Intelligent gas leakage monitoring system based on wireless passive detection technology

Abstract

The invention discloses an intelligent gas leakage monitoring system based on a wireless passive detection technology, and relates to the technical field of gas leakage monitoring. The intelligent gas leakage monitoring system based on the wireless passive detection technology comprises a monitoring data acquisition module used for acquiring gas monitoring data of a plurality of monitoring sub-domains in a set area in real time, a monitoring data feature analysis module used for performing feature extraction processing on the gas monitoring data of each monitoring sub-domain, and a wireless passive detection module used for performing wireless passive detection on the gas monitoring data of each monitoring sub-domain. The gas leakage comprehensive evaluation module is used for carrying out comprehensive analysis on the leakage evaluation index set of each monitoring sub-domain to obtain a comprehensive gas leakage risk index of each monitoring sub-domain, and the comprehensive gas leakage risk index of each monitoring sub-domain is used for carrying out comprehensive analysis on the leakage evaluation index set of each monitoring sub-domain. According to the invention, intelligent alarm is carried out on each monitoring sub-domain through comprehensive gas leakage risk indexes in the gas leakage feedback module, so that the system can adapt to complex and changeable environments such as underground mines and the like, and more accurate and more stable risk assessment judgment is carried out on gas leakage.

Description

Technical Field

[0001] This invention relates to the field of gas leak monitoring technology, specifically to an intelligent gas leak monitoring system based on wireless passive detection technology. Background Technology

[0002] Gas leaks frequently occur in enclosed or semi-enclosed spaces such as underground mines, urban pipeline networks, and chemical tunnels, easily leading to major safety incidents such as explosions, poisoning, and fires. Especially in complex environments such as underground mines, traditional gas monitoring methods suffer from problems such as difficulty in power supply deployment, high line maintenance costs, sensor response delays, and blind spots in coverage. Wireless passive detection technology, on the other hand, is a sensing method that acquires monitoring data through wireless excitation without the need for external power. This technology typically relies on passive sensor structures such as surface acoustic waves and radio frequency identification. The sensor receives an external excitation signal, generates a response signal, and sends it back. Based on the characteristics of the reflected signal, it extracts information about the target's physical quantity. Because it does not require an internal power supply, it can achieve long-term stable operation and has advantages such as simple structure, small size, and strong adaptability to extreme environments. Therefore, it is very suitable for deployment in underground areas where power is limited, the environment is complex, and manual access is not possible.

[0003] The limitations of existing technologies include at least the following problems: existing technologies suffer from narrow sensing information dimensions and insufficient data analysis capabilities, which easily leads to difficulties in the system's accurate and dynamic comprehensive assessment of leakage risks in complex scenarios. For example, existing technologies ignore the dynamic characteristics of gas diffusion paths, speeds, and behavioral trends in space, and lack spatiotemporal risk evolution identification. At the same time, they lack modeling and response mechanisms for the geological structural characteristics of the leakage environment, making it difficult to reflect the impact of rock fissures, pore channels, etc. on gas migration trajectories. Furthermore, changes in sensor operating status are not included in the overall assessment system, which can easily lead to misjudgments and missed reports due to equipment accuracy degradation. Because the monitoring system lacks the ability to acquire and fuse multi-dimensional data on the coupling relationship between behavior, structure, and equipment, its sensing coverage, judgment accuracy, and response timeliness for gas leakage risks in complex underground spaces are all significantly limited. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides an intelligent gas leak monitoring system based on wireless passive detection technology, which solves the problems of limited sensing dimensions and single judgment criteria in existing technologies, making it difficult to accurately monitor and assess leaks.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an intelligent gas leak monitoring system based on wireless passive detection technology, comprising: a monitoring data acquisition module, used to acquire gas monitoring data of several monitoring sub-domains within a set area in real time, wherein the gas monitoring data includes gas behavior data, geological structure data, and monitoring equipment operation data; a monitoring data feature analysis module, used to perform feature extraction processing on the gas monitoring data of each monitoring sub-domain within the set area to obtain a leak assessment index set for each monitoring sub-domain within the set area, including an initial gas leak risk index, a geological leak correction index, and an equipment accuracy correction index; a gas leak comprehensive assessment module, used to comprehensively analyze the leak assessment index set of each monitoring sub-domain within the set area to obtain a comprehensive gas leak risk index for each monitoring sub-domain within the set area; and a gas leak feedback module, used to provide intelligent alarm for each monitoring sub-domain within the set area based on the comprehensive gas leak risk index.

[0006] Furthermore, the specific formula for calculating the comprehensive gas leak risk index of a certain monitoring sub-domain within the designated area is as follows: ;in, To set a comprehensive gas leak risk index for a specific monitoring sub-domain within a region, To set the initial gas leak risk index for a specific monitoring sub-domain within the region, The initial adjustment coefficients are stored in the database. To set a geological leakage correction index for a specific monitoring sub-domain within the region, These are the geological correction adjustment coefficients stored in the database. To set the device accuracy correction index for a specific monitoring sub-domain within a defined area. Adjust the adjustment coefficients for the devices stored in the database. These are the coordination coefficients stored in the database.

[0007] Furthermore, the gas behavior data includes gas diffusion angle values, gas diffusion velocity gradient values, gas density anomaly index, gas combustion anomaly index, and gas specific heat capacity values. The specific steps for obtaining the initial gas leakage risk index of each monitoring sub-domain within the set area are as follows: The gas behavior data of each monitoring sub-domain within the set area are comprehensively analyzed to obtain a gas assessment index set for each monitoring sub-domain within the set area, including a gas propagation risk index and a gas risk response index; the environmental impact factors of each monitoring sub-domain within the set area are obtained and comprehensively analyzed in conjunction with the gas assessment index set to obtain the initial gas leakage risk index of each monitoring sub-domain within the set area.

[0008] Furthermore, the specific steps for obtaining the gas assessment index set for each monitoring sub-domain within the designated area are as follows: read the gas diffusion angle value and gas diffusion velocity gradient value of each monitoring sub-domain within the designated area, and perform comprehensive analysis to obtain the gas propagation risk index of each monitoring sub-domain within the designated area; read the gas density anomaly index, gas anomaly index, and gas specific heat capacity value of each monitoring sub-domain within the designated area, and perform comprehensive analysis to obtain the gas risk response index of each monitoring sub-domain within the designated area.

[0009] Furthermore, the geological structure data includes porosity values, microcrack density, crack connectivity index, gas permeability index, and flow obstruction index. The specific steps for obtaining the geological leakage correction index for each monitoring sub-domain within the designated area are as follows: A comprehensive analysis is performed on the geological structure data of each monitoring sub-domain within the designated area to obtain a set of geological correction assessment indices for each monitoring sub-domain within the designated area, including rock mass fragility index and gas diffusion accessibility index; a comprehensive analysis is then performed on the set of geological correction assessment indices for each monitoring sub-domain within the designated area to obtain the geological leakage correction index for each monitoring sub-domain within the designated area.

[0010] Furthermore, the specific steps for obtaining the geological correction assessment index set for each monitoring subdomain within the designated area are as follows: read the porosity value, microcrack density, and crack connectivity index of each monitoring subdomain within the designated area, and perform comprehensive analysis to obtain the rock mass structural fragility index of each monitoring subdomain within the designated area; read the gas permeability index and flow obstruction index of each monitoring subdomain within the designated area, and perform comprehensive analysis to obtain the gas diffusion accessibility index of each monitoring subdomain within the designated area.

[0011] Furthermore, the specific formula for calculating the geological leakage correction index of a certain monitoring sub-domain within the designated area is as follows: ;in, To set a geological leakage correction index for a specific monitoring sub-domain within the region, To set the rock mass structural fragility index for a specific monitoring subdomain within the region, The structural fragility adjustment coefficient is stored in the database. To determine the gas diffusion accessibility index for a specific monitoring sub-domain within a given area, The diffusion accessibility adjustment coefficients are stored in the database. The coupling suppression adjustment coefficients are stored in the database. These are the interaction adjustment coefficients stored in the database.

[0012] Furthermore, the monitoring equipment operating data includes signal strength response value, sensitivity value, temperature drift deviation value, calibration drift residual value, and self-excited vibration response anomaly value. The specific steps to obtain the equipment accuracy correction index for each monitoring subdomain within the set area are as follows: Standardize the signal strength response value, sensitivity value, temperature drift deviation value, calibration drift residual value, and self-excited vibration response anomaly value for each monitoring subdomain within the set area; comprehensively analyze the standardized signal strength response value, sensitivity value, temperature drift deviation value, calibration drift residual value, and self-excited vibration response anomaly value for each monitoring subdomain within the set area to obtain the equipment accuracy correction index for each monitoring subdomain within the set area.

[0013] Furthermore, the specific formula for calculating the equipment accuracy correction index of a certain monitoring sub-domain within the designated area is as follows: ;in, To set the device accuracy correction index for a specific monitoring sub-domain within a defined area. This refers to the signal strength response value of a specific monitoring sub-domain within a defined area after standardization. These are the signal strength adjustment coefficients stored in the database. The sensitivity value of a specific monitoring sub-domain within the standardized area. The sensitivity adjustment coefficient is stored in the database. The temperature drift deviation value of a certain monitoring sub-domain within the set area after standardization. The temperature drift adjustment coefficient is stored in the database. The calibration drift residual value of a certain monitoring subdomain within the standardized area. The calibration drift adjustment coefficients are stored in the database. The abnormal value of self-excited vibration response in a certain monitoring subdomain within the standardized area. The self-excited vibration adjustment coefficients are stored in the database. These are the superimposed adjustment coefficients stored in the database.

[0014] Furthermore, the specific steps for intelligent alarming of each monitoring sub-domain of the designated area based on the comprehensive gas leak risk index are as follows: The comprehensive gas leak risk index of each monitoring sub-domain within the designated area is compared and analyzed with a preset comprehensive gas leak risk index threshold; if the comprehensive gas leak risk index of each monitoring sub-domain within the designated area is lower than or equal to the preset comprehensive gas leak risk index threshold, no alarm is triggered; if the comprehensive gas leak risk index of each monitoring sub-domain within the designated area is higher than the preset comprehensive gas leak risk index threshold, an alarm is triggered, and preset alarm measures are taken.

[0015] The present invention has the following beneficial effects: (1) The intelligent gas leak monitoring system based on wireless passive detection technology can collect multi-source gas monitoring information, including gas behavior data, geological structure data, and monitoring equipment operation data in real time without relying on external power supply. This enables the system to comprehensively characterize key indicators in multiple dimensions and build a leak risk modeling system covering multiple dimensions of behavior, structure, and equipment. This allows the system to adapt to complex and changeable environments such as underground mines and make more accurate and robust risk assessments of gas leaks, thereby significantly improving the depth and breadth of intelligent gas leak perception.

[0016] (2) The intelligent gas leak monitoring system based on wireless passive detection technology constructs a multi-dimensional evaluation system of initial gas leak risk index, geological leak correction index and equipment accuracy correction index, and designs a nonlinear interactive fusion formula in the gas leak comprehensive evaluation module to avoid the problem of error accumulation. In particular, the system sets up an adaptive weight calculation mechanism based on particle swarm optimization algorithm, which can dynamically adjust the sensitivity and relative weight of the index combination according to the differences in environmental impact factors, propagation characteristics and response capabilities of different monitoring subdomains, thereby ensuring the relative stability of the output of various indicators and the environmental adaptability of the judgment results, thus effectively improving the reliability and data interpretation of the overall monitoring results, and thereby enhancing the self-stabilization capability of the system in long-term operation.

[0017] (3) The intelligent gas leak monitoring system based on wireless passive detection technology constructs a multi-level leak assessment index set. Starting from the original gas characteristic parameters, it gradually derives intermediate sub-indices such as gas propagation risk index, response risk index, rock mass structural fragility index and gas diffusion accessibility index, and finally integrates them into a comprehensive gas leak risk index. This makes the index system have a clear causal chain and supports traceability of risk contribution factors. It also compares the comprehensive risk index with the preset threshold in real time, thereby ensuring that early warning response is carried out in the first time under high risk conditions and can automatically execute preset measures. Thus, it realizes a complete closed-loop gas leak monitoring system from data collection to automatic intervention, thereby effectively improving monitoring efficiency and decision response speed.

[0018] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0019] Figure 1 This is a block diagram of an intelligent gas leak monitoring system based on wireless passive detection technology according to the present invention.

[0020] Figure 2This is a flowchart illustrating the specific steps involved in obtaining the initial gas leak risk index for each monitoring sub-domain within a designated area in an intelligent gas leak monitoring system based on wireless passive detection technology, as described in this invention.

[0021] Figure 3 This is a flowchart illustrating the specific steps involved in obtaining the geological leak correction index for each monitoring sub-domain within a designated area in an intelligent gas leak monitoring system based on wireless passive detection technology, as described in this invention.

[0022] Figure 4 This is a schematic diagram of the geological correction assessment index monitoring subdomain sequence set within a designated area in an intelligent gas leak monitoring system based on wireless passive detection technology according to the present invention. Detailed Implementation

[0023] Please see Figure 1 This invention provides a technical solution: an intelligent gas leak monitoring system based on wireless passive detection technology, comprising: a monitoring data acquisition module, used to acquire in real time gas monitoring data (all acquired via wireless passive devices) of several monitoring sub-domains within a set area (such as an underground mine), the gas monitoring data including gas behavior data, geological structure data, and monitoring equipment operation data; a monitoring data feature analysis module, used to perform feature extraction processing on the gas monitoring data of each monitoring sub-domain within the set area to obtain a leak assessment index set for each monitoring sub-domain within the set area, including an initial gas leak risk index, a geological leak correction index, and an equipment accuracy correction index; a gas leak comprehensive assessment module, used to comprehensively analyze the leak assessment index set of each monitoring sub-domain within the set area to obtain a comprehensive gas leak risk index for each monitoring sub-domain within the set area; and a gas leak feedback module, used to provide intelligent alarms for each monitoring sub-domain within the set area based on the comprehensive gas leak risk index.

[0024] The specific formula for calculating the comprehensive gas leak risk index of a specific monitoring sub-area within a designated area is as follows: ;in, To set a comprehensive gas leak risk index for a specific monitoring sub-domain within a region, To set the initial gas leak risk index for a specific monitoring sub-domain within the region, The initial adjustment coefficients are stored in the database. To set a geological leakage correction index for a specific monitoring sub-domain within the region, These are the geological correction adjustment coefficients stored in the database. To set the device accuracy correction index for a specific monitoring sub-domain within a defined area. Adjust the adjustment coefficients for the devices stored in the database. These are the coordination coefficients stored in the database.

[0025] It needs to be explained that the specific form of the tanh function is as follows: ,in, It is a natural constant, and in this example it can be taken as 2.71, with a domain of (−∞, +∞) and a range of (−1, +1).

[0026] in the formula This item is used to adjust the superposition effect of the initial gas leak risk index, the geological leak correction index, and the equipment accuracy correction index, so as to avoid the overall gas leak risk index being too high or too low.

[0027] , , , The following steps can be taken to obtain the following: Using historical data, combined with the initial gas leak risk index, geological leak correction index, and equipment accuracy correction index, statistical regression analysis is performed to quantify the specific impact of each factor on the comprehensive gas leak risk index, thereby fitting initial weight values. Next, sensitivity analysis is used to adjust the value range of each coefficient and observe its impact on the comprehensive gas leak risk assessment results, ensuring the stability and rationality of the model. Based on the characteristics of the monitoring subdomain and the actual situation, the initially fitted coefficients are corrected and optimized, and finally, coefficient values ​​applicable to the specific monitoring subdomain are determined.

[0028] Specifically, such as Figure 2As shown, the gas behavior data includes gas diffusion angle, gas diffusion velocity gradient, gas density anomaly index, gas combustion anomaly index, and gas specific heat capacity. The specific steps to obtain the initial gas leakage risk index for each monitoring sub-domain within the designated area are as follows: The gas behavior data for each monitoring sub-domain within the designated area are comprehensively analyzed to obtain a gas assessment index set for each monitoring sub-domain, including the gas propagation risk index and the gas risk response index. The environmental impact factors for each monitoring sub-domain within the designated area are obtained and comprehensively analyzed in conjunction with the gas assessment index set (i.e., weighted processing). Based on the particle swarm optimization algorithm, the weight coefficients of the environmental impact factors, gas propagation risk index, and gas risk response index are adaptively calculated. That is, within each monitoring sub-domain, a particle swarm is constructed, where each particle represents a set of weight coefficients to be optimized, specifically including the weights of the environmental impact factors, the gas propagation risk index, and the gas risk response index. The initial weight values ​​of the particles are generated randomly, and the weighted sets are normalized to ensure that the sum of the weights of all particles equals one. A fitness function is defined to evaluate the particle weights. The fitness function optimizes the initial gas leakage risk index over a certain period of time by minimizing the fluctuation of the weighted group represented by each particle. The particle swarm is iteratively updated. In each iteration, for each particle, based on its historical best position and the position of the current best particle in the entire swarm, the update direction and magnitude are comprehensively calculated to adjust the current weighted group of the particle. The adjusted particle positions are then normalized to ensure a constant total weight. During the particle update process, the fitness value of each particle is continuously monitored, and the individual historical best position of each particle is recorded, along with the global best position of the entire swarm. Through multiple iterations, the particle swarm gradually converges within the search space, approaching the optimal weighted combination. When a set termination condition is met, such as the maximum number of iterations or the overall fitness change of the particle swarm being less than a preset threshold, the iteration ends. At this point, the weighted group of the globally optimal particle in the particle swarm is extracted as the final weighting coefficient for the environmental impact factor, gas propagation risk index, and gas risk response index, thus obtaining the initial gas leakage risk index for each monitoring subdomain within the set area.

[0029] Among them, the gas diffusion angle value is the direction of airflow within the monitoring sub-domain, that is, the azimuth angle of the wind, which can be obtained by a wind direction sensor.

[0030] The gas diffusion velocity gradient value is the standard deviation of the airflow velocity at multiple monitoring points within the monitoring subdomain, and the airflow velocity at each monitoring point can be obtained through an airflow velocity sensor.

[0031] The gas density anomaly index is the deviation of the gas density in the monitored subdomain from the normal value. It can be calculated by obtaining gas pressure (which can be obtained through a pressure sensor), gas molecular weight (which can be obtained through a gas sensor, detecting the components of the gas, then obtaining the molecular weight of each component stored in the database and performing weighted processing), gas constant 8.314 J / (mol·K), and gas temperature (which can be obtained through a temperature sensor), and then performing calculations to obtain the reference density of the gas, i.e. (gas pressure × gas molecular weight) / (gas constant × gas temperature). The actual density of the gas is obtained based on the gas mass flow sensor, and the ratio is processed with the reference density. The result is the gas density anomaly index.

[0032] The gas anomaly index is the degree of anomaly in the gas concentration within the monitoring subdomain. It can be obtained by electrochemical sensors to acquire the concentration of each combustible gas and the corresponding reference concentration value (by acquiring the concentration values ​​at several historical time points and averaging them), and then performing ratio processing, i.e., concentration / reference concentration value, and weighting processing based on the ratio processing results. The result is the gas anomaly index.

[0033] The environmental impact factor is the comprehensive impact of ambient temperature, ambient humidity, and ambient air pressure on gas combustion within the monitoring sub-domain. It can be obtained by acquiring ambient temperature (obtained by temperature sensor), ambient humidity (obtained by humidity sensor), ambient air pressure (obtained by air pressure sensor), and ambient temperature reference values ​​(obtained from several historical time points and averaged), ambient humidity reference values ​​(obtained from several historical time points and averaged), and ambient air pressure reference values ​​(obtained from several historical time points and averaged), and then performing ratio processing (e.g., ambient temperature value / ambient temperature reference value). The results are then weighted based on the ratio processing results, and the obtained result is the environmental impact factor.

[0034] The specific heat capacity of a gas is the amount of heat absorbed by a unit mass of gas when its temperature increases by 1°C (or 1K). The specific heat capacity of a gas has a significant impact on its diffusion characteristics. It can be obtained by acquiring multiple gases in the air through a gas sensor, using a standard gas table stored in a database to obtain the specific heat capacity of each gas, and then performing weighted processing to obtain the gas specific heat capacity value.

[0035] The specific steps to obtain the gas assessment index set for each monitoring sub-domain within the designated area are as follows: Read the gas diffusion angle value and gas diffusion velocity gradient value for each monitoring sub-domain within the designated area, and perform comprehensive analysis (i.e., first perform standardization processing, and then perform weighted analysis based on the standardization processing). The weighting coefficients for the gas diffusion angle value and gas diffusion velocity gradient value can be obtained through the following steps: Collect historical risk event data, such as leak accidents and concentration exceedance records; construct features, i.e., diffusion angle, velocity gradient, and whether a risk has occurred; and combine this with regression models stored in the database, such as random forests, to fit the relationship between features and risk. Then, feature importance is extracted from the model and used as dynamic weights for gas diffusion angle and gas diffusion velocity gradient values ​​to obtain the gas propagation risk index for each monitoring sub-domain within the set area. The gas density anomaly index, gas anomaly index, and gas specific heat capacity value of each monitoring sub-domain within the set area are read and comprehensively analyzed (i.e., advanced standardization processing, and weighted analysis based on standardization processing, and the weighting coefficients of gas density anomaly index, gas anomaly index, and gas specific heat capacity value are obtained in the same logic as the weighting coefficients of gas diffusion angle and gas diffusion velocity gradient values) to obtain the gas risk response index for each monitoring sub-domain within the set area.

[0036] In this implementation scheme, by acquiring and fusing high-dimensional features such as gas diffusion angle, diffusion velocity gradient, gas density anomaly index, gas anomaly index, and gas specific heat capacity, the system can accurately reflect the diffusion directionality, velocity fluctuation, and physical diffusion capacity of gas in the monitoring subdomain. This significantly enhances the system's spatial resolution and alarm capabilities in complex scenarios. Furthermore, in constructing the gas propagation risk index and risk response index, the system incorporates historical risk event data (such as leak records and exceedance cases) and combines them with machine learning regression models such as random forests to automatically extract the importance of each feature as a weighting basis, thereby ensuring that the weights of each indicator are data-driven and reasonable. The system adapts to the subdomain environment and allows for adaptive weight distribution schemes across different monitoring areas, resulting in final calculations that better reflect the actual leakage risk profile. This significantly improves the reliability and versatility of the initial gas leakage risk index. Finally, to rationally integrate environmental impact factors with the gas assessment index set, the system introduces a particle swarm optimization algorithm to iteratively optimize the weighting coefficients, making the output results more stable and reliable. Furthermore, it supports automatic weight adjustment for different monitoring subdomains based on their sensing environment, terrain features, and gas behavior, avoiding misjudgments caused by parameter rigidity in traditional models. This effectively enhances the system's generalization ability and monitoring accuracy in multi-region and multi-scenario deployments.

[0037] Specifically, such as Figure 3As shown, the geological structure data includes porosity values, microfracture density, fracture connectivity index, gas permeability index, and flow obstruction index. The specific steps to obtain the geological leakage correction index for each monitoring sub-domain within the designated area are as follows: A comprehensive analysis is performed on the geological structure data of each monitoring sub-domain within the designated area to obtain a set of geological correction assessment indices for each monitoring sub-domain within the designated area, including rock mass fragility index and gas diffusion accessibility index; a comprehensive analysis is then performed on the set of geological correction assessment indices for each monitoring sub-domain within the designated area to obtain the geological leakage correction index for each monitoring sub-domain within the designated area.

[0038] Porosity is the proportion of the volume of voids within the rock mass of the monitoring subdomain to the total volume. High-porosity areas are prone to becoming gas accumulation zones, with faster gas diffusion and increased leakage risk, while low-porosity areas hinder gas diffusion. Porosity values ​​can be obtained using surface acoustic wave (SAW) sensors (the more pores, the slower the SAW propagation speed, and the more severe the sound wave energy attenuation; the sound wave path becomes longer and the propagation time is extended in high-porosity media). Wireless passive SAW sensors are deployed within this monitoring subdomain to measure the sound wave propagation speed (obtained from the standard sound speed of dense rock stored in the data) based on excited SAW. Combined with the sound wave propagation reference speed, the local porosity is calculated as 1 - (sound wave propagation speed / sound wave propagation reference speed). Furthermore, in rock masses with pores, cracks, or anomalies, the sound wave propagation speed will inevitably be less than that of dense, non-porous rocks, so negative values ​​will not occur.

[0039] The microcrack density value is the number of tiny cracks existing per unit volume of rock within the monitoring subdomain. Microcracks can serve as the initial diffusion path for micro-leaks of gas. The increase in microcracks increases the risk of leakage and makes it more concealed. The microcrack density value can be obtained by a surface acoustic wave (SAW) sensor (microcracks cause strong scattering of high-frequency surface acoustic waves, which disperses the signal energy, and the more microcracks there are, the stronger the scattered signal). The SAW emits and receives high-frequency acoustic pulses and monitors the increase in the scattering amplitude of the received signal. The microcrack number density is calculated by the ratio of scattered energy to direct energy, i.e., scattered energy (representing the energy dispersed by cracks) / direct energy (representing the energy transmitted through the intact medium).

[0040] The crack connectivity index measures the degree of interconnection between different cracks within a monitored subdomain. Gas in highly connected crack zones can migrate rapidly, forming leakage acceleration channels. The crack connectivity index can be obtained using surface acoustic wave (SAW) sensors (in connected crack regions, SAW propagation paths are straighter and propagation times are shorter; when cracks are not connected, sound waves detour, increasing propagation time). This involves deploying multiple wireless passive SAW nodes at the boundary and within the monitored subdomain, acquiring node coordinates, and having each node sequentially generate a sound wave, which is received by other nodes. The arrival time of the sound waves between each pair of nodes is recorded. Then, from the source node to the target node, the path with the shortest travel time (the measured time) is calculated, along with the theoretical straight-line time, the straight-line distance (calculated based on the Euclidean distance formula for node coordinates, i.e., from the source node to the target node), and the reference sound velocity. The straight-line distance / reference sound velocity equals the theoretical straight-line time, therefore, the crack connectivity index = measured time / theoretical straight-line time.

[0041] The gas permeability index represents the ability of gas to pass through a rock medium within a monitored subdomain. High permeability areas indicate that gas is more likely to leak and diffuse rapidly. The gas permeability index can be obtained using surface acoustic wave (SAW) sensors (in highly permeable rock formations, sound waves travel slower and attenuate more; permeability reflects the ability of gas to pass through the rock mass). This involves deploying several SAW sensor nodes within the monitored subdomain, exciting SAW pulse signals to propagate sound waves within the subdomain, dividing it into several groups of nodes, and recording the initial sound wave energy emitted by the excited node in each group. The receiving node detects the received sound wave energy, compares the difference between the transmitted and received energy, and combines this with the propagation distance between nodes (calculated based on the Euclidean distance formula) to calculate the attenuation rate of sound wave energy per unit distance in real time. Based on this, the propagation time of the sound wave from the transmitting node to the receiving node is measured, and the propagation speed of the sound wave in the medium is calculated by combining this with the known spatial distance between the nodes. Then, the energy attenuation rate and the sound wave propagation speed of each group of nodes are standardized and weighted, and the average value is calculated based on the weighted average value. The result is the gas permeability index.

[0042] The flow resistance index is the structural strength and continuity that hinders the free flow of gas within the monitored subdomain. Low flow resistance leads to rapid diffusion of leaks. The flow resistance index can be obtained using surface acoustic wave (SAW) sensors (dense barrier areas, such as hard rock zones, reflect a large amount of sound waves, significantly reducing the energy transmitted; the degree of flow resistance can be measured by the energy loss ratio). Specifically, pairs of SAW sensor nodes are deployed within the monitored subdomain. For each pair, one node is used to excite the sound wave, and the other node is used to receive it. The initial sound wave energy emitted by the excitation node is recorded, and the remaining sound wave energy detected by the receiving node after passing through the barrier structure of the monitored subdomain is measured. By comparing the energy loss ratio between the emitted and received energy of each pair and averaging the results, the flow resistance index is obtained.

[0043] The specific steps for obtaining the geological correction assessment index set for each monitoring subdomain within the designated area are as follows: Read the porosity value, microfracture density, and fracture connectivity index of each monitoring subdomain within the designated area, and perform a comprehensive analysis (i.e., first perform standardization processing, and then perform weighted analysis based on the standardization processing, with the weighting coefficients of porosity value, microfracture density, and fracture connectivity index being obtained in the same logical manner as the weighting coefficients of gas diffusion angle value and gas diffusion velocity gradient value), to obtain the rock mass structural fragility index of each monitoring subdomain within the designated area (characterizing the potential risk of increased overall structural fragility and gas leakage due to increased porosity, microfracture development, and increased fracture interconnection within the monitoring subdomain); read the gas permeability index and flow resistance index of each monitoring subdomain within the designated area, and perform a comprehensive analysis (i.e., first perform standardization processing, and then perform weighted analysis based on the standardization processing, with the weighting coefficients of gas permeability index and flow resistance index being obtained in the same logical manner as the weighting coefficients of gas diffusion angle value and gas diffusion velocity gradient value), to obtain the gas diffusion accessibility index of each monitoring subdomain within the designated area (characterizing the ease or difficulty of actual gas diffusion in the rock medium within the monitoring subdomain).

[0044] The specific formula for calculating the geological leakage correction index of a specific monitoring sub-domain within a designated area is as follows: ;in, To set a geological leakage correction index for a specific monitoring sub-domain within the region, To set the rock mass structural fragility index for a specific monitoring subdomain within the region, The structural fragility adjustment coefficient is stored in the database. To determine the gas diffusion accessibility index for a specific monitoring sub-domain within a given area, The diffusion accessibility adjustment coefficients are stored in the database. The coupling suppression adjustment coefficients are stored in the database. These are the interaction adjustment coefficients stored in the database.

[0045] It needs to be explained that, , , , The following steps can be taken to obtain the following: Utilize historical data, combined with the rock mass fragility index and gas diffusion accessibility index, to conduct statistical regression analysis, quantify the specific impact of each factor on the geological leakage correction index, and thus fit the initial weight values. Next, use sensitivity analysis to adjust the value range of each coefficient, observe its impact on the geological leakage correction assessment results, and ensure the stability and rationality of the model. Based on the characteristics of the monitoring subdomain and the actual situation, correct and optimize the initially fitted coefficients, and finally determine the coefficient values ​​applicable to the specific monitoring subdomain.

[0046] The following is a specific implementation example for calculating the geological leakage correction index of a monitoring sub-domain within a designated area. The available data includes the rock mass structural fragility index and gas diffusion accessibility index of five randomly selected monitoring sub-domains within the designated area, as detailed in Table 1 and... Figure 4 As shown: Table 1. Set of monitoring subdomain sequences for geological correction assessment index within the designated area.

[0047] Structural fragility adjustment coefficients stored in the database Approximately 0.467; Diffusion access regulation coefficients stored in the database Approximately 0.384; Coupling suppression adjustment coefficients stored in the database Approximately 1.295; Interaction adjustment coefficients stored in the database Approximately 0.327; Substituting the data from Table 1 and the aforementioned adjustment coefficients into the specific formula for calculating the geological leakage correction index of a certain monitoring sub-domain within the designated area, we obtain: The geological leakage correction index for the first monitoring subdomain within the set area is calculated as ln(1 + (0.713)). 0.467 +0.682 0.384 () / 1.295)×exp(0.327×0.713×0.682)≈0.989; The geological leakage correction index for the second monitoring subdomain within the set area is calculated as ln(1 + (0.594)). 0.467 +0.523 0.384 () / 1.295)×exp(0.327×0.594×0.523)≈0.877; The geological leakage correction index for the third monitoring subdomain within the set area is calculated as ln(1 + (0.462)).0.467 +0.284 0.384 () / 1.295)×exp(0.327×0.462×0.284)≈0.732; The geological leakage correction index for the fourth monitoring subdomain within the designated area is calculated as ln(1 + (0.408)). 0.467 +0.338 0.384 () / 1.295)×exp(0.327×0.408×0.338)≈0.736; The geological leakage correction index for the fifth monitoring subdomain within the designated area is calculated as ln(1 + (0.798)). 0.467 +0.724 0.384 () / 1.295)×exp(0.327×0.798×0.724)≈1.044.

[0048] In this implementation scheme, by introducing various geological structural parameters such as porosity, microcrack density, crack connectivity index, gas permeability index, and flow resistance index, the system can comprehensively identify the structural vulnerability and gas propagation accessibility of the rock mass within the monitoring subdomain. Furthermore, this scheme models gas leakage paths from both structural genesis and diffusion channels, effectively characterizing the amplification or inhibition mechanisms of the geological environment on gas leakage trends. This enhances the adaptability and explanatory power of leakage assessment to the complexity of real rock strata. Secondly, all geological structural parameters relied upon in this step are acquired through a wireless passive SAW sensor network, which has advantages such as no power requirement, real-time data transmission, and wide coverage, making it extremely suitable for mining applications. Deploying in harsh underground environments such as wells enables instantaneous quantitative identification of structural parameters, allowing for efficient regional structural scanning without damaging the rock mass. This significantly improves the practicality and timeliness of the monitoring system. Finally, the system decomposes the five types of structural parameters into two intermediate evaluation indicators—rock mass structural fragility index and gas diffusion accessibility index—based on causal logic. These are then fused to calculate the geological leakage correction index, achieving hierarchical abstraction of the correction logic and explanation of the physical mechanism. Combined with a weight optimization mechanism trained on historical data, the correction model has a clear structure and can dynamically adjust the adjustment coefficient according to the characteristics of the subdomain, thus significantly improving the reliability and accuracy of geological influence correction in leakage judgment.

[0049] Specifically, the monitoring equipment operation data includes signal strength response values, sensitivity values, temperature drift deviation values, calibration drift residual values, and self-excited vibration response anomaly values. The specific steps to obtain the equipment accuracy correction index for each monitoring subdomain within the set area are as follows: Standardize the signal strength response values, sensitivity values, temperature drift deviation values, calibration drift residual values, and self-excited vibration response anomaly values ​​for each monitoring subdomain within the set area; Perform comprehensive analysis on the standardized signal strength response values, sensitivity values, temperature drift deviation values, calibration drift residual values, and self-excited vibration response anomaly values ​​for each monitoring subdomain within the set area to obtain the equipment accuracy correction index for each monitoring subdomain within the set area.

[0050] The signal strength response value is the average instantaneous amplitude of the echo (or sensing signal) received by each sensor in the monitoring subdomain, and the instantaneous amplitude of each sensor can be extracted in real time by the wireless module of the main body.

[0051] Sensitivity values ​​can be obtained from the technical specifications stored in the data.

[0052] The temperature drift deviation value is the average value of the sensor output offset caused by changes in ambient temperature for each sensor. The output offset of each sensor can be obtained through the following steps: A temperature-sensitive path is integrated inside the monitoring device. Specifically, it can be the temperature compensation channel built into the surface acoustic wave (SAW) device, or the thermal element module attached to the gas sensor or pressure sensor. This path is used to sense changes in ambient temperature in real time. Within a set detection period, the temperature change in the set area is collected in real time based on the temperature-sensitive path, and the sensor output change at the corresponding time point is collected simultaneously. Then, the temperature change and the output change are compared and combined with the temperature drift compensation reference curve preset at the factory of the monitoring device to calculate the temperature drift deviation value at the current moment.

[0053] The calibration drift residual value is the mean of the difference between the output value of each sensor and the corresponding historical benchmark calibration output value. The difference of each sensor can be obtained through the following steps: obtain the output curve of the real-time output signal and compare it with the sensor standard response curve stored in the database (such as mean square error (MSE) or mean absolute error (MAE).

[0054] The self-excited vibration response anomaly value is the average of the abnormal output fluctuations of each sensor caused by micro-vibration, loosening, mechanical noise, etc., when there is no significant external physical input. The abnormal output fluctuation of each sensor can be obtained through the following steps: acquire the sensor's output signal, perform statistical analysis on the output signal fluctuation, calculate the output standard deviation per unit time, and set a preset micro-perturbation fluctuation threshold as the judgment threshold. If the short-time standard deviation of the output signal is detected to exceed the set micro-perturbation threshold, it is determined that there is an abnormal self-excited vibration response. After the abnormal state is determined, the maximum amplitude change value in the abnormal fluctuation is extracted as the self-excited vibration response anomaly value.

[0055] The specific formula for calculating the equipment accuracy correction index of a certain monitoring sub-domain within a designated area is as follows: ;in, To set the device accuracy correction index for a specific monitoring sub-domain within a defined area. This refers to the signal strength response value of a specific monitoring sub-domain within a defined area after standardization. These are the signal strength adjustment coefficients stored in the database. The sensitivity value of a specific monitoring sub-domain within the standardized area. The sensitivity adjustment coefficient is stored in the database. The temperature drift deviation value of a certain monitoring sub-domain within the set area after standardization. The temperature drift adjustment coefficient is stored in the database. The calibration drift residual value of a certain monitoring subdomain within the standardized area. The calibration drift adjustment coefficients are stored in the database. The abnormal value of self-excited vibration response in a certain monitoring subdomain within the standardized area. The self-excited vibration adjustment coefficients are stored in the database. These are the superimposed adjustment coefficients stored in the database.

[0056] It needs to be explained that, , , , , , The following steps can be taken to obtain the following: Using historical data, combined with signal strength response values, sensitivity values, temperature drift deviation values, calibration drift residual values, and self-excited vibration response anomalies, statistical regression analysis is performed to quantify the specific impact of each factor on the equipment accuracy correction index, thereby fitting initial weight values. Next, sensitivity analysis is used to adjust the value range of each coefficient and observe its impact on the equipment accuracy correction evaluation results, ensuring the stability and rationality of the model. Based on the characteristics of the monitoring subdomain and the actual situation, the initially fitted coefficients are corrected and optimized, and finally, coefficient values ​​suitable for the specific monitoring subdomain are determined.

[0057] This implementation scheme identifies five key error sources that sensors are prone to accuracy degradation in complex environments, such as underground mines: signal amplitude weakening, decreased sensitivity, temperature sensitivity shift, long-term calibration deviation, and mechanical disturbances caused by structural loosening. Through standardized processing and weighted combination, an equipment accuracy correction index is constructed to provide real-time reliability scoring for the collected data. This introduces an equipment status assessment mechanism at the source, effectively preventing false alarms, missed alarms, or delayed alarms caused by equipment aging, misalignment, or accidental triggering. This ensures the long-term operational stability of the monitoring system. Furthermore, all parameters designed in this step can be implemented through embedded modules within the equipment itself, such as wireless reflection modules and SAW device temperature sensors. The path and vibration interference identification loops are acquired in real time, fully adapting to the deployment requirements of low power consumption, maintenance-free operation, and inaccessibility in mining environments. This results in excellent deployment flexibility and practicality. Finally, the system's adjustment coefficients are quantified through regression analysis of historical operating data to assess the actual impact of five types of equipment errors on monitoring reliability. Combined with sensitivity analysis and subdomain environment fine-tuning mechanisms, the final equipment correction weight combination suitable for specific scenarios is determined. This ensures that the correction logic remains reasonable and reliable under different monitoring points, different equipment aging cycles, or different operating conditions, effectively preventing overfitting or weight distortion. Ultimately, a differentiated response mechanism for equipment accuracy correction is achieved, thereby improving the model's environmental adaptability and algorithm stability.

[0058] Specifically, the steps for intelligent alarm activation for each monitoring sub-domain within a designated area based on the comprehensive gas leak risk index are as follows: The comprehensive gas leak risk index for each monitoring sub-domain within the designated area is compared and analyzed with a preset comprehensive gas leak risk index threshold. If the comprehensive gas leak risk index for each monitoring sub-domain within the designated area is lower than or equal to the preset comprehensive gas leak risk index threshold, no alarm is triggered (for that monitoring sub-domain). If the comprehensive gas leak risk index for each monitoring sub-domain within the designated area is higher than the preset comprehensive gas leak risk index threshold, an alarm is triggered (for that monitoring sub-domain). The pre-set alarm measures are as follows: a leak alarm message is sent to the control center, and the location and risk index of the high-risk sub-domain are marked on the monitoring terminal interface. The local ventilation system or positive pressure exhaust system of the area covered by the sub-domain is automatically activated to increase the air circulation rate and reduce the concentration of gas accumulation. If the monitored sub-domain is a personnel activity area, an evacuation command is immediately pushed to the underground personnel positioning terminal, and the evacuation status is reported to the superior joint control platform. Then, the emergency broadcast system or audible and visual alarm device is activated to issue continuous warnings, and the alarm event information is written to the data log at the same time for subsequent leak evolution tracking and system response retrospective analysis.

[0059] In this implementation plan, the monitoring sub-domains are judged point by point based on the comprehensive gas leak risk index. The alarm triggering mechanism combines the comprehensive evaluation results of multiple sub-indicators to impose penalties, thereby realizing a regional hierarchical response. This effectively avoids global redundant response or delayed response at high-risk points, thereby improving the local decision-making accuracy and response sensitivity of the overall system. Secondly, a complete linkage mechanism is designed, including alarms to the control center, real-time visual marking of risk sub-domains on the terminal, linkage broadcasting, and data log feedback. This forms a closed-loop logical chain from intelligent judgment to on-site handling and data archiving, thereby improving emergency response efficiency and avoiding response silos and information chain breaks. This significantly enhances the overall stability of the system's operation and accident control capabilities. Finally, after the alarm is triggered, the system not only automatically ventilates but also links personnel terminals to send evacuation signals. This is particularly suitable for work scenarios such as mines where the distribution of workers is not fixed and communication is limited, thereby effectively improving the safety resilience and risk transfer capability of the work area in the event of a sudden leak.

[0060] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0061] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. An intelligent gas leak monitoring system based on wireless passive detection technology, characterized in that, include: The monitoring data acquisition module is used to acquire gas monitoring data of several monitoring sub-domains within a set area in real time. The gas monitoring data includes gas behavior data, geological structure data, and monitoring equipment operation data. The monitoring data feature analysis module is used to extract features from the gas monitoring data of each monitoring sub-domain within the set area to obtain a set of leakage assessment indices for each monitoring sub-domain within the set area, including the initial gas leakage risk index, the geological leakage correction index, and the equipment accuracy correction index. The gas leak comprehensive assessment module is used to comprehensively analyze the leak assessment index set of each monitoring sub-domain within a set area to obtain the comprehensive gas leak risk index of each monitoring sub-domain within the set area. The gas leak feedback module is used to provide intelligent alarms for each monitoring sub-domain of a designated area based on a comprehensive gas leak risk index.

2. The intelligent gas leak monitoring system based on wireless passive detection technology according to claim 1, characterized in that, The specific formula for calculating the comprehensive gas leak risk index of a specific monitoring sub-area within a designated area is as follows: ； in, , , , The following are, in order: comprehensive gas leak risk index, initial gas leak risk index, geological leak correction index, and equipment accuracy correction index for a specific monitoring sub-domain within the designated area. , , , The coefficients are, in order, the initial adjustment coefficient, the geological correction adjustment coefficient, the equipment correction adjustment coefficient, and the collaborative adjustment coefficient stored in the database.

3. The intelligent gas leak monitoring system based on wireless passive detection technology according to claim 1, characterized in that, The gas behavior data includes gas diffusion angle values, gas diffusion velocity gradient values, gas density anomaly index, gas combustion anomaly index, and gas specific heat capacity values. The specific steps to obtain the initial gas leakage risk index for each monitoring sub-domain within the designated area are as follows: The gas behavior data of each monitoring sub-domain within the designated area are comprehensively analyzed to obtain a set of gas assessment indices for each monitoring sub-domain within the designated area, including the gas propagation risk index and the gas risk response index. The environmental impact factors of each monitoring sub-domain within the designated area are obtained, and combined with the gas assessment index set for comprehensive analysis to obtain the initial gas leakage risk index of each monitoring sub-domain within the designated area.

4. The intelligent gas leak monitoring system based on wireless passive detection technology according to claim 3, characterized in that, The specific steps to obtain the gas assessment index set for each monitoring sub-domain within the designated area are as follows: The gas diffusion angle and gas diffusion velocity gradient values ​​of each monitoring sub-domain within the set area are read and comprehensively analyzed to obtain the gas propagation risk index of each monitoring sub-domain within the set area. The gas density anomaly index, gas combustion anomaly index, and gas specific heat capacity value of each monitoring sub-domain within the set area are read and comprehensively analyzed to obtain the gas combustion risk response index of each monitoring sub-domain within the set area.

5. The intelligent gas leak monitoring system based on wireless passive detection technology according to claim 1, characterized in that, The geological structure data includes porosity values, microfracture density, fracture connectivity index, gas permeability index, and flow resistance index. The specific steps for obtaining the geological leakage correction index for each monitoring sub-domain within the designated area are as follows: The geological structure data of each monitoring subdomain within the designated area are comprehensively analyzed to obtain a set of geological correction assessment indices for each monitoring subdomain within the designated area, including the rock mass structure fragility index and the gas diffusion accessibility index. A comprehensive analysis of the geological correction assessment index set for each monitoring subdomain within the designated area is conducted to obtain the geological leakage correction index for each monitoring subdomain within the designated area.

6. The intelligent gas leak monitoring system based on wireless passive detection technology according to claim 5, characterized in that, The specific steps to obtain the set of geological correction assessment indices for each monitoring sub-domain within the designated area are as follows: The porosity value, microcrack density, and crack connectivity index of each monitoring subdomain within the set area are read and comprehensively analyzed to obtain the rock mass structural fragility index of each monitoring subdomain within the set area. The gas permeability index and flow resistance index of each monitoring sub-domain within the set area are read and comprehensively analyzed to obtain the gas diffusion accessibility index of each monitoring sub-domain within the set area.

7. The intelligent gas leak monitoring system based on wireless passive detection technology according to claim 5, characterized in that, The specific formula for calculating the geological leakage correction index of a specific monitoring sub-domain within a designated area is as follows: ； in, , , The indicators, in order, are the geological leakage correction index, rock mass fragility index, and gas diffusion accessibility index for a specific monitoring sub-domain within the designated area. , , , The coefficients are, in order, the structural vulnerability adjustment coefficient, the diffusion accessibility adjustment coefficient, the coupling inhibition adjustment coefficient, and the interaction adjustment coefficient stored in the database.

8. The intelligent gas leak monitoring system based on wireless passive detection technology according to claim 1, characterized in that, The monitoring equipment operating data includes signal strength response values, sensitivity values, temperature drift deviation values, calibration drift residual values, and self-excited vibration response anomaly values. The specific steps for obtaining the equipment accuracy correction index for each monitoring sub-domain within the set area are as follows: The signal strength response value, sensitivity value, temperature drift deviation value, calibration drift residual value, and self-excited vibration response anomaly value of each monitoring subdomain within the set area are standardized. By comprehensively analyzing the signal strength response value, sensitivity value, temperature drift deviation value, calibration drift residual value, and self-excited vibration response anomaly value of each monitoring subdomain within the standardized set area, the equipment accuracy correction index of each monitoring subdomain within the set area is obtained.

9. The intelligent gas leak monitoring system based on wireless passive detection technology according to claim 8, characterized in that, The specific formula for calculating the equipment accuracy correction index of a certain monitoring sub-domain within a designated area is as follows: ； in, To set the device accuracy correction index for a specific monitoring sub-domain within a defined area. , , , , The values, in order, are the signal strength response, sensitivity, temperature drift deviation, calibration drift residual, and self-excited vibration response anomaly values ​​for a specific monitoring subdomain within the standardized area. , , , , , The coefficients stored in the database are, in order: signal strength adjustment coefficient, sensitivity adjustment coefficient, temperature drift adjustment coefficient, calibration drift adjustment coefficient, self-excited vibration adjustment coefficient, and superposition adjustment coefficient.

10. The intelligent gas leak monitoring system based on wireless passive detection technology according to claim 1, characterized in that, The specific steps for intelligent alarm generation for each monitoring sub-domain of a designated area based on the comprehensive gas leak risk index are as follows: The comprehensive gas leak risk index of each monitoring sub-domain within the designated area is compared and analyzed with the preset comprehensive gas leak risk index threshold. If the comprehensive gas leak risk index of each monitoring sub-domain within the set area is lower than or equal to the preset comprehensive gas leak risk index threshold, no alarm will be triggered; If the comprehensive gas leak risk index of each monitoring sub-domain within the set area is higher than the preset comprehensive gas leak risk index threshold, an alarm will be triggered and preset alarm measures will be taken.

Images