Coal seam drilling gas concentration monitoring method and system based on multi-sensor fusion

Abstract

The present application discloses a coal seam drilling gas concentration monitoring method and system based on multi-sensor fusion, comprising: analyzing the gas concentration risks of different depth layers according to preset coal seam drilling information, and dividing the coal seams into multiple levels; for each level of coal seam, dividing the coal seam into multiple monitoring areas by analyzing the gas concentration gradients in different areas; arranging multiple sensors in each monitoring area, and building a sensor network by analyzing the communication relationship between the sensors; performing concentration monitoring according to the data collected by each sensor network through a preset concentration safety monitoring model, and issuing an early warning when abnormal gas concentration results are shown; the present invention divides the coal seam into layers and areas, arranges a sensor network in each area to monitor the gas concentration, and performs real-time correction on the collected data between the sensor networks, thereby improving the accuracy of the gas concentration monitoring results and effectively preventing the occurrence of gas accidents.

Description

Technical Field

[0001] The present invention relates to the technical field of coal mine monitoring, and in particular to a method and system for monitoring coal seam borehole gas concentration based on multi-sensor fusion. Background Art

[0002] The traditional method of monitoring coal seam gas concentration through coal seam drilling directly monitors the gas concentration of the coal seam, lacks stratified and regional monitoring of the coal seam, and the measured results cannot accurately reflect the actual gas concentration at different locations of the coal seam, resulting in inaccurate monitoring results; in the process of sensor data transmission, the poor signal transmission quality of the underground coal seam is not taken into account, resulting in insufficient accuracy of the collected data and difficulty in obtaining true gas concentration data.

[0003] The existing technology has the following problems: there is a lack of stratified and regional monitoring of coal seams, and the measured results cannot accurately reflect the actual gas concentration at different locations of the coal seams, resulting in inaccurate monitoring results; in the process of sensor data transmission, the poor signal transmission quality of underground coal seams is not taken into account, resulting in insufficient accuracy of the collected data; in order to solve at least one of the above problems, the present invention proposes a coal seam borehole gas concentration monitoring method and system based on multi-sensor fusion. Summary of the Invention

[0004] In response to the shortcomings of the existing technology, the main purpose of the present invention is to provide a method and system for monitoring coal seam borehole gas concentration based on multi-sensor fusion, which can effectively solve the problems in the background technology. The specific technical solutions of the present invention are as follows:

[0005] The coal seam drilling gas concentration monitoring method based on multi-sensor fusion includes:

[0006] Based on the preset coal seam drilling information, the gas concentration risk of different depth layers is analyzed and divided into multiple levels of coal seams;

[0007] For each coal seam, multiple monitoring areas are divided by analyzing the gas concentration gradient in different areas;

[0008] Multiple sensors are set up in each monitoring area. By analyzing the communication relationship between sensors and combining the voting results between sensors, the master sensors and slave sensors are divided and a sensor network is constructed.

[0009] Based on the data collected by each sensor network, concentration monitoring is carried out through the preset concentration safety monitoring model. When abnormal results are found in the gas concentration, an early warning is issued to realize gas concentration monitoring.

[0010] Specifically, the gas concentration risk of different depth layers is analyzed based on the preset coal seam drilling information, and the coal seams are divided into multiple levels, including:

[0011] According to the preset drilling information of each layer, the coal seam permeability, historical gas emission and drilling trajectory data are obtained;

[0012] Based on the coal seam permeability, historical gas emission volume and drilling trajectory data, the coal seams are vertically clustered to obtain first-risk coal seams, second-risk coal seams and third-risk coal seams;

[0013] When the gas concentration increase rate of the coal seam exceeds the preset concentration change threshold, the coal seam is upgraded;

[0014] When the gas concentration reduction rate of the coal seam exceeds the preset concentration change threshold, the coal seam will be downgraded.

[0015] Specifically, for each coal seam, multiple monitoring areas are divided by analyzing the gas concentration gradient in different areas, including:

[0016] For each coal seam, the initial grid size is set according to the preset drilling spacing;

[0017] Dividing the coal seam into grids according to the initial grid size to obtain a plurality of grid areas;

[0018] According to the gas concentration of each grid area, calculate the gas concentration gradient value between adjacent grids;

[0019] When the gas concentration gradient value is less than a preset gradient threshold, the corresponding adjacent grids are merged to obtain multiple monitoring areas.

[0020] Specifically, multiple sensors are set up in each monitoring area, and by analyzing the communication relationship between the sensors and the voting results between the sensors, the master sensors and slave sensors are divided, and a sensor network is constructed, including:

[0021] Multiple sensors are set up in each monitoring area, and the master sensors and slave sensors are divided according to the communication relationship between different sensors and the voting results between sensors;

[0022] According to the positional relationship and functional dependency of the master sensor and the slave sensor, a communication link is established between the master sensor and the slave sensor to obtain a sensor network.

[0023] Specifically, multiple sensors are set in each monitoring area, and master sensors and slave sensors are divided according to the communication relationship between different sensors and the voting results between the sensors, including:

[0024] In each monitoring area, the initial main sensor is set according to the performance data of each sensor;

[0025] Within a preset time period, the weight value of each sensor is calculated through a preset dynamic weight calculation model;

[0026] When the weight value of the initial main sensor is less than a preset first weight threshold, sensors with weight values ​​greater than a preset second weight threshold are selected as a candidate sensor set, wherein the preset first weight threshold is less than the preset second weight threshold;

[0027] According to the sensor performance in the candidate sensor set, each sensor votes for each sensor in the candidate sensor set, and the sensor with the most votes is used as the update master sensor;

[0028] The initial master sensor acts as a slave sensor and communicates with the update master sensor.

[0029] Specifically, the sensor network is obtained by establishing a communication link between the master sensor and the slave sensor based on the positional relationship and functional dependency between the master sensor and the slave sensor, including:

[0030] Construct an adjacency matrix based on the location distance of each sensor;

[0031] Connecting two sensors with the shortest distance between them according to the adjacency matrix;

[0032] When the number of sensors communicating between the slave sensor and the master sensor is greater than a preset number threshold, the communication link is updated, and a path with a smaller number of sensors than the preset number threshold and the shortest overall communication link distance is selected as the updated communication link;

[0033] According to the updated communication link, communication between each slave sensor and the master sensor is established to obtain a sensor network.

[0034] Specifically, the gas concentration monitoring is performed based on the data collected by each sensor network through a preset concentration safety monitoring model, and an early warning is issued when an abnormal result is found in the gas concentration, thereby achieving gas concentration monitoring, including:

[0035] According to the data collected by each sensor network, the sensor nodes with data transmission failure in the sensor network are detected and the data is corrected to obtain multi-sensor corrected data;

[0036] Performing hierarchical fusion on the multi-sensor correction data to obtain fused data;

[0037] According to the fused data, concentration monitoring is performed through a preset concentration safety monitoring model, and an early warning is issued when an abnormal result occurs in the gas concentration, thereby realizing gas concentration monitoring.

[0038] Specifically, the method of detecting sensor nodes in the sensor network where data transmission fails and correcting the data based on the data collected by each sensor network to obtain multi-sensor corrected data includes:

[0039] According to the data collected by each sensor network, the sensor nodes whose data packet loss rate is greater than the preset loss threshold are regarded as failed sensor nodes;

[0040] The spatial correction value is obtained by calculating the distance weighted values ​​of a preset number of adjacent non-failed sensor nodes of the failed sensor node;

[0041] According to the historical data collected by the failed sensor node, the data is predicted through the preset trend prediction model to obtain the predicted value;

[0042] The spatial correction value and the predicted value are fused by using preset weights to obtain multi-sensor correction data.

[0043] Specifically, the step of performing hierarchical fusion on the multi-sensor correction data to obtain fused data includes:

[0044] According to the distance between the master sensor node and each slave sensor node, the data of each slave sensor in the multi-sensor correction data is corrected to obtain the slave sensor correction data;

[0045] Fusing the master sensor data with the slave sensor correction data to obtain regional fusion data;

[0046] The gas concentration in the regional fusion data is corrected for the data with different gas concentration gradient trends from the adjacent areas to obtain the fusion data.

[0047] The coal seam borehole gas concentration monitoring system based on multi-sensor fusion is used to implement the coal seam borehole gas concentration monitoring method based on multi-sensor fusion, including:

[0048] The coal seam classification module analyzes the gas concentration risk of different depth layers based on the preset coal seam drilling information and divides the coal seams into multiple levels;

[0049] The regional division module divides each coal seam into multiple monitoring areas by analyzing the gas concentration gradient in different areas;

[0050] The sensor network construction module sets up multiple sensors in each monitoring area, analyzes the communication relationship between sensors and combines the voting results between sensors to divide the master sensors and slave sensors, and builds a sensor network;

[0051] The gas concentration monitoring module monitors the gas concentration based on the data collected by each sensor network through a preset concentration safety monitoring model, and issues an early warning when abnormal gas concentration results are detected, thereby achieving gas concentration monitoring.

[0052] Compared with the prior art, this application has the following beneficial effects:

[0053] This application divides the coal seams into layers and regions, sets up a sensor network in each region to monitor the gas concentration, and performs real-time correction on the collected data between the sensor networks. It is possible to obtain data that accurately reflects the changes in gas concentration in different regions, identify the gas concentration based on accurate monitoring data, improve the accuracy of gas concentration monitoring results, effectively prevent the occurrence of gas accidents, and ensure the safety of coal miners and the safe and stable operation of coal mine production. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is a workflow diagram of the coal seam drilling gas concentration monitoring method based on multi-sensor fusion in Example 1 of the present invention;

[0055] Figure 2 This is a schematic diagram of the division of coal seam monitoring areas in Example 1 of the present invention;

[0056] Figure 3 A schematic diagram of the sensor network construction in Example 1 of the present invention;

[0057] Figure 4 This is a structural diagram of a coal seam drilling gas concentration monitoring system based on multi-sensor fusion in Example 2 of the present invention. DETAILED DESCRIPTION

[0058] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0059] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0060] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0061] Example 1:

[0062] This embodiment provides a coal seam drilling gas concentration monitoring method based on multi-sensor fusion, such as Figure 1 As shown, the coal seam drilling gas concentration monitoring method based on multi-sensor fusion includes:

[0063] S101. Analyze the gas concentration risk of different depth layers based on preset coal seam drilling information and classify the coal seams into multiple levels;

[0064] S102. For each coal seam, divide the coal seam into multiple monitoring areas by analyzing the gas concentration gradient in different areas.

[0065] S103, setting up multiple sensors in each monitoring area, dividing the sensors into master sensors and slave sensors by analyzing the communication relationship between the sensors and the voting results between the sensors, and building a sensor network;

[0066] S104. Based on the data collected by each sensor network, concentration monitoring is performed through a preset concentration safety monitoring model, and an early warning is issued when abnormal results are found in the gas concentration to achieve gas concentration monitoring.

[0067] Compared with the traditional method of monitoring gas concentration from the coal seam as a whole, this embodiment achieves comprehensive and accurate monitoring of coal seam borehole gas concentration through multi-level coal seam division, monitoring area division based on gas gradient, sensor network construction, and multi-level fusion and monitoring and early warning of multi-sensor data. It covers coal seams of different depths and different areas, can accurately obtain gas concentration information, and respond quickly when gas concentration is abnormal, providing strong protection for coal mine safety production.

[0068] In this embodiment, the gas concentration risk of coal seams at different depths is first evaluated by analyzing the coal seam permeability, historical gas outburst volume and drilling trajectory data. Based on the coal seam permeability, historical gas outburst volume and drilling trajectory data, a vertical clustering algorithm is used to divide coal seams with similar risk characteristics into the same level; at the same time, the coal seam level is dynamically adjusted according to the real-time changes in gas concentration. By setting a concentration change threshold, when the gas concentration increase rate or decrease rate exceeds the concentration change threshold, the coal seam level is dynamically adjusted. By accurately stratifying and dynamically adjusting the coal seams, the changing trend of gas concentration can be reflected in a timely manner, thereby improving the accuracy and effectiveness of risk assessment.

[0069] Specifically, after dividing the coal seams, each grade of coal seams is divided into regions. The coal seams are gridded by setting the initial grid size to obtain multiple grid areas. Then, the gas concentration gradient value between adjacent grids is calculated, and the degree of spatial variation of the gas concentration is analyzed. When the gas concentration gradient value is less than the preset gradient threshold, it means that the difference in gas concentration between adjacent grids is small. By merging adjacent grids, a more reasonable monitoring area can be obtained, which can more accurately reflect the distribution of gas concentration in different areas, avoid monitoring blind spots or repeated monitoring due to simple division, and improve monitoring efficiency.

[0070] Specifically, multiple sensors are set up in each monitoring area. By analyzing the communication relationship between sensors, master sensors and slave sensors are divided. The master sensor is responsible for collecting and processing the data of the slave sensors and communicating with the external system. According to the positional relationship and functional dependence of the master and slave sensors, a communication link is established to build a sensor network. At the same time, the master sensor is dynamically adjusted according to the changes in the performance of the master sensor, which can ensure the reliability and stability of the sensor network and ensure that the network can continue to operate efficiently when the sensor performance changes. By dynamically dividing the master and slave sensors and optimizing the communication link, the adaptability and reliability of the sensor network are improved, which can ensure the efficient transmission and accurate collection of data, provide accurate data for gas concentration monitoring, and ensure the normal operation of the monitoring system.

[0071] Specifically, during the data transmission process of the sensor network, the data transmission results are corrected. First, the sensor nodes in the sensor network where data transmission fails are detected, and the data of the failed sensor nodes are corrected through adjacent sensor nodes. The corrected data are hierarchically fused, including correcting the data according to the distance between the master and slave sensors, fusing the master and slave sensor data, and correcting the abnormal data. The fused data is input into the preset concentration safety monitoring model for concentration monitoring. When abnormal results are detected in the gas concentration, an early warning is issued in time to achieve effective monitoring of the gas concentration. By detecting and correcting the sensor nodes where data transmission fails, and hierarchically fusing the multi-sensor data, the accuracy and reliability of the data are improved, ensuring that the monitoring results can truly reflect the gas concentration situation. The timely and effective early warning mechanism can quickly notify relevant personnel when the gas concentration is abnormal, so that timely measures can be taken to prevent the occurrence of gas accidents and ensure the safety of coal mine production.

[0072] This application divides the coal seams into layers and regions, sets up a sensor network in each region to monitor the gas concentration, and performs real-time correction on the collected data between the sensor networks. It is possible to obtain data that accurately reflects the changes in gas concentration in different regions, identify the gas concentration based on accurate monitoring data, improve the accuracy of gas concentration monitoring results, effectively prevent the occurrence of gas accidents, and ensure the safety of coal miners and the safe and stable operation of coal mine production.

[0073] Furthermore, the gas concentration risk of different depth layers is analyzed based on the preset coal seam drilling information, and the coal seams are divided into multiple levels, including:

[0074] S201, obtaining coal seam permeability, historical gas emission volume, and drilling trajectory data based on preset drilling information for each layer;

[0075] S202, vertically clustering the coal seams according to the coal seam permeability, historical gas emission volume, and drilling trajectory data to obtain first-risk coal seams, second-risk coal seams, and third-risk coal seams;

[0076] S203, when the gas concentration increase rate of the coal seam exceeds a preset concentration change threshold, upgrading the coal seam;

[0077] S204: When the gas concentration reduction rate of the coal seam exceeds a preset concentration change threshold, the coal seam is downgraded.

[0078] In this embodiment, core samples taken from the coal seam are tested through geological exploration means, specifically laboratory core analysis, and the permeability value of the coal seam is calculated using Darcy's law and other related principles; historical data are retrieved from the coal mine's production record system, including gas emission monitoring data for different time periods and mining areas; during the drilling construction process, drilling trajectory measuring instruments, such as measurement while drilling systems and wired inclinometers while drilling, are used to measure parameters such as the depth, inclination, and azimuth of the borehole in real time. Detailed drilling trajectory data is generated through software analysis, which can intuitively display the direction and spatial distribution of the borehole in the coal seam. By analyzing multi-dimensional data, the one-sidedness that may be caused by a single data source is avoided, making the evaluation process more scientific and comprehensive.

[0079] Specifically, the acquired coal seam permeability, historical gas outburst volume and drilling trajectory data are cleaned to remove outliers and missing values. Missing values ​​can be supplemented by methods such as mean filling and regression prediction. Outliers are corrected or eliminated according to the data distribution. The data are then standardized to convert data of different dimensions to the same scale. The processed data are clustered vertically using a clustering algorithm to classify coal seams with similar characteristics into the same category, thereby dividing coal seams into different risk levels. For example, coal seams with high permeability, high historical gas outburst volume and complex drilling trajectory have relatively high gas concentration risks and will be divided into higher risk levels. Clustering results in first-risk level coal seams, second-risk level coal seams and third-risk level coal seams. By dividing the coal seams into risk levels, coal mine managers can quickly and intuitively understand the risk status of coal seams in different areas.

[0080] At the same time, the gas concentration in a coal seam is in a dynamic process of change. The coal seam classification results and performance are dynamically adjusted based on the changes in gas concentration. When the increase rate exceeds the preset concentration change threshold, it indicates that the gas concentration risk of the coal seam has increased significantly in the short term, and the original risk level no longer accurately reflects the current actual risk situation. The coal seam risk level is upgraded to attract the attention of relevant personnel and to promptly implement more stringent preventive measures. The preset concentration change threshold can be set according to the actual situation of the coal mine and safety standards, for example, setting it to a gas concentration increase of 5% per hour. When the coal seam gas concentration decrease rate exceeds the preset concentration change threshold, it indicates that the coal seam gas concentration risk is decreasing and the original risk level is relatively high. Downgrading the coal seam risk level can more accurately reflect the current actual risk situation of the coal seam, rationally allocate monitoring and prevention resources, and avoid resource waste. By dynamically adjusting the coal seam risk level, resource allocation is more reasonable and efficient.

[0081] Furthermore, for each coal seam, multiple monitoring areas are divided by analyzing the gas concentration gradient in different areas, including:

[0082] S301. For each coal seam, set an initial grid size according to a preset drilling spacing;

[0083] S302, dividing the coal seam into grids according to the initial grid size to obtain a plurality of grid areas;

[0084] S303, calculating the gas concentration gradient between adjacent grids based on the gas concentration in each grid area;

[0085] S304: When the gas concentration gradient value is less than a preset gradient threshold, the corresponding adjacent grids are merged to obtain multiple monitoring areas.

[0086] like Figure 2 This embodiment divides each level of coal seam into regions and dynamically optimizes the regional division results based on the gas concentration of the grid area. The optimized monitoring area division reduces unnecessary monitoring duplication and avoids waste of resources. At the same time, it highlights the key monitoring of areas with obvious changes in gas concentration, thereby improving the efficiency and response speed of the entire gas concentration monitoring system.

[0087] In this embodiment, at each level of coal seam, the initial grid size is set according to the borehole spacing. The borehole spacing is closely related to the accuracy of coal seam gas concentration monitoring. The smaller the borehole spacing, the denser the gas concentration data obtained. For example, in a coal mine mining plan, the borehole spacing is clearly stipulated to be 5 meters, and the initial grid size is set to an integer multiple or an appropriate proportion of the borehole spacing. The initial grid size is set to twice the borehole spacing, that is, 10 meters; setting the initial grid size according to the borehole spacing can make full use of existing borehole data, reduce data acquisition costs, and ensure that each grid area has sufficient data to support gas concentration analysis.

[0088] Specifically, grid division is performed according to the initial grid size, and the coal seam is divided into regular grid areas according to the initial grid size. The complex coal seam gas concentration distribution problem is converted into an analysis of the gas concentration of multiple discrete grid areas. Each grid area is regarded as a relatively independent unit, and multiple grid areas are obtained; the regular grid area division facilitates the calculation of the gas concentration gradient value between adjacent grids, which provides data support for the accurate division of the monitoring area; the gas concentration data in each grid area is calculated, and the interpolation calculation is performed based on the drilling data to obtain the average gas concentration of each grid area. For each pair of adjacent grid areas, the gas concentration gradient value is calculated. By calculating the gas concentration gradient value, areas with drastic changes in gas concentration can be discovered in a timely manner, which helps to take preventive measures in advance and ensure safe production in coal mines.

[0089] The grid area is optimized according to the calculated gas concentration gradient value. When the gas concentration gradient value between adjacent grids is less than the preset gradient threshold, it means that the difference in gas concentration in adjacent grid areas is small, and they are merged into one monitoring area. By merging monitoring areas, the number of monitoring areas can be reduced without affecting the accuracy of the division of gas concentration distribution areas. For adjacent grids with gas concentration gradient values ​​greater than the preset gradient threshold, they are retained as independent monitoring areas. The preset gradient threshold can be set according to the actual situation of the coal mine, historical monitoring data and safety standards. For example, the preset gradient threshold is set to 0.5 (unit: concentration value / meter). By merging adjacent grids with similar gas concentrations, the number of monitoring areas is reduced and the complexity of the monitoring system is reduced.

[0090] Furthermore, multiple sensors are set up in each monitoring area, and by analyzing the communication relationship between the sensors and the voting results between the sensors, the master sensors and slave sensors are divided, and a sensor network is constructed, including:

[0091] S401, setting multiple sensors in each monitoring area, and dividing them into master sensors and slave sensors based on the communication relationship between different sensors and the voting results between the sensors;

[0092] S402 : Building a communication link between the master sensor and the slave sensor based on the positional relationship and functional dependency between the master sensor and the slave sensor to obtain a sensor network.

[0093] like Figure 3 In this embodiment, multiple sensors are installed in each monitoring area. Based on differences in performance and communication capabilities, the sensors are rationally divided into master and slave sensors to achieve efficient data collection and transmission. The master sensor is responsible for data aggregation, processing, and communication with external systems, while the slave sensor is responsible for collecting local data and transmitting it to the master sensor. By analyzing the communication relationships between sensors, including signal strength, transmission rate, and stability, and combining the sensor's own performance (measurement accuracy, power consumption, etc.), the master and slave sensors are divided. The sensor allocation is dynamically adjusted based on the real-time performance of the master sensor. This dynamic adjustment of the master sensor allows the sensor network to adapt to environmental changes and sensor performance degradation. When the performance of a master sensor degrades, the system can promptly replace it, ensuring continuous and stable network operation and improving the accuracy of gas concentration monitoring data.

[0094] Specifically, based on the positional relationship and functional dependency between the master sensor and the slave sensor, a communication link is established between the master sensor and the slave sensor. The positional relationship reflects the distance and path of data transmission. The shorter the distance, the smaller the signal attenuation and interference during the transmission process. The functional dependency requires that the slave sensor can accurately and timely transmit data to the master sensor for processing. The positional relationship and functional dependency are comprehensively analyzed to establish the optimal communication link, ensure the efficiency and stability of data transmission in the sensor network, enable the master sensor to quickly collect data from all slave sensors, and realize real-time monitoring of the gas concentration in the monitoring area. By establishing a communication link, signal attenuation and interference can be reduced, the probability of errors in the data transmission process can be reduced, the stability of the sensor network can be enhanced, and reliable operation can be ensured even in complex coal mine environments.

[0095] Furthermore, the method of setting up multiple sensors in each monitoring area and dividing the master sensor and the slave sensor into two groups according to the communication relationship between different sensors and the voting results between the sensors includes:

[0096] S501. In each monitoring area, set an initial master sensor based on the performance data of each sensor;

[0097] S502: Calculate the weight value of each sensor using a preset dynamic weight calculation model within a preset time period;

[0098] S503: When the weight value of the initial primary sensor is less than a preset first weight threshold, sensors having weight values ​​greater than a preset second weight threshold are selected as a candidate sensor set, wherein the preset first weight threshold is less than the preset second weight threshold;

[0099] S504: Based on the sensor performance in the candidate sensor set, each sensor votes for each sensor in the candidate sensor set, and the sensor with the most votes is used as the updated main sensor;

[0100] S505 : The initial master sensor serves as a slave sensor and communicates with the updated master sensor.

[0101] In this embodiment, in each monitoring area, an initial main sensor is set according to the different performance data of the sensors, and the performance data of each sensor is obtained through the parameter configuration file provided by the sensor. A weight is set for each performance indicator according to the actual needs of gas concentration monitoring; for example, the measurement accuracy weight accounts for 40%, the data transmission rate weight accounts for 30%, the battery life weight accounts for 20%, and the anti-interference ability weight accounts for 10%; the performance indicator values ​​of each sensor are multiplied by the corresponding weights, and then summed to obtain the comprehensive performance score of each sensor; the comprehensive performance scores of all sensors are compared, and the sensor with the highest score is selected as the initial main sensor. When there are multiple sensors with the same comprehensive performance scores, the sensor with a higher data transmission rate is preferentially selected as the initial main sensor; selecting the sensor with the best performance as the initial main sensor can efficiently collect and process data from the sensors in the early stage of sensor network operation and transmit it to the external monitoring system in a timely manner.

[0102] Specifically, during the data transmission process, the master sensor and the slave sensor are dynamically adjusted according to the changes in sensor performance. Considering that in the complex environment of a coal mine, the performance of the sensor will change over time, including battery power consumption leading to unstable operation, equipment aging affecting measurement accuracy, environmental interference changing data transmission quality, etc., adjusting the master sensor can ensure that the master sensor always has the best data transmission performance and ensure the accuracy and efficiency of data transmission; according to the actual needs of coal mine gas concentration monitoring and the law of sensor performance changes, a suitable time period is set. In this embodiment, the time period is set to one hour. The preset dynamic weight calculation model comprehensively considers multiple factors, including the current measurement of the sensor. Error, data transmission success rate, remaining battery power, signal strength, etc. The weight of each performance indicator can be set according to the actual calculation accuracy requirements, such as the measurement accuracy weight is 0.4, the data transmission weight is 0.3, the battery weight is 0.2, and the signal weight is 0.1; in each time period, the measurement error, data transmission success rate, remaining battery power, signal strength and other data of each sensor are collected in real time; the collected data are input into the preset dynamic weight calculation model, and the weight value of each sensor in the time period is calculated by weighted calculation; by dynamically calculating the weight value, the sensor network can adapt to the complex and changeable environment underground in the coal mine, timely reflect the dynamic changes in sensor performance, and ensure that the network always maintains a good operating state.

[0103] Specifically, according to the actual situation of coal mine gas concentration monitoring and the sensor performance standard, a preset first weight threshold and a preset second weight threshold are set. For example, the preset first weight threshold is set to 0.6, and the preset second weight threshold is set to 0.7. After calculating the weight value of the sensor in each preset time period, the weight value of the initial main sensor is compared with the preset first weight threshold, and the weight values ​​of other sensors are compared with the preset second weight threshold. When the weight value of the initial main sensor is less than the preset first weight threshold and there are other sensors with weight values ​​greater than the preset second weight threshold, the sensors with weight values ​​greater than the preset second weight threshold are screened out to form a candidate sensor set; when the weight value of the initial main sensor is less than the preset first weight threshold, it indicates that its performance can no longer meet the working requirements of the main sensor; and the sensors with weight values ​​greater than the preset second weight threshold indicate that their performance is relatively good and have the potential to become the main sensor; by comparing with the threshold, the performance degradation of the initial main sensor can be discovered in time, avoiding interruption or inaccuracy of monitoring data due to failure of the main sensor, and ensuring the continuity of monitoring work.

[0104] At the same time, after screening the candidate sensor set, each sensor votes for the sensors in the candidate sensor set. Through the voting mechanism, the opinions of multiple sensors are integrated to select the sensor that performs better and is more recognized in actual work as the updated main sensor; the voting basis includes the actual working performance of the sensor, such as measurement accuracy stability, data transmission reliability, and anti-interference ability. Each sensor votes for each sensor in the candidate sensor set within the specified time, compares the number of votes for the candidate sensors, and determines the sensor with the most votes as the updated main sensor. When the number of votes is the same, the comprehensive performance scores of the sensors are further compared, and the sensor with the higher score is selected as the updated main sensor; the voting mechanism fully considers the actual working experience and evaluation of multiple sensors, and can select the main sensor that better meets the needs in actual operation, thereby improving the scientificity and rationality of the main sensor selection.

[0105] Specifically, after determining to update the main sensor, a role conversion instruction is sent to the initial main sensor to notify it to convert from the main sensor role to the slave sensor role. After receiving the role conversion instruction, the initial main sensor establishes a communication connection with the updated main sensor in accordance with the preset communication protocol; after the initial main sensor is converted to a slave sensor, it continues to collect data in the monitoring area and transmits the data to the updated main sensor in accordance with the new communication link. The updated main sensor receives and processes the data and then transmits it to the external monitoring system; by replacing the main sensor, the initial main sensor with degraded performance is converted into a slave sensor and continues to be used for data collection, thus quickly completing the role conversion of the master-slave sensor and establishing the communication connection, so that the sensor network can reduce the impact on data collection and transmission during the replacement of the main sensor, thereby ensuring the continuity of the monitoring work and the stability of the network.

[0106] Furthermore, the sensor network is obtained by constructing a communication link between the master sensor and the slave sensor based on the positional relationship and functional dependency between the master sensor and the slave sensor, including:

[0107] S601, constructing an adjacency matrix based on the location distance of each sensor;

[0108] S602: Connect two sensors with the shortest distance between them according to the adjacency matrix;

[0109] S603: When the number of sensors that are connected to the master sensor for communication is greater than a preset number threshold, the communication link is updated, and a path with a smaller number of sensors than the preset number threshold and the shortest overall communication link distance is selected as the updated communication link;

[0110] S604: Establish communication between each slave sensor and the master sensor according to the updated communication link to obtain a sensor network.

[0111] In this embodiment, the distance between sensors is calculated based on the location coordinates of each sensor, and an adjacency matrix is ​​constructed using the calculated distances. In a sensor network, each sensor is considered a node, and the distances between sensors serve as the connection weights between nodes. By constructing the adjacency matrix, the distance relationship between sensors is intuitively presented. When establishing a communication link, the distance information between any two sensors can be quickly obtained, thereby efficiently planning the connection path. Specifically, based on the adjacency matrix, the two sensors with the shortest distance between them are selected for connection. The shorter the distance, the less signal attenuation during transmission, the less interference is encountered, and the more stable and accurate the data transmission. By gradually connecting sensors in this way, a communication network topology is constructed, and sensor energy consumption can be reduced to a certain extent, as short-distance transmission consumes less energy. By prioritizing the connection of sensors with the shortest distance, signal attenuation and interference can be effectively reduced, the success rate and accuracy of data transmission can be improved, and the monitoring data can be reliably transmitted to the main sensor.

[0112] Specifically, the communication link is updated based on the number of sensors spaced apart in the path connecting the slave sensor and the master sensor, thereby avoiding the risk of increased data transmission delay and data loss due to an excessive number of sensors spaced apart in the communication link from the slave sensor to the master sensor. A preset number threshold is set based on the actual communication needs and sensor performance in the coal mine. In this embodiment, it is set to 3. All communication links from the slave sensor to the master sensor are traversed, and the number of sensors spaced apart in each link is counted. For example, the link from sensor A to master sensor B passes through sensors C, D, and E, and the number of sensors spaced apart is 3. When the number of sensors spaced apart in a link is greater than the preset number threshold, a new communication path is searched from the adjacency matrix to select a set of paths with a number of sensors spaced apart that is less than the preset number threshold. For each path in the selected path set, the overall distance of the path is calculated based on the distance between sensors recorded in the adjacency matrix. The overall distances of the paths in the path set are compared, and the path with the shortest overall distance is selected as the updated communication link. If there are multiple paths with the same overall distance and the same shortest distance, the path with the best sensor transmission performance is selected as the updated communication link.

[0113] According to the updated communication link, the communication connection between sensors is reconfigured, the redundant connections in the original link are disconnected, and a new connection relationship is established. A stable and efficient communication connection is established between each slave sensor and the master sensor, and all sensors are connected to form a complete sensor network to ensure that data can be transmitted according to the new link; by reducing the number of interval sensors in the communication link from the slave sensor to the master sensor, the data transmission delay can be significantly reduced, enabling the master sensor to obtain data from the slave sensors more quickly, and improving the response speed of the entire sensor network; shorter communication links and fewer intermediate links reduce the risk of data transmission failure due to sensor failure or signal interference, enhance the stability of the communication link, and ensure the continuity and reliability of monitoring data transmission.

[0114] Furthermore, the gas concentration monitoring is performed based on the data collected by each sensor network through a preset concentration safety monitoring model, and an early warning is issued when an abnormal result is found in the gas concentration, thereby achieving gas concentration monitoring, including:

[0115] S701, based on the data collected by each sensor network, detecting the sensor nodes in the sensor network where data transmission fails, and performing data correction to obtain multi-sensor corrected data;

[0116] S702, performing hierarchical fusion on the multi-sensor correction data to obtain fused data;

[0117] S703. Based on the fused data, concentration monitoring is performed using a preset concentration safety monitoring model. When an abnormal result occurs in the gas concentration, an early warning is issued to achieve gas concentration monitoring.

[0118] In this embodiment, the data is corrected based on the data collected by each sensor network, and the nodes in the sensor network where data transmission fails are detected. The data of the failed sensor nodes are corrected by combining the spatial correlation and time trend of the data collected by the sensor nodes to obtain more accurate and reliable multi-sensor corrected data, thereby avoiding the impact of data transmission failure caused by electromagnetic interference, equipment failure, signal blocking, etc. in the complex environment of coal mines, effectively avoiding the interference of abnormal data on the monitoring results, and enabling the multi-sensor corrected data to truly reflect the actual gas concentration, thereby improving the accuracy of the data.

[0119] Specifically, data fusion is performed based on multiple sensor data collected by the sensor network. By performing layered processing on the data, the slave sensor data is first corrected according to the positional relationship between the master and slave sensors to eliminate measurement deviations caused by distance; the master and slave sensor data are then fused to obtain comprehensive data within the area; finally, the data between areas are analyzed and abnormal data are corrected so that the fused data can more accurately and comprehensively reflect the gas concentration distribution in the monitored area, providing more accurate data for the concentration safety monitoring model; the multi-sensor corrected data is comprehensively processed through hierarchical fusion, which reduces data redundancy and inconsistency, improves data quality and availability, provides more accurate data for the concentration safety monitoring model, and enhances the reliability of the monitoring results.

[0120] Furthermore, based on the fused data, the gas concentration is monitored using a preset concentration safety monitoring model. The concentration safety monitoring model in this embodiment is specifically a random forest model, which is trained using a large amount of historical data to obtain a pre-trained concentration safety monitoring model. The fused data is input into the pre-trained concentration safety monitoring model, and the model outputs a gas concentration safety judgment result based on the safety threshold of the gas concentration and the abnormality judgment rule. When the gas concentration exceeds 80% of the safety threshold or the gas concentration rises by more than 50% within 10 minutes, it is determined that the gas concentration is abnormal. When the model detects an abnormal result, it immediately triggers the early warning mechanism, and sends early warning information to coal mine safety management personnel, underground workers and other relevant personnel through text messages, sound and light alarms, and coal mine safety production management system push, reminding them to take corresponding preventive and handling measures. Through the preset concentration safety monitoring model, gas concentration abnormalities can be identified quickly and accurately, and early warnings can be issued in time to gain valuable time for coal mine safety production and effectively prevent the occurrence of gas accidents.

[0121] Furthermore, the method of detecting sensor nodes in the sensor network where data transmission fails and correcting the data based on the data collected by each sensor network to obtain multi-sensor corrected data includes:

[0122] S801, based on the data collected by each sensor network, a sensor node whose data packet loss rate is greater than a preset loss threshold is regarded as a failed sensor node;

[0123] S802, obtaining a spatial correction value by calculating weighted distance values ​​of a preset number of adjacent non-failed sensor nodes of the failed sensor node;

[0124] S803, predicting the data using a preset trend prediction model based on historically collected data of the failed sensor node to obtain a predicted value;

[0125] S804: Fusing the spatial correction value and the predicted value using a preset weight to obtain multi-sensor correction data.

[0126] In this embodiment, sensor nodes with a high data loss rate during data transmission in the sensor network are first identified, the data of failed sensor nodes is corrected, and a data loss threshold is set according to the actual calculation accuracy requirements. In this embodiment, the preset loss threshold is set to 15%. The sensor network management system continuously monitors the data transmission status of each sensor node and records the total number of data packets sent by each sensor node and the number of data packets successfully transmitted to the target node (such as the main sensor) within a unit of time (such as every minute). The data packet loss rate of each sensor node is calculated as follows: (total number of data packets sent - number of data packets successfully transmitted) ÷ total number of data packets sent × 100%. The calculated data packet loss rate of each sensor node is compared with the preset loss threshold. When the data packet loss rate of a sensor node is greater than 15%, the sensor node is identified as a failed sensor node. The failed sensor node is discovered in a timely manner to prevent its unreliable data from being mixed into the concentration safety monitoring data, thereby ensuring the overall quality of the data used for gas concentration monitoring and improving the credibility of the monitoring results.

[0127] Specifically, after identifying a failed sensor node, the system uses the failed sensor node as the center and filters out the non-failed sensor nodes within a preset range (e.g., a circular area with a radius of 5 meters and centered on the failed sensor node). At the same time, the number of adjacent non-failed sensor nodes to be included in the calculation is set. For example, the three adjacent non-failed sensor nodes closest to the failed sensor node are selected. Weighted corrections are then applied to the adjacent non-failed sensor nodes based on the distance between the nodes. The correction formula is:

[0128] ;

[0129] Where S is the spatial correction value, n is the number of adjacent non-failed sensor nodes, di is the distance between the i-th adjacent non-failed sensor node and the failed sensor node, dj is the distance between the j-th adjacent non-failed sensor node and the failed sensor node, and Ci is the gas concentration data value collected by the i-th adjacent non-failed sensor node. By fully exploiting the spatial information of the data and the spatial relationship between adjacent non-failed sensor nodes, the corrected data is more consistent with the actual gas concentration distribution, improving the accuracy of the data correction.

[0130] At the same time, based on the historical collected data of the failed sensor node, the trend information of the gas concentration at its location changing over time is analyzed, and predictions are made through a preset trend prediction model. The trend prediction model is specifically an LSTM model. A large amount of historical data is used to train the LSTM model to obtain a pre-trained trend prediction model. The time information of the failure time period (such as timestamp) is input into the trained trend prediction model. The model predicts the gas concentration value within the time period based on the learned historical data rules to obtain the predicted value; using historical data and trend prediction models, the data of the failed sensor node is predicted and supplemented from the time dimension, fully exploring the time series characteristics of the data, improving the integrity of the data, and enabling the monitoring data to more comprehensively reflect the changes in gas concentration over time.

[0131] Specifically, according to the actual calculation requirements and the analysis of the monitoring data, the fusion weights of the spatial correction value and the predicted value are set; for example, it is believed that spatial correlation has a greater impact on data correction, and the spatial correction value weight is set to 0.7, and the predicted value weight is set to 0.3; the spatial correction value and the predicted value are fused according to the set weight values, and the multi-sensor correction data is calculated; by fusing the spatial correction value and the predicted value, the information of the data in the spatial and temporal dimensions is fully utilized, which makes up for the shortcomings of a single correction method, makes the corrected data closer to the actual gas concentration, and improves the quality and accuracy of the data.

[0132] Furthermore, the step of performing hierarchical fusion on the multi-sensor correction data to obtain fused data includes:

[0133] S901, correcting the data of each slave sensor in the multi-sensor correction data according to the distance between the master sensor node and each slave sensor node to obtain slave sensor correction data;

[0134] S902, fusing the master sensor data with the slave sensor correction data to obtain regional fusion data;

[0135] S903. Correct the data in the regional fusion data where the gas concentration is different from the gas concentration gradient trend in the adjacent regions to obtain fusion data.

[0136] In this embodiment, the data of each slave sensor is first corrected according to the distance between the main sensor and the slave sensor. The calculated distance is combined with the correction empirical formula, and the correction empirical formula is set according to the sensor correction experience to calculate the correction coefficient. The correction coefficient and the corrected data are weighted and calculated to calculate the corrected data of each slave sensor. By correcting the data of the slave sensors, the data deviation caused by the difference in sensor position is reduced, so that the data of the slave sensors are closer to the actual gas concentration value.

[0137] Specifically, based on factors such as the reliability and accuracy of the master and slave sensors, a corresponding weight is assigned to each sensor. The weighted sum of each sensor data and the corresponding weight is calculated to obtain regional fusion data. By fusing the data of multiple sensors, the data of the master and slave sensors are fully utilized, so that the fused data contains more information and can better reflect the overall gas concentration in the area. For each area, the gas concentration gradient between it and the adjacent area is calculated, and a gradient difference threshold is set. When the difference between the gas concentration gradient of a region and the gradient of the adjacent area exceeds the gradient difference threshold, the fused data of the region is considered to be abnormal. The fused data of the region is corrected through interpolation correction method. The specific interpolation correction method is the spline interpolation algorithm. The corrected fused data can more accurately reflect the actual gas concentration distribution, which helps to promptly detect abnormal changes in gas concentration and ensure safe production.

[0138] Example 2:

[0139] In this embodiment, if Figure 4 , providing a coal seam borehole gas concentration monitoring system based on multi-sensor fusion, for implementing the coal seam borehole gas concentration monitoring method based on multi-sensor fusion, including:

[0140] The coal seam classification module analyzes the gas concentration risk of different depth layers based on the preset coal seam drilling information and divides the coal seams into multiple levels;

[0141] The regional division module divides each coal seam into multiple monitoring areas by analyzing the gas concentration gradient in different areas;

[0142] The sensor network construction module sets up multiple sensors in each monitoring area, analyzes the communication relationship between sensors and combines the voting results between sensors to divide the master sensors and slave sensors, and builds a sensor network;

[0143] The gas concentration monitoring module monitors the gas concentration based on the data collected by each sensor network through a preset concentration safety monitoring model, and issues an early warning when abnormal gas concentration results are detected, thereby achieving gas concentration monitoring.

[0144] In this embodiment, the coal seam division module analyzes the gas concentration risks of different depth layers based on the preset coal seam drilling information, and comprehensively considers various characteristics of the coal seam and historical data and other factors to divide the coal seam into multiple levels according to the different gas concentration risks, so that targeted monitoring measures can be taken for coal seams of different levels in the future, providing a basis for accurate monitoring of gas concentration; the regional division module further divides each level of coal seam into multiple monitoring areas by analyzing the gas concentration gradients in different areas. There will be differences in the changes in gas concentration in different areas of the same level of coal seam. Through regional division, the distribution of gas concentration in the coal seam can be understood in more detail, making the monitoring work more targeted and accurate, and helping to timely discover areas with abnormal gas concentration.

[0145] Specifically, the sensor network construction module sets up multiple sensors in each monitoring area and builds a sensor network by analyzing the communication relationship between sensors. First, the initial master sensor is determined based on the sensor performance data, and then the weight value of each sensor is calculated through a dynamic weight calculation model. Candidate sensors are screened according to the weight value and the updated master sensor is determined by voting. Finally, a communication link is established between the master and slave sensors. The constructed sensor network can optimize the collaboration and communication between sensors and improve the efficiency and reliability of data collection and transmission.

[0146] Specifically, the gas concentration monitoring module monitors the gas concentration based on the data collected by each sensor network using a preset concentration safety monitoring model. It first detects and corrects the sensor nodes where data transmission fails, then integrates the corrected data in a hierarchical manner, and finally monitors the concentration based on the integrated data. When the gas concentration is abnormal, an early warning is issued in time, realizing real-time and accurate monitoring of the gas concentration in the coal seam borehole, which can timely discover potential safety hazards and provide strong support for ensuring safe production in coal mines.

[0147] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A coal seam drilling gas concentration monitoring method based on multi-sensor fusion is characterized by: include: Based on the preset coal seam drilling information, the gas concentration risk of different depth layers is analyzed and divided into multiple levels of coal seams; For each coal seam, multiple monitoring areas are divided by analyzing the gas concentration gradient in different areas; In each monitoring area, the initial main sensor is set according to the performance data of each sensor; Within a preset time period, the weight value of each sensor is calculated through a preset dynamic weight calculation model; When the weight value of the initial main sensor is less than a preset first weight threshold, sensors with weight values ​​greater than a preset second weight threshold are selected as a candidate sensor set, wherein the preset first weight threshold is less than the preset second weight threshold; According to the sensor performance in the candidate sensor set, each sensor votes for each sensor in the candidate sensor set, and the sensor with the most votes is used as the updated main sensor; The initial master sensor acts as a slave sensor and communicates with the updated master sensor; According to the positional relationship and functional dependency of the master sensor and the slave sensor, a communication link is established between the master sensor and the slave sensor to obtain a sensor network; Based on the data collected by each sensor network, concentration monitoring is carried out through the preset concentration safety monitoring model, and an early warning is issued when abnormal results appear in the gas concentration to realize gas concentration monitoring.

2. The method for monitoring coal seam drilling gas concentration based on multi-sensor fusion according to claim 1, characterized in that: The gas concentration risk of different depth layers is analyzed based on the preset coal seam drilling information, and the coal seams are divided into multiple levels, including: According to the preset drilling information of each layer, the coal seam permeability, historical gas emission and drilling trajectory data are obtained; Based on the coal seam permeability, historical gas emission volume and drilling trajectory data, the coal seams are vertically clustered to obtain first-risk coal seams, second-risk coal seams and third-risk coal seams; When the gas concentration increase rate of the coal seam exceeds the preset concentration change threshold, the coal seam is upgraded; When the gas concentration reduction rate of the coal seam exceeds the preset concentration change threshold, the coal seam will be downgraded.

3. The method for monitoring coal seam drilling gas concentration based on multi-sensor fusion according to claim 1, characterized in that: For each coal seam, multiple monitoring areas are divided by analyzing the gas concentration gradient in different areas, including: For each coal seam, the initial grid size is set according to the preset drilling spacing; Dividing the coal seam into grids according to the initial grid size to obtain a plurality of grid areas; According to the gas concentration of each grid area, calculate the gas concentration gradient value between adjacent grids; When the gas concentration gradient value is less than a preset gradient threshold, the corresponding adjacent grids are merged to obtain multiple monitoring areas.

4. The method for monitoring coal seam drilling gas concentration based on multi-sensor fusion according to claim 1, characterized in that: The method of constructing a communication link between the master sensor and the slave sensor based on the positional relationship and functional dependency between the master sensor and the slave sensor to obtain a sensor network includes: Construct an adjacency matrix based on the location distance of each sensor; Connecting two sensors with the shortest distance between them according to the adjacency matrix; When the number of sensors communicating between the slave sensor and the master sensor is greater than a preset number threshold, the communication link is updated, and a path with a smaller number of sensors than the preset number threshold and the shortest overall communication link distance is selected as the updated communication link; According to the updated communication link, communication between each slave sensor and the master sensor is established to obtain a sensor network.

5. The method for monitoring coal seam drilling gas concentration based on multi-sensor fusion according to claim 1, characterized in that: The gas concentration monitoring is performed based on the data collected by each sensor network through a preset concentration safety monitoring model. When the gas concentration shows abnormal results, an early warning is issued to achieve gas concentration monitoring, including: According to the data collected by each sensor network, the sensor nodes with data transmission failure in the sensor network are detected and the data is corrected to obtain multi-sensor corrected data; Performing hierarchical fusion on the multi-sensor correction data to obtain fused data; According to the fused data, concentration monitoring is performed through a preset concentration safety monitoring model, and an early warning is issued when an abnormal result occurs in the gas concentration, thereby realizing gas concentration monitoring.

6. The method for monitoring coal seam drilling gas concentration based on multi-sensor fusion according to claim 5, characterized in that: The method of detecting sensor nodes in the sensor network where data transmission fails and correcting the data based on the data collected by each sensor network to obtain multi-sensor corrected data includes: According to the data collected by each sensor network, the sensor nodes whose data packet loss rate is greater than the preset loss threshold are regarded as failed sensor nodes; The spatial correction value is obtained by calculating the distance weighted values ​​of a preset number of adjacent non-failed sensor nodes of the failed sensor node; According to the historical data collected by the failed sensor node, the data is predicted through the preset trend prediction model to obtain the predicted value; The spatial correction value and the predicted value are fused by using preset weights to obtain multi-sensor correction data.

7. The method for monitoring coal seam drilling gas concentration based on multi-sensor fusion according to claim 5, characterized in that: The step of performing hierarchical fusing of the multi-sensor correction data to obtain fused data includes: According to the distance between the master sensor node and each slave sensor node, the data of each slave sensor in the multi-sensor correction data is corrected to obtain the slave sensor correction data; Fusing the master sensor data with the slave sensor correction data to obtain regional fusion data; The gas concentration in the regional fusion data is corrected for the data with different gas concentration gradient trends from the adjacent areas to obtain the fusion data.

8. The coal seam drilling gas concentration monitoring system based on multi-sensor fusion is characterized by: The method for monitoring coal seam drilling gas concentration based on multi-sensor fusion according to any one of claims 1 to 7 comprises: The coal seam classification module analyzes the gas concentration risk of different depth layers based on the preset coal seam drilling information and divides the coal seams into multiple levels; The regional division module divides each coal seam into multiple monitoring areas by analyzing the gas concentration gradient in different areas; A sensor network construction module sets an initial master sensor in each monitoring area based on the performance data of each sensor; calculates the weight value of each sensor within a preset time period using a preset dynamic weight calculation model; when the weight value of the initial master sensor is less than a preset first weight threshold, selects sensors with weight values ​​greater than a preset second weight threshold as a candidate sensor set, wherein the preset first weight threshold is less than the preset second weight threshold; based on the sensor performance of the candidate sensor set, each sensor votes for each sensor in the candidate sensor set, and selects the sensor with the most votes as the updated master sensor; the initial master sensor serves as a slave sensor and communicates with the updated master sensor; based on the positional relationship and functional dependency of the master sensor and the slave sensor, a communication link is established between the master sensor and the slave sensor to obtain a sensor network; The gas concentration monitoring module monitors the gas concentration based on the data collected by each sensor network through a preset concentration safety monitoring model, and issues an early warning when abnormal gas concentration results are detected, thereby achieving gas concentration monitoring.

Images