A method and system for online monitoring of pollution sources

Abstract

The present invention relates to the field of pollution source monitoring technology, and in particular to a method and system for online monitoring of pollution sources. The method comprises the following steps: acquiring target pollution area data, and performing area cutting through simulation model restoration processing to obtain simulated cut pollution areas; then, using a uniform measurement point array to measure the oxygen flux of the cut area, and analyzing the flux fluctuation to generate a normal fluctuation range; based on this fluctuation range, reversely track the pollution source and locate the initial pollution source data. Subsequently, combining the oxygen flux data of each area, the initial pollution source is regionally calibrated, and the candidate direction of pollution diffusion is calculated; finally, according to the diffusion direction and the initial positioning data, the pollution area is dynamically monitored and adjusted to generate the final pollution source monitoring results. The present invention realizes more flexible and accurate online monitoring of pollution sources.

Description

Technical Field

[0001] The present invention relates to the technical field of pollution source monitoring, and in particular to an online pollution source monitoring method and system. Background Art

[0002] In the process of modern industrialization and urbanization, environmental pollution problems are becoming more and more serious, especially air pollution caused by industrial emissions. In order to effectively monitor and control pollution sources, studying online monitoring technology of pollution sources has become an important topic in the field of environmental protection. Traditional pollution monitoring methods rely on fixed sites and manual sampling, which cannot track and monitor pollution sources in real time and dynamically, resulting in low monitoring efficiency and difficulty in taking effective measures in the early stages of pollution diffusion. At present, there are many problems with common pollution monitoring methods. For example, monitoring equipment can usually only cover a limited area and it is difficult to cope with complex environmental changes. Especially in the process of pollution source diffusion, air flow, terrain conditions and meteorological factors will lead to deviations in monitoring results. In addition, many monitoring methods rely on a single sensor or monitoring parameter, which cannot fully reflect the changes in pollutants in space and time, and it is difficult to effectively locate and track the diffusion path of pollution sources. The resulting errors will lead to inaccurate identification of pollution sources, which in turn affects the implementation of pollution control measures. Summary of the invention

[0003] Based on this, it is necessary to provide a pollution source online monitoring method and system to solve at least one of the above technical problems.

[0004] To achieve the above object, a pollution source online monitoring method comprises the following steps:

[0005] Step S1: obtaining target contaminated area data; performing simulation model restoration processing on the target contaminated area data, and performing evenly divided area cutting to obtain simulated cut contaminated areas;

[0006] Step S2: obtaining a uniform measurement point array; performing point-by-point oxygen flux measurements on the simulated segmented pollution area according to the uniform measurement point array to obtain oxygen flux data for each area; performing flux fluctuation analysis on the oxygen flux data for each area to generate a normal fluctuation range of oxygen flux;

[0007] Step S3: based on the normal fluctuation range of oxygen flux and the oxygen flux data of each area, reverse pollution source tracking is performed on the simulated segmented pollution area to obtain initial pollution source positioning data;

[0008] Step S4: calibrate the pollution source area of ​​the initial pollution source positioning data according to the oxygen flux data of each area and the oxygen flux data of each area, and calculate the diffusion tendency to generate candidate diffusion directions of the pollution source;

[0009] Step S5: Based on the candidate pollution source diffusion directions and the initial pollution source positioning data, dynamic monitoring and adjustment are performed on the simulated segmented pollution area to obtain dynamic pollution source monitoring results.

[0010] The present invention can refine the target pollution area into multiple small areas through simulation model restoration processing and evenly divided area cutting technology, effectively improving the restoration degree of complex pollution environment, making subsequent monitoring and analysis more accurate. This subdivision helps to more accurately grasp the diffusion and distribution of pollutants in various areas, and provides a good foundation for pollution source tracking. Through the uniform measurement point array and the point oxygen flux measurement technology, comprehensive oxygen flux monitoring can be performed on each simulated cut area, and the normal fluctuation range can be generated through flux fluctuation analysis. This technical feature helps to monitor the oxygen fluctuation in the pollution area in real time, can effectively detect the impact of pollutants on the oxygen content in the environment, and provides key data support for the identification of pollution sources. Through the reverse pollution source tracking technology, combined with the diffusion tendency calculation, it is possible to further dynamically adjust the monitoring scheme through the diffusion direction prediction on the basis of the preliminary positioning of the pollution source. Through this technology, the system can not only track the initial position of the pollution source, but also predict the future diffusion direction of the pollutant, realize the real-time monitoring and dynamic adjustment of the pollution source, and greatly improve the accuracy of pollution source positioning and the real-time monitoring. Through the dynamic monitoring adjustment technology based on the diffusion candidate direction and initial positioning data of the pollution source, the monitoring strategy and area can be adjusted in time to form a closed-loop feedback mechanism. This feature improves the responsiveness of the monitoring system, enabling it to continuously optimize monitoring strategies during the pollution spread process, ensure the accuracy and timeliness of monitoring data, and effectively respond to complex and dynamically changing pollution source spread situations.

[0011] The present invention also provides a pollution source online monitoring system for executing the pollution source online monitoring method as described above, the pollution source online monitoring system comprising:

[0012] The pollution area restoration module is used to obtain the target pollution area data; perform simulation model restoration processing on the target pollution area data, and perform evenly divided area cutting to obtain simulated cut pollution areas;

[0013] The oxygen flux calculation module is used to obtain a uniform measurement point array; perform point-by-point oxygen flux measurements on the simulated segmented pollution area according to the uniform measurement point array to obtain oxygen flux data for each area; perform flux fluctuation analysis on the oxygen flux data for each area to generate a normal fluctuation range for the oxygen flux;

[0014] The pollution source positioning module is used to reversely track the pollution sources of the simulated and segmented pollution areas based on the normal fluctuation range of oxygen flux and the oxygen flux data of each area to obtain the initial pollution source positioning data;

[0015] The diffusion trend calculation module is used to calibrate the pollution source area based on the oxygen flux data of each area and the initial pollution source positioning data, and perform diffusion tendency calculation to generate candidate pollution source diffusion directions;

[0016] The dynamic monitoring and adjustment module is used to dynamically monitor and adjust the simulated segmented pollution area based on the candidate pollution source diffusion direction and the initial pollution source positioning data to obtain dynamic pollution source monitoring results.

[0017] The present invention uses a pollution area restoration module, and the system can perform detailed restoration of the target pollution area based on the simulation model, and perform evenly divided area cutting to generate simulated cut pollution areas. The technical features of this module are helpful for accurately dividing complex pollution areas, thereby providing an accurate spatial distribution basis for subsequent pollution monitoring and analysis, and improving the accuracy and reliability of overall monitoring. The oxygen flux calculation module can obtain a uniform measurement point array, perform point-by-point oxygen flux measurement, and perform detailed analysis of oxygen changes in each simulated cut pollution area. The flux fluctuation analysis further generates a normal fluctuation range of the oxygen flux, thereby providing important benchmark data for the diffusion of pollutants. This modular design can achieve high-precision, multi-point distributed real-time monitoring, making the detection of oxygen flux changes more accurate and improving the effectiveness of monitoring. The pollution source positioning module uses the oxygen flux fluctuation range and the oxygen flux data of each area for reverse tracking, and the initial pollution source can be effectively located through this module. This technical feature can quickly identify the location of the pollution source, and ensure the accuracy of positioning by reverse path tracking, which is helpful for real-time detection and rapid response to pollution source diffusion problems, and improves the efficiency of pollution source identification. The diffusion trend calculation module can calibrate the pollution source area according to the oxygen flux data of each area, and generate candidate directions for the diffusion of pollution sources through calculation. This function can effectively predict the diffusion trend of pollution sources, making the monitoring of the diffusion of pollutants more forward-looking and proactive, and facilitating the adoption of early prevention and response measures. The dynamic monitoring and adjustment module makes dynamic adjustments based on the candidate directions of pollution source diffusion and the initial pollution source positioning data to achieve real-time monitoring and feedback of pollution source diffusion. By combining candidate directions and historical positioning data, this module can optimize the monitoring scope and strategy in real time, ensuring that the system can flexibly respond to and adjust the monitoring plan during the process of pollution diffusion, thereby improving the intelligence and adaptability of the system and ensuring the timeliness and accuracy of the monitoring results. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of the steps of an online monitoring method for pollution sources;

[0019] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0020] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0021] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0022] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0023] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0024] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0025] To achieve this, please refer to Figures 1 to 3 , a pollution source online monitoring method, comprising the following steps:

[0026] Step S1: obtaining target contaminated area data; performing simulation model restoration processing on the target contaminated area data, and performing evenly divided area cutting to obtain simulated cut contaminated areas;

[0027] Step S2: obtaining a uniform measurement point array; performing point-by-point oxygen flux measurements on the simulated segmented pollution area according to the uniform measurement point array to obtain oxygen flux data for each area; performing flux fluctuation analysis on the oxygen flux data for each area to generate a normal fluctuation range of oxygen flux;

[0028] Step S3: based on the normal fluctuation range of oxygen flux and the oxygen flux data of each area, reverse pollution source tracking is performed on the simulated segmented pollution area to obtain initial pollution source positioning data;

[0029] Step S4: calibrate the pollution source area of ​​the initial pollution source positioning data according to the oxygen flux data of each area and the oxygen flux data of each area, and calculate the diffusion tendency to generate candidate diffusion directions of the pollution source;

[0030] Step S5: Based on the candidate pollution source diffusion directions and the initial pollution source positioning data, dynamic monitoring and adjustment are performed on the simulated segmented pollution area to obtain dynamic pollution source monitoring results.

[0031] The present invention can refine the target pollution area into multiple small areas through simulation model restoration processing and evenly divided area cutting technology, effectively improving the restoration degree of complex pollution environment, making subsequent monitoring and analysis more accurate. This subdivision helps to more accurately grasp the diffusion and distribution of pollutants in various areas, and provides a good foundation for pollution source tracking. Through the uniform measurement point array and the point oxygen flux measurement technology, comprehensive oxygen flux monitoring can be performed on each simulated cut area, and the normal fluctuation range can be generated through flux fluctuation analysis. This technical feature helps to monitor the oxygen fluctuation in the pollution area in real time, can effectively detect the impact of pollutants on the oxygen content in the environment, and provides key data support for the identification of pollution sources. Through the reverse pollution source tracking technology, combined with the diffusion tendency calculation, it is possible to further dynamically adjust the monitoring scheme through the diffusion direction prediction on the basis of the preliminary positioning of the pollution source. Through this technology, the system can not only track the initial position of the pollution source, but also predict the future diffusion direction of the pollutant, realize the real-time monitoring and dynamic adjustment of the pollution source, and greatly improve the accuracy of pollution source positioning and the real-time monitoring. Through the dynamic monitoring adjustment technology based on the diffusion candidate direction and initial positioning data of the pollution source, the monitoring strategy and area can be adjusted in time to form a closed-loop feedback mechanism. This feature improves the responsiveness of the monitoring system, enabling it to continuously optimize monitoring strategies during the pollution spread process, ensure the accuracy and timeliness of monitoring data, and effectively respond to complex and dynamically changing pollution source spread situations.

[0032] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of an online pollution source monitoring method of the present invention. In this example, the online pollution source monitoring method includes the following steps:

[0033] Step S1: obtaining target contaminated area data; performing simulation model restoration processing on the target contaminated area data, and performing evenly divided area cutting to obtain simulated cut contaminated areas;

[0034] In this embodiment, a three-dimensional laser scanner is used to acquire all-round data of the target pollution area and generate a point cloud data model to ensure accurate reproduction of environmental features including topography and buildings. On this basis, simulation software (such as CFD simulation software) is used to restore the simulation model to simulate the air flow and potential pollution diffusion pattern in the target area. After the simulation model is restored, the target area is divided into multiple small areas by a meshing tool to ensure that the pollution characteristics of each divided area are uniform. The generated simulated divided pollution area will serve as the basis for subsequent analysis and measurement.

[0035] Step S2: obtaining a uniform measurement point array; performing point-by-point oxygen flux measurements on the simulated segmented pollution area according to the uniform measurement point array to obtain oxygen flux data for each area; performing flux fluctuation analysis on the oxygen flux data for each area to generate a normal fluctuation range of oxygen flux;

[0036] In this embodiment, based on the contaminated area after segmentation, a multi-point oxygen measurement system based on an optical sensor is used to arrange measurement points at the center of each segmented area to form a uniform measurement point array. Subsequently, a measuring device (such as a DO sensor) is used to measure the oxygen flux at each measurement point in real time to ensure the accuracy and stability of the data. The oxygen flux data obtained in each area will be calculated by a time series analysis method for fluctuation amplitude, and the Fourier transform and other tools will be used to perform spectrum analysis on the flux fluctuation of each area to determine the normal fluctuation range of the oxygen flux in each area, providing a reference for subsequent steps.

[0037] Step S3: based on the normal fluctuation range of oxygen flux and the oxygen flux data of each area, reverse pollution source tracking is performed on the simulated segmented pollution area to obtain initial pollution source positioning data;

[0038] In this embodiment, after determining the normal fluctuation range of oxygen flux in each area, a reverse tracking algorithm (such as a reverse model based on particle tracking) is used based on the flux data of each area to gradually trace back the pollution diffusion path. In this process, the initial location area of ​​the pollution source is inferred by reversely deducing the changes in oxygen flux in each area. Using simulation analysis tools, combined with the pollution diffusion trajectory and oxygen consumption law of each area, the location of the initial pollution source is accurately calibrated, and preliminary pollution source location data is generated.

[0039] Step S4: calibrate the pollution source area of ​​the initial pollution source positioning data according to the oxygen flux data of each area and the oxygen flux data of each area, and calculate the diffusion tendency to generate candidate diffusion directions of the pollution source;

[0040] In this embodiment, based on the initial pollution source location data, the regional calibration algorithm is used, combined with the oxygen flux data of each segmented area, to further refine the precise location of the pollution source. By calculating the diffusion tendency of the pollution source in each area, evaluating the probability of the pollution source diffusing in different directions, and using methods such as multivariate linear regression or correlation analysis, the candidate diffusion directions of the pollution source are generated. This process is completed through mathematical modeling and numerical simulation to ensure that the diffusion trend in each direction is fully verified.

[0041] Step S5: Based on the candidate pollution source diffusion directions and the initial pollution source positioning data, dynamic monitoring and adjustment are performed on the simulated segmented pollution area to obtain dynamic pollution source monitoring results.

[0042] In this embodiment, according to the candidate diffusion direction, dynamic monitoring equipment (such as drones equipped with gas sensors or fixed air quality monitoring stations) is used to conduct real-time dynamic monitoring of the area where the pollution source is located and its surroundings, and the measurement parameters are adjusted at any time. Combined with the initial pollution source location data and its diffusion trend, the oxygen flux data of each measurement point is updated in real time, and the diffusion path of the pollution source is dynamically corrected through the feedback adjustment mechanism. Ultimately, the generated dynamic pollution source monitoring results will show the diffusion range, trend and real-time concentration distribution of the pollution source, which will be used for further pollution control and response measures.

[0043] Preferably, step S1 comprises:

[0044] Step S11: Acquire target polluted area data; perform multi-spectral remote sensing data collection on the target polluted area data to obtain multi-dimensional pollution feature data;

[0045] Step S12: performing principal component analysis on the multi-dimensional pollution feature data to obtain a reduced-dimensional pollution feature vector;

[0046] Step S13: constructing a three-dimensional pollution distribution model for the reduced-dimensional pollution feature vector to generate a three-dimensional distribution map of the target pollution area;

[0047] Step S14: uniformly grid the three-dimensional distribution map of the target pollution area to obtain uniformly distributed pollution grid units;

[0048] Step S15: performing boundary mesh refinement processing on the uniformly distributed polluted mesh units to generate simulated segmented polluted areas.

[0049] The present invention collects pollution characteristic data of the target pollution area from multiple spectral dimensions through multi-spectral remote sensing data collection. This technical feature can capture rich information that cannot be obtained by traditional single monitoring methods, including the concentration of pollutants in the air, diffusion path and type of pollutants, etc., effectively improving the collection accuracy and comprehensiveness of pollution data, and providing more accurate basic data for subsequent analysis and processing. The multi-dimensional pollution characteristic data is reduced in dimension by principal component analysis (PCA), and the complex pollution data is converted into a reduced-dimensional pollution characteristic vector. This technical feature can not only reduce redundant information and retain the main features, but also greatly reduce the computational complexity of the system, improve the efficiency of data analysis, and provide optimized data input for the construction of subsequent pollution models. A three-dimensional pollution distribution model is constructed for the reduced-dimensional pollution characteristic vector to generate a three-dimensional distribution map of the target pollution area. This technical feature allows the system to accurately simulate the distribution of pollutants in space, provide a more intuitive and comprehensive display of pollution areas, lay an important foundation for the diffusion trend analysis and source tracking of pollutants, and greatly improve the spatial analysis capability of the monitoring system. Grid division and boundary refinement can cut the three-dimensional pollution area into multiple pollution grid units according to uniform standards, and refine the boundary area to generate more accurate simulated segmentation areas. This modular design enables the system to monitor and analyze pollutant diffusion areas with higher resolution, ensuring that the pollution characteristics of each area can be captured in detail, avoiding the omission of pollution information due to coarse grids, and improving the overall monitoring accuracy. By generating simulated segmented pollution areas, the system can more accurately locate and monitor pollution sources for each grid unit. This technical feature allows the system to adopt corresponding monitoring strategies for areas with different pollution levels, significantly improving the efficiency and accuracy of pollution source identification, and also providing more accurate basic data for subsequent pollution diffusion prediction and pollution source location.

[0050] In this embodiment, multispectral remote sensing technology is used to obtain data of the target pollution area. Equipped with a high-resolution multispectral imager, remote sensing data collection of different bands (such as visible light, near infrared, short-wave infrared, etc.) in the region is performed. The device can capture the spectral information of various pollutants in the target area, such as the absorption characteristics of gaseous pollutants and the scattering characteristics of particulate matter. The acquired multispectral remote sensing data will include information such as spectral reflectance and radiation intensity of different bands. These multi-dimensional pollution characteristic data are processed by data processing software to extract the spatial distribution and concentration distribution information of pollutants, providing basic data for subsequent analysis. The pollution characteristic data of each band is standardized to eliminate dimensional differences. Subsequently, the main components are extracted by eigenvalue decomposition of the covariance matrix, the weight of each principal component is calculated, and the most representative first few principal components are retained. These principal components constitute the pollution feature vector after dimensionality reduction, which can effectively compress the data dimension while retaining most of the variability of the original data. Select a suitable three-dimensional modeling tool, such as MATLAB's three-dimensional data visualization tool or a dedicated environmental modeling software. The eigenvector data after dimensionality reduction is input into the modeling tool, and a three-dimensional distribution model of the target pollution area is generated based on the pollution concentration information in the eigenvector. The model will show the three-dimensional distribution of pollutants in the target area, including the spatial distribution and concentration changes of pollutants. The three-dimensional distribution map of the target pollution area is uniformly gridded. Use gridding tools (such as ArcGIS's grid generation tool or other spatial analysis software) to divide the three-dimensional pollution distribution map into uniformly sized grid cells. Ensure that the size and shape of each grid cell are consistent throughout the area to facilitate subsequent processing. The result of uniform grid division will generate pollution grid cells. The boundary grid of the uniformly distributed pollution grid cells is refined to generate simulated segmented pollution areas. Apply boundary refinement algorithms (such as adaptive grid refinement methods) to refine the preliminary grid, especially in areas where pollution concentrations change dramatically or boundaries are unclear. The refinement process uses high-precision grid generation software to adjust the density and shape of the grid according to the concentration gradient and distribution characteristics of the pollutants.

[0051] Preferably, step S2 comprises:

[0052] Step S21: inserting unit area measurement points into the simulated segmented pollution area to generate a uniform measurement point array;

[0053] Step S22: performing continuous sampling of the oxygen sensor according to the uniform measurement point array to obtain oxygen time series data;

[0054] Step S23: Calculate the oxygen flux at each point of the oxygen time series data to generate oxygen flux data for each area;

[0055] Step S24: performing spatial density clustering processing on the oxygen flux data of each region to obtain clustered oxygen flux;

[0056] Step S25: performing flux fluctuation analysis on the clustered oxygen flux to generate a normal fluctuation range of the oxygen flux.

[0057] The present invention inserts unit area measurement points into the simulated segmented polluted area, and the system can generate a uniform array of measurement points. This technical feature ensures that the monitoring coverage in the entire polluted area is uniform and representative, thereby avoiding data deviation caused by uneven distribution of measurement points and improving the comprehensiveness and reliability of data acquisition. Continuous sampling of oxygen sensors is performed using a uniform array of measurement points to obtain oxygen time series data. This feature provides a detailed time record of changes in oxygen concentration in the polluted area, allowing the system to capture the changing trend of pollutants at different time points, supporting dynamic monitoring and real-time analysis, and improving the timeliness and accuracy of monitoring data. The oxygen flux of each point in the oxygen time series data is calculated to generate oxygen flux data for each region. This technical feature can convert time series data into spatially distributed data, accurately reflect the oxygen flux situation in different regions, provide quantitative basic data for subsequent pollution analysis, and enhance the accuracy of pollution source monitoring. The oxygen flux data of each region is subjected to spatial density clustering processing to obtain clustered oxygen flux. This technical feature classifies data with similar pollution characteristics through spatial density analysis methods, thereby identifying high-density and low-density areas of pollutants, improving the spatial identification ability of pollution distribution, and helping to accurately locate pollution sources and analyze pollution diffusion patterns. By performing flux fluctuation analysis on clustered oxygen fluxes, the normal fluctuation range of oxygen flux is generated. This technical feature can identify the normal fluctuation range and abnormal fluctuation of oxygen flux, thereby providing a standard for judging whether pollution is abnormal, improving the system's ability to detect abnormal pollution events, and ensuring that it can respond to pollution changes in a timely manner and take corresponding measures.

[0058] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0059] Step S21: inserting unit area measurement points into the simulated segmented pollution area to generate a uniform measurement point array;

[0060] In this embodiment, in the simulated segmented contaminated area, a gridding tool is used to insert uniform measurement points in each grid unit. This process is completed by a high-precision measurement point layout system (such as a high-precision GPS positioning system or measurement point layout software) to ensure that the measurement points are evenly distributed in each unit. The layout spacing of the measurement points is set according to the scale of the simulation area and the required data accuracy to ensure the comprehensiveness of data collection. The final uniform measurement point array will be used for the subsequent layout and data collection of oxygen sensors.

[0061] Step S22: performing continuous sampling of the oxygen sensor according to the uniform measurement point array to obtain oxygen time series data;

[0062] In this embodiment, oxygen sensors are arranged on a uniform array of measurement points, and these sensors can collect oxygen concentration data at each measurement point in real time. Using the continuous sampling mode, the configured sensors monitor the oxygen concentration at each measurement point at a fixed time interval (such as every minute or every hour) to generate time series data. The data collection process is carried out through a sensor data recorder, which has high-precision data collection and storage capabilities to ensure the integrity and accuracy of the oxygen time series data.

[0063] Step S23: Calculate the oxygen flux at each point of the oxygen time series data to generate oxygen flux data for each area;

[0064] In this embodiment, the collected oxygen time series data is processed. First, the time series data of each measurement point is input into a calculation tool (such as MATLAB or Python data analysis library). A data processing algorithm (such as integration method or difference method) is applied to calculate the oxygen flux of each measurement point. The flux calculation results are summarized to generate oxygen flux data for each area. These data represent the oxygen flow or consumption in each area, providing basic data for subsequent spatial density clustering.

[0065] Step S24: performing spatial density clustering processing on the oxygen flux data of each region to obtain clustered oxygen flux;

[0066] In this embodiment, the oxygen flux data of each region is subjected to spatial density clustering processing, using a spatial clustering analysis algorithm (such as DBSCAN or K-means clustering). First, the oxygen flux data is input into the clustering analysis tool, and the data is grouped according to spatial density by setting an appropriate distance threshold and clustering parameters. This process classifies the oxygen flux data of each region into different clusters to identify regions with similar flux characteristics. The clustering results generate clustered oxygen fluxes, which provide useful information for subsequent flux fluctuation analysis.

[0067] Step S25: performing flux fluctuation analysis on the clustered oxygen flux to generate a normal fluctuation range of the oxygen flux.

[0068] In this embodiment, the clustered oxygen flux is subjected to flux fluctuation analysis, and statistical analysis tools (such as statistical analysis libraries of R language or Python) are used for data processing. First, the mean and standard deviation of the oxygen flux data in each cluster are calculated, and the fluctuation range is analyzed. A time series analysis method (such as moving average or standard deviation analysis) is used to generate the normal fluctuation range of the oxygen flux for each cluster. Through this analysis, the normal flux fluctuation range is determined and used as a reference standard for subsequent anomaly detection and pollution source monitoring.

[0069] Preferably, step S25 includes:

[0070] Step S251: Obtaining environmental conditions of the target pollution area;

[0071] Step S252: performing correlation analysis on the environmental conditions of the target pollution area and the clustered oxygen flux to obtain environment-oxygen impact data;

[0072] Step S253: performing support vector regression analysis on the environment-oxygen impact data to generate oxygen content impact factors;

[0073] Step S254: Evaluate the environmental impact of the target polluted area based on the oxygen content impact factor to obtain environmental impact data for each area;

[0074] Step S255: Calculate the maximum oxygen fluctuation of the clustered oxygen flux according to the environmental impact data of each region to generate a normal fluctuation range of the oxygen flux.

[0075] By acquiring the environmental conditions of the target pollution area, the system can fully understand the environmental factors that affect pollution monitoring. The correlation analysis between the environmental conditions and the clustered oxygen flux in step S252 enables the system to identify the specific impact of environmental factors on the oxygen flux and provides contextual information for pollution monitoring. This correlation analysis helps to improve the accuracy of data interpretation and make the monitoring results more reliable and targeted. Support vector regression (SVR) is used to analyze the environmental-oxygen impact data to generate oxygen content impact factors. SVR is a powerful regression analysis tool that can handle nonlinear relationships and generate accurate impact factors. This technical feature provides an in-depth understanding of how environmental conditions affect oxygen content and enhances the system's ability to predict the impact of environmental changes on pollution data. Based on the oxygen content impact factor, the environmental conditions of the target pollution area are evaluated for their impact degree and environmental impact data for each region is generated. This technical feature can evaluate the pollution degree and environmental impact of different regions by quantifying the impact of environmental factors, provide data support for accurate pollution control and management, and enable the monitoring system to more effectively identify and respond to pollution sources. The maximum oxygen fluctuation of the clustered oxygen flux is calculated according to the environmental impact data of each region, thereby generating a normal fluctuation range of the oxygen flux. This technical feature ensures that the system can dynamically adjust the fluctuation range to adapt to environmental changes, provides flexible fluctuation range standards, helps to accurately identify and distinguish normal fluctuations from abnormal fluctuations, and improves the monitoring system's ability to detect pollution anomalies. By combining environmental conditions, oxygen flux data and advanced regression analysis methods, the system can provide more comprehensive and accurate pollution monitoring results. Comprehensive environmental impact assessment and fluctuation range calculation ensure that the system can maintain efficient monitoring performance under changing environmental conditions, and improve the adaptability and accuracy of the overall monitoring system.

[0076] In this embodiment, the environmental condition data of the target contaminated area is obtained by a weather station and an environmental monitoring device. These data include environmental parameters such as temperature, humidity, wind speed, and air pressure, and collection equipment such as meteorological sensors, humidity sensors, and anemometers are used for real-time monitoring. These devices should have high-precision measurement functions and be able to record environmental condition data at fixed intervals. The acquired data will form an environmental condition data set to provide basic information for subsequent analysis. The acquired environmental condition data and clustered oxygen flux data are associated with analysis. Statistical analysis tools (such as Pandas and SciPy libraries in Python) are used for data processing. First, the environmental condition data and clustered oxygen flux data are aligned in time and space. By calculating the correlation coefficient and regression analysis, the degree of influence of environmental conditions on oxygen flux is evaluated. The generated environment-oxygen impact data will reveal the relationship between environmental factors (such as temperature, humidity, etc.) and oxygen flux, providing a basis for establishing an environmental impact model. The support vector regression (SVR) algorithm is applied to the environment-oxygen impact data to generate oxygen content influencing factors. Use SVR tools (such as Python's scikit-learn library) to build a regression model, taking environmental condition data as input features and oxygen flux data as target variables for training. By selecting appropriate kernel functions and parameter settings, optimize the regression model to obtain high-precision influencing factors. These oxygen content influencing factors will be used to evaluate the changes in oxygen concentration under different environmental conditions. Based on the generated oxygen content influencing factors, the environmental impact degree of the environmental conditions in the target pollution area is evaluated. Apply environmental impact assessment models (such as weighted scoring models) to combine the influencing factors with the actual environmental condition data to calculate the environmental impact degree of each area. Mathematical models and statistical methods (such as weighted average or linear regression) are used in the assessment process to generate environmental impact data for each area to reflect the specific impact of environmental conditions on oxygen flux. Based on the environmental impact data of each area, the maximum oxygen fluctuation of the clustered oxygen flux is calculated. The clustered oxygen flux data is analyzed using mathematical modeling tools (such as MATLAB or Python's NumPy library) to calculate the maximum oxygen flux fluctuation range under different environmental conditions. The normal fluctuation range of oxygen flux is generated through statistical analysis of the maximum fluctuation amplitude. This range will be used as a subsequent anomaly detection criterion to determine the normal fluctuation limit of oxygen flux.

[0077] Preferably, step S3 comprises:

[0078] Step S31: performing outlier detection on oxygen flux data of each region based on the normal fluctuation range of oxygen flux to obtain an abnormal flux point set;

[0079] Step S32: performing spatiotemporal clustering processing on the abnormal flux point set to obtain abnormal spatiotemporal evolution characteristics;

[0080] Step S33: constructing a pollution diffusion model based on the abnormal spatiotemporal evolution characteristics to generate a pollution diffusion model;

[0081] Step S34: reversely trace the pollution source of the simulated segmented pollution area according to the pollution diffusion model to obtain initial pollution source location data.

[0082] The present invention can accurately identify abnormal flux point sets by performing abnormal value detection on oxygen flux data of each region based on the normal fluctuation range of oxygen flux. This technical feature enables the system to quickly discover abnormal situations in a large amount of data, ensures the timely discovery and accurate positioning of pollution anomalies, and improves the system's abnormality detection capability. Spatiotemporal clustering of abnormal flux point sets can reveal the spatiotemporal evolution characteristics of abnormal pollution events. Through this technical feature, the system can identify the spatial distribution pattern and time evolution trend of abnormal phenomena, thereby providing a more in-depth dynamic analysis of pollution, laying the foundation for the accurate tracking of pollution sources and the prediction of diffusion trends. A pollution diffusion model is constructed based on the abnormal spatiotemporal evolution characteristics to generate a pollution diffusion model. This technical feature can establish an accurate pollution diffusion model by comprehensively considering the spatiotemporal characteristics of abnormal data, simulate the propagation process of pollutants, improve the system's ability to predict pollution diffusion behavior, and optimize the identification process of pollution sources. According to the generated pollution diffusion model, reverse pollution source tracking is performed on the simulated segmented pollution area to obtain initial pollution source location data. Through this technical feature, the system can infer the original location of the pollution source based on the pollution diffusion model, realize efficient tracking and positioning of the pollution source, provide accurate data support for pollution control, and improve the accuracy and reliability of pollution source identification. By organically combining technologies such as outlier detection, spatiotemporal clustering, pollution diffusion model construction, and reverse tracking, the system can comprehensively and deeply analyze the characteristics and diffusion behavior of pollution sources. This comprehensive technical feature ensures the comprehensiveness and accuracy of pollution monitoring, enables the system to effectively respond to complex pollution situations, and improves the overall effectiveness of monitoring and management.

[0083] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0084] Step S31: performing outlier detection on oxygen flux data of each region based on the normal fluctuation range of oxygen flux to obtain an abnormal flux point set;

[0085] In this embodiment, based on the above-mentioned normal fluctuation range of oxygen flux, outlier detection is performed on the oxygen flux data of each region. Statistical analysis tools (such as the SciPy library in Python or the statistical toolbox of MATLAB) are used to perform outlier detection, and the normal fluctuation range is first set as the upper and lower limits. By calculating the deviation of the oxygen flux value of each measurement point from the normal fluctuation range, the abnormal flux points that exceed the range are identified. The outlier detection algorithm (such as the Z-score method or the IQR method) will help determine the outliers and generate an abnormal flux point set, recording all identified abnormal data points and their locations.

[0086] Step S32: performing spatiotemporal clustering processing on the abnormal flux point set to obtain abnormal spatiotemporal evolution characteristics;

[0087] In this embodiment, the abnormal flux point set is subjected to spatiotemporal clustering processing to identify the spatiotemporal evolution characteristics of the anomaly. A spatiotemporal clustering algorithm (such as the spatial clustering algorithm DBSCAN or K-means combined with time series analysis) is applied to perform cluster analysis on the abnormal flux points. First, the time and space information of the abnormal flux points are input into the clustering tool, and the data is grouped into several spatiotemporal clusters by setting the spatiotemporal distance parameters. The analysis results will reveal the spatiotemporal distribution pattern and evolution trend of the abnormal points, and generate an abnormal spatiotemporal evolution feature map for identifying the occurrence and development of pollution events.

[0088] Step S33: constructing a pollution diffusion model based on the abnormal spatiotemporal evolution characteristics to generate a pollution diffusion model;

[0089] In this embodiment, a pollution diffusion model is constructed according to the abnormal spatiotemporal evolution characteristics. An appropriate pollution diffusion model (such as a Gaussian diffusion model or a Lagrangian model) is selected, and the abnormal spatiotemporal evolution data is input as the parameters of the model. A modeling tool (such as Simulink of MATLAB or SciPy library of Python) is used to simulate the diffusion process of pollutants. The process includes setting factors such as the initial pollution source location, diffusion speed, and meteorological conditions to generate a pollution diffusion model. This model will be used to predict the diffusion path and final distribution of pollutants, and help understand the dynamic process of pollution diffusion.

[0090] Step S34: reversely trace the pollution source of the simulated segmented pollution area according to the pollution diffusion model to obtain initial pollution source location data.

[0091] In this embodiment, reverse pollution source tracking is performed according to the pollution diffusion model to determine the location data of the initial pollution source. The diffusion path generated by the pollution diffusion model is compared with the actual monitoring data using a reverse tracking algorithm (such as a reverse model based on particle swarm optimization). The source location of the pollutant is determined by the reverse algorithm, and the location of the pollution source is optimized taking into account the diffusion parameters in the model and the actual observation data. Ultimately, the initial pollution source location data obtained will reveal the specific location of the pollution source and provide a basis for further pollution control and governance measures.

[0092] Preferably, step S34 includes:

[0093] According to the pollution diffusion model, the simulated segmented pollution area is captured for diffusion nodes to obtain simulated diffusion nodes;

[0094] Perform main path identification processing on simulated diffusion nodes to generate main diffusion paths;

[0095] The main diffusion paths are traced back in reverse order to obtain the initial pollution source location data.

[0096] The present invention captures diffusion nodes in simulated segmented pollution areas, and the system can identify key diffusion nodes of pollutants in the area. This technical feature enables the system to accurately capture the key points of pollutant diffusion, provides detailed data on pollution diffusion, helps to more accurately understand the diffusion pattern and intensity of pollutants, and lays the foundation for subsequent path analysis. The main path identification processing is performed on the simulated diffusion nodes to generate the main diffusion path. This technical feature can extract the most important path from many diffusion nodes and reveal the main diffusion route of pollutants. By identifying the main path, the system can more effectively analyze the propagation direction of pollutants, optimize pollution control and response strategies, and improve the accuracy and practicality of the diffusion path. By performing reverse path tracing on the main diffusion path, the system can obtain initial pollution source location data. This technical feature enables the system to reversely infer the location of the pollution source from the diffusion path of the pollutant, and provides an accurate pollution source location method. Reverse tracing improves the accuracy of pollution source identification and helps to implement more targeted pollution control measures. By organically combining diffusion node capture, main path identification and reverse path tracing, the system can achieve a comprehensive analysis of pollutant diffusion. This comprehensive technical feature improves the accuracy of pollution source monitoring, allowing the system to accurately track the propagation path of pollutants, fully understand the scope of pollution impact, and improve the overall monitoring and management effect. By identifying and analyzing diffusion nodes and main paths, the system can grasp the dynamic situation of pollution diffusion in real time and quickly adjust monitoring and response strategies. This technical feature makes the system more flexible and responsive when facing pollution diffusion, enhances the management ability of sudden pollution incidents, and helps protect the environment.

[0097] In this embodiment, the simulated segmented pollution area is captured for diffusion nodes according to the constructed pollution diffusion model. Using a pollution diffusion simulation tool (such as MATLAB's Simulink module or Python's diffusion model library), diffusion node sampling is performed in the simulation area with a high-density grid coverage. Through the simulation model operation, the pollutant concentration changes in each grid unit are recorded, and the points with significant concentration changes are defined as diffusion nodes. The obtained simulated diffusion nodes include their spatial coordinates and pollution concentration values ​​to form a diffusion node data set for subsequent path identification and analysis. The main path identification processing is performed on the obtained simulated diffusion nodes. A path analysis algorithm (such as Dijkstra algorithm or A* algorithm) is applied to process the diffusion node data. First, the node data is used as the vertex in the graph, and the pollution concentration changes between nodes are used as the weight of the edge. The main path of pollutant diffusion is determined by the path analysis algorithm. The main path identification processing will calculate the shortest path or the maximum probability path between nodes to generate a diffusion main path diagram. This figure shows the main propagation route of pollutants from the source to each node, providing a reference for further source tracking. The generated main diffusion path is traced back to the source to determine the location of the initial pollution source. Use reverse path tracing algorithms (such as reverse particle tracing or methods based on reverse diffusion models) to reverse the diffusion path of pollutants from the end point of the main path. By comparing the main path map with the pollution diffusion model, the propagation trajectory of pollutants is gradually traced back until the location of the pollution source is determined. In this process, the impact of environmental factors and model parameters on the path is considered to optimize the location of the pollution source. Ultimately, the initial pollution source location data obtained will provide the precise location of the pollution source for pollution control and treatment decisions.

[0098] Preferably, step S4 comprises:

[0099] Step S41: Analyze the time series distribution characteristics of the oxygen flux data of each area to obtain the time series change curve of the oxygen flux of each area;

[0100] Step S42: dynamically calibrate the initial pollution source location data according to the oxygen flux time series change curve of each zone to obtain the pollution source oxygen distribution matrix;

[0101] Step S43: performing environmental field simulation on the pollution source oxygen distribution matrix to generate a pollution source-oxygen environmental field;

[0102] Step S44: Calculate the diffusion tendency of the initial pollution source positioning data based on the pollution source-oxygen environment field and the oxygen flux data of each area to generate candidate pollution source diffusion directions.

[0103] The present invention generates a time series change curve of oxygen flux in each area by analyzing the time series distribution characteristics of oxygen flux data in each area. This technical feature allows the system to capture and analyze the time change trend of oxygen flux, provides an in-depth understanding of the dynamic change of pollution, and helps to identify the occurrence time, frequency and fluctuation pattern of pollution events, thereby enhancing the monitoring ability of pollution changes. The initial pollution source positioning data is dynamically characterized according to the oxygen flux time series change curve to obtain the pollution source oxygen distribution matrix. This technical feature enables the system to dynamically adjust the pollution source positioning results based on the time-varying oxygen data, generate a more accurate pollution source oxygen distribution matrix, effectively reflect the actual distribution of pollution sources in different time periods, and improve the accuracy and reliability of pollution source positioning. The pollution source oxygen distribution matrix is ​​simulated by the environmental field to generate the pollution source-oxygen environmental field. This technical feature can comprehensively evaluate the impact of pollution sources on the environment by simulating the environmental field, reveal the actual performance of pollution sources in the environment, help understand the propagation and diffusion characteristics of pollutants, and provide a scientific basis for subsequent pollution control and governance strategies. Based on the pollution source-oxygen environmental field and the oxygen flux data of each region, the diffusion tendency of the initial pollution source positioning data is calculated to generate candidate directions for the diffusion of the pollution source. This technical feature can predict the diffusion trend of pollutants based on the simulated environmental field and actual oxygen data, thereby providing diffusion directions, providing forward-looking guidance for pollution control, and improving the system's ability to predict pollution diffusion trends. By comprehensively applying technologies such as time series distribution feature analysis, dynamic calibration, environmental field simulation, and diffusion tendency calculation, the system can conduct a comprehensive analysis of pollution sources in multiple dimensions. This comprehensive technical feature ensures accurate monitoring of pollution sources and their diffusion behaviors, improves the overall monitoring accuracy and practicality of the system, and makes pollution control and response measures more scientific and effective.

[0104] In this embodiment, the oxygen flux data of each measuring point is collected and processed using a data analysis tool (such as MATLAB's time series toolbox or Python's pandas library). The time series data is plotted into a time series diagram to show the change of oxygen flux in each region over time. By analyzing the time series change curve, the periodic changes and trends of oxygen flux are identified, revealing the dynamic characteristics of oxygen flux in different regions. This analysis helps to understand the impact pattern of pollution sources on regional oxygen flux. The characteristic data in the time series change curve is associated with the pollution source location data, and the impact of pollution sources on oxygen flux in each region is calculated using a dynamic feature calibration tool (such as MATLAB's regression analysis tool or Python's scikit-learn library). By establishing a regression model, the impact characteristics of the initial pollution source are mapped to the oxygen flux data of each region, and a pollution source oxygen distribution matrix is ​​generated, which describes the degree of oxygen influence of the pollution source in different regions. The generated pollution source oxygen distribution matrix is ​​subjected to environmental field simulation to generate a pollution source-oxygen environmental field. Using an environmental modeling tool (such as MATLAB's environmental simulation toolbox or Python's environmental modeling library), the pollution source oxygen distribution matrix is ​​used as input data to construct an environmental field model. The model simulates the relationship between pollution sources and oxygen distribution in the environment. By calculating the distribution of oxygen concentration in space, a pollution source-oxygen environmental field map is generated. The map shows the impact of pollution sources on environmental oxygen distribution and provides a visual reference for understanding the spatial distribution of pollutants. Based on the pollution source-oxygen environmental field and the oxygen flux data of each region, the diffusion tendency of the initial pollution source positioning data is calculated to generate candidate directions for pollution source diffusion. Diffusion tendency analysis tools (such as MATLAB's diffusion model or Python's spatial analysis library) are used to combine environmental field models and actual oxygen flux data to calculate the diffusion trend of pollutants. The diffusion direction of pollutants is identified by simulating the diffusion path of pollutants in the environmental field. The diffusion tendency calculation will provide a candidate direction map for the diffusion of pollution sources, which can be used to optimize pollution control strategies and measures.

[0105] Step S44 includes:

[0106] Based on the pollution source-oxygen environmental field, the initial pollution source location data is reconstructed into a three-dimensional pollution source area to generate a pollution source-oxygen model;

[0107] Extract oxygen data of environmental pollution sources from the pollution source-oxygen model to generate oxygen data of environmental pollution sources;

[0108] Compare the oxygen data of environmental pollution sources and oxygen flux data of each region with the oxygen flux of the same region to obtain the oxygen difference data of environmental pollution sources;

[0109] When the oxygen difference data of the surrounding pollution source is included in the normal fluctuation range of the oxygen flux, the direction is determined to be a direction that is not easy to diffuse;

[0110] When the oxygen difference data of the ring pollution source is not included in the normal fluctuation range of the oxygen flux, the direction is determined to be an easy diffusion direction;

[0111] Integrate data on directions that are easy to spread and generate candidate directions for pollution source spread.

[0112] The present invention reconstructs the three-dimensional pollution source area of ​​the initial pollution source positioning data based on the pollution source-oxygen environmental field to generate a pollution source-oxygen model. This technical feature provides a three-dimensional representation of the pollution source, which can more accurately depict the distribution of the pollution source in three-dimensional space, enhance the understanding of the structure and behavior of the pollution source, and improve the accuracy and practicality of the model. The pollution source-oxygen model extracts the oxygen data of the surrounding pollution source to generate the oxygen data of the surrounding pollution source. This technical feature can analyze the local environmental characteristics around the pollution source in more detail by extracting the oxygen data surrounding the pollution source, which helps to identify the local impact range and intensity of the pollution source and improves the ability of local pollution analysis. The oxygen data of the surrounding pollution source and the oxygen flux data of each region are compared with the oxygen flux of the same region to obtain the oxygen difference data of the surrounding pollution source. This technical feature can identify the oxygen changes around the pollution source by comparing and analyzing the oxygen flux data of different regions, help accurately identify the diffusion trend and abnormal situation of pollutants, and optimize the identification process of the diffusion direction. The difficulty of the diffusion direction is determined by judging whether the oxygen difference data of the surrounding pollution source is within the normal fluctuation range of the oxygen flux. This technical feature enables the system to dynamically adjust the assessment of the pollution diffusion direction and provide accurate diffusion trend predictions, thereby providing a scientific decision-making basis for pollution control and response measures. Data integration is performed on the directions that are easy to diffuse, and candidate diffusion directions of pollution sources are generated. This technical feature can generate diffusion directions by integrating diffusion data and provide accurate diffusion prediction results. This helps to optimize pollution source control strategies and resource allocation, and improve the pertinence and effectiveness of pollution prevention and control.

[0113] In this embodiment, the initial pollution source location data is reconstructed in a three-dimensional pollution source area based on the pollution source-oxygen environmental field to generate a pollution source-oxygen model. Using a three-dimensional modeling tool (such as MATLAB's 3D modeling toolbox or Python's Matplotlib library), the pollution source-oxygen environmental field data is input into the model to construct a three-dimensional spatial distribution model of the pollution source. The model reconstruction process includes combining the spatial position of the pollution source with the oxygen distribution data of the environmental field, using an interpolation algorithm (such as Kriging interpolation or three-dimensional spline interpolation) to fill the data gaps and generate a pollution source-oxygen model. This model shows the oxygen impact range and intensity of the pollution source in three-dimensional space, providing a basis for further analysis. The pollution source-oxygen model is subjected to ring pollution source oxygen data extraction to generate ring pollution source oxygen data. By setting multiple annular areas (such as annular slices or equidistant circular rings) in the pollution source-oxygen model, the oxygen data in each annular area is extracted. Using a data extraction tool (such as MATLAB's data analysis toolbox or Python's SciPy library), the average or total oxygen concentration in each annular area is calculated to form a ring pollution source oxygen data set. These data sets describe the oxygen distribution in the annular area and provide a basis for comparative analysis. The oxygen data of the annular pollution source and the oxygen flux data of each region are compared with the oxygen flux of the same region to obtain the oxygen difference data of the annular pollution source. Use comparative analysis tools (such as Python's pandas library or MATLAB's data analysis tools) to compare the oxygen data of the annular pollution source with the oxygen flux data of the corresponding region one by one. Calculate the difference between the oxygen data of the annular pollution source and the regional oxygen flux data to generate the oxygen difference data of the annular pollution source. The difference data is used to identify the degree of influence of the pollution source in different regions and provide support for determining the diffusion direction. The oxygen difference data of the annular pollution source is judged according to the normal fluctuation range of the oxygen flux. When the oxygen difference data of the annular pollution source falls within the normal fluctuation range of the oxygen flux, the direction is judged to be a direction that is not easy to diffuse. This process uses the fluctuation range tool (such as the statistical library in Python or the statistical analysis function of MATLAB) to check whether the difference data is within the preset normal fluctuation range. If the difference data is within the range, it indicates that the diffusion of pollutants is restricted by environmental factors; conversely, if the difference data exceeds the normal fluctuation range, it is judged to be an easy diffusion direction. Based on these judgments, subsequent candidate diffusion directions of pollution sources are generated. The data determined to be easy to diffuse are integrated to generate candidate diffusion directions of pollution sources. All difference data determined to be easy to diffuse are summarized and analyzed, and the average values ​​and diffusion trends of these directions are calculated using data integration tools (such as MATLAB's data processing function or Python's NumPy library). The generated candidate diffusion directions of pollution sources show the diffusion path of pollutants and provide guidance for further pollution control and governance measures.

[0114] Preferably, step S5 comprises:

[0115] Step S51: performing diffusion simulation on the initial pollution source location data based on the candidate diffusion direction of the pollution source to obtain the simulated diffusion pollution source location;

[0116] Step S52: performing delayed pollution area update on the simulated segmented pollution area according to the simulated diffuse pollution source location to generate an updated pollution area;

[0117] Step S53: reconstructing the uniform measurement point array based on the updated contaminated area to obtain an updated measurement point array;

[0118] Step S54: Dynamically monitor the pollution sources of the target pollution area data by updating the measurement point array to obtain dynamic pollution source monitoring results.

[0119] The present invention performs diffusion simulation on the initial pollution source positioning data based on the candidate direction of pollution source diffusion to obtain the simulated diffusion pollution source positioning. This technical feature can simulate on the basis of the candidate direction of pollution source diffusion, predict the actual diffusion of pollution sources under different conditions, thereby improving the accuracy and reliability of the prediction of pollution source behavior. According to the simulated diffusion pollution source positioning, the simulated segmented pollution area is delayed to update the pollution area, and an updated pollution area is generated. This technical feature allows the system to dynamically update the pollution area according to the latest diffusion simulation results, ensure the real-time and accuracy of the pollution area information, and enhance the real-time monitoring and management capabilities of the pollution source. Based on the updated pollution area, the uniform measurement point array is reconstructed to obtain an updated measurement point array. This technical feature adjusts the measurement point array so that it better covers the updated pollution area, improves the spatial distribution and coverage effect of the measurement points, and ensures comprehensive monitoring of the pollution source. The target pollution area data is dynamically monitored by updating the measurement point array to obtain a dynamic pollution source monitoring result. This technical feature can obtain the latest pollution data and dynamic changes by monitoring the pollution source of the dynamically updated measurement point array, thereby improving the accurate detection and monitoring capabilities of the pollution source. The whole process is a close combination of diffusion simulation, pollution area update, array reconstruction and dynamic monitoring, which enables the system to respond quickly to changes in pollution sources. In this way, the system can adjust monitoring strategies and measures in a timely manner, effectively respond to dynamic changes in pollution sources, and improve the efficiency and effectiveness of pollution source management.

[0120] In this embodiment, the initial pollution source location data is diffused based on the candidate direction of pollution source diffusion to obtain the simulated diffusion pollution source location. Using a pollution diffusion simulation tool (such as Simulink of MATLAB or diffusion simulation library of Python), the candidate direction of pollution source diffusion is used as an input condition to run the diffusion model. During the simulation process, the location of the initial pollution source, the candidate diffusion direction, and environmental factors such as wind speed and temperature are considered to predict the spatial distribution of pollutants at future moments. The simulation results will generate a new set of pollution source location data, namely, simulated diffusion pollution source location, which represent the location of the pollution source after diffusion. According to the simulated diffusion pollution source location, the simulated segmented pollution area is delayed to update the pollution area and generate an updated pollution area. Using a geographic information system (GIS) tool or environmental modeling software (such as MappingToolbox of MATLAB or geopandas library of Python), the simulated diffusion pollution source location data is compared with the original pollution area data. The update process includes applying the simulated pollution source location to the original pollution area model and re-dividing the boundaries of the pollution area. The impact of pollution diffusion on each area is calculated by an algorithm to generate new pollution area data, namely, update the pollution area, and show the pollution distribution after diffusion. Based on the updated pollution area, the uniform measurement point array is reconstructed to obtain the updated measurement point array. Using spatial analysis tools (such as MATLAB's Spatial Statistics Toolbox or Python's shapely library), the data of the updated pollution area is used as input to re-plan the measurement point array. According to the new pollution area boundary, the layout and density of the measurement points are adjusted to ensure effective coverage of the updated pollution area. Generate an updated measurement point array, and by comparing the positions of the new and old measurement points, ensure that the new pollution area is covered to meet the needs of dynamic monitoring. The target pollution area data is dynamically monitored by updating the measurement point array to obtain dynamic pollution source monitoring results. Use environmental monitoring equipment (such as portable gas sensors or fixed monitoring stations) to collect real-time data at the location of the updated measurement point array. The data collection process includes recording oxygen concentration, pollutant concentration, and environmental parameters. The collected data is input into a data analysis tool (such as MATLAB's data processing toolbox or Python's data analysis library) for dynamic monitoring and analysis. Finally, the dynamic pollution source monitoring results are generated to describe the current status and distribution of the pollution source, providing a basis for real-time management and control of the pollution source.

[0121] The present invention also provides a pollution source online monitoring system for executing the pollution source online monitoring method as described above, the pollution source online monitoring system comprising:

[0122] The pollution area restoration module is used to obtain the target pollution area data; perform simulation model restoration processing on the target pollution area data, and perform evenly divided area cutting to obtain simulated cut pollution areas;

[0123] The oxygen flux calculation module is used to obtain a uniform measurement point array; perform point-by-point oxygen flux measurements on the simulated segmented pollution area according to the uniform measurement point array to obtain oxygen flux data for each area; perform flux fluctuation analysis on the oxygen flux data for each area to generate a normal fluctuation range for the oxygen flux;

[0124] The pollution source positioning module is used to reversely track the pollution sources of the simulated and segmented pollution areas based on the normal fluctuation range of oxygen flux and the oxygen flux data of each area to obtain the initial pollution source positioning data;

[0125] The diffusion trend calculation module is used to calibrate the pollution source area based on the oxygen flux data of each area and the initial pollution source positioning data, and perform diffusion tendency calculation to generate candidate pollution source diffusion directions;

[0126] The dynamic monitoring and adjustment module is used to dynamically monitor and adjust the simulated segmented pollution area based on the candidate pollution source diffusion direction and the initial pollution source positioning data to obtain dynamic pollution source monitoring results.

[0127] The pollution area restoration module of the present invention can restore the target pollution area in detail based on the simulation model, and divide the area equally to generate the simulated cut pollution area. The technical features of this module are helpful for the accurate division of complex pollution areas, thereby providing an accurate spatial distribution basis for subsequent pollution monitoring and analysis, and improving the accuracy and reliability of overall monitoring. The oxygen flux calculation module can obtain a uniform measurement point array, and perform point-by-point oxygen flux measurement, and carefully analyze the oxygen changes in each simulated cut pollution area. The flux fluctuation analysis further generates the normal fluctuation range of the oxygen flux, thereby providing important benchmark data for the diffusion of pollutants. This modular design can realize high-precision, multi-point distributed real-time monitoring, making the detection of oxygen flux changes more accurate and improving the effectiveness of monitoring. The pollution source positioning module uses the oxygen flux fluctuation range and the oxygen flux data of each area for reverse tracking, and the initial pollution source can be effectively located through this module. This technical feature can quickly identify the location of the pollution source, and ensure the accuracy of positioning by reverse path tracking, which is helpful for real-time detection and rapid response to the problem of pollution source diffusion, and improves the efficiency of pollution source identification. The diffusion trend calculation module can calibrate the pollution source area according to the oxygen flux data of each area, and generate candidate directions for the diffusion of pollution sources through calculation. This function can effectively predict the diffusion trend of pollution sources, making the monitoring of the diffusion of pollutants more forward-looking and proactive, and facilitating the adoption of early prevention and response measures. The dynamic monitoring and adjustment module makes dynamic adjustments based on the candidate directions of pollution source diffusion and the initial pollution source positioning data to achieve real-time monitoring and feedback of pollution source diffusion. By combining candidate directions and historical positioning data, this module can optimize the monitoring scope and strategy in real time, ensuring that the system can flexibly respond to and adjust the monitoring plan during the process of pollution diffusion, thereby improving the intelligence and adaptability of the system and ensuring the timeliness and accuracy of the monitoring results.

[0128] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0129] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A pollution source online monitoring method, characterized in that: The following steps are involved: Step S1: Acquire target contaminated area data; Perform simulation model restoration on the target contaminated area data and perform evenly divided area cutting to obtain simulated cut contaminated areas; Step S2: obtaining a uniform measurement point array; performing point-by-point oxygen flux measurements on the simulated segmented pollution area according to the uniform measurement point array to obtain oxygen flux data for each area; performing flux fluctuation analysis on the oxygen flux data for each area to generate a normal fluctuation range of oxygen flux; Step S3: based on the normal fluctuation range of oxygen flux and the oxygen flux data of each area, reverse pollution source tracking is performed on the simulated segmented pollution area to obtain initial pollution source positioning data; Step S4: calibrate the pollution source area of ​​the initial pollution source positioning data according to the oxygen flux data of each area and the oxygen flux data of each area, and calculate the diffusion tendency to generate the candidate diffusion direction of the pollution source, wherein step S4 includes the following steps: Step S41: Analyze the time series distribution characteristics of the oxygen flux data of each area to obtain the time series change curve of the oxygen flux of each area; Step S42: dynamically calibrate the initial pollution source location data according to the oxygen flux time series change curve of each zone to obtain the pollution source oxygen distribution matrix; Step S43: performing environmental field simulation on the pollution source oxygen distribution matrix to generate a pollution source-oxygen environmental field; Step S44: Calculate the diffusion tendency of the initial pollution source location data based on the pollution source-oxygen environment field and the oxygen flux data of each region to generate candidate pollution source diffusion directions, wherein step S44 includes the following steps: Based on the pollution source-oxygen environmental field, the initial pollution source location data is reconstructed into a three-dimensional pollution source area to generate a pollution source-oxygen model; Extract oxygen data of environmental pollution sources from the pollution source-oxygen model to generate oxygen data of environmental pollution sources; Compare the oxygen data of environmental pollution sources and oxygen flux data of each region with the oxygen flux of the same region to obtain the oxygen difference data of environmental pollution sources; When the oxygen difference data of the surrounding pollution source is included in the normal fluctuation range of the oxygen flux, the direction is determined to be a direction that is not easy to diffuse; When the oxygen difference data of the ring pollution source is not included in the normal fluctuation range of the oxygen flux, the direction is determined to be an easy diffusion direction; Integrate data on directions that are easy to spread and generate candidate directions for pollution source spread; Step S5: Based on the candidate pollution source diffusion directions and the initial pollution source positioning data, dynamic monitoring and adjustment are performed on the simulated segmented pollution area to obtain dynamic pollution source monitoring results.

2. The method for online monitoring of pollution sources according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire target polluted area data; perform multi-spectral remote sensing data collection on the target polluted area data to obtain multi-dimensional pollution feature data; Step S12: performing principal component analysis on the multi-dimensional pollution feature data to obtain a reduced-dimensional pollution feature vector; Step S13: constructing a three-dimensional pollution distribution model for the reduced-dimensional pollution feature vector to generate a three-dimensional distribution map of the target pollution area; Step S14: uniformly grid the three-dimensional distribution map of the target pollution area to obtain uniformly distributed pollution grid units; Step S15: performing boundary mesh refinement processing on the uniformly distributed polluted mesh units to generate simulated segmented polluted areas.

3. The method for online monitoring of pollution sources according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: inserting unit area measurement points into the simulated segmented pollution area to generate a uniform measurement point array; Step S22: performing continuous sampling of the oxygen sensor according to the uniform measurement point array to obtain oxygen time series data; Step S23: Calculate the oxygen flux at each point of the oxygen time series data to generate oxygen flux data for each area; Step S24: performing spatial density clustering processing on the oxygen flux data of each region to obtain clustered oxygen flux; Step S25: performing flux fluctuation analysis on the clustered oxygen flux to generate a normal fluctuation range of the oxygen flux.

4. The method for online monitoring of pollution sources according to claim 3, characterized in that: Step S25 includes the following steps: Step S251: Obtaining environmental conditions of the target pollution area; Step S252: performing correlation analysis on the environmental conditions of the target pollution area and the clustered oxygen flux to obtain environment-oxygen impact data; Step S253: performing support vector regression analysis on the environment-oxygen impact data to generate oxygen content impact factors; Step S254: Evaluate the environmental impact of the target polluted area based on the oxygen content impact factor to obtain environmental impact data for each area; Step S255: Calculate the maximum oxygen fluctuation of the clustered oxygen flux according to the environmental impact data of each region to generate a normal fluctuation range of the oxygen flux.

5. The method for online monitoring of pollution sources according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: performing outlier detection on oxygen flux data of each region based on the normal fluctuation range of oxygen flux to obtain an abnormal flux point set; Step S32: performing spatiotemporal clustering processing on the abnormal flux point set to obtain abnormal spatiotemporal evolution characteristics; Step S33: constructing a pollution diffusion model based on the abnormal spatiotemporal evolution characteristics to generate a pollution diffusion model; Step S34: reversely trace the pollution source of the simulated segmented pollution area according to the pollution diffusion model to obtain initial pollution source location data.

6. The method for online monitoring of pollution sources according to claim 5, characterized in that: Step S34 includes the following steps: According to the pollution diffusion model, the simulated segmented pollution area is captured for diffusion nodes to obtain simulated diffusion nodes; Perform main path identification processing on simulated diffusion nodes to generate main diffusion paths; The main diffusion paths are traced back in reverse order to obtain the initial pollution source location data.

7. The method for online monitoring of pollution sources according to claim 1, characterized in that: Step S5 includes the following steps: Step S51: performing diffusion simulation on the initial pollution source location data based on the candidate diffusion direction of the pollution source to obtain the simulated diffusion pollution source location; Step S52: performing delayed pollution area update on the simulated segmented pollution area according to the simulated diffuse pollution source location to generate an updated pollution area; Step S53: reconstructing the uniform measurement point array based on the updated contaminated area to obtain an updated measurement point array; Step S54: Dynamically monitor the pollution sources of the target pollution area data by updating the measurement point array to obtain dynamic pollution source monitoring results.

8. A pollution source online monitoring system, characterized in that: Used to execute the pollution source online monitoring method as claimed in claim 1, the pollution source online monitoring system comprises: The pollution area restoration module is used to obtain the target pollution area data; perform simulation model restoration processing on the target pollution area data, and perform evenly divided area cutting to obtain simulated cut pollution areas; The oxygen flux calculation module is used to obtain a uniform measurement point array; perform point-by-point oxygen flux measurements on the simulated segmented pollution area according to the uniform measurement point array to obtain oxygen flux data for each area; perform flux fluctuation analysis on the oxygen flux data for each area to generate a normal fluctuation range for the oxygen flux; The pollution source positioning module is used to reversely track the pollution sources of the simulated and segmented pollution areas based on the normal fluctuation range of oxygen flux and the oxygen flux data of each area to obtain the initial pollution source positioning data; The diffusion trend calculation module is used to calibrate the pollution source area based on the oxygen flux data of each area and the initial pollution source positioning data, and perform diffusion tendency calculation to generate candidate pollution source diffusion directions; The dynamic monitoring and adjustment module is used to dynamically monitor and adjust the simulated segmented pollution area based on the candidate pollution source diffusion direction and the initial pollution source positioning data to obtain dynamic pollution source monitoring results.

Images