, the system can quickly detect and locate the problem area, and dynamically adjust the ventilation mode to concentrate the main airflow in the affected area. At the same time, through precise control of regional classification, the shutdown of the entire mine or the full evacuation of personnel is avoided, and local problems are quickly resolved. This rapid response capability significantly improves the safety of the mine, reduces the risk of event deterioration and spread, and maximizes the protection of the lives of miners. In addition, the precise control strategy avoids unnecessary airflow disturbances, reduces the diffusion of gas in the mine, and helps prevent the occurrence of secondary disasters.

[0107] By adopting time-series deep learning models such as LSTM, the present invention enables the system to predict the development trend of events in advance and adopt preventive control strategies to reduce the occurrence of potential risks. For example, after detecting a decrease in wind speed and a slow increase in gas concentration, the system can increase the fan power in advance and open the spare damper for ventilation to prevent the gas concentration from further increasing. The combination of prediction and prevention enables the system to take emergency measures before an event occurs, buying more time to deal with potential dangers. In addition, the system also supports real-time adjustment strategies. If the initial prediction deviates, the algorithm can quickly correct and redeploy the best solution. This capability makes the mine's response to emergencies more flexible and efficient, avoiding the limitations of traditional management with delayed reactions.

[0108] The present invention adopts a staged ventilation mode. The above scheme not only ensures the safe operation of the mine, but also greatly reduces energy consumption. In the early stage of the event, the system runs the ventilation equipment at high power to quickly reduce the concentration of harmful gases; when the air quality gradually recovers, the system will reduce the fan power and close some unnecessary dampers to reduce unnecessary airflow waste. This scheme records the energy consumption data and response effects of historical events, continuously optimizes the energy consumption level of each stage, and achieves the best balance between safety and energy efficiency. Compared with the traditional full-power ventilation scheme, this multi-stage mode significantly reduces power consumption and equipment wear, reduces the long-term operating costs of the mine, and improves the economy and sustainability of the ventilation system.

[0109] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for optimizing coal mine ventilation and controlling air quality based on adaptive learning, characterized in that: The steps include: Various sensors are deployed in the mine to collect and monitor key environmental parameters in real time, and the collected data is uploaded to the central control system; Compare the collected real-time data with historical data, and divide them into normal working condition data and abnormal working condition data according to the environmental status. Use K-means clustering classification algorithm to identify potential extreme conditions to ensure that subsequent algorithm optimization can cover the control needs under different working conditions. Based on the mine's historical abnormal events, a library of multiple ventilation plans and emergency response strategies is established, including multi-layer ventilation modes to deal with gas surges, fires and equipment failures, and the plan library is regularly updated based on new data; Using reinforcement learning algorithms, we generate preliminary ventilation strategies based on real-time data and suggestions from the plan library, continuously optimize through interactive feedback with historical data, and simulate the adjustment effects in the airflow and air quality model within the mine to obtain the optimal preliminary strategy; Use multiple anomaly detection algorithms to analyze real-time mine data in parallel. Once a data pattern deviates from the normal state, an alarm is triggered, the current preliminary ventilation strategy is interrupted, and emergency response mode is entered; After an emergency occurs, a deep learning algorithm is activated to re-evaluate the current status and predict the development trend of the incident based on historical abnormal data. Based on the prediction results, the ventilation mode is adjusted dynamically in real time to ensure that the air quality in the mine is restored to a safe range in the shortest time possible while minimizing energy consumption.

2. The method for optimizing coal mine ventilation and controlling air quality based on adaptive learning according to claim 1, characterized in that: The specific steps of using K-means clustering algorithm to classify mine environment data are as follows: Extract key features from real-time data collected by sensors, perform outlier detection and noise filtering on sensor data, and eliminate data anomalies caused by sensor false alarms or failures; The preprocessed data also needs to be normalized to map data of different units and dimensions to a unified scale to ensure that the weights of various parameters are balanced in cluster analysis. Finally, the processed data is merged with historical data to form a complete data set. Divide the data set into K clusters. After determining the K value, select the initial cluster center point through random initialization or K-means++ algorithm to reduce the risk of the algorithm falling into the local optimal solution. Assign each piece of data to the nearest cluster center according to the Euclidean distance, and then recalculate the cluster center position based on all the data points assigned to the cluster. Repeat the process of data assignment and cluster center update until the position of the cluster center no longer changes significantly or reaches the set number of iterations. After clustering is completed, different labels are assigned to each cluster, and the characteristic centers of each cluster are analyzed. Isolated data that cannot be classified into regular clusters are marked as abnormal conditions, triggering further detection and alarm.

3. The method for optimizing coal mine ventilation and controlling air quality based on adaptive learning according to claim 1, characterized in that: The specific steps to establish a library of multiple ventilation plans and emergency response strategies are as follows: Collect data on various abnormal events that have occurred in the mine in the past; Different abnormal events are classified into multiple levels according to their severity and impact scope; In the process of building the emergency plan library, all ventilation modes and emergency response measures are encoded in the form of rules to form a modular strategy library; To ensure that the plan library can respond to the ever-changing mine environment, new data and the latest safety incident feedback are regularly incorporated into the analysis and existing plans are optimized.

4. The method for optimizing coal mine ventilation and controlling air quality based on adaptive learning according to claim 1, characterized in that: The specific steps for generating a preliminary ventilation strategy using a reinforcement learning algorithm are as follows: In the reinforcement learning framework, the state space, action space and reward mechanism are first defined. The state space contains the environmental parameters in the mine, the action space refers to the control instructions that can be executed by the ventilation system, and the reward mechanism is designed according to the ventilation effect and safety of the system. Based on the current real-time data, the reinforcement learning algorithm is used to read the historical cases and emergency plans that are closest to the current environment from the plan library as a reference for generating preliminary strategies; After generating the preliminary strategy, we conducted virtual tests in the mine’s airflow and air quality simulation model to verify the effectiveness of the strategy in various extreme scenarios by simulating different working conditions. When the preliminary strategy passes the simulation test, it will be deployed to the actual mine ventilation system and the execution effect will be monitored in real time. If the ventilation effect meets expectations and meets safety standards, the strategy will be marked as qualified and recorded in the plan library for reference in similar scenarios in the future. If deviations occur during execution, the algorithm will adjust the strategy based on the new data to ensure that the ventilation system always remains in the optimal state.

5. The method for optimizing coal mine ventilation and controlling air quality based on adaptive learning according to claim 1, characterized in that: The specific steps of using multiple anomaly monitoring algorithms to analyze real-time mine data in parallel are as follows: In the process of anomaly detection, the mine environment parameters X collected from the sensor are i }={x1,x2,…,x n } is input into the algorithm module, where x i Represents the real-time data of the i-th sensor. In order to ensure the stability and efficiency of the algorithm, the collected data is feature extracted and standardized. Let X∈R m×n Represents the data matrix, where m is the number of samples and n is the dimension of the monitored environmental parameter. The standardized formula is: Among them, μ j and σ j are the mean and standard deviation of parameter j, and the standardized data z ij It is passed to the subsequent detection algorithm to eliminate the influence of different parameter scales; The isolation forest algorithm is used to construct a random tree to evaluate the isolation degree of the sample points. For each sample z i , the isolation forest will generate T random trees, the depth of each tree represents the number of steps required to completely separate the sample points, let sample z i The depth of the t-th tree is H(z i ), then the average depth of all trees is: Combined with the expected tree depth c(n), the anomaly score S(z i ) is calculated as follows: , by setting the threshold α, such as S(z i )>α, it is marked as abnormal.

6. A method for optimizing coal mine ventilation and controlling air quality based on adaptive learning according to claim 5, characterized in that: A class of support vector machines is used to construct boundaries in high-dimensional space to detect abnormal data points. Given a data set Z = {z1, z2, ..., z m }, SVM separates normal data from abnormal data by finding a hyperplane w·z-ρ=0, and the optimization goal is: subjectto:w·z i ≥ρ-ξ i ,ξ i ≥0, where ν is the parameter that controls the abnormality rate, ξ i It is a slack variable used to process data points on the soft boundary. When new sample data falls outside the hyperplane, it is marked as an outlier. Through parallel analysis of isolation forest and SVM, two independent anomaly scores are calculated for each data, namely S IF (z i ) and S SVM (z i ), in order to achieve multi-algorithm fusion, a weighted anomaly scoring strategy is adopted. The specific expression is: S total (z i )=β·S IF (z i )+(1-β)·S SVM (z i ), where β is the algorithm weight parameter, reflecting the importance of isolation forest and SVM in different scenarios. total (z i )>α, the system immediately triggers an alarm, interrupts the current ventilation strategy, enters the emergency response mode, and executes the corresponding plan.

7. The method for optimizing coal mine ventilation and controlling air quality based on adaptive learning according to claim 1, characterized in that: The specific steps to use deep learning algorithms to re-evaluate emergencies and dynamically adjust ventilation modes are as follows: When an emergency is detected in the mine, the latest real-time data is collected immediately; After the initial status assessment, predict the development trend of the emergency through similar cases in historical data; Generate and execute real-time ventilation adjustment instructions based on the prediction results; After adjusting the ventilation mode, feedback data is continuously collected and analyzed to ensure that the air quality gradually returns to a safe range. If any abnormal changes are detected or the strategy execution does not meet expectations, the situation will be immediately re-evaluated through the deep learning algorithm, and the instructions will be automatically optimized and adjusted to achieve secondary or multiple iterative optimizations. In addition, the data and response process of this emergency will be stored in the historical database for reference for similar events in the future and to improve the model's adaptive capabilities.

Images