A gas detection system and apparatus

Abstract

The application provides a gas detection system and device, relates to the technical field of gas detection, and the system comprises: a configuration module, which is used for type selection and configuration of a monitoring sensor according to a monitoring gas; a reference construction module, which is used for constructing a reference grid density based on a minimum coverage range of the monitoring sensor; a monitoring node establishment module, which is used for calculating the importance of a region to be monitored and configuring a monitoring node; a cooperative analysis module, which is used for acquiring a monitoring sensor array and establishing a correlation cooperative coefficient; and a detection module, which is used for calling a decision fusion network to make an abnormal decision based on the correlation cooperative coefficient on monitoring data and generating a gas detection result. Through the application, the technical problem that the gas detection precision is low due to the fact that the selection and configuration of the sensor are not adjusted according to actual demands in the prior art can be solved, the sensor is reasonably configured according to the gas type and the importance of the region, and the precision of gas detection is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of gas detection, and in particular to a gas detection system and device. BACKGROUND

[0002] Gas detection technology is widely used in industrial production, environmental monitoring, public safety and other fields, aiming to monitor and detect harmful gases in the air in real time to ensure personnel safety, environmental health and normal operation of equipment. However, in complex scenarios, the selection and configuration of gas detection equipment may not be flexible enough, resulting in unsatisfactory detection results. Different sensors have significant differences in sensitivity and selectivity to specific gases, and the selection of inappropriate sensors may reduce the accuracy of monitoring results, especially in cases where the types of gases are complex, the concentrations vary dramatically, or the environmental conditions in the region differ greatly. Many sensors only work at a fixed accuracy, and existing gas detection often does not flexibly select and configure sensors according to actual application requirements (such as the types of gases to be monitored, the characteristics of the monitoring area, etc.).

[0003] In summary, the prior art has the technical problem of low gas detection accuracy due to the lack of adjustment of sensor selection and configuration according to actual requirements. SUMMARY

[0004] The purpose of the present application is to provide a gas detection system and device to solve the technical problem of low gas detection accuracy in the prior art due to the lack of adjustment of sensor selection and configuration according to actual requirements.

[0005] In view of the above problems, the present application provides a gas detection system and device.

[0006] In a first aspect, the present application provides a gas detection system, wherein the gas detection system comprises: a configuration module configured to, after determining a monitored gas, select and configure a monitoring sensor according to the monitored gas, the monitoring sensor comprising a first-precision sensor and a second-precision sensor; a reference construction module configured to obtain a minimum coverage range of the monitoring sensor and construct a reference grid density based on the minimum coverage range; a monitoring node establishment module configured to calculate the importance of a region for a region to be monitored, and configure a monitoring node according to the importance of the region and the reference grid density; a collaborative analysis module configured to obtain an accuracy difference between the first-precision sensor and the second-precision sensor, and distribute the monitoring sensor according to the accuracy difference and the importance of the node of the monitoring node, establish a monitoring sensor array, and establish an associated collaborative coefficient of the monitoring sensor; and a detection module configured to read monitoring data of the monitoring sensor array, call a decision fusion network to make an abnormal decision based on the associated collaborative coefficient for the monitoring data, and generate a gas detection result.

[0007] Optionally, the fusion identification unit is used to call the decision fusion network and perform fusion decision analysis: a: after the monitoring data is synchronized and aligned, a spatial anomaly correlation analysis based on the correlation synergy coefficient is performed through the spatial correlation channel to establish a first identification anomaly; b: a time series concentration anomaly analysis of the monitoring results at the same location is performed on the monitoring data to establish a second identification anomaly; c: a joint anomaly decision is made on the first identification anomaly and the second identification anomaly.

[0008] Optionally, a positioning unit is used to establish an abnormal positioning point based on a joint abnormality decision; a clustering unit is used to perform fine-tuning clustering of monitoring sensors based on the abnormal positioning point and establish a fine-tuning clustering result; an adjustment unit is used to fine-tune the position of the monitoring sensor based on the fine-tuning clustering result and obtain an adjusted additional monitoring data set; a compensation unit is used to compensate for the gas detection result based on the additional monitoring data set and generate an updated gas detection result.

[0009] Optionally, the importance calculation unit is used to calculate the region importance using the formula as follows:

[0010] ;in, Represents the importance of the region and indicates the location In time The importance index of Characterized by location The number of high-risk equipment per unit area of ​​the center, Characterizes the highest device density, Characterization by The real-time leakage probability obtained by simulation, is the exponential influence coefficient of device density, is the index influence coefficient, Characterizes the strength of the pressure gradient, Representation time The wind speed, Characterizes the reference wind speed, used to normalize the wind speed effect, Characterizes the angle between the wind speed direction and the main diffusion direction of the region, is the cosine coupling coefficient of the angle between wind direction and regional principal axis.

[0011] Optionally, an importance segmentation unit is configured to determine an importance segmentation constraint based on the precision difference using an importance constraint network; an importance screening unit is configured to screen the node importance based on the importance segmentation constraint to determine an initial distribution of the first precision sensor; a screening unit is configured to perform distribution weakness analysis according to the initial distribution of the first precision sensor, and perform additional screening based on the distribution weakness analysis result and the node importance to establish an additional distribution of the first precision sensor; and a sensor distribution unit is configured to complete the monitoring sensor distribution according to the additional distribution and the initial distribution.

[0012] Optionally, a gas release module is configured to move to a corresponding random position point to perform gas release after the random position point is configured, and generate a release timing record; and a feedback module is configured to perform deviation verification based on a gas detection result and the release timing record after the gas detection result is received, the deviation verification including position deviation verification and sensitivity deviation verification, establish an identification feedback based on a deviation verification result, and perform system optimization management based on the identification feedback.

[0013] Optionally, a collaborative calculation unit is configured to calculate a correlation collaborative coefficient by a formula as follows:

[0014] ; wherein, a correlation collaborative coefficient between the monitoring sensor and the monitoring sensor , a precision difference factor, , a measurement error percentage of the monitoring sensor , a measurement error percentage of the monitoring sensor , a Euclidean distance between the monitoring sensor and the monitoring sensor , and a node importance, a spatial attenuation coefficient.

[0015] In a second aspect, the present application further provides a gas detection device, comprising: at least one processor; a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to implement the gas detection system of any one of the first aspect.

[0016] Optionally, a pre-warning module is configured to, after receiving the gas detection result, match a pre-warning level according to the gas detection result, configure a pre-warning scheme according to the pre-warning level matching result and the gas detection result, and perform pre-warning according to the pre-warning scheme.

[0017] Optionally, a self-monitoring module is configured to, after reading the monitoring data, perform same-position monitoring deviation verification of the first precision sensor and the second precision sensor according to the monitoring data, generate a same-position deviation verification result, and report a monitoring anomaly according to the same-position deviation verification result.

[0018] The one or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0019] The configuration module is configured to, after determining a monitored gas, perform type selection and configuration of a monitoring sensor according to the monitored gas, the monitoring sensor including a first precision sensor and a second precision sensor; the reference construction module is configured to obtain a minimum coverage range of the monitoring sensor, and construct a reference grid density based on the minimum coverage range; the monitoring node establishment module is configured to perform regional importance calculation on a region to be monitored, and configure a monitoring node according to the regional importance calculation result and the reference grid density; the collaborative analysis module is configured to obtain an accuracy difference of the first precision sensor and the second precision sensor, perform monitoring sensor distribution according to the accuracy difference and node importance of the monitoring node, establish a monitoring sensor array, and establish an associated collaborative coefficient of the monitoring sensor; and the detection module is configured to read monitoring data of the monitoring sensor array, call a decision fusion network to perform abnormal decision based on the associated collaborative coefficient on the monitoring data, and generate a gas detection result. That is, by dynamically selecting sensors of different accuracies according to a monitored gas type, constructing a reference grid density according to a minimum coverage range of a monitoring sensor, configuring a sensor array in combination with importance of a region to be monitored, and establishing an associated collaborative coefficient, gas detection is performed, such as detecting gas components, such as volatile organic compounds, by various organic matter measuring instruments, effectively identifying potential gas abnormal problems, and improving the accuracy of gas detection.

[0020] The above description is only a summary of the technical solutions of the present application. In order to more clearly understand the technical means of the present application, the contents of the specification can be implemented, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application are described below. It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present application, nor are they intended to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings described below are only exemplary, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of the provided drawings.

[0022] Figure 1 A structural schematic diagram of a gas detection system according to the application.

[0023] Figure 2 A structural schematic diagram of a gas detection device according to the application.

[0024] Legend: configuration module 11, reference construction module 12, monitoring node establishment module 13, collaborative analysis module 14, detection module 15. DETAILED DESCRIPTION

[0025] The application provides a gas detection system and device, which solves the technical problem of low gas detection accuracy in the prior art due to the fact that the selection and configuration of sensors are not adjusted according to actual needs. By dynamically selecting sensors of different accuracies according to the type of monitored gas, constructing a reference grid density according to the minimum coverage range of the monitoring sensor, configuring a sensor array in combination with the importance of the monitored area, and establishing an associated collaborative coefficient, gas detection is performed, such as detecting gas components such as volatile organic compounds by various organic matter measuring instruments, effectively identifying potential gas abnormal problems, and improving the accuracy of gas detection.

[0026] The technical solutions in the application will be described clearly and completely below with reference to the drawings. Obviously, the described embodiments are only a part of the embodiments of the application, rather than all the embodiments of the application. It should be understood that the application is not limited by the example embodiments described herein. Based on the embodiments of the application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the application. In addition, it should be noted that, for convenience of description, only parts related to the application are shown in the drawings, not all.

[0027] Embodiment one, please refer to the attached Figure 1 The application provides a gas detection system, wherein the gas detection system comprises:

[0028] The configuration module 11 is configured to select and configure monitoring sensors according to the monitored gas after determining the monitored gas, wherein the monitoring sensors comprise first-accuracy sensors and second-accuracy sensors.

[0029] Specifically, first, the monitoring gas such as carbon monoxide, sulfur dioxide, nitrogen oxides, etc. is determined. Different gases have different molecular structures and characteristics, so their monitoring also has different requirements. For example, for flammable gas, an infrared absorption method sensor can be selected, because gas molecules have unique absorption characteristics in the infrared spectrum, so by measuring the degree of absorption of infrared light by the gas, the gas concentration can be accurately determined; for harmful gas, an electrochemical sensor can be selected, because electrochemical sensors have higher sensitivity at low concentrations. Then, according to the characteristics of the selected gas and the environment it is in, consult the relevant technical specifications and sensor performance data sheets to determine the appropriate sensor type. That is, the gas parameters of the monitoring gas are input, and the combination of the first precision sensor and the second precision sensor is automatically matched. Generally, one sensor has higher precision and the other has lower precision. In the same system, high-precision sensors and lower-precision but more economical sensors are combined to achieve complementary advantages.

[0030] Exemplarily, the gas parameters of the monitoring gas are input, and the first precision (TDLAS laser sensor) and the second precision (MEMS sensor) are automatically matched. The TDLAS laser sensor is based on laser absorption spectroscopy technology and can accurately measure the concentration of the gas, especially suitable for high-precision detection of low-concentration gas. By adjusting the laser wavelength to match the target gas absorption line, the light intensity attenuation is measured to calculate the gas concentration. The MEMS sensor (Micro Electro Mechanical System sensor) is a common low-cost, low-precision gas sensor widely used in monitoring conventional gases based on metal oxide resistance changes. The precision of the two is complementary, covering the full range, and can verify false positives. TDLAS as the gold standard ensures the credibility of key data; MEMS expands the monitoring dimension and improves system robustness.

[0031] After determining the sensor, the appropriate number and type of first-precision sensors and second-precision sensors are configured according to the size of the monitoring area and the monitoring requirements. By selecting and configuring appropriate sensors, efficient and accurate monitoring of specific gases is ensured, which helps to improve the accuracy and reliability of monitoring data.

[0032] The reference modeling module 12 is configured to obtain a minimum coverage range of the monitoring sensor and construct a reference grid density based on the minimum coverage range.

[0033] Specifically, after determining the monitoring sensors, the minimum coverage range of each monitoring sensor is obtained according to the working characteristics and monitoring capabilities of the monitoring sensor, that is, the minimum area range that the sensor can effectively monitor, which is usually affected by the sensitivity, working conditions, detection range and environmental factors of the sensor. For example, some gas sensors have high sensitivity within a certain concentration range, but as the monitoring range expands, its detection capability may gradually weaken. Therefore, the minimum coverage range refers to the minimum area or minimum concentration range that the sensor can accurately and effectively detect. Usually, by reading the technical specifications of the sensor, the detection range and minimum detection concentration of the sensor are understood, so as to determine the effective detection radius or distance of the sensor, which is usually the minimum area that the sensor can reliably detect the gas. At the same time, according to the characteristics of the detection environment, such as wind speed, temperature, humidity, obstacles, etc., these factors may affect the coverage range of the sensor, and the minimum coverage range of the sensor is determined together.

[0034] Based on the minimum sensor coverage radius, the reference grid density is set according to the size of the monitoring area, and the grid density determines the deployment spacing of the sensor, that is, how many sensors are needed per unit area to ensure coverage of the entire area. By calculating the minimum coverage range of the monitoring sensor, a reasonable grid density can be determined, so as to ensure that the sensor can effectively cover and provide accurate monitoring data in the entire monitoring area. After determining the grid density, the monitoring area can be subdivided into multiple grid units, and a corresponding sensor is configured in each grid unit. When configuring the sensor, appropriate consideration is given to factors such as the trend of gas concentration change in the area, the importance of the monitoring target, etc., for example, the configuration of sensors is densified near the gas leakage source. The reference grid is constructed according to the calculated grid density in the monitoring area, and the layout of the grid can be square, hexagonal or other shapes, depending on the geometric characteristics of the monitoring area and the layout of the sensor. The sensor is arranged at the center or appropriate position of each grid unit, ensuring that the entire monitoring area is covered by the sensor without monitoring blind area.

[0035] Exemplarily, according to the minimum sensor coverage radius r, the side length of the grid is set to 2r, aiming to ensure that there is no blind area between sensors in the grid, while maintaining a reasonable spatial distribution and avoiding the deployment of redundant sensors. The area is divided by the Voronoi polygon algorithm, and in each Voronoi polygon, the sensor is responsible for monitoring the gas concentration in the area. In the Voronoi polygon grid, the sensors are distributed at the center of each grid according to the previously set grid density, ensuring that each sensor can cover its responsibility area and the entire monitoring area can be effectively monitored. The Voronoi polygon grid is a graph that divides the area according to certain rules. In the area of each polygon, the sensor closest to the boundary point of the polygon is the center sensor of the polygon. Simply put, each sensor will create a responsibility area, i.e. the area that the sensor can most effectively monitor, which is defined by the Voronoi polygon boundary.

[0036] With reasonable grid density settings, it can be ensured that there is no blind area in the monitoring area, and the gas concentration of all areas can be effectively monitored. For example, the minimum effective monitoring radius of the sensor is 20 meters, and accordingly the side length of the grid is determined to be 40 meters, i.e. the monitoring area of each sensor is a square grid with a side length of 40 meters. The 120m x 120m area will be divided into 9 square grids with a side length of 40 meters, and a sensor will be placed at the center of each grid. Each sensor is responsible for monitoring the nearest area, forming a Voronoi diagram (Voronoi polygon grid) to ensure that the monitoring area has no overlap and no blind area.

[0037] The monitoring node establishment module 13 is configured to calculate the area importance of the area to be monitored, and configure the monitoring node according to the area importance calculation result and the reference grid density.

[0038] Further, the monitoring node establishment module 13 in the gas detection system is further configured to:

[0039] The area importance is calculated by the formula as follows:

[0040] ; wherein, characterizes the area importance, indicating the importance index of the position at time , characterizes the number of high-risk equipment per unit area centered at the position , characterizes the highest equipment density, characterizes the real-time leakage probability obtained by simulation, is an exponential influence coefficient of equipment density, is an exponential influence coefficient, is an exponential influence coefficient, characterizes the air pressure gradient strength, characterizing time characterizing wind speed, characterizing reference wind speed for normalizing wind speed influence, characterizing the angle between wind direction and the main diffusion direction of the area, is the cosine coupling factor for the angle between wind direction and the main axis of the area.

[0041] Specifically, in gas monitoring and risk assessment, the area importance is used to quantify the monitoring priority of a certain area. Places with high area importance need more monitoring resources because there may be higher risks. The formula for calculating area importance is as follows: ; wherein, characterizing area importance, indicating the importance index of position at time . characterizing the number of high-risk equipment per unit area centered at position , which is a factor for measuring the density of risk sources in the area, reflecting the contribution of equipment to gas leakage risk. characterizing the maximum equipment density, which is a constant representing the maximum limit of equipment density, used for normalization to ensure fair comparison of equipment density between different areas. The larger the ratio of , the more equipment-intensive the area is, and therefore the higher its importance. α is the exponential influence coefficient of equipment density, used to adjust the degree of contribution of equipment density to area importance. Different application scenarios may require different values of α in order to give equipment density appropriate weight according to actual risk.

[0042] characterizing the real-time leakage probability obtained by (computational fluid dynamics) simulation, reflecting the possibility of gas leakage at position at time t. CFD is a numerical simulation technique that can be used to predict fluid flow. In practical applications, gas leakage diffusion is complex and influenced by environmental factors such as air pressure, temperature, wind speed, etc. CFD simulation can calculate the leakage probability of a certain area based on these factors. CFD simulation usually predicts the process of gas diffusion through numerical methods such as finite element method. , 1 means if there is no leakage risk, the contribution of the area is 1, The larger the value of , the higher the risk of leakage in the area, thereby increasing the risk value of the area.

[0043] is the exponential influence coefficient, used to adjust the influence of air pressure gradient on area importance. By adjusting the value of , the sensitivity of air pressure gradient to area importance can be controlled, for example, When =1, the impact of the barometric gradient is linearly related to it, and When >1, the impact of the barometric gradient is amplified. The barometric gradient intensity, i.e., the position The barometric gradient intensity at time t. The barometric gradient refers to the degree of change in air pressure in space, which is often an important factor in gas leakage diffusion. The stronger the barometric gradient, the faster the gas diffusion speed and the wider the leakage range. The calculation in exponential form makes the impact of the barometric gradient on the regional importance non-linear, which means that the greater the barometric gradient, the stronger the effect on the regional importance.

[0044] The wind speed at time t, which is an important factor in gas diffusion. The greater the wind speed, the faster the gas diffusion speed. The reference wind speed, used to normalize the wind speed impact, so that the impact under different wind speed conditions can be compared. The angle between the wind direction and the main diffusion direction of the region, reflecting the actual impact of the wind direction on gas diffusion. If the wind direction is consistent with the direction of gas diffusion, the gas will be quickly diffused and the risk of the region will increase; if the directions are opposite, the gas diffusion speed will slow down and the risk of the region will be lower. The cosine coupling coefficient of the wind direction-region main axis angle, used to adjust the impact between the wind direction and the main diffusion direction of the region. When the angle between the wind direction and the diffusion direction is small, the gas diffusion speed is fast and the risk of the region increases; when the angle is large, the diffusion speed slows down and the risk decreases.

[0045] For example, assume that gas detection is carried out in a factory area, the equipment density of the region is 10 high-risk equipment per square meter, the maximum equipment density is 15 per square meter, the exponential impact coefficient α=2, the exponential impact coefficient β=1.5, the cosine coupling coefficient of the wind direction-region main axis angle γ=0.9. The real-time leakage probability obtained by CFD simulation is 0.4, the barometric gradient intensity is 0.1 Pa / m, the current wind speed is 5 m / s, the reference wind speed is 10 m / s, and the angle between the wind speed and the diffusion direction is 30°. Substitute these values into the above formula, and the importance value of the region calculated is approximately equal to 1.01, indicating that under the given parameter conditions, the monitoring priority of the region is high and it is a region that needs more attention.

[0046] ​The region importance of the region to be detected is calculated by using a formula, and according to the region importance and the reference grid density, it is determined how many monitoring nodes are arranged in the region. The reference grid density determines how many sensors are needed in each grid to ensure coverage of the region. For example, in a high importance region, more sensors will be arranged to ensure higher monitoring density; in a low importance region, the number of sensors can be reduced. If the number of high-risk devices in a region is dense, and the wind speed in the region is low, and the air pressure gradient is large, the importance value of the region will be relatively high, and therefore more sensors need to be arranged and monitored. Assuming that the region importance of a certain region is higher than that of other regions, more sensors will be added in the region, and monitoring nodes will be arranged in places with higher region importance. By calculating the region importance and configuring sensors according to the result, more monitoring resources are ensured for high-risk regions, improving monitoring efficiency and detection accuracy.

[0047] The collaborative analysis module 14 is configured to obtain the accuracy difference between the first accuracy sensor and the second accuracy sensor, and to distribute the monitoring sensors according to the accuracy difference and the node importance of the monitoring nodes, to establish a monitoring sensor array, and to establish a correlation coefficient of the monitoring sensors.

[0048] Further, the collaborative analysis module 14 in the gas detection system is further configured to:

[0049] The importance segmentation unit is configured to determine an importance segmentation constraint based on the accuracy difference using an importance constraint network; the importance screening unit is configured to screen the node importance based on the importance segmentation constraint to determine an initial distribution of the first accuracy sensor; the screening unit is configured to perform a distribution weakness analysis according to the initial distribution of the first accuracy sensor, to perform a new screening with the distribution weakness analysis result and the node importance, and to establish an additional distribution of the first accuracy sensor; and the sensor distribution unit is configured to complete the distribution of the monitoring sensors according to the additional distribution and the initial distribution.

[0050] Specifically, the accuracy difference between the first accuracy sensor and the second accuracy sensor is calculated according to the accuracy of the two sensors, which is obtained by comparing the test results of the two sensors under the same environmental conditions. For example, under the same gas concentration, the error of the first accuracy sensor can be ±0.5%, while the error of the second accuracy sensor can be ±5%, and the accuracy difference is 5%-0.5%=4.5%. The accuracy difference refers to the difference in accuracy of the output results of the first accuracy sensor and the second accuracy sensor in actual detection.

[0051] According to the specific requirements and goals of the monitoring area, an importance constraint network is established. In the importance constraint network, different monitoring areas will be divided into multiple importance levels according to their importance (such as equipment density, leakage risk, wind speed, pressure difference, etc.). The importance constraint network is a mathematical model used to analyze and set the relationship between area importance and sensor distribution. In this network, the monitoring needs of the area will affect the configuration of the sensors, including the distribution of first-precision sensors and second-precision sensors. The importance segmentation constraint is used to limit the allocation of sensor types and quantities according to the different importance values of the area. High-importance areas will be constrained to place more high-precision sensors, while low-importance areas may only place low-precision sensors.

[0052] Each monitoring node (i.e. the location of the sensor) has a certain node importance, which is usually calculated by an importance formula, including the number of high-risk equipment, gas leakage probability, gas pressure, wind speed, etc. Each monitoring node (i.e. each grid or location within the monitoring area) is screened according to the importance value of the node. After screening by node importance, it is determined whether to place a first-precision sensor according to the importance of each node, thereby determining the initial distribution of first-precision sensors. That is, in the preliminary configuration process, according to the screening results of the node importance, high-precision sensors (such as TDLAS laser sensors) are placed in the preliminary layout of the monitoring area. For example, through precision difference analysis and node importance screening, it is determined to place 25 first-precision sensors in high-risk areas, 10 first-precision sensors in medium-risk areas, and 1 first-precision sensor in low-risk areas.

[0053] According to the initial distribution of first-precision sensors, a distribution weakness analysis is performed on the placement of sensors to identify the shortcomings in the distribution of sensors, i.e. those areas with less coverage or insufficient precision. Through a comprehensive analysis of the sensor distribution within the monitoring area, it is determined which areas have insufficient monitoring precision or insufficient monitoring coverage, and further optimization and supplementation are performed. Using data analysis methods such as spatial analysis, nearest neighbor analysis, etc., the coverage of sensors in each area is evaluated. By comparing the response precision of sensors in different areas and combining the importance of the area, high-risk areas and areas with lower monitoring precision are identified. For example, assuming that in a monitoring area with an area of 1000 meters x 1000 meters, 70 first-precision sensors are preliminarily placed, area A (a high-risk gas leakage area) has only 2 sensors and the distance is far, which cannot effectively monitor the gas concentration in this area; area B (a device-intensive area) has only 3 sensors due to large wind speed changes, and the monitoring effect is poor.

[0054] According to the results of the weakness analysis, combined with the node importance, the areas that need to add sensors are screened out, ensuring that when arranging sensors in weak areas, not only the lack of coverage is considered, but also the number and accuracy of the added sensors are determined according to the importance of the nodes. According to the importance of the area, it is determined whether more sensors need to be arranged; according to the accuracy requirement of the weak area, it is determined whether to arrange the first-precision sensor; for the area with higher risk, the first-precision sensor is preferentially selected to be added. For example, area A is a high-risk area, and the node importance is very high, so more first-precision sensors need to be added in this area. On the other hand, area B may be in a medium-risk area, and the node importance is low, so it may only need to add some second-precision sensors.

[0055] After screening out the areas that need to add sensors, the next step is to perform additional distribution, that is, to arrange more first-precision sensors in weak areas or areas with insufficient accuracy. After additional distribution, the final sensor layout will include the initial arrangement and additional distribution, forming an efficient and accurate monitoring array. Additional distribution refers to the arrangement of additional sensors based on the results of the weak distribution analysis and the original sensor arrangement, which usually supplements the weak areas under the existing sensor configuration, ensuring the comprehensiveness and accuracy of the monitoring system. By distributing sensors with different accuracies in different areas, resources are maximized, the overall efficiency of the monitoring system is improved, unnecessary high-precision sensor investment is reduced, and the accuracy of the monitoring area is ensured.

[0056] Through initial distribution and additional distribution, the arrangement of monitoring sensors in the entire monitoring area is completed. The monitoring sensor array refers to the arrangement of all sensors in the monitoring area through reasonable distribution, forming a sensor network with extensive coverage and high-efficiency monitoring capability. According to the node importance, area risk, and other conditions, the first-precision sensors are preliminarily arranged to form the initial distribution, and the placement position of each sensor depends on the risk level of the selected node and the monitoring accuracy requirement. Through weakness analysis and node importance screening, the monitoring areas that need to be further strengthened are found, and more sensors are added in these areas, especially first-precision sensors, second-precision sensors, or the arrangement of sensors is adjusted, so that the original layout is supplemented in areas with insufficient layout, forming additional distribution.

[0057] After the initial sensor distribution, it is also necessary to consider whether the location of each sensor can maximize its monitoring effectiveness. In this process, the position of the sensor can be fine-tuned. Each sensor can be fine-tuned at the center of the monitoring node it is located in, moving a certain distance to optimize coverage or improve monitoring accuracy. The direction and amplitude of fine-tuning can be adjusted based on the specific needs of the area, the mutual interference between sensors, the direction of air flow, and other factors. Specifically, through real-time monitoring data analysis of the sensors, those with low monitoring accuracy or unstable data, usually located in areas with greater interference, or greatly affected by environmental conditions (such as wind speed, air flow direction, etc.), are identified. Under the premise of maintaining the original monitoring range, the position of these sensors is slightly adjusted, usually moving a certain degree along the center of the node it is located in. For example, the sensor can be fine-tuned along the direction of the air flow or the blank area of the coverage area to ensure more comprehensive and accurate coverage.

[0058] After initial distribution, additional distribution, and fine-tuning, a complete monitoring sensor array is finally formed. At this point, each node in the array is equipped with appropriate sensors and is reasonably configured according to the needs of the monitoring area. The monitoring sensor array not only contains high-precision first-precision sensors but also contains second-precision sensors to ensure that the needs of different risk areas are met. The layout of the array is continuously optimized through continuous monitoring and adaptive adjustment as the environment changes or needs change, ensuring that each high-risk area is adequately monitored with high precision, and other low-risk areas are also adequately monitored. By deploying the sensor array and continuously optimizing the arrangement of sensors, the monitoring accuracy and coverage rate are optimized to the best state. The sensor array will be arranged according to the importance and risk level of the area to ensure that high-risk areas are covered by more sensors.

[0059] Further, the collaborative analysis module 14 in the gas detection system is also used for:

[0060] The correlation synergy coefficient is calculated by formula as follows:

[0061] ; wherein, characterizes the monitoring sensor and the monitoring sensor , characterizes the accuracy difference factor, , is the measurement error percentage of the monitoring sensor , is the measurement error percentage of the monitoring sensor , characterizes the Euclidean distance between the monitoring sensor and the monitoring sensor , and characterizing the node importance, a spatial decay coefficient.

[0062] Specifically, the correlation synergy coefficient is used to measure the degree of synergy between two monitoring sensors, reflecting the cooperation between the monitoring sensors and monitoring sensor , considering the spatial distance, accuracy difference, node importance, etc. between them. A high correlation synergy coefficient means that the two sensors can highly synergize when monitoring the same target, and a lower coefficient indicates that the synergy effect between them is poor. By calculating the accuracy difference factor between monitoring sensor and monitoring sensor , that is, by calculating the measurement error percentage of each sensor, and then calculating the measurement error percentage difference between the two sensors.

[0063] calculating the Euclidean distance of monitoring sensor and monitoring sensor , for quantifying the relative position of the two sensors in space. For example, assuming the coordinates of monitoring sensor are (100, 200) and the coordinates of monitoring sensor are 200, 300), then (100-200)²+ (200-300²)=20000, and the Euclidean distance is 141.42 meters. The node importance and indicates the importance of the node where monitoring sensor and monitoring sensor are located, reflecting the monitoring priority of the node where the sensor is located. Usually through analysis of the monitoring area, it is determined that some areas have higher requirements for safety or monitoring, so the node importance of this area is also higher. The higher the importance of the node, the more urgent and important the monitoring task of the sensor.

[0064] a spatial decay coefficient, which determines the rate of decay, as the distance between the two sensors increases, the synergy coefficient will decrease, so the spatial decay coefficient controls the rate of this decay. indicates that as the accuracy difference factor increases, the synergy coefficient will decrease, indicating that the greater the accuracy difference between the two sensors, the worse their synergy effect; indicates that as the distance between the two sensors increases, the synergy coefficient will decrease, and the spatial decay coefficient λ determines the rate of decay; The average value of the node importance represents the overall importance of the node where the sensor is located. By calculating and adjusting the associated synergy coefficient of the monitoring sensor, the cooperation ability between two sensors can be effectively evaluated, and optimization can be carried out accordingly.

[0065] The detection module 15 is configured to read the monitoring data of the monitoring sensor array, call the decision fusion network to make an abnormal decision based on the associated synergy coefficient for the monitoring data, and generate a gas detection result.

[0066] Specifically, the monitoring sensor array refers to a network array composed of multiple sensors arranged in the monitoring area. Each sensor is responsible for collecting gas data in a specific area, and these sensors work together to achieve real-time monitoring of a large area. The decision fusion network is called to make a fusion decision analysis. The decision fusion network is a system that integrates multiple data sources, multiple monitoring point information, and makes comprehensive analysis. Through multi-dimensional analysis of monitoring data, the final decision output is generated. The data collected by different sensors are fused to identify abnormal situations and provide more accurate gas detection results.

[0067] The detection data of the monitoring sensor array is read, and the monitoring data is synchronized and aligned. Since each monitoring sensor may have a time delay or different sampling intervals, it is necessary to align the monitoring data of all sensors to ensure that their timestamps are consistent. After completing data synchronization, spatial correlation channel analysis is performed, and the associated synergy coefficient between sensors is calculated to identify which regions have abnormal data relationships between monitoring sensors. Time series concentration anomaly analysis is performed on the same location monitoring results to identify the gas concentration fluctuations at different time points at the same location (or monitoring node). Under normal circumstances, the gas concentration should have certain regular changes. If the concentration fluctuation at a certain time point is abnormally severe, or the concentration changes at consecutive time points do not meet expectations, there may be a gas leak or other abnormal situation. After spatial anomaly correlation analysis and time series concentration anomaly analysis, first and second identified abnormalities are generated, respectively. At this time, the joint abnormal decision method is used to fuse the abnormal information of the two, and the final abnormal judgment is made to generate a gas detection result. By fusing spatial anomaly and time series concentration anomaly analysis, gas leakage or other abnormal situations can be comprehensively and accurately identified, thereby improving the reliability of detection.

[0068] Further, the detection module 15 in the gas detection system further comprises:

[0069] The fusion recognition unit is configured to call the decision fusion network and perform fusion decision analysis: a: after data synchronization alignment of the monitoring data, spatial correlation channel is used to perform spatial anomaly correlation analysis based on correlation synergy coefficient to establish a first identified anomaly; b: time series concentration anomaly analysis is performed on the monitoring data to establish a second identified anomaly; c: the first identified anomaly and the second identified anomaly are combined for joint anomaly decision.

[0070] Specifically, the decision fusion network is called to perform fusion decision analysis on the monitoring data to identify the anomaly of the monitored gas, determine whether there is an actual gas leakage or abnormal situation, and generate a gas detection result. Different sensors may record data at different timestamps, so data synchronization alignment is needed to adjust the monitoring data of all sensors to the same time basis so that they can be compared and analyzed at the same time point. The detection data is synchronized and aligned to unify the data to the same time scale. For missing data, linear interpolation or spline interpolation can be used for data synchronization.

[0071] Spline interpolation is an interpolation method used to generate a smooth curve or function from known data points, especially suitable for cases where the difference between data points is large or the distribution of data points is uneven. A common spline interpolation method is cubic spline interpolation, which uses a multi-segment cubic polynomial interpolation function to approximate the change between data points and ensures the continuity of the interpolation curve and the continuity of the first and second derivatives at the nodes, effectively eliminating abrupt changes between data.

[0072] Exemplarily, assuming that the gas concentration data collected by two sensors are not at the same time point, in order to compare and analyze the data, the time stamps of the data need to be aligned, so that there are corresponding values of all sensors at the same time. The data of sensor i is time: [0s, 5s, 10s, 15s, 20s], concentration: [5ppm, 8ppm, 12ppm, 18ppm, 20ppm]; the data of sensor j is time: [2s, 6s, 8s, 14s, 19s], concentration: [4ppm, 9ppm, 10ppm, 16ppm, 22ppm]. For each pair of adjacent time points, a cubic polynomial is obtained, which can connect two data points, and the concentration values of each data point and their time stamps are used to solve the coefficients of the polynomials. This process is repeated until the interpolation curve is constructed for all data points. The cubic polynomial is well known and will not be expanded here. Through spline interpolation, the concentration data of sensor j can be interpolated to the time stamp aligned with the data of sensor i, generating a new data comparison. The data of sensor i is time: [0s, 5s, 10s, 15s, 20s], and the time of sensor j after spline interpolation is the same as that of sensor i, and the concentration is: [5.5ppm, 8.3ppm, 12.2ppm, 17.8ppm, 19.6ppm]. After spline interpolation, the time series of sensor i and sensor j can now be compared on a unified time axis. Through spline interpolation, the difference in data collection time can be eliminated, and the data of multiple sensors can be effectively compared at the same time point.

[0073] After completing the data synchronization alignment, enter the spatial correlation channel analysis. According to the spatial position between the sensors, the correlation synergy coefficient is calculated to determine whether there is spatial anomaly between the sensors. The correlation synergy coefficient between the sensors is calculated, the spatial correlation between the sensors is analyzed, and the abnormal correlation between the sensors is identified. If the correlation synergy coefficient is lower than a certain threshold and the data fluctuates abnormally, it means that the monitoring results of the two sensors are inconsistent, and there may be regional anomalies or faults, which are recorded as the first identified anomaly.

[0074] The calculated correlation synergy coefficients are compared, and if the correlation synergy coefficient between a pair of sensors is below a certain threshold and their concentration data fluctuates greatly, it is considered that a gas leak or other abnormality may have occurred in this area. Based on the spatial correlation analysis, areas with a high likelihood of abnormality are marked. The sensors in these areas show significant differences in correlation, which may be caused by gas leaks, equipment failures, etc. According to the results of the spatial correlation analysis, a first identified abnormality is established, indicating that the area needs further investigation and monitoring. Spatial anomaly correlation analysis uses the spatial relationship between sensors (such as location, synergy coefficient, etc.) to determine whether an area is abnormal. It can identify potential gas leak points, pollution sources, etc. based on the similarity or difference of sensor data.

[0075] In the monitoring data, select the monitoring data at the same location and analyze the time series of the concentration. That is, collect the concentration data of multiple sensors at the same time point at the same location. These sensors monitor the same gas, so their concentration data should have some correlation and higher consistency for abnormal changes in the same location. Time series concentration anomaly analysis is an analysis of the monitoring data of multiple sensors at the same location in the time dimension to identify abnormal fluctuations in gas concentration within a certain period of time. Normally, gas concentration will have a certain fluctuation range, but if the concentration fluctuation exceeds the expected range, it may indicate an abnormal situation (such as leakage, equipment failure, etc.). For each time point, the concentration data of these sensors should be similar, assuming that their concentration data fluctuates within a certain range. If the concentration data of a sensor suddenly deviates from that of other sensors, it may indicate that an abnormality has occurred in this area at this time.

[0076] For each time point, the concentration data is analyzed and the fluctuation between them is calculated. By calculating the concentration mean, standard deviation, and comparing it with a pre-set normal concentration fluctuation range, it is determined whether there is an abnormality. The normal concentration fluctuation range is set according to historical experience, etc. When the standard deviation or concentration change exceeds the pre-set threshold, it is considered that the concentration at this time point is abnormal, and it is recorded as a second identified abnormality.

[0077] The first identified anomaly (based on spatial correlation analysis) is comprehensively judged with the second identified anomaly (based on time series concentration anomaly analysis). If the spatial anomaly and time series anomaly results are consistent, that is, both anomaly analyses point to the same area or time period, it is judged as a reliable abnormal event. The final decision scheme is determined in combination with the severity of each anomaly (such as anomaly amplitude, duration, number of involved sensors, etc.). If the anomaly results of the two are inconsistent, the final result is determined by weighting, priority ranking or other decision rules. For example, assuming that at a certain monitoring node, the time series analysis shows that the concentration of the node suddenly rises, and the spatial analysis shows that the coordination coefficient between multiple sensors in the region is low, and the data fluctuation is large. Since both point to the same abnormal position, the gas detection result of the region is gas leakage or other abnormalities.

[0078] By fusing spatial correlation analysis and time series concentration analysis, the abnormal situation of gas monitoring data is comprehensively analyzed, and the data from each sensor is processed and decided in real time, so that when gas leakage or other safety hazards occur, a quick response can be made to avoid safety accidents.

[0079] Further, the detection module 15 in the gas detection system further comprises:

[0080] A positioning unit is configured to establish an abnormal positioning point according to the joint abnormal decision; a clustering unit is configured to perform fine-tuning clustering of the monitoring sensors based on the abnormal positioning point, and establish a fine-tuning clustering result; an adjustment unit is configured to fine-tune the positions of the monitoring sensors based on the fine-tuning clustering result, and obtain an adjusted additional monitoring data set; and a compensation unit is configured to compensate the gas detection result according to the additional monitoring data set, and generate an updated gas detection result.

[0081] Specifically, by combining multiple anomaly detection methods (such as spatial anomaly correlation and time series concentration anomaly) together, a joint abnormal decision is obtained, which accurately identifies gas leakage or other dangerous situations and reduces false positives and false negatives of single anomaly identification. According to the joint abnormal decision result, an abnormal positioning point is determined, that is, the area pointed to by the joint abnormal decision result. The abnormal positioning point refers to the specific position or range of a certain abnormal event in space or time, which helps to determine the specific area where the anomaly occurs.

[0082] According to the abnormal positioning point, the sensors in the area are fine-tuned and clustered, that is, the positions of the sensors are optimized and adjusted according to the data volatility of each sensor, the distance from other sensors, and the distribution of the abnormal positioning point, and the sensors are moved or redeployed to optimize the monitoring coverage. For example, assuming that a leak occurs in a certain area (for example, near a storage tank), the fine-tuned clustering module will concentrate the surrounding sensors to this area, so as to ensure that the sensors can monitor the leak point more densely. The fine-tuned clustering result is the clustering information of the adjusted distribution of the sensors based on the correlation of the data between the sensors and the abnormal identification result, which reflects the optimization of the positions and configurations of the sensors, ensuring that there are more sensors or more accurate arrangements in the key areas.

[0083] According to the fine-tuned clustering result, the positions of the monitoring sensors are fine-tuned to be more reasonably distributed in the monitoring area. The fine-tuning of the positions of the sensors can be automatically performed based on an algorithm or completed by correcting the devices under manual control. For example, after fine-tuning, new sensors may be arranged in areas with higher risk of leakage, thereby optimizing the layout of the monitoring network. The gas in the area is monitored again through the adjusted and increased sensor positions, and new additional monitoring data sets are generated by re-collecting data, reflecting the changes in the gas concentration in the optimized monitoring area. For example, if the original sensor configuration is relatively sparse, resulting in insufficient monitoring of the gas concentration in some areas, after fine-tuning, the new sensor positions may cover more high-risk areas, thereby providing more accurate monitoring data.

[0084] The gas detection results are compensated and corrected through the additional monitoring data sets, and the purpose of compensation is to ensure that the final gas detection results are more accurate, especially in the case of abnormal situations such as leakage, the compensated results can provide more accurate position and concentration information, thereby generating updated gas detection results. For example, assuming that in a certain leakage area, the original gas detection result shows that the concentration in the area is low, but due to the sparseness of the sensor arrangement, the center point of the leak is not fully detected. After fine-tuning, the newly added sensor data set reflects a significant increase in the gas concentration in the area, and the compensated gas detection result will show a higher concentration, thereby warning the leakage event in advance.

[0085] By fine-tuning the distribution of the sensors, the high-risk areas can be more densely covered, and the accuracy of gas detection can be improved, especially the monitoring capability in abnormal areas. Through fine-tuned clustering and position adjustment, a dynamic and flexible sensor layout can be achieved, so that the monitoring system can automatically optimize according to the actual situation, and the gas detection results are more accurate, thereby reducing the possibility of false negatives and false positives.

[0086] Further, the gas detection system further comprises a gas release module and a feedback module. The gas release module is configured to move to the corresponding random position point after the random position point is configured, perform gas release at the corresponding random position point, and generate a release time record. The feedback module is configured to receive a gas detection result, perform deviation verification according to the gas detection result and the release time record, the deviation verification includes position deviation verification and sensitivity deviation verification, establish an identification feedback according to a deviation verification result, and perform system optimization management according to the identification feedback.

[0087] Specifically, a random position point in the monitoring area is selected, which can be a place where gas leakage may occur in a simulated environment (for example, in a factory, a warehouse area, etc.). By moving to the corresponding random position point, a gas release operation is performed, and the time, concentration, type, and other information of the release are recorded to generate a release time record. The gas release time record records the specific time and position of the gas release, reflecting the dynamic process of the gas leakage. For example, the release time record can include: at time T1, 0.03 ppm of gas is released at location A.

[0088] After the gas release, the gas concentration change of the monitoring area is detected, and the gas detection result is generated through the foregoing complete steps. The gas detection result is compared with the release time record to perform deviation verification. The deviation verification is performed by comparing the gas detection result with the release time record to check whether there is a deviation. The deviation verification includes position deviation verification and sensitivity deviation verification. The position deviation verification is used to check the deviation between the gas detection result and the actual gas release position. The sensitivity deviation verification is used to evaluate the sensitivity of the monitoring sensor to see whether it can correctly reflect the change of the gas concentration.

[0089] By comparing the positions of the actual release point and the sensor detection point, it is determined whether there is a deviation. For example, if the actual leakage point A is 100 meters away from sensor B, the position deviation is recorded. In addition to the position deviation, it is also compared whether the detected gas concentration matches the actual concentration. For example, if the gas release time record shows that 10 cubic meters of gas is leaked, but sensor B only detects a concentration of 5 ppm, it may be because the sensor sensitivity is insufficient, resulting in inaccurate detection results, and sensitivity deviation verification is needed.

[0090] After completing the deviation verification, generate an identification feedback that provides detailed feedback on the current gas detection capabilities, pointing out potential problems with the system, such as positioning errors, insufficient sensitivity, etc. Based on the identification feedback, conduct system optimization management, adjust the position of the monitoring sensor or calibrate the sensitivity of the sensor to improve the accuracy of the system. Optimize the operation process of the gas release module to ensure the reliability and repeatability of the test. Through position deviation verification and sensitivity deviation verification, potential problems of the monitoring system are found, and the detection accuracy of gas leakage is improved through optimization adjustment. The data provided by the identification feedback can help optimize the position and arrangement of the sensor, ensure sufficient monitoring coverage in high-risk areas, and improve the overall monitoring capability.

[0091] Further, the gas detection system further comprises a pre-warning module, which is configured to receive the gas detection result, match the pre-warning level according to the gas detection result, configure a pre-warning scheme according to the pre-warning level matching result and the gas detection result, and give a pre-warning according to the pre-warning scheme.

[0092] Specifically, after receiving the gas detection result, including gas type, concentration value, position, time, etc., the real-time state of gas leakage in the target area is understood. According to the concentration data and leakage risk in the gas detection result, the level of pre-warning is determined. For example, if the detected gas concentration is higher than a certain set threshold, different levels of pre-warning (such as low, medium, high pre-warning) will be triggered. For example, set 10 ppm or less as low concentration gas leakage, triggering low level pre-warning; 10 ppm to 50 ppm is medium concentration gas leakage, triggering medium level pre-warning; more than 50 ppm is high concentration gas leakage, triggering high level pre-warning.

[0093] According to the detected gas concentration, the corresponding pre-warning level can be determined. According to the matched pre-warning level, a suitable pre-warning scheme is automatically configured. Each pre-warning level will correspond to different emergency handling schemes, such as low level pre-warning through monitoring personnel to increase close monitoring; medium level pre-warning needs to start equipment inspection, increase the vigilance of regional personnel; high level pre-warning needs to start emergency shutdown, personnel evacuation, linkage fire fighting system and other more stringent emergency response measures.

[0094] According to the configured pre-warning scheme, a pre-warning is given, which warns the relevant personnel through sound and light alarm (emitting sound and light signals through alarm equipment) and digital notification (delivering information through SMS, email or system notification, etc.). Through real-time matching of gas detection results and pre-warning levels, the most suitable emergency response scheme is automatically generated to ensure that personnel at all levels can receive information in the shortest time and take appropriate measures in time, while reducing unnecessary pre-warning and avoiding resource waste caused by false or missed reports.

[0095] Further, the gas detection system further comprises a self-monitoring module configured to read the monitoring data, perform same-location monitoring deviation verification of the first-precision sensor and the second-precision sensor according to the monitoring data, generate a same-location deviation verification result, and report a monitoring anomaly according to the same-location deviation verification result.

[0096] Specifically, real-time monitoring data in the sensor array is read, including gas concentration, gas type, sensor location, time, etc. According to the monitoring data, monitoring data of the first-precision sensor and the second-precision sensor at the same location is extracted, and the results of the two are compared. If the detection results of the two are significantly different, deviation verification is generated, indicating that there may be a problem.

[0097] According to the deviation between the data of the two sensors, a same-location deviation verification result is generated, including deviation value, occurrence time, location information, etc. If the deviation exceeds a preset threshold, it means that the results of the two sensors are too different, indicating that the sensor may have a problem. Once the deviation verification result exceeds the threshold, a monitoring anomaly is reported, indicating device failure, environmental factor interference, or sensor precision problem, etc. According to the monitoring anomaly, an anomaly report is generated, including sensor number, anomaly type (such as too large deviation, sensor failure, etc.), anomaly level (such as warning, serious warning, etc.). According to the anomaly report, the operator or the system automatically performs corresponding emergency measures, such as sensor calibration, system check, or alarm notification.

[0098] Illustratively, the data of the two sensors at the same location and the same time is read, the first-precision sensor shows a concentration of 10 ppm, and the second-precision sensor shows a concentration of 75 ppm. The deviation between the two readings is calculated, and it is found that the deviation is 65 ppm, which is significantly higher than the preset deviation threshold (such as ±5 ppm), a same-location deviation verification result is generated, and a monitoring anomaly is reported. After receiving the anomaly report, the operator checks and calibrates the sensor to ensure the accuracy and reliability of the monitoring system.

[0099] Through same-location deviation verification, when the sensor fails or is interfered by environmental factors, early warning and measures are taken, such as recalibrating the sensor or replacing the failed device, to ensure the accuracy of the monitoring data and the stable operation of the system.

[0100] In summary, the gas detection system provided in the present application has the following technical effects:

[0101] The configuration module is configured to determine a monitoring gas, and select and configure a monitoring sensor according to the monitoring gas, wherein the monitoring sensor comprises a first precision sensor and a second precision sensor; the reference construction module is configured to obtain a minimum coverage range of the monitoring sensor, and construct a reference grid density based on the minimum coverage range; the monitoring node establishment module is configured to perform regional importance calculation on a region to be monitored, and configure a monitoring node according to the regional importance calculation result and the reference grid density; the collaborative analysis module is configured to obtain a precision difference value of the first precision sensor and the second precision sensor, perform monitoring sensor distribution according to the precision difference value and node importance of the monitoring node, establish a monitoring sensor array, and establish a correlation and collaboration coefficient of the monitoring sensor; and the detection module is configured to read monitoring data of the monitoring sensor array, call a decision fusion network to perform abnormal decision on the monitoring data based on the correlation and collaboration coefficient, and generate a gas detection result. That is, by dynamically selecting sensors with different precisions according to the type of the monitored gas, constructing a reference grid density based on the minimum coverage range of the monitoring sensor, configuring a sensor array in combination with the importance of the region to be monitored, and establishing a correlation and collaboration coefficient, gas detection is performed, such as detecting gas components such as volatile organic compounds by various organic matter measuring instruments, effectively identifying potential gas abnormal problems, and improving the precision of gas detection.

[0102] In the second embodiment, based on the same inventive concept as the gas detection system in the first embodiment, the application further provides a gas detection device, comprising: at least one processor; a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to implement any one of the gas detection systems in the first embodiment.

[0103] The configuration module is configured to determine a monitoring gas, and select and configure a monitoring sensor according to the monitoring gas, wherein the monitoring sensor comprises a first precision sensor and a second precision sensor; the reference construction module is configured to obtain a minimum coverage range of the monitoring sensor, and construct a reference grid density based on the minimum coverage range; the monitoring node establishment module is configured to perform regional importance calculation on a region to be monitored, and configure a monitoring node according to the regional importance calculation result and the reference grid density; the collaborative analysis module is configured to obtain a precision difference value of the first precision sensor and the second precision sensor, perform monitoring sensor distribution according to the precision difference value and node importance of the monitoring node, establish a monitoring sensor array, and establish a correlation and collaboration coefficient of the monitoring sensor; and the detection module is configured to read monitoring data of the monitoring sensor array, call a decision fusion network to perform abnormal decision on the monitoring data based on the correlation and collaboration coefficient, and generate a gas detection result. That is, by dynamically selecting sensors with different precisions according to the type of the monitored gas, constructing a reference grid density based on the minimum coverage range of the monitoring sensor, configuring a sensor array in combination with the importance of the region to be monitored, and establishing a correlation and collaboration coefficient, gas detection is performed, such as detecting gas components such as volatile organic compounds by various organic matter measuring instruments, effectively identifying potential gas abnormal problems, and improving the precision of gas detection. Figure 2 The configuration module is configured to determine a monitoring gas, and select and configure a monitoring sensor according to the monitoring gas, wherein the monitoring sensor comprises a first precision sensor and a second precision sensor; the reference construction module is configured to obtain a minimum coverage range of the monitoring sensor, and construct a reference grid density based on the minimum coverage range; the monitoring node establishment module is configured to perform regional importance calculation on a region to be monitored, and configure a monitoring node according to the regional importance calculation result and the reference grid density; the collaborative analysis module is configured to obtain a precision difference value of the first precision sensor and the second precision sensor, perform monitoring sensor distribution according to the precision difference value and node importance of the monitoring node, establish a monitoring sensor array, and establish a correlation and collaboration coefficient of the monitoring sensor; and the detection module is configured to read monitoring data of the monitoring sensor array, call a decision fusion network to perform abnormal decision on the monitoring data based on the correlation and collaboration coefficient, and generate a gas detection result. That is, by dynamically selecting sensors with different precisions according to the type of the monitored gas, constructing a reference grid density based on the minimum coverage range of the monitoring sensor, configuring a sensor array in combination with the importance of the region to be monitored, and establishing a correlation and collaboration coefficient, gas detection is performed, such as detecting gas components such as volatile organic compounds by various organic matter measuring instruments, effectively identifying potential gas abnormal problems, and improving the precision of gas detection. Figure 2In particular embodiments, bus architecture 300 is represented as a bus 300, which can include any number of interconnecting buses and bridges, and the bus 300 connects various circuits such as one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art, and therefore, will not be described any further. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 can be the same device, i.e., a transceiver, providing a unit for communicating with various other apparatus over the transmission medium. Processor 302 is responsible for managing the bus 300 and general processing, while the memory 304 can be used for storing data used by the processor 302 in executing operational processes.

[0104] The above description of disclosed embodiments provides enabling concepts for making or using the application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0105] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the application, the application can be practiced otherwise than as specifically set forth herein. With this in mind, the present application is intended to cover any and all adaptations or variations of preferred embodiments contemplated herein.

Claims

1. A gas detection system, characterized in that: The gas detection system comprises: A configuration module is used to select and configure a monitoring sensor according to the monitoring gas after determining the monitoring gas, wherein the monitoring sensor includes a first precision sensor and a second precision sensor; A benchmark construction module, configured to obtain a minimum coverage range of the monitoring sensor and construct a benchmark grid density based on the minimum coverage range; The monitoring node establishment module is used to calculate the regional importance of the monitored area and configure the monitoring nodes according to the regional importance calculation results and the benchmark grid density; a collaborative analysis module, configured to obtain a precision difference between the first precision sensor and the second precision sensor, distribute the monitoring sensors according to the precision difference and the node importance of the monitoring nodes, establish a monitoring sensor array, and establish an associated collaborative coefficient of the monitoring sensors; a detection module, configured to read the monitoring data of the monitoring sensor array, invoke a decision fusion network to perform an abnormality decision on the monitoring data based on the correlation synergy coefficient, and generate a gas detection result; The monitoring node establishment module also includes: The importance calculation unit is used to calculate the regional importance using the formula as follows: ； in, Represents the importance of the region and indicates the location In time The importance index of Characterized by location The number of high-risk equipment per unit area of ​​the center, Characterizes the highest device density, Characterization by Real-time leakage probability obtained from computational fluid dynamics simulation, is the exponential influence coefficient of device density, is the index influence coefficient, Characterizes the strength of the pressure gradient, Representation time The wind speed, Characterizes the reference wind speed, used to normalize the wind speed effect, Characterizes the angle between the wind speed direction and the main diffusion direction of the region, is the cosine coupling coefficient of the angle between wind direction and regional main axis; The collaborative analysis module also includes: The collaborative calculation unit is used to calculate the correlation synergy coefficient through the formula as follows: ； in, Characterization monitoring sensors and monitoring sensors The correlation coefficient of Characterize the accuracy difference factor, , For monitoring sensors The percentage of measurement error, monitor , Characterization monitoring sensors and monitoring sensors The Euclidean distance, and Represents the importance of the node, is the spatial attenuation coefficient.

2. A gas detection system according to claim 1, characterized in that: The detection module includes: The fusion identification unit is used to call the decision fusion network and perform fusion decision analysis: a: After aligning the monitoring data synchronously, performing spatial anomaly correlation analysis based on the correlation synergy coefficient through a spatial correlation channel to establish a first identified anomaly; b: performing a time series concentration anomaly analysis of the monitoring data for the same location monitoring results to establish a second identified anomaly; c: Perform a joint abnormality decision on the first identified abnormality and the second identified abnormality.

3. A gas detection system according to claim 2, characterized in that: The detection module also includes: A positioning unit, used to establish an anomaly positioning point based on the joint anomaly decision; A clustering unit, configured to perform fine-tuning clustering of monitoring sensors based on the abnormal positioning points and establish a fine-tuning clustering result; an adjusting unit, configured to fine-tune the position of the monitoring sensor based on the fine-tuning clustering result, and obtain an adjusted additional monitoring data set; The compensation unit is used to compensate the gas detection result according to the additional monitoring data set to generate an updated gas detection result.

4. A gas detection system according to claim 1, characterized in that: The collaborative analysis module also includes: an importance segmentation unit, configured to determine an importance segmentation constraint based on the precision difference using an importance constraint network; An importance screening unit, configured to screen the node importance based on the importance splitting constraint and determine an initial distribution of first-precision sensors; A screening unit, configured to perform a distribution weakness analysis based on the initial distribution of the first precision sensors, perform additional screening based on the distribution weakness analysis results and the node importance, and establish an additional distribution of the first precision sensors; The sensor distribution unit is used to complete the monitoring sensor distribution according to the additional distribution and the initial distribution.

5. A gas detection system according to claim 1, characterized in that: The gas detection system further comprises: The gas release module is used to configure random position points, move to the corresponding random position points to perform gas release, and generate release time sequence records; The feedback module is used to perform deviation verification based on the gas detection results and the release timing records after receiving the gas detection results. The deviation verification includes position deviation verification and sensitivity deviation verification. Identification feedback is established based on the deviation verification results, and system optimization management is performed based on the identification feedback.

6. A gas detection system according to claim 1, characterized in that: The gas detection system further comprises: The early warning module is used to receive the gas detection result, perform early warning level matching according to the gas detection result, configure an early warning plan according to the early warning level matching result and the gas detection result, and issue an early warning according to the early warning plan.

7. A gas detection system according to claim 1, characterized in that: The gas detection system further comprises: The self-monitoring module is used to read the monitoring data, perform the same-position monitoring deviation verification of the first precision sensor and the second precision sensor according to the monitoring data, generate a same-position deviation verification result, and report a monitoring abnormality according to the same-position deviation verification result.

8. A gas detection device, characterized in that: include: at least one processor; a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and when the at least one processor executes the instructions, a gas detection system as described in any one of claims 1 to 7 is implemented.

Images