Industrial gas component monitoring system and method based on big data analysis

Abstract

The invention discloses an industrial gas component monitoring system and method based on big data analysis, and relates to the technical field of big data, and the method comprises the steps: building a three-dimensional model of an industrial place, obtaining a historical leakage record, and carrying out the judgment and extraction of a target record; analyzing the component concentration of the gas to obtain the target concentration and the target distance of the monitoring item corresponding to the storage tank; dividing the industrial place into a plurality of clustering areas, obtaining clustering points of each clustering area, and calculating the early warning degree of the storage tank; according to the method, an industrial place is divided into a plurality of sub-regions, the feature ratio of each sub-region is obtained, region iteration judgment is performed, feature points corresponding to each sub-region are extracted, and then sampling is performed on the feature points. According to the invention, the historical leakage record of the storage tank in the industrial site is analyzed, and the current reasonable and reliable sampling point position is set, so that the sampled data can be more representative and better meet the actual monitoring requirement, the data distortion is avoided, and the sample reliability is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data, in particular to an industrial gas component monitoring system and method based on big data analysis. BACKGROUND

[0002] In order to ensure the stability and safety of industrial gas, the industrial gas is generally stored in a storage tank for storage, and the gas needs to be monitored to determine whether the storage tank has leakage and other abnormal conditions. The gas monitoring instrument is an instrument directly installed in the industrial production process for continuous or intermittent real-time detection of gas components or physical parameters. Its core function is to realize real-time monitoring and optimization of the production process by online collection, processing and analysis of sampling data. However, when the current gas monitoring instrument samples industrial gas, due to the random setting of sampling points, it does not analyze the distribution of storage tanks and historical leakage, which makes it difficult to reflect the true state of the sampled data and lacks sample reliability. SUMMARY

[0003] The purpose of the present application is to provide an industrial gas component monitoring system and method based on big data analysis to solve the problems in the prior art.

[0004] To achieve the above purpose, the present application provides the following technical scheme: The industrial gas component monitoring method based on big data analysis comprises the following steps: Obtain the layout drawing of the industrial site and the storage tank layout drawing, establish a three-dimensional model of the industrial site, and mark the location of the storage tank in the three-dimensional model; Obtain the historical leakage record of the storage tank, extract and analyze the physical parameters of the gas recorded during the monitoring of the gas, and realize the judgment and extraction of the target record in the leakage record; Extract the storage tank corresponding to the target record, analyze the component concentration of the gas at each position in the industrial site during the monitoring process, obtain the target concentration and target distance of the monitoring item in the target record corresponding to the storage tank, obtain the historical monitoring video of the industrial site, divide the industrial site into a plurality of clustering areas according to the location of the staff in the monitoring video, and obtain the clustering points of each clustering area; According to the target concentration and target distance of the monitoring item and the clustering points of each clustering area, the warning degree of the storage tank is calculated; Based on the current sample quantity of industrial gas, the industrial site is divided into a plurality of sub-regions, the feature ratio of each sub-region is obtained according to the warning degree and location of each storage tank, whether to perform regional iteration on each sub-region is judged according to the feature ratio, and then the final each sub-region is obtained, and the feature points corresponding to each sub-region are extracted, and then sampling is performed at the feature points.

[0005] Preferably, the step of judging and extracting the target record is as follows: The leakage record of the storage tank history is obtained, which is formed when the gas concentration around the target storage tank monitored by the gas monitoring instrument exceeds the preset concentration threshold, and only the target storage tank is confirmed to be leaking after investigation; The gas monitoring instrument monitors the gas at fixed time intervals. For each monitoring item in the monitoring process of a certain leakage record, the gas physical parameters including pressure and flow rate are extracted. The variance between all pressures is calculated as the first target value, and the variance between all flow rates is calculated as the second target value. According to the preset weight values corresponding to the pressure and flow rate, the total target value of a certain leakage record is obtained. If the total target value is less than the preset numerical threshold, the certain leakage record is taken as the target record.

[0006] Pressure and flow rate provide key environmental and dynamic parameter support in the process of monitoring gas by the gas monitoring instrument, and are important auxiliary indicators to ensure the accuracy, integrity and scene adaptability of monitoring data. Gas concentration is related to pressure, and gas flow rate is related to flow rate. In the process of monitoring gas, if the pressure and flow rate suddenly change, it may be caused by instantaneous equipment failure, poor sensor contact and environmental interference. Since factors such as instantaneous equipment failure, poor sensor contact and environmental interference will cause the monitored gas composition data to deviate from the actual value, such records with sudden changes in pressure and flow rate cannot provide reliable data support for the following calculations. Therefore, the target record needs to be judged and extracted in this step to make the calculation result more reliable.

[0007] Preferably, the step of obtaining the target concentration and target distance of the monitoring item in the target record corresponding to the storage tank is as follows: The industrial site includes several storage tanks storing the same gas Q, and the composition concentration C of gas Q in the air is obtained in advance Q The position P of the storage tank T corresponding to a certain target record in the three-dimensional model is obtained T The position P of the gas monitoring instrument at the time of a certain monitoring item t is extracted t , and the composition concentration C of gas Q of the gas monitoring instrument recorded in the monitoring item t is extracted t The composition concentration C t is subtracted from the composition concentration C Q , and the leakage concentration C t of gas Q at position P T t ; According to the leakage concentration C T of gas Q at position P T , the target concentration of monitoring item t is CT -C T t ; Position P T and position P t The distance between them is used as the target distance for monitoring entry t.

[0008] Preferably, the steps for obtaining the cluster points of each cluster area are as follows: establishing a plane coordinate system of the industrial site, extracting several historical monitoring screens of the industrial site, obtaining the positions of the staff in the monitoring screens, and marking them in the plane coordinate system; using a clustering algorithm to aggregate the personnel position points in the plane coordinate system to obtain several cluster areas, and randomly extracting several personnel position points from the cluster areas, calculating the average coordinate value, obtaining cluster points, and obtaining cluster points for each cluster area.

[0009] In this scheme, a clustering algorithm that does not require the number of categories to be set in advance and does not change the original coordinates of the sample points during the clustering process is used; Preferably, the steps for calculating the warning level of a storage tank are as follows: according to the target concentration and target distance of several monitoring items corresponding to a storage tank T, a function of the change of target concentration with target distance is established, and a function fitting is performed to obtain the corresponding slope K after fitting, and the coordinates of the storage tank T in the plane coordinate system are used as F T , according to the area of ​​each cluster area and the number of personnel location points therein, as well as the coordinates of each cluster point and the coordinates F T The distance between them can be used to obtain the warning level of the storage tank T. , where W1 and W2 are the first and second weights respectively, e is the natural index, D is the number of cluster regions, S d is the area of ​​the dth cluster region, N d is the number of personnel location points in the dth cluster area, L d The coordinates of the cluster point corresponding to the d-th cluster area and the coordinate F T The distance between them.

[0010] Preferably, the steps of extracting the feature points corresponding to each sub-region are as follows: Obtain the number of samples M currently collected for industrial gas sampling, and evenly divide the industrial site into M sub-areas of equal area; extract several location points within a sub-area r, and calculate the average coordinate value as the target point; obtain the distance H between a target point G and a storage tank X, and calculate the warning level Y of the storage tank X according to the warning level Y. X , the influence degree of storage tank X on target point G is obtained as , sum up the impact of all storage tanks on the target point G to get the total impact of the target point G; Get the total influence degree of each target point, sum them up, get the target degree, divide each total influence degree by the target degree, and get the characteristic ratio of each sub-region; calculate the variance between all characteristic ratios, if the variance is greater than the preset variance threshold, according to the area A of a sub-region r r , characteristic ratio R r , the iterative area of ​​sub-region r is: A r (1-R r +1 / M), and then the iteration area of ​​all sub-regions is obtained, and regional iteration is performed on each sub-region according to the iteration area; A larger characteristic ratio indicates that the storage tank has a greater impact on the sub-region, so the monitoring intensity of the sub-region should be greater and the sampling points should be more dense. Therefore, the larger the characteristic ratio, the smaller the iteration area should be set for the sub-region to ensure the reliability of the sampling points. The variance of the characteristic ratio is an important factor in measuring whether the monitoring intensity of each sub-region is balanced. The feature ratio is obtained again until the number of iterations is greater than the preset number threshold or the variance is not greater than the variance threshold, and the final sub-regions are obtained. The target points of the last iteration are used as the feature points of the corresponding sub-regions.

[0011] Industrial gas composition monitoring system based on big data analysis, including target record extraction module, warning degree calculation module, and feature point extraction module; Target record extraction module: used to obtain the layout drawings and storage tank layout drawings of the industrial site, build a 3D model of the industrial site, and mark the location of the storage tanks in the 3D model; obtain the historical leakage records of the storage tanks, extract and analyze the gas physical parameters recorded during gas monitoring, and realize the judgment and extraction of target records in the leakage records; Warning degree calculation module: This module is used to extract the storage tank corresponding to the target record and analyze the gas component concentration at each location in the industrial site during the monitoring process to obtain the target concentration and target distance of the monitoring item in the target record corresponding to the storage tank; obtain the historical monitoring video of the industrial site, divide the industrial site into several cluster areas based on the location of the staff in the monitoring video, and obtain the cluster points of each cluster area; calculate the warning degree of the storage tank based on the target concentration and target distance of the monitoring item and the cluster points of each cluster area; Feature point extraction module: It is used to divide the industrial site into several sub-areas based on the current number of samples of industrial gas sampling, obtain the feature ratio of each sub-area according to the warning level and location of each storage tank, and determine whether to perform regional iteration on each sub-area based on the feature ratio, and then obtain the final sub-areas, extract the feature points corresponding to each sub-area, and then perform sampling at the feature points.

[0012] Preferably, the early warning degree calculation module comprises a monitoring entry analysis unit, a clustering area division unit and an early warning degree calculation unit. The monitoring entry analysis unit is configured to extract a storage tank corresponding to a target record, analyze the component concentration of the gas at each position in the industrial site during the monitoring process, and obtain the target concentration and target distance of the monitoring entry in the target record corresponding to the storage tank. The clustering area division unit is configured to obtain historical monitoring videos of the industrial site, divide the industrial site into a plurality of clustering areas according to the positions of the workers in the monitoring videos, and obtain clustering points of each clustering area. The early warning degree calculation unit is configured to calculate the early warning degree of the storage tank according to the target concentration and target distance of the monitoring entry and the clustering points of each clustering area.

[0013] Preferably, the feature point extraction module comprises a total influence degree calculation unit and a feature point extraction unit. The total influence degree calculation unit is configured to obtain the number of samples of the industrial gas at present, divide the industrial site into a plurality of sub-areas with the same area, obtain target points of the sub-areas, obtain the distance between the target points and the storage tank, obtain the influence degree of the storage tank on the target points according to the early warning degree of the storage tank, and further obtain the total influence degree of the target points. The feature point extraction unit is configured to obtain the total influence degree of each target point, obtain the feature ratio of each sub-area, determine whether to perform area iteration on each sub-area according to the feature ratio, further obtain the final sub-area, and extract the feature points corresponding to each sub-area.

[0014] Compared with the prior art, the industrial gas component monitoring system and method based on big data analysis provided by the present application have the following beneficial effects: the present application provides an industrial gas component monitoring system and method based on big data analysis, which comprises the following steps: establishing a three-dimensional model of an industrial site, obtaining historical leakage records, judging and extracting target records, analyzing the component concentration of the gas, obtaining the target concentration and target distance of the monitoring entry corresponding to the storage tank, dividing the industrial site into a plurality of clustering areas, obtaining clustering points of each clustering area, calculating the early warning degree of the storage tank, dividing the industrial site into a plurality of sub-areas, obtaining the feature ratio of each sub-area, performing area iteration judgment, extracting the feature points corresponding to each sub-area, and further sampling at the feature points. The present application analyzes the historical leakage records of the storage tanks in the industrial site, sets a reasonable and reliable sampling point position at present, can effectively make the sampled data more representative and more in line with the actual monitoring requirements, avoids data distortion, and improves the reliability of the samples. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 FIG. 1 is a flowchart of the industrial gas component monitoring method based on big data analysis of the present application. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0017] Embodiment: As shown in the figure, the present application provides an industrial gas component monitoring method based on big data analysis, comprising the following steps: Figure 1 1. Obtain the layout drawing of the industrial site and the storage tank layout drawing, establish a three-dimensional model of the industrial site, and mark the location of the storage tank in the three-dimensional model. 2. Obtain the historical leakage record of the storage tank, extract and analyze the gas physical parameters recorded during the monitoring of the gas, and realize the judgment and extraction of the target record in the leakage record.

[0018] The leakage record of the storage tank is formed when the gas concentration around the target storage tank monitored by the gas monitoring instrument exceeds the preset concentration threshold, and only the target storage tank is confirmed to be leaking after investigation;The gas monitoring instrument monitors the gas at fixed time intervals, and the gas physical parameters corresponding to each monitoring item in the monitoring process of a leakage record are extracted, including pressure and flow. The variance between all pressures is calculated as the first target value, and the variance between all flow rates is calculated as the second target value. According to the preset weight values corresponding to the pressure and flow, the total target value of a certain leakage record is obtained. If the total target value is less than the preset numerical threshold, the certain leakage record is taken as the target record.

[0019] Pressure and flow are key environmental and dynamic parameter supports provided by the gas monitoring instrument during the monitoring of the gas, and are important auxiliary indicators for ensuring the accuracy, integrity and scene adaptability of the monitoring data. Gas concentration is related to pressure, and gas flow rate is related to flow. During the monitoring of the gas, if the pressure and flow suddenly change, it may be caused by equipment instantaneous failure, sensor contact failure and environmental interference. Since factors such as equipment instantaneous failure, sensor contact failure and environmental interference will cause the monitored gas component data to deviate from the actual value, such records with sudden changes in pressure and flow cannot provide reliable data support for the following calculation. Therefore, the target record needs to be judged and extracted in this step to make the calculation result more reliable.

[0020] Pressure and flow are key environmental and dynamic parameter supports provided by the gas monitoring instrument during the monitoring of the gas, and are important auxiliary indicators for ensuring the accuracy, integrity and scene adaptability of the monitoring data. Gas concentration is related to pressure, and gas flow rate is related to flow. During the monitoring of the gas, if the pressure and flow suddenly change, it may be caused by equipment instantaneous failure, sensor contact failure and environmental interference. Since factors such as equipment instantaneous failure, sensor contact failure and environmental interference will cause the monitored gas component data to deviate from the actual value, such records with sudden changes in pressure and flow cannot provide reliable data support for the following calculation. Therefore, the target record needs to be judged and extracted in this step to make the calculation result more reliable.

[0021] 3, extract the storage tank corresponding to the target record, and analyze the component concentration of the gas at each position in the industrial site during the monitoring process to obtain the target concentration and target distance of the monitoring item in the target record corresponding to the storage tank.

[0022] The industrial site includes several storage tanks storing the same gas Q, and the component concentration C of gas Q in the air is obtained in advance Q ; obtain the position P of the storage tank T corresponding to a certain target record in the three-dimensional model T , extract the position P of the gas monitoring instrument at the time of a certain monitoring item t t , and the component concentration C of gas Q of the gas monitoring instrument recorded in the monitoring item t t , subtract the component concentration C t from the component concentration C Q , and obtain the leakage concentration C t of gas Q at position P T t ; According to the leakage concentration C T of gas Q at position P T , the target concentration of monitoring item t is C T -C T t ; the distance between position P T and position P t is the target distance of monitoring item t.

[0023] 4, obtain the historical monitoring video of the industrial site, divide the industrial site into several clustering areas according to the positions of the staff in the monitoring video, and obtain the clustering points of each clustering area.

[0024] A plane coordinate system of the industrial site is established, several historical monitoring pictures of the industrial site are extracted, the positions of the staff in the monitoring pictures are obtained, and are marked in the plane coordinate system; the clustering algorithm is used to aggregate the staff position points in the plane coordinate system, to obtain several clustering areas, and to randomly extract several staff position points from the clustering areas, to calculate the coordinate average value, to obtain the clustering points, and to obtain the clustering points of each clustering area.

[0025] In this scheme, the clustering algorithm that does not need to set the number of categories in advance and does not change the original coordinates of the sample points during the clustering process is needed, and in this embodiment, the DBSCAN algorithm is used. The clustering area after clustering is divided by DBSCAN, and the staff position points in the plane coordinate system are clustered by using the DBSCAN algorithm, which is the prior art, and will not be described in detail here.

[0026] 5. Calculate the early warning degree of the storage tank according to the target concentration and target distance of the monitoring items and the cluster points of each cluster area.

[0027] According to the target concentration and target distance of the monitoring items corresponding to the storage tank T, a function of the target concentration changing with the target distance is established, and a linear function fitting is performed to obtain the corresponding slope K after fitting, and the coordinates of the storage tank T in the plane coordinate system are taken as F T , and the early warning degree of the storage tank T is obtained according to the area of each cluster area and the number of personnel position points therein, and the distance between the coordinates of each cluster point and the coordinates F T , wherein W1 and W2 are the first weight and the second weight respectively, e is the natural exponential, D is the number of cluster areas, S d is the area of the dth cluster area, N d is the number of personnel position points in the dth cluster area, and L d is the distance between the coordinates of the cluster point corresponding to the dth cluster area and the coordinates F T .

[0028] When the slope K is small, it means that more leaked gas can be monitored at positions far away from the leaking tank, which means that the leakage degree of the leaking tank is more serious. When the slope K is large, it means that less leaked gas can be monitored at positions far away from the leaking tank, which means that the leakage degree of the leaking tank is lighter. Therefore, when the slope K is small, the early warning degree of the storage tank T is larger. The formula y=e -x is a function of y taking an integer from 0 to 1 when x>0, and y decreases with the increase of x. Therefore, the formula y=e -x can be used to analyze the slope K. In the present scheme, the cluster area is a region where personnel are densely present. The cluster area can be understood as various work areas. S d / N d characterizes the personnel quantity density corresponding to the dth cluster area. When S d / N d is larger, it means that the number or time length of people in the area is larger. When L d is smaller, it means that the dth cluster area is closer to the storage tank T, and the influence degree on the storage tank T is larger. Therefore, when S d / N d is larger, L d is smaller, which means that the early warning degree of the storage tank T is larger. The formula y=1-e -x is a function of y taking an integer from 0 to 1 when x>0, and y increases with the increase of x. Therefore, the formula y=1-e -x can be used to analyze S d / N​d and L d , see the degree of warning Y T .

[0029] 6, based on the current number of samples of industrial gas sampling, industrial sites are divided into several sub-regions, according to the degree of warning of each tank and the location, get the characteristic ratio of each sub-region, and according to the characteristic ratio to determine whether to iterate each sub-region, and then get the final each sub-region, and extract the corresponding feature points of each sub-region, and then sample at the feature points.

[0030] 6-1 get the current number of samples of industrial gas sampling M, the industrial sites are evenly divided into M sub-regions with the same area; extract a number of position points in a sub-region r, and take the average of the coordinates as the target point; get the distance H between a target point G and a tank X, according to the degree of warning Y X of the tank X, the influence degree of the tank X on the target point G is , the total influence degree of the target point G is obtained by summing the influence degree of all tanks on the target point G.

[0031] Here the meaning of the formula of the influence degree of the target point G can be referred to the analysis of the degree of warning of the tank above, which is not repeated here.

[0032] 6-2 get the total influence degree of each target point, and sum them up to get the target degree, divide each total influence degree by the target degree to get the characteristic ratio of each sub-region; get the variance between all characteristic ratios, if the variance is greater than the preset variance threshold, according to the area A r of a sub-region r, the characteristic ratio R r , the iteration area of the sub-region r is: A r (1-R r +1 / M), and then get the iteration area of all sub-regions, and iterate each sub-region according to the iteration area; The larger the feature ratio is, the greater the influence of the storage tank on the sub-region is, and then the monitoring intensity on the sub-region should be greater, and then the sampling points should be denser, so the smaller the iteration area should be set for the sub-region with the larger feature ratio to ensure the reliability of the sampling points; and the variance obtained by the feature ratio is an important factor for measuring whether the monitoring intensity of each sub-region is balanced. The following example is given: set M=10, that is, the number of sampling points is 10, and the industrial site is divided into 10 sub-regions. Since the feature ratio is obtained according to the total influence degree of each target point, if the total influence degree of each target point is balanced, that is, the total influence degree of each target point is the same, the feature ratio of each sub-region should be 0.1. However, if the feature ratio of a certain sub-region is 0.12, it means that the monitoring intensity on the sub-region should be greater, and the iteration area should be smaller, so according to the area A r before iteration, the area after iteration is obtained as: A r (1-R r +1 / M)=0.98A r , and similarly, if the feature ratio of the sub-region is 0.08, the area after iteration is obtained as: A r (1-R r +1 / M)=1.02A r .

[0033] The feature ratio is obtained again until the iteration number is greater than the preset number threshold or the variance obtained is not greater than the variance threshold, and the final sub-regions are obtained, and the target points of the last iteration are taken as the feature points of the corresponding sub-regions.

[0034] The application also provides an industrial gas component monitoring system based on big data analysis, which comprises a target record extraction module, a warning degree calculation module and a feature point extraction module. The warning degree calculation module comprises a monitoring item analysis unit, a clustering region division unit and a warning degree calculation unit, and the feature point extraction module comprises a total influence degree calculation unit and a feature point extraction unit. The system realizes the above-mentioned industrial gas component monitoring method based on big data analysis when executing a computer program. Since the industrial gas component monitoring method based on big data analysis has been described in detail above, no further description is given here.

[0035] It will be apparent to those skilled in the art that the application is not limited to the details of the above-exemplified embodiments and that the present application can be implemented in other particular forms without departing from the spirit or essential characteristics of the present application. The embodiments should therefore be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the above description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. No reference signs in the claims should be considered as limiting the scope of the claims with respect to the figures of the patent document.

Claims

1. An industrial gas composition monitoring method based on big data analysis, characterized in that: The following steps are involved: Obtain the layout drawings of the industrial site and the storage tank layout drawings, create a 3D model of the industrial site, and mark the locations of the storage tanks in the 3D model; Obtain historical leakage records of storage tanks, extract and analyze gas physical parameters recorded during gas monitoring, and realize judgment and extraction of target records in leakage records; Extract the storage tank corresponding to the target record and analyze the gas component concentration at each location in the industrial site during the monitoring process to obtain the target concentration and target distance of the monitoring item in the target record corresponding to the storage tank; obtain historical surveillance video of the industrial site, divide the industrial site into several cluster areas based on the location of the staff in the surveillance video, and obtain the cluster points of each cluster area; Calculate the warning level of the storage tank based on the target concentration and target distance of the monitoring items and the cluster points of each cluster area; Based on the current number of samples taken for industrial gas sampling, the industrial site is divided into several sub-areas. According to the warning level and location of each storage tank, the characteristic ratio of each sub-area is obtained. Based on the characteristic ratio, it is determined whether to perform regional iteration on each sub-area to obtain the final sub-areas, and the corresponding characteristic points of each sub-area are extracted, and sampling is performed at the characteristic points.

2. The industrial gas composition monitoring method based on big data analysis according to claim 1 is characterized in that: The steps for judging and extracting target records are as follows: Obtaining historical leakage records of a storage tank, wherein the leakage record is generated when a gas monitoring instrument detects that the gas concentration around a target storage tank exceeds a preset concentration threshold, and after investigation, it is confirmed that only the target storage tank is leaking; The gas monitoring instrument monitors gas at fixed time intervals, extracts the gas physical parameters corresponding to each monitoring item of a leakage record during the monitoring process, and the gas physical parameters include pressure and flow. The variance between all pressures is calculated as the first target value, and the variance between all flow rates is calculated as the second target value. According to the preset weights corresponding to the pressure and flow, the total target value of the leakage record is obtained. If the total target value is less than the preset numerical threshold, the leakage record is used as the target record.

3. The industrial gas composition monitoring method based on big data analysis according to claim 1 is characterized in that: The steps to obtain the target concentration and target distance of the monitoring item in the target record corresponding to the storage tank are as follows: The industrial site includes several storage tanks storing the same gas. The stored gas is referred to as Q, and the component concentration C of the gas Q in the air is obtained in advance. Q ; Get the position P of the storage tank T corresponding to a target record in the three-dimensional model T , extract the location P of the gas monitoring instrument at the time of a monitoring item t t , and the component concentration C of the gas Q recorded by the gas monitoring instrument in monitoring item t t , the component concentration C t Subtract component concentration C Q , we get gas Q at position P t Leakage concentration C T t ; According to the gas Q at position P T Leakage concentration C T , the target concentration of monitoring item t is C T -C T t ; Position P T and position P t The distance between them is used as the target distance for monitoring entry t.

4. The industrial gas composition monitoring method based on big data analysis according to claim 3 is characterized in that: The steps for obtaining the cluster points of each cluster area are as follows: establish a plane coordinate system for the industrial site, extract several historical monitoring images of the industrial site, obtain the positions of the staff in the monitoring images, and mark them in the plane coordinate system; use a clustering algorithm to aggregate the personnel position points in the plane coordinate system to obtain several cluster areas, and randomly extract several personnel position points from the cluster areas, calculate the average coordinate value, obtain cluster points, and obtain cluster points for each cluster area.

5. The industrial gas composition monitoring method based on big data analysis according to claim 4 is characterized in that: The steps for calculating the warning level of a storage tank are as follows: Based on the target concentration and target distance of several monitoring items corresponding to a storage tank T, a function of the target concentration changing with the target distance is established, and a function fitting is performed to obtain the corresponding slope K after fitting, and the coordinates of the storage tank T in the plane coordinate system are used as F T , according to the area of ​​each cluster area and the number of personnel location points therein, as well as the coordinates of each cluster point and the coordinates F T The distance between them can be used to obtain the warning level of the storage tank T. , where W1 and W2 are the first and second weights respectively, e is the natural index, D is the number of cluster regions, S d is the area of ​​the dth cluster region, N d is the number of personnel location points in the dth cluster area, L d The coordinates of the cluster point corresponding to the d-th cluster area and the coordinate F T The distance between them.

6. The industrial gas composition monitoring method based on big data analysis according to claim 1 is characterized in that: The steps for extracting the feature points corresponding to each sub-region are as follows: Obtain the current number of industrial gas samples, M, and evenly divide the industrial site into M sub-areas of equal area. Extract several locations within a sub-area r and calculate the average coordinate value as the target point. Get the distance H between a target point G and a storage tank X, and the warning level Y of the storage tank X. X , the influence degree of the storage tank X on the target point G is obtained as , sum up the impact of all storage tanks on the target point G to get the total impact of the target point G; Get the total influence degree of each target point, sum them up, get the target degree, divide each total influence degree by the target degree, and get the characteristic ratio of each sub-region; calculate the variance between all characteristic ratios, if the variance is greater than the preset variance threshold, according to the area A of a sub-region r r , characteristic ratio R r , the iterative area of ​​sub-region r is: A r (1-R r +1 / M), and then the iteration area of ​​all sub-regions is obtained, and regional iteration is performed on each sub-region according to the iteration area; The feature ratio is obtained again until the number of iterations is greater than the preset number threshold or the variance is not greater than the variance threshold, and the final sub-regions are obtained. The target points of the last iteration are used as the feature points of the corresponding sub-regions.

7. An industrial gas composition monitoring system, configured to implement the industrial gas composition monitoring method based on big data analysis according to any one of claims 1 to 6, characterized in that: The system includes a target record extraction module, a warning degree calculation module, and a feature point extraction module; Target record extraction module: used to obtain the layout drawings and storage tank layout drawings of the industrial site, build a 3D model of the industrial site, and mark the location of the storage tanks in the 3D model; obtain the historical leakage records of the storage tanks, extract and analyze the gas physical parameters recorded during gas monitoring, and realize the judgment and extraction of target records in the leakage records; Warning degree calculation module: This module is used to extract the storage tank corresponding to the target record and analyze the gas component concentration at each location in the industrial site during the monitoring process to obtain the target concentration and target distance of the monitoring item in the target record corresponding to the storage tank; obtain the historical monitoring video of the industrial site, divide the industrial site into several cluster areas based on the location of the staff in the monitoring video, and obtain the cluster points of each cluster area; calculate the warning degree of the storage tank based on the target concentration and target distance of the monitoring item and the cluster points of each cluster area; Feature point extraction module: It is used to divide the industrial site into several sub-areas based on the current number of samples of industrial gas sampling, obtain the feature ratio of each sub-area according to the warning level and location of each storage tank, and determine whether to perform regional iteration on each sub-area based on the feature ratio, and then obtain the final sub-areas, extract the feature points corresponding to each sub-area, and then perform sampling at the feature points.

8. The industrial gas composition monitoring system according to claim 7, characterized in that: The warning degree calculation module includes a monitoring item analysis unit, a cluster area division unit and a warning degree calculation unit; Monitoring item analysis unit: used to extract the storage tank corresponding to the target record, and analyze the component concentration of the gas at each location in the industrial site during the monitoring process to obtain the target concentration and target distance of the monitoring item in the target record corresponding to the storage tank; Clustering area division unit: used to obtain historical surveillance videos of industrial sites, divide the industrial sites into several cluster areas according to the locations of workers in the surveillance videos, and obtain cluster points for each cluster area; Warning degree calculation unit: used to calculate the warning degree of the storage tank according to the target concentration and target distance of the monitoring item and the cluster points of each cluster area.

9. The industrial gas composition monitoring system according to claim 7, characterized in that: The feature point extraction module includes a total influence degree calculation unit and a feature point extraction unit; Total impact calculation unit: used to obtain the current number of industrial gas samples, evenly divide the industrial site into several sub-areas of equal area, and obtain the target point of the sub-area; obtain the distance between the target point and the storage tank, and according to the warning level of the storage tank, obtain the impact of the storage tank on the target point, and then obtain the total impact of the target point; Feature point extraction unit: used to obtain the total influence of each target point, and obtain the feature ratio of each sub-region, and determine whether to perform regional iteration on each sub-region based on the feature ratio, and then obtain the final sub-regions and extract the feature points corresponding to each sub-region.

Images