Coal mining roadway gas monitoring system and method
By deploying gas sensors and machine learning models in coal mining tunnels, real-time monitoring and processing of harmful gases is solved, the problem of single functions of the existing system is solved, gas separation and recycling is realized, and safety and practicality are improved.
Patent Information
- Application Number
- CN202410792659.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-19
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing coal mining tunnel gas monitoring system has a single function when dealing with harmful gases, and is poor in practicality, so it cannot effectively perform gas separation treatment.
The coal mining tunnel gas data acquisition module, data preprocessing module, data feature extraction module, monitoring model training module and alarm and processing system module are used to monitor and preprocess data in real time through gas sensors, and use neural network models to evaluate gas concentration and safety status. Associate and issue an early warning when an abnormality is detected and perform air separation treatment.
Real-time monitoring and separation of harmful gases in coal mining tunnels is realized, the safety of staff is improved, and the practicality of the device is improved through gas recycling.
Smart Images

Figure CN118911768A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of coal mining tunnel gas monitoring, and more specifically, to a coal mining tunnel gas monitoring system and method. Background Art
[0002] Gas monitoring in coal mine tunnels is one of the important measures to ensure safe production in coal mines, mainly including the following aspects:
[0003] Harmful gas monitoring: monitor the concentration of harmful gases in coal mine tunnels, such as methane, carbon monoxide, hydrogen sulfide, etc. These gases are the main risk factors for coal mine accidents, and their concentration exceeding the safety standard may cause serious accidents such as explosions and poisoning.
[0004] Oxygen content monitoring: Monitor the oxygen content in coal mine tunnels to ensure that workers have sufficient oxygen supply to avoid accidents such as suffocation.
[0005] Wind speed and direction monitoring: Monitor wind speed and direction in coal mine tunnels to detect air flow anomalies in a timely manner, ensure the effective operation of the ventilation system, and prevent the accumulation and spread of harmful gases.
[0006] Temperature and humidity monitoring: Monitor temperature and humidity changes in coal mine tunnels to help assess the comfort and safety of the mine environment and take timely measures to prevent accidents caused by excessively high or low temperatures.
[0007] Fire monitoring: Equipped with a fire monitoring system to monitor possible signs of fire in coal mine tunnels, such as smoke, high temperature, etc., to promptly alarm and take measures to prevent the occurrence or spread of fire.
[0008] Safety alarm system: Establish a complete safety alarm system, including sound and light alarms, voice prompts, etc., to ensure that workers can obtain information about coal mine tunnel gas and environment in a timely manner and take necessary response measures.
[0009] Through the monitoring and management of these aspects, the safety and production efficiency of coal mine tunnels can be effectively improved, the risk of accidents can be reduced, and the safety of life and property of workers can be protected.
[0010] The document with the prior art publication number CN105372387A provides a coal mine tunnel gas monitoring system, which can uniformly monitor the gas in the tunnel and manage it in a unified manner without missing any tunnel working conditions, thereby improving the safety of the tunnel and allowing miners to work in a safer and more secure environment.
[0011] Although the above-mentioned prior art solution can achieve the relevant beneficial effects through the structure of the prior art, it still has the following defects: when the device is used, it is not convenient to separate and treat the harmful gases in the tunnel, resulting in its single function and poor practicality.
[0012] In view of this, we propose a coal mining tunnel gas monitoring system and method. Summary of the invention
[0013] 1. Technical problems to be solved
[0014] The purpose of the present application is to provide a coal mining tunnel gas monitoring system and method, which solves the technical problems raised in the above-mentioned background technology and achieves the technical effect of facilitating the separation and treatment of harmful gases in the tunnel.
[0015] 2. Technical solution
[0016] The embodiment of the present application provides a coal mining tunnel gas monitoring system and method, including: a coal mining tunnel gas data acquisition module, a coal mining tunnel gas data preprocessing module, a coal mining tunnel gas data feature extraction module, a coal mining tunnel gas monitoring model training module, and an alarm and processing system module.
[0017] Coal mining tunnel gas data acquisition module: The coal mining tunnel gas data acquisition module deploys gas sensors inside the coal mining tunnel to monitor the concentration data of harmful gases such as methane, carbon monoxide, and hydrogen sulfide in real time;
[0018] Coal mining tunnel gas data preprocessing module: The coal mining tunnel gas data preprocessing module preprocesses the gas concentration data collected by the sensor, including data interpolation, anomaly detection, etc., to ensure data quality and consistency;
[0019] Coal mining tunnel gas data feature extraction module: The coal mining tunnel gas data feature extraction module extracts the features of gas concentration data, such as mean value, variance, trend, etc., for subsequent model training and analysis;
[0020] Coal mining tunnel gas monitoring model training module: The coal mining tunnel gas monitoring model training module selects a suitable machine learning model to establish a correlation model between gas concentration and coal mining tunnel safety status;
[0021] Alarm and processing system module: When the alarm and processing system module detects that the gas concentration is abnormal or exceeds the safety threshold, the system should promptly issue a warning signal and process the air.
[0022] As an optional solution to the technical solution of the present application document, the coal mining tunnel gas data acquisition module deploys gas sensors inside the coal mining tunnel to monitor the concentration data of harmful gases such as methane, carbon monoxide, and hydrogen sulfide in real time. The methane concentration data is detected by the methane sensor using the infrared absorption principle, the carbon monoxide sensor: an electrochemical or semiconductor sensor is used to detect the concentration data of carbon monoxide, and the hydrogen sulfide sensor: an electrochemical or semiconductor sensor is usually used to detect its concentration data.
[0023] As an optional solution of the technical solution of this application document, the coal mining tunnel gas data preprocessing module preprocesses the gas concentration data collected by the sensor, including data interpolation, anomaly detection, etc., to ensure data quality and consistency. The data interpolation: when the sensor fails or the data transmission is interrupted, data may be missing, and the mean interpolation method is used to fill the missing values;
[0024] The anomaly detection is used to identify and process data that does not conform to the normal pattern through statistical methods (such as Z-score, IQR, etc.).
[0025] As an optional solution of the technical solution of this application document, the coal mining tunnel gas data feature extraction module extracts the features of the gas concentration data, such as the mean value, variance, trend, etc., for subsequent model training and analysis. The mean value: calculates the average value of the gas concentration data, which can reflect the overall concentration level of the gas in the tunnel. If the average value exceeds the safety threshold, it may mean that there is a gas leak or other safety hazards;
[0026] The variance is used to measure the degree of dispersion of gas concentration data. A large variance means that the data fluctuates greatly and there may be local changes in gas concentration.
[0027] The trend: By analyzing the change trend of gas concentration data over time, possible future changes in gas concentration can be predicted.
[0028] As an optional solution to the technical solution of the present application document, the coal mining tunnel gas monitoring model training module selects a neural network machine learning model to establish a correlation model between gas concentration and the safety status of coal mining tunnels. Through training, the model can learn the correlation between gas concentration characteristics and potential risks, and evaluate the gas safety risks in coal mining tunnels.
[0029] As an optional solution of the technical solution of this application document, when the alarm and processing system module detects that the gas concentration is abnormal or exceeds the safety threshold, the system should promptly issue a warning signal to notify relevant personnel so that they can respond quickly and take additional safety measures, and process the air and separate harmful gases in the air.
[0030] A coal mining tunnel gas monitoring system and method, comprising the following steps:
[0031] S1. When used in coal mining tunnels, gas sensors are deployed inside the coal mining tunnels using the coal mining tunnel gas data acquisition module to monitor the concentration data of harmful gases such as methane, carbon monoxide, and hydrogen sulfide in real time. The methane sensor uses the infrared absorption principle to detect the concentration data of methane, the carbon monoxide sensor uses an electrochemical or semiconductor sensor to detect the concentration data of carbon monoxide, and the hydrogen sulfide sensor usually uses an electrochemical or semiconductor sensor to detect its concentration data;
[0032] S2. Then the coal mining tunnel gas data preprocessing module preprocesses the gas concentration data collected by the sensor, including data interpolation, anomaly detection, etc., to ensure data quality and consistency. Data interpolation: When the sensor fails or the data transmission is interrupted, data may be missing. The mean interpolation method is used to fill the missing values;
[0033] Anomaly detection: Anomaly detection is used to identify and process data that does not conform to the normal pattern through statistical methods (such as Z-score, IQR, etc.);
[0034] S3. Extract the features of gas concentration data, such as mean value, variance, trend, etc., through the coal mining tunnel gas data feature extraction module for subsequent model training and analysis. Average value: Calculate the average value of gas concentration data to reflect the overall concentration level of gas in the tunnel. If the average value exceeds the safety threshold, it may mean that there is a gas leak or other safety hazard.
[0035] Variance: Variance is used to measure the degree of dispersion of gas concentration data. A larger variance means that the data fluctuates more and there may be local changes in gas concentration.
[0036] Trend: By analyzing the trend of gas concentration data over time, it is possible to predict possible changes in gas concentration in the future;
[0037] S4. Using the coal mining tunnel gas monitoring model training module, a neural network machine learning model is selected to establish a correlation model between gas concentration and the safety status of the coal mining tunnel. Through training, the model can learn the correlation between gas concentration characteristics and potential risks, and evaluate the gas safety risks in the coal mining tunnel;
[0038] S5. Then the alarm and processing system module, when it is detected that the gas concentration is abnormal or exceeds the safety threshold, the system should promptly issue a warning signal to notify relevant personnel so that they can respond quickly and take additional safety measures, and process the air to separate the harmful gases in the air.
[0039] 3. Beneficial effects
[0040] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
[0041] 1. This application adopts technical means such as a coal mining tunnel gas data acquisition module, which effectively solves the technical problems in the prior art, and further realizes the real-time collection of coal mining tunnel gas data through sensor equipment when coal mining is carried out in the coal mining tunnel, and the use of a coal mining tunnel gas monitoring model to analyze the data. When an abnormal gas concentration is detected or exceeds a safety threshold, the system should promptly issue an early warning signal to notify relevant personnel so that they can respond quickly and take additional safety measures, and process the air to separate harmful gases in the air.
[0042] 2. This application sets up a harmful gas separation mechanism. After the tunnel air is sucked into the tunnel gas collection box through the fan blades, the polymer membrane cylinder is used to separate the methane, carbon monoxide, hydrogen sulfide and other harmful gases in the air, thereby reducing the content of harmful gases in the air, ensuring the safety of the staff, and realizing the functional diversification of the device.
[0043] 3. The present application sets up a gas recovery and utilization mechanism. When the fan blades suck and separate the air, the separated harmful gases are filled into the gas tank through the suction and pressure plug for collection and utilization. Gases such as methane, carbon monoxide, and hydrogen sulfide can be utilized as resources, thereby improving the practicality of the device. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] Figure 1 A schematic diagram of the overall structure of a gas monitoring process of a coal mining tunnel gas monitoring system and method disclosed in a preferred embodiment of the present application;
[0045] Figure 2 This is a schematic diagram of the overall structure of a coal mining tunnel gas monitoring system and method disclosed in a preferred embodiment of the present application;
[0046] Figure 3 A schematic cross-sectional view of the overall structure of a coal mining tunnel gas monitoring system and method disclosed in a preferred embodiment of the present application;
[0047] Figure 4A schematic cross-sectional view of a tunnel gas collection box structure of a coal mining tunnel gas monitoring system and method disclosed in a preferred embodiment of the present application;
[0048] Figure 5 A schematic diagram of a cross-sectional expansion of the harmful gas separation mechanism structure of a coal mining tunnel gas monitoring system and method disclosed in a preferred embodiment of the present application;
[0049] Figure 6 A schematic cross-sectional view of the gas recovery mechanism structure of a coal mining tunnel gas monitoring system and method disclosed in a preferred embodiment of the present application;
[0050] Explanation of the numbers in the figure: 1. Equipment seat; 2. Tunnel gas collection box; 3. Harmful gas separation mechanism; 4. Gas recovery and utilization mechanism; 5. Gas tank; 201. Motor; 202. Fan blade; 203. Universal joint; 204. Cam; 301. Gas guide seat; 302. Polymer membrane cylinder; 303. Limit sealing cover; 304. Sealing plug; 305. Exhaust pipe; 401. Piston seat; 402. Pumping plug; 403. Spring; 404. Contact connecting rod; 405. Connecting sleeve. DETAILED DESCRIPTION
[0051] The present application is further described in detail below in conjunction with the accompanying drawings.
[0052] Reference Figure 1 A coal mining tunnel gas monitoring system and method, comprising: a coal mining tunnel gas data acquisition module, a coal mining tunnel gas data preprocessing module, a coal mining tunnel gas data feature extraction module, a coal mining tunnel gas monitoring model training module, and an alarm and processing system module.
[0053] Coal mining tunnel gas data acquisition module: The coal mining tunnel gas data acquisition module deploys gas sensors inside the coal mining tunnel to monitor the concentration data of harmful gases such as methane, carbon monoxide, and hydrogen sulfide in real time;
[0054] Coal mining tunnel gas data preprocessing module: The coal mining tunnel gas data preprocessing module preprocesses the gas concentration data collected by the sensor, including data interpolation, anomaly detection, etc., to ensure data quality and consistency;
[0055] Coal mining tunnel gas data feature extraction module: The coal mining tunnel gas data feature extraction module extracts the features of gas concentration data, such as mean value, variance, trend, etc., for subsequent model training and analysis;
[0056] Coal mining tunnel gas monitoring model training module: The coal mining tunnel gas monitoring model training module selects a suitable machine learning model to establish a correlation model between gas concentration and coal mining tunnel safety status;
[0057] Alarm and processing system module: When the alarm and processing system module detects that the gas concentration is abnormal or exceeds the safety threshold, the system should promptly issue a warning signal and process the air.
[0058] As an optional solution to the technical solution of the present application document, the coal mining tunnel gas data acquisition module deploys gas sensors inside the coal mining tunnel to monitor the concentration data of harmful gases such as methane, carbon monoxide, and hydrogen sulfide in real time. The methane concentration data is detected by the methane sensor using the infrared absorption principle, the carbon monoxide sensor: an electrochemical or semiconductor sensor is used to detect the concentration data of carbon monoxide, and the hydrogen sulfide sensor: an electrochemical or semiconductor sensor is usually used to detect its concentration data.
[0059] By adopting the above technical solution, methane concentration exceeds 5% in the air and becomes explosive. The U.S. Environmental Protection Agency (EPA) stipulates that the safety standard concentration of carbon monoxide in the air is 9 parts per million (9ppm), and the U.S. Occupational Safety and Health Administration (OSHA) stipulates that the concentration of hydrogen sulfide should not exceed 100 parts per million (100ppm), and the exposure limit in a short period of time is 200 parts per million (200ppm).
[0060] As an optional solution of the technical solution of this application document, the coal mining tunnel gas data preprocessing module preprocesses the gas concentration data collected by the sensor, including data interpolation, anomaly detection, etc., to ensure data quality and consistency. The data interpolation: when the sensor fails or the data transmission is interrupted, data may be missing, and the mean interpolation method is used to fill the missing values;
[0061] The anomaly detection is used to identify and process data that does not conform to the normal pattern through statistical methods (such as Z-score, IQR, etc.).
[0062] As an optional solution of the technical solution of this application document, the coal mining tunnel gas data feature extraction module extracts the characteristics of gas concentration data, such as mean value, variance, trend, etc., for subsequent model training and analysis. The mean value: Calculate the mean value of gas concentration data, which can reflect the overall concentration level of gas in the tunnel. If the mean value exceeds the safety threshold, it may mean that there is a gas leak or other safety hazard; the mean value is the sum of all values in the data set divided by the number of values in the data set. The formula is as follows:
[0063] [\text{Mean}=\frac{1}{n}\sum_{i=1}^{n}x_i]
[0064] Where (n) is the number of samples in the dataset and (x_i) is the value of the (i)th sample.
[0065] The variance: Variance is used to measure the degree of dispersion of gas concentration data. A larger variance means that the data fluctuates more and there may be local changes in gas concentration. Variance measures the degree of deviation between each value in the data set and the average value. The formula is as follows:
[0066] [\text{Variance}=\frac{1}{n}
[0067] \sum_{i=1}^{n}
[0068] (x_i-\text{Mean})^2]
[0069] Where (n) is the number of samples in the dataset, (x_i) is the value of the (i)th sample, and (\text{Mean}) is the mean of the dataset.
[0070] The trend: By analyzing the change trend of gas concentration data over time, possible future changes in gas concentration can be predicted.
[0071] By using the above technical solution, the trend is approximated by the slope of the linear regression:
[0072] [\text{Slope}=\frac{n(\sum_{i=1}^{n}x_iy_i)-(\sum_{i=1}^{n}x_i)(\sum_{i=1}^{n}y_i)}{n(\sum_{i=1}^{n}x_i^2)-(\sum_{i=1}^{n}x_i)^2}]
[0073] Where (n) is the number of samples in the data set, (x_i) is the time or sequence number, and (y_i) is the corresponding gas concentration data.
[0074] As an optional solution to the technical solution of the present application document, the coal mining tunnel gas monitoring model training module selects a neural network machine learning model to establish a correlation model between gas concentration and the safety status of coal mining tunnels. Through training, the model can learn the correlation between gas concentration characteristics and potential risks, and evaluate the gas safety risks in coal mining tunnels.
[0075] As an optional solution of the technical solution of this application document, when the alarm and processing system module detects that the gas concentration is abnormal or exceeds the safety threshold, the system should promptly issue a warning signal to notify relevant personnel so that they can respond quickly and take additional safety measures, and process the air and separate harmful gases in the air.
[0076] A coal mining tunnel gas monitoring system and method, comprising the following steps:
[0077] S1. When used in coal mining tunnels, gas sensors are deployed inside the coal mining tunnels using the coal mining tunnel gas data acquisition module to monitor the concentration data of harmful gases such as methane, carbon monoxide, and hydrogen sulfide in real time. The methane sensor uses the infrared absorption principle to detect the concentration data of methane, the carbon monoxide sensor uses an electrochemical or semiconductor sensor to detect the concentration data of carbon monoxide, and the hydrogen sulfide sensor usually uses an electrochemical or semiconductor sensor to detect its concentration data;
[0078] S2. Then the coal mining tunnel gas data preprocessing module preprocesses the gas concentration data collected by the sensor, including data interpolation, anomaly detection, etc., to ensure data quality and consistency. Data interpolation: When the sensor fails or the data transmission is interrupted, data may be missing. The mean interpolation method is used to fill the missing values;
[0079] Anomaly detection: Anomaly detection is used to identify and process data that does not conform to the normal pattern through statistical methods (such as Z-score, IQR, etc.);
[0080] S3. Extract the features of gas concentration data, such as mean value, variance, trend, etc., through the coal mining tunnel gas data feature extraction module for subsequent model training and analysis. Average value: Calculate the average value of gas concentration data to reflect the overall concentration level of gas in the tunnel. If the average value exceeds the safety threshold, it may mean that there is a gas leak or other safety hazard.
[0081] Variance: Variance is used to measure the degree of dispersion of gas concentration data. A larger variance means that the data fluctuates more and there may be local changes in gas concentration.
[0082] Trend: By analyzing the trend of gas concentration data over time, it is possible to predict possible changes in gas concentration in the future;
[0083] S4. Using the coal mining tunnel gas monitoring model training module, a neural network machine learning model is selected to establish a correlation model between gas concentration and the safety status of the coal mining tunnel. Through training, the model can learn the correlation between gas concentration characteristics and potential risks, and evaluate the gas safety risks in the coal mining tunnel;
[0084] S5. Then the alarm and processing system module, when it is detected that the gas concentration is abnormal or exceeds the safety threshold, the system should promptly issue a warning signal to notify relevant personnel so that they can respond quickly and take additional safety measures, and process the air to separate the harmful gases in the air.
[0085] Reference Figure 2 and Figure 3 A coal mining tunnel gas monitoring system and method, comprising an equipment base 1, a tunnel gas collection box 2, a harmful gas separation mechanism 3, a gas recovery mechanism 4, and a gas tank 5,
[0086] A tunnel gas collection box 2 is fixedly connected to the equipment base 1, a harmful gas separation mechanism 3 is fixedly connected to the tunnel gas collection box 2, a gas recovery mechanism 4 is fixedly connected to the tunnel gas collection box 2, and a gas tank 5 is placed on the equipment base 1.
[0087] Reference Figure 4 A methane sensor, a carbon monoxide sensor, and a hydrogen sulfide sensor are installed on the tunnel gas collection box 2. A motor 201 is installed at the opening of the tunnel gas collection box 2. A fan blade 202 is fixedly connected to the output end of the motor 201. A universal joint 203 is connected to one side of the fan blade 202. The other end of the universal joint 203 extends into the tunnel gas collection box 2 and is connected to a cam 204. The fan blade 202 speeds up the air flow and improves the monitoring efficiency.
[0088] Reference Figure 5 The harmful gas separation mechanism 3 includes a gas guide seat 301, the input end of the gas guide seat 301 is connected to the opening of the tunnel gas collection box 2, a polymer membrane cylinder 302 is movably inserted on the gas guide seat 301, a limited sealing cover 303 is threadedly provided on the gas guide seat 301, an outlet pipe 305 is connected to one side of the gas guide seat 301, and the other end of the outlet pipe 305 extends to the outside of the tunnel gas collection box 2, and a sealing plug 304 is slidably provided on the inner wall of the outlet pipe 305. The polymer membrane cylinder 302 can be disassembled for easy cleaning and use. The sealing plug 304 realizes intermittent exhaust and achieves a full filtering effect.
[0089] Reference Figure 6 The gas recovery mechanism 4 includes a piston seat 401, a pumping plug 402 is provided in a sliding manner through the inner wall of the piston seat 401, a spring 403 is connected between the pumping plug 402 and the inner wall of the piston seat 401, a contact connecting rod 404 is connected to the pumping plug 402, the outer end of the contact connecting rod 404 is movably contacted with the cam 204, one end of the contact connecting rod 404 is connected to the sealing plug 304, the output end of the piston seat 401 extends to the outside of the tunnel gas collection box 2 and is threadedly connected with a connecting sleeve 405, and the other end of the connecting sleeve 405 is threadedly connected with the output end of the gas tank 5. A one-way valve is installed in the input and output of the piston seat 401.
[0090] The implementation principle of a coal mining tunnel gas monitoring system and method according to the embodiment of the present application is as follows: when used in a coal mining tunnel, the device is placed in the tunnel, and the motor 201 is used to drive the fan blade 202 to rotate, and the air is sucked into the polymer membrane cylinder 302 for methane, carbon monoxide, and hydrogen sulfide separation treatment. At this time, the fan blade 202 is used to drive the cam 204 connected to the universal joint 203 to rotate, and the spring 403 drives the pumping and pressure plug 402 to move back and forth, so that the methane, carbon monoxide, hydrogen sulfide and other harmful gases in the tunnel gas collection box 2 are sucked into the piston seat 401, and injected into the gas tank 5 for collection and treatment. At the same time, when the pumping and pressure plug 402 moves back and forth, it drives the sealing plug 304 to open and close, so as to realize the intermittent discharge of the air in the polymer membrane cylinder 302;
[0091] Gas sensors are deployed inside the coal mining tunnels using the coal mining tunnel gas data acquisition module to monitor the concentration data of harmful gases such as methane, carbon monoxide, and hydrogen sulfide in real time. The methane sensor uses the infrared absorption principle to detect the concentration data of methane. The carbon monoxide sensor uses an electrochemical or semiconductor sensor to detect the concentration data of carbon monoxide. The hydrogen sulfide sensor usually uses an electrochemical or semiconductor sensor to detect its concentration data.
[0092] Then the coal mining tunnel gas data preprocessing module preprocesses the gas concentration data collected by the sensor, including data interpolation, anomaly detection, etc., to ensure data quality and consistency. Data interpolation: When the sensor fails or the data transmission is interrupted, data may be missing. The mean interpolation method is used to fill the missing values;
[0093] Anomaly detection: Anomaly detection is used to identify and process data that does not conform to the normal pattern through statistical methods such as Z-score and IQR.
[0094] The coal mining tunnel gas data feature extraction module is used to extract the features of gas concentration data, such as mean value, variance, trend, etc., for subsequent model training and analysis. Average value: Calculate the average value of gas concentration data to reflect the overall concentration level of gas in the tunnel. If the average value exceeds the safety threshold, it may mean that there is a gas leak or other safety hazard.
[0095] Variance: Variance is used to measure the degree of dispersion of gas concentration data. A larger variance means that the data fluctuates more and there may be local changes in gas concentration.
[0096] Trend: By analyzing the trend of gas concentration data over time, it is possible to predict possible changes in gas concentration in the future;
[0097] The coal mining tunnel gas monitoring model training module is used to select a neural network machine learning model to establish a correlation model between gas concentration and the safety status of coal mining tunnels. Through training, the model can learn the correlation between gas concentration characteristics and potential risks, and evaluate the gas safety risks in coal mining tunnels.
[0098] Then, when the alarm and processing system module detects that the gas concentration is abnormal or exceeds the safety threshold, the system should promptly issue a warning signal to notify relevant personnel so that they can respond quickly and take additional safety measures, and process the air to separate the harmful gases in the air.
Claims
1. A coal mining tunnel gas monitoring system and method, comprising: a coal mining tunnel gas data acquisition module, a coal mining tunnel gas data preprocessing module, a coal mining tunnel gas data feature extraction module, a coal mining tunnel gas monitoring model training module, and an alarm and processing system module, characterized in that: Coal mining tunnel gas data acquisition module: The coal mining tunnel gas data acquisition module deploys gas sensors inside the coal mining tunnel to monitor the concentration data of harmful gases such as methane, carbon monoxide, and hydrogen sulfide in real time; Coal mining tunnel gas data preprocessing module: The coal mining tunnel gas data preprocessing module preprocesses the gas concentration data collected by the sensor, including data interpolation, anomaly detection, etc., to ensure data quality and consistency; Coal mining tunnel gas data feature extraction module: The coal mining tunnel gas data feature extraction module extracts the features of gas concentration data, such as mean value, variance, trend, etc., for subsequent model training and analysis; Coal mining tunnel gas monitoring model training module: The coal mining tunnel gas monitoring model training module selects a suitable machine learning model to establish a correlation model between gas concentration and coal mining tunnel safety status; Alarm and processing system module: When the alarm and processing system module detects that the gas concentration is abnormal or exceeds the safety threshold, the system should promptly issue a warning signal and process the air.
2. The coal mining tunnel gas monitoring system and method according to claim 1, characterized in that: The coal mining tunnel gas data acquisition module deploys gas sensors inside the coal mining tunnel to monitor the concentration data of harmful gases such as methane, carbon monoxide, and hydrogen sulfide in real time. The methane sensor uses the infrared absorption principle to detect the concentration data of methane, the carbon monoxide sensor uses an electrochemical or semiconductor sensor to detect the concentration data of carbon monoxide, and the hydrogen sulfide sensor usually uses an electrochemical or semiconductor sensor to detect its concentration data.
3. The coal mining tunnel gas monitoring system and method according to claim 1, characterized in that: The coal mining tunnel gas data preprocessing module preprocesses the gas concentration data collected by the sensor, including data interpolation, anomaly detection, etc., to ensure data quality and consistency. The data interpolation: when the sensor fails or the data transmission is interrupted, data may be missing, and the mean interpolation method is used to fill the missing values; The anomaly detection is used to identify and process data that does not conform to the normal pattern through statistical methods (such as Z-score, IQR, etc.).
4. The coal mining tunnel gas monitoring system and method according to claim 1, characterized in that: The coal mining tunnel gas data feature extraction module extracts the features of the gas concentration data, such as the mean value, variance, trend, etc., for subsequent model training and analysis. The mean value: the mean value of the gas concentration data is calculated to reflect the overall concentration level of the gas in the tunnel. If the mean value exceeds the safety threshold, it may mean that there is a gas leak or other safety hazard. The variance is used to measure the degree of dispersion of gas concentration data. A large variance means that the data fluctuates greatly and there may be local changes in gas concentration. The trend: By analyzing the change trend of gas concentration data over time, possible future changes in gas concentration can be predicted.
5. The coal mining tunnel gas monitoring system and method according to claim 1, characterized in that: The coal mining tunnel gas monitoring model training module selects a neural network machine learning model to establish a correlation model between gas concentration and the safety status of the coal mining tunnel. Through training, the model can learn the correlation between gas concentration characteristics and potential risks, and evaluate the gas safety risks in the coal mining tunnel.
6. The coal mining tunnel gas monitoring system and method according to claim 1, characterized in that: When the alarm and processing system module detects that the gas concentration is abnormal or exceeds the safety threshold, the system should promptly issue a warning signal to notify relevant personnel so that they can respond quickly and take additional safety measures, and process the air to separate harmful gases in the air.
7. A coal mining tunnel gas monitoring system and method, comprising the following steps: S1. When used in coal mining tunnels, gas sensors are deployed inside the coal mining tunnels using the coal mining tunnel gas data acquisition module to monitor the concentration data of harmful gases such as methane, carbon monoxide, and hydrogen sulfide in real time. The methane sensor uses the infrared absorption principle to detect the concentration data of methane, the carbon monoxide sensor uses an electrochemical or semiconductor sensor to detect the concentration data of carbon monoxide, and the hydrogen sulfide sensor usually uses an electrochemical or semiconductor sensor to detect its concentration data; S2. Then the coal mining tunnel gas data preprocessing module preprocesses the gas concentration data collected by the sensor, including data interpolation, anomaly detection, etc., to ensure data quality and consistency. Data interpolation: When the sensor fails or the data transmission is interrupted, data may be missing. The mean interpolation method is used to fill the missing values; Anomaly detection: Anomaly detection is used to identify and process data that does not conform to the normal pattern through statistical methods (such as Z-score, IQR, etc.); S3. Extract the features of gas concentration data, such as mean value, variance, trend, etc., through the coal mining tunnel gas data feature extraction module for subsequent model training and analysis. Average value: Calculate the average value of gas concentration data to reflect the overall concentration level of gas in the tunnel. If the average value exceeds the safety threshold, it may mean that there is a gas leak or other safety hazard. Variance: Variance is used to measure the degree of dispersion of gas concentration data. A larger variance means that the data fluctuates more and there may be local changes in gas concentration. Trend: By analyzing the trend of gas concentration data over time, it is possible to predict possible changes in gas concentration in the future; S4. Using the coal mining tunnel gas monitoring model training module, a neural network machine learning model is selected to establish a correlation model between gas concentration and the safety status of the coal mining tunnel. Through training, the model can learn the correlation between gas concentration characteristics and potential risks, and evaluate the gas safety risks in the coal mining tunnel; S5. Then the alarm and processing system module, when it is detected that the gas concentration is abnormal or exceeds the safety threshold, the system should promptly issue a warning signal to notify relevant personnel so that they can respond quickly and take additional safety measures, and process the air to separate the harmful gases in the air.
Citation Information
Patent Citations
Mine harmful gas detection alarm system and control method thereof
CN117334016A
Roadway gas concentration prediction method based on model and big data dual drive
CN117371813A
Safety monitoring and prevention system
CN117857601A
Deep recurrent neural network-based coal and gas outburst accident prediction and recognition method
WO2023056695A1
