Industrial park-oriented multi-pollution-source cooperative treatment and emission optimization regulation and control method

Abstract

The invention provides an industrial park-oriented multi-pollution source collaborative treatment and emission optimization regulation and control method, which relates to the technical field of environmental pollution abatement, and comprises the following steps: obtaining real-time monitoring data and meteorological data, generating emission characteristic fingerprint data and a pollutant distribution weight coefficient, and calculating the emission characteristic fingerprint data and the pollutant distribution weight coefficient according to the emission characteristic fingerprint data and the pollutant distribution weight coefficient; a bidirectional fluid-solid coupling calculation method is adopted to generate pollutant transmission path data, management and control partitions are divided, a pollutant migration and diffusion model is constructed to calculate a pollution source correlation intensity matrix, and therefore the optimal emission reduction proportion and dynamic emission regulation and control parameters are determined, and a multi-pollution-source linkage control strategy is established. According to the invention, accurate identification and cooperative treatment of multiple pollution sources are realized, and the pollution treatment efficiency is improved.

Description

Technical Field

[0001] The present invention relates to environmental pollution control technology, and in particular to a method for collaborative control of multiple pollution sources and emission optimization and regulation for industrial parks. Background Art

[0002] As industrial parks continue to expand, the interactions between multiple pollution sources are becoming increasingly complex. Traditional approaches to single-source pollution control are no longer sufficient to meet environmental management needs. Existing technologies, primarily based on fixed emission standards, lack in-depth analysis of the interrelationships between pollution sources, making it difficult to achieve precise control.

[0003] At present, there are three main problems in the coordinated control of pollution sources in industrial parks: first, it is difficult to accurately identify the emission characteristics of each pollution source and their mutual influence; second, the complex processes of gas-liquid phase transformation, chemical reaction and sedimentation of pollutants during transmission are not fully considered; third, there is a lack of differentiated regulatory mechanisms based on the correlation strength of pollution sources.

[0004] Therefore, it is urgent to establish a method for coordinated governance and emission optimization control of multiple pollution sources for industrial parks. By analyzing the emission characteristic fingerprints and transmission paths of pollution sources, a pollutant migration and diffusion model can be constructed, and differentiated control can be achieved based on the correlation strength of pollution sources, thereby improving the scientificity and accuracy of environmental governance in industrial parks. Summary of the Invention

[0005] The embodiment of the present invention provides a method for collaboratively controlling multiple pollution sources and optimizing emissions in industrial parks, which can solve the problems in the prior art.

[0006] According to a first aspect of the embodiments of the present invention,

[0007] Provides a method for collaboratively controlling multiple pollution sources and optimizing emissions in industrial parks, including:

[0008] Obtain real-time monitoring data and meteorological data for multiple pollution sources within the industrial park;

[0009] Based on real-time monitoring data, by analyzing the concentration of characteristic pollutant components and the ratio of characteristic pollutant component concentrations of each pollution source, the emission characteristic fingerprint data of each pollution source is generated, and the pollutant distribution weight coefficient is calculated based on the emission characteristic fingerprint data;

[0010] Based on emission fingerprint data, meteorological data, and pollutant distribution weight coefficients, a two-way fluid-solid coupling calculation method is used to take the gas-liquid phase conversion rate, chemical reaction rate, and sedimentation rate of pollutants as calculation parameters to generate pollutant transmission path data. Based on this pollutant transmission path data, the industrial park is divided into control zones.

[0011] A pollutant migration and diffusion model is constructed based on the control zoning and pollutant transmission path data, the pollutant superposition impact coefficients between pollution sources are calculated, and a pollution source correlation intensity matrix is ​​generated. The optimal emission reduction ratio of each pollution source is calculated based on the pollution source correlation intensity matrix and the pollutant distribution weight coefficient. The dynamic emission control parameters of each pollution source are calculated based on the optimal emission reduction ratio. Based on the dynamic emission control parameters and pollutant transmission path data, a multi-pollution source linkage control strategy is established to generate coordinated control instructions for each pollution source.

[0012] In an optional embodiment,

[0013] Based on real-time monitoring data, by analyzing the concentration of characteristic pollutant components and the ratio of characteristic pollutant component concentrations of each pollution source, the emission characteristic fingerprint data of each pollution source is generated. The pollutant distribution weight coefficients calculated based on the emission characteristic fingerprint data include:

[0014] Acquire real-time monitoring data of multiple pollution sources in the industrial park, the real-time monitoring data including characteristic pollutant component concentration data, perform wavelet transform decomposition on the characteristic pollutant component concentration data to obtain first frequency band component concentration data and second frequency band component concentration data;

[0015] constructing a chemical reaction kinetics correction model based on the component concentration data of the first frequency band and the component concentration data of the second frequency band, calculating the direct reaction amount of pollutants, the synergistic reaction amount of pollutants, and the attenuation amount of pollutants through the chemical reaction kinetics correction model, and generating corrected component concentration data;

[0016] The attention mechanism is used to perform time series analysis on the corrected component concentration data to extract the time distribution characteristics of the component concentrations and generate time characteristic data. The transformation relationship between the pollutant components is calculated based on the time characteristic data to generate component transformation characteristic data.

[0017] Calculate the correlation between pollutant components based on the time characteristic data and the component conversion characteristic data to generate a component action coefficient, and use the component action coefficient to perform weighted fusion on the time characteristic data and the component conversion characteristic data to obtain pollution source emission characteristic fingerprint data;

[0018] Substituting the emission characteristic fingerprint data of the pollution source into the optimization equation, and satisfying the component action constraint and component transformation constraint conditions, the pollutant distribution weight coefficient is obtained. The pollutant distribution weight coefficient is used to characterize the pollutant emission contribution of each pollution source.

[0019] In an optional embodiment,

[0020] A chemical reaction kinetics correction model is constructed based on the component concentration data of the first frequency band and the component concentration data of the second frequency band. The direct reaction amount, synergistic reaction amount, and attenuation amount of pollutants are calculated using the chemical reaction kinetics correction model to generate the corrected component concentration data.

[0021] Normalizing the concentration data of the components in the first frequency band and the concentration data of the components in the second frequency band to obtain standardized concentration data, constructing a reaction network structure based on the standardized concentration data, establishing a substance conversion relationship between the components using the components as nodes, and calculating the concentration gradient between the components to obtain the reaction intensity;

[0022] Establishing a reaction rate equation of a chemical reaction kinetics correction model according to the reaction intensity, wherein the reaction rate equation includes a reactant concentration term, a reaction rate constant term, and a correction coefficient term;

[0023] Solving the reaction rate equation using the standardized concentration data to obtain a frequency band coupling coefficient, establishing a component concentration change matrix based on the frequency band coupling coefficient, substituting the component concentration change matrix into the reaction rate equation to obtain a reaction rate value, and calculating the direct reaction amount of the pollutant based on the product of the reaction rate value and the time step;

[0024] constructing a component interaction matrix based on the component concentration change matrix, substituting the component interaction matrix into the reaction rate equation, and calculating the synergistic reaction amount of the pollutants;

[0025] Acquiring environmental monitoring data, and correcting the correction coefficient term in the reaction rate equation according to the environmental monitoring data to calculate the pollutant attenuation;

[0026] The pollutant direct reaction amount and the pollutant synergistic reaction amount are added to the standardized concentration data, and the pollutant attenuation amount is subtracted to generate corrected component concentration data.

[0027] In an optional embodiment,

[0028] Based on emission characteristic fingerprint data, meteorological data, and pollutant distribution weight coefficients, a two-way fluid-solid coupling calculation method is used to take the gas-liquid phase conversion rate, chemical reaction rate, and sedimentation rate of pollutants as calculation parameters to generate pollutant transmission path data. Based on the pollutant transmission path data, the control zones of the industrial park are divided into the following:

[0029] Analyze the concentration distribution characteristics of different pollutant components in the emission characteristic fingerprint data, calculate the mutual promotion and mutual inhibition strengths between pollutant components, and construct the interaction strength matrix between components;

[0030] The intercomponent interaction intensity matrix is ​​combined with the pollutant distribution weight coefficient, and the local pollutant concentration distribution characteristic value is calculated based on the temperature and humidity information in the meteorological data to obtain the local concentration correction coefficient. The mass transfer resistance at the gas-liquid interface is corrected based on the local concentration correction coefficient, and the phase conversion rate considering the interface resistance is calculated in combination with the intercomponent interaction intensity matrix;

[0031] Calculating a mass transfer flux at the gas-liquid interface based on the phase conversion rate, combining the mass transfer flux with a local concentration correction coefficient to calculate a chemical reaction rate that takes into account local distribution characteristics, and calculating a pollutant deposition rate that takes into account interfacial mass transfer characteristics based on the chemical reaction rate and the phase conversion rate;

[0032] Substituting the phase conversion rate, chemical reaction rate, and sedimentation rate into the bidirectional fluid-solid coupling governing equation, which includes the interaction term between gaseous pollutants and particulate matter, an adaptive parameter adjustment mechanism is established based on real-time changes in environmental monitoring data. The pollutant transmission flux at each grid point is calculated through iterative solution.

[0033] Analyzing the spatiotemporal variation characteristics of the transmission flux, identifying the main transmission channels and calculating the pollution load index of each transmission channel to generate pollutant transmission path data;

[0034] The diffusion risk coefficient of each grid point is calculated according to the pollutant transmission path data, and the industrial park is divided into control zones based on the pollution load index and the diffusion risk coefficient.

[0035] In an optional embodiment,

[0036] Analyzing the spatiotemporal variation characteristics of the transmission flux, identifying the main transmission channels and calculating the pollution load index of each transmission channel to generate pollutant transmission path data includes:

[0037] The spatial gradient of pollutant concentration of the transmission flux is calculated using a sliding time window method. The length of the sliding time window is dynamically adjusted according to the rate of change of the pollutant concentration. The temporal characteristics of the spatial gradient are analyzed, and a gradient discrimination threshold is set according to the physicochemical properties of the pollutants. When the spatial gradient is greater than the gradient discrimination threshold, data sampling points are added to obtain transmission flux sampling data.

[0038] Performing spatiotemporal decomposition on the transmission flux sampling data to obtain the temporal evolution characteristics and spatial distribution characteristics of the transmission flux, performing multi-factor correlation analysis on the spatiotemporal variation characteristics with the temperature field, humidity field, and wind field, and establishing a quantitative correspondence between the spatiotemporal variation characteristics of the transmission flux and the environmental field;

[0039] An environmental stress index is constructed based on the quantitative correspondence, wherein the environmental stress index represents the comprehensive impact of the environmental field on the diffusion, deposition and accumulation of pollutants, and the environmental stress index is weightedly combined with the transmission flux to calculate the pollution load index of each transmission channel;

[0040] Construct an intensity-direction phase diagram of the transmission flux, extract the transmission flux intensity contour lines and direction field in the phase diagram, determine the main transmission channel based on the continuity of the contour lines and direction field, and integrate the spatial position, transmission flux and pollution load of the main transmission channel to generate pollutant transmission path data.

[0041] In an optional embodiment,

[0042] Based on the control zones and pollutant transmission path data, a pollutant migration and diffusion model is constructed to calculate the pollutant superposition impact coefficient between pollution sources and generate a pollution source correlation intensity matrix including:

[0043] Gridding the control zones based on pollutant transmission path data, adaptively adjusting the grid density using concentration gradients calculated based on pollutant concentration monitoring data, establishing mass and momentum conservation equations within the grid that include pollutant chemical reaction rates, gas-liquid phase conversion rates, and sedimentation rates, and constructing a pollutant migration and diffusion model;

[0044] The pollutant migration and diffusion model is used to solve the pollutant concentration field distribution data, and based on the pollutant concentration field distribution data, a sensitivity coefficient characterizing the impact of changes in pollution source emissions on receptor point concentration is calculated. The sensitivity coefficient is substituted into a nonlinear response function including gas phase oxidation, liquid phase oxidation, and heterogeneous reaction to calculate the pollutant superposition influence coefficient;

[0045] The single-source transmission influence coefficient is calculated based on the pollutant superposition influence coefficient, and the single-source transmission influence coefficient is input into the transitive closure algorithm for calculating the multi-source coupled transmission effect of pollutants to obtain the coupled transmission influence coefficient. The single-source transmission influence coefficient and the coupled transmission influence coefficient are combined based on a sliding window of a time series to generate a pollution source correlation intensity matrix.

[0046] In an optional embodiment,

[0047] The optimal emission reduction ratio for each pollution source is calculated based on the pollution source correlation intensity matrix and the pollutant distribution weight coefficient. The dynamic emission control parameters for each pollution source are calculated based on the optimal emission reduction ratio. Based on the dynamic emission control parameters and pollutant transmission path data, a multi-pollution source linkage control strategy is established to generate coordinated control instructions for each pollution source, including:

[0048] The pollution source correlation intensity matrix and the pollutant distribution weight coefficient are input into a nonlinear programming model, wherein the nonlinear programming model includes objective functions of maximizing pollutant reduction and minimizing economic costs, and the optimal emission reduction ratio of each pollution source is obtained by solving the model through a genetic algorithm;

[0049] A state space model is established based on the optimal emission reduction ratio, including pollution source characteristics, meteorological conditions, and environmental capacity. A Kalman filter algorithm is used to estimate the system state in real time. The state estimation results are input into a model predictive controller to calculate the dynamic emission control parameters of each pollution source.

[0050] A weighted directed graph of pollution sources is constructed based on the dynamic emission control parameters and pollutant transmission path data, a community discovery algorithm is used to identify strongly correlated pollution source groups in the weighted directed graph, and differentiated group control strategies are generated according to the dynamic emission control parameters of each group to establish a multi-pollution source linkage control strategy;

[0051] A hierarchical control structure is constructed based on the multi-pollution source linkage control strategy, a feedback compensation mechanism is set in the hierarchical control structure, actual pollutant concentration change data is input into the feedback compensation mechanism for dynamic correction, and coordinated control instructions for each pollution source are generated.

[0052] In an optional embodiment,

[0053] A weighted directed graph of pollution sources is constructed based on the dynamic emission control parameters and pollutant transmission path data. A community discovery algorithm is used to identify strongly correlated pollution source groups in the weighted directed graph. Differentiated group control strategies are generated based on the dynamic emission control parameters of each group. Establishing a multi-pollution source linkage control strategy includes:

[0054] Dynamic emission control parameters are used as node eigenvalues, node connection relationships are constructed based on pollutant transmission path data, and the transmission volume between nodes is updated using an exponential decay method to obtain edge eigenvalues. A weighted directed graph of pollution sources is constructed based on the node eigenvalues ​​and edge eigenvalues.

[0055] Calculating the actual transmission strength between nodes and the network benchmark transmission strength based on the pollution source weighted directed graph, inputting the actual transmission strength and the network benchmark transmission strength into a community discovery algorithm, and obtaining an initial group division scheme by iteratively optimizing the group division index;

[0056] Calculating an inter-group transmission distance coefficient and a meteorological similarity coefficient based on the initial group division scheme, combining the transmission distance coefficient and meteorological similarity coefficient with a group division index to construct a group optimization criterion, optimizing the initial group division scheme according to the group optimization criterion to obtain a target pollution source group, constructing a group control model including pollutant reduction amounts and control costs for the target pollution source group, and obtaining a pollution source group control target by solving the group control model;

[0057] Calculating the connectivity coefficient, transmission flux coefficient, and position correlation coefficient of the nodes in each pollution source group, combining the connectivity coefficient, transmission flux coefficient, and position correlation coefficient to obtain a node priority coefficient, and grading the nodes in the pollution source group based on the node priority coefficient to obtain an intra-group grading scheme;

[0058] A group game model including pollutant reduction amounts and control costs is constructed based on the intra-group grading scheme and pollution source group control targets. The group game model is solved to obtain differentiated group control strategies, and real-time monitoring data is collected to calculate control correction amounts. The control correction amounts are input into the compensation model to make real-time adjustments to the differentiated group control strategies, thereby establishing a multi-pollution source linkage control strategy.

[0059] According to a second aspect of the embodiments of the present invention,

[0060] An electronic device is provided, comprising:

[0061] processor;

[0062] a memory for storing processor-executable instructions;

[0063] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0064] According to a third aspect of the embodiments of the present invention,

[0065] A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described above is implemented.

[0066] In this embodiment, by obtaining real-time monitoring data and meteorological data of multiple pollution sources in the industrial park, generating emission characteristic fingerprint data and pollutant distribution weight coefficients, the precise identification and quantitative analysis of multiple pollution sources are achieved, and the accuracy and timeliness of pollution source analysis are improved. A two-way fluid-solid coupling calculation method is adopted, and the gas-liquid phase conversion rate, chemical reaction rate and sedimentation rate of pollutants are used as calculation parameters to generate pollutant transmission path data, and a more accurate pollutant migration and diffusion model is constructed, which can accurately reflect the mutual influence relationship between different pollution sources and provide a scientific basis for collaborative governance. The optimal emission reduction ratio is calculated based on the pollution source correlation intensity matrix and the pollutant distribution weight coefficient, and dynamic emission control parameters and multi-pollution source linkage control strategy are generated, which realizes the collaborative governance and emission optimization control of multiple pollution sources in the industrial park, which not only ensures that the environmental quality meets the standards, but also minimizes the emission reduction costs of enterprises and improves the scientificity and economy of environmental management. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 This is a flow chart of a method for collaboratively controlling multiple pollution sources and optimizing emissions in industrial parks according to an embodiment of the present invention;

[0068] Figure 2 This is a graph analyzing the pollutant synergistic effect capture capability of an embodiment of the present invention;

[0069] Figure 3 This is a diagram showing the spatiotemporal decomposition and multi-factor correlation analysis of the transmission flux according to an embodiment of the present invention;

[0070] Figure 4 This is a simulation diagram of real-time effect monitoring of the multi-pollution source linkage control strategy according to an embodiment of the present invention. DETAILED DESCRIPTION

[0071] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0072] The following specific embodiments are used to describe the technical solution of the present invention in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0073] Figure 1 This is a flow chart of a method for collaboratively controlling multiple pollution sources and optimizing emissions in industrial parks according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0074] Obtain real-time monitoring data and meteorological data for multiple pollution sources within the industrial park;

[0075] Based on real-time monitoring data, by analyzing the concentration of characteristic pollutant components and the ratio of characteristic pollutant component concentrations of each pollution source, the emission characteristic fingerprint data of each pollution source is generated, and the pollutant distribution weight coefficient is calculated based on the emission characteristic fingerprint data;

[0076] Based on emission fingerprint data, meteorological data, and pollutant distribution weight coefficients, a two-way fluid-solid coupling calculation method is used to take the gas-liquid phase conversion rate, chemical reaction rate, and sedimentation rate of pollutants as calculation parameters to generate pollutant transmission path data. Based on this pollutant transmission path data, the industrial park is divided into control zones.

[0077] A pollutant migration and diffusion model is constructed based on the control zoning and pollutant transmission path data, the pollutant superposition impact coefficients between pollution sources are calculated, and a pollution source correlation intensity matrix is ​​generated. The optimal emission reduction ratio of each pollution source is calculated based on the pollution source correlation intensity matrix and the pollutant distribution weight coefficient. The dynamic emission control parameters of each pollution source are calculated based on the optimal emission reduction ratio. Based on the dynamic emission control parameters and pollutant transmission path data, a multi-pollution source linkage control strategy is established to generate coordinated control instructions for each pollution source.

[0078] In an optional embodiment, based on real-time monitoring data, by analyzing the characteristic pollutant component concentrations and the ratio of characteristic pollutant component concentrations of each pollution source, emission characteristic fingerprint data of each pollution source is generated, and the pollutant distribution weight coefficient calculated based on the emission characteristic fingerprint data includes:

[0079] Acquire real-time monitoring data of multiple pollution sources in the industrial park, the real-time monitoring data including characteristic pollutant component concentration data, perform wavelet transform decomposition on the characteristic pollutant component concentration data to obtain first frequency band component concentration data and second frequency band component concentration data;

[0080] constructing a chemical reaction kinetics correction model based on the component concentration data of the first frequency band and the component concentration data of the second frequency band, calculating the direct reaction amount of pollutants, the synergistic reaction amount of pollutants, and the attenuation amount of pollutants through the chemical reaction kinetics correction model, and generating corrected component concentration data;

[0081] The attention mechanism is used to perform time series analysis on the corrected component concentration data to extract the time distribution characteristics of the component concentrations and generate time characteristic data. The transformation relationship between the pollutant components is calculated based on the time characteristic data to generate component transformation characteristic data.

[0082] Calculate the correlation between pollutant components based on the time characteristic data and the component conversion characteristic data to generate a component action coefficient, and use the component action coefficient to perform weighted fusion on the time characteristic data and the component conversion characteristic data to obtain pollution source emission characteristic fingerprint data;

[0083] Based on the emission characteristic fingerprint data of the pollution sources, the fluctuation pattern of the component concentration of each pollution source in different time periods is analyzed, the mean value, fluctuation amplitude and fluctuation period of the pollutant concentration in each time period are calculated, and the pollutant distribution weight coefficient is obtained. The pollutant distribution weight coefficient is used to characterize the pollutant emission contribution of each pollution source.

[0084] For example, real-time monitoring data of multiple pollution sources in an industrial park is obtained. In this embodiment, taking a chemical park as an example, five major pollution sources in the park are selected, including two chemical plants, one power plant, one garbage treatment plant, and one sewage treatment plant. By installing online monitoring equipment at each pollution source, data is collected once an hour for seven consecutive days to obtain characteristic pollutant component concentration data, including concentration values ​​of pollutants such as SO2, nitrogen oxides (NOx), volatile organic compounds (VOCs), PM2.5, and NH3.

[0085] The acquired characteristic pollutant component concentration data are decomposed using a wavelet transform. Using the db4 wavelet basis function, the component concentration data for each pollution source are decomposed into three layers, yielding component concentration data in the first frequency band (the low-frequency portion, representing the long-term trend of pollutant concentration) and component concentration data in the second frequency band (the high-frequency portion, representing short-term fluctuations in pollutant concentration). For example, for the SO2 concentration data from Chemical Plant A, after wavelet decomposition, the first frequency band reflects concentration changes caused by the production cycle, while the second frequency band reflects concentration fluctuations caused by sudden emissions or changes in meteorological conditions.

[0086] A chemical reaction kinetics correction model is constructed based on the decomposed frequency band component concentration data. This model takes into account the chemical reaction relationship between pollutants, including direct reaction, synergistic reaction and natural attenuation. For direct reaction, taking the photochemical reaction of NOx and VOCs as an example, when the monitored sunlight intensity is greater than 500W / m 2 When temperatures are above 25°C, the reaction rate of NOx and VOCs increases by approximately 30%. For example, the synergistic reaction between SO2 and NH3 to form ammonium sulfate increases by approximately 25% when relative humidity is above 70%. For pollutant attenuation, using VOCs as an example, the natural attenuation is calculated based on the half-lives of different VOC components (e.g., benzene has a half-life of approximately 12 hours, and alkanes have a half-life of approximately 24 hours). These calculations generate corrected component concentration data.

[0087] An attention mechanism is used to perform time series analysis on the corrected component concentration data. Specifically, a multi-head self-attention mechanism is used, with eight attention heads, each with a dimension of 64, to extract characteristics of component concentrations at different time scales. For example, for power plant NOx emission data, the attention mechanism can identify differences in emission patterns between weekdays and weekends, as well as emission characteristics during peak hours in the morning and evening. In this way, temporal feature data is generated, including daily and weekly variation patterns and sudden event characteristics.

[0088] A pollutant component transformation network was constructed based on temporal feature data. A graph neural network model was used, treating each pollutant component as a node and the transformation relationships between components as edges. The number of graph convolutional layers was set to three, with 128 hidden units per layer and a Reinforced Luminance (ReLU) activation function. This network calculated the transformation relationships between pollutant components, such as the ratio of NOx converted to secondary organic aerosols under specific conditions and the rate of SO2 conversion to sulfate, thereby generating component transformation feature data.

[0089] Correlations between pollutant components were calculated based on temporal and component transformation data. Pearson's correlation coefficients were used to calculate correlations between components and generate a component interaction coefficient matrix. For example, in the waste treatment plant data, the correlation coefficient between NH3 and H2S was 0.85, indicating a high correlation and possible origin of the two emissions from the same process.

[0090] The component interaction coefficients are used to perform a weighted fusion of the time signature data and the component conversion signature data. The weight of the time signature is set to 0.6, and the weight of the component conversion signature is set to 0.4. The pollution source emission fingerprint data is obtained through weighted summation. For example, the signature fingerprint of chemical plant B shows a VOCs / NOx ratio of 3.2, while the ratio for the power plant is 0.8. This difference can be used to distinguish different types of pollution sources.

[0091] Based on the emission fingerprint data of pollution sources, the fluctuation pattern of component concentrations of each pollution source in different time periods is analyzed. The mean concentration, fluctuation amplitude and fluctuation period of pollutants in each time period are calculated to obtain the pollutant distribution weight coefficient. Taking pollution source A as an example, the mean concentration of SO2 is 28mg / m3 during the period of 9:00-17:00 on weekdays. 3 , the fluctuation range is ±7mg / m 3 , with a fluctuation period of approximately 90 minutes. During the same period on non-working days, the average SO2 concentration was 12 mg / m3, with a fluctuation range of ±3 mg / m3 and a fluctuation period of approximately 120 minutes. Using these characteristic parameters, we calculated that the SO2 distribution weight coefficients for source A on working days and non-working days were 0.65 and 0.25, respectively, indicating that this source contributes significantly more to regional SO2 pollution on working days than on non-working days.

[0092] In this embodiment, characteristic pollutant concentration data is decomposed using wavelet transforms to effectively extract pollution characteristics across different frequency bands, improving data processing accuracy. Combined with a chemical reaction kinetics correction model, the direct reaction, synergistic reaction, and attenuation of pollutants can be corrected, making component concentration data more consistent with actual pollution diffusion. Using an attention mechanism for time series analysis, the temporal evolution of pollutant concentrations can be explored, enhancing the ability to capture dynamic changes in pollution. A graph neural network is used to calculate the transformation relationships between pollutant components and construct a pollutant component transformation network, improving the accuracy of analyzing interactions between components. By calculating component interaction coefficients and performing weighted fusion, efficient extraction of pollution source emission fingerprint data is achieved, thereby enhancing the traceability of pollution sources. Finally, by calculating the pollutant distribution weight coefficient, the calculation of pollutant emission contributions is made more scientific and reasonable, providing a reliable decision-making basis for pollution tracing, environmental supervision, and pollution control.

[0093] In an optional embodiment, a chemical reaction kinetics correction model is constructed based on the first frequency band component concentration data and the second frequency band component concentration data. The direct reaction amount, synergistic reaction amount, and attenuation amount of pollutants are calculated using the chemical reaction kinetics correction model. Generating the corrected component concentration data includes:

[0094] Normalizing the concentration data of the components in the first frequency band and the concentration data of the components in the second frequency band to obtain standardized concentration data, constructing a reaction network structure based on the standardized concentration data, establishing a substance conversion relationship between the components using the components as nodes, and calculating the concentration gradient between the components to obtain the reaction intensity;

[0095] Establishing a reaction rate equation of a chemical reaction kinetics correction model according to the reaction intensity, wherein the reaction rate equation includes a reactant concentration term, a reaction rate constant term, and a correction coefficient term;

[0096] Solving the reaction rate equation using the standardized concentration data to obtain a frequency band coupling coefficient, establishing a component concentration change matrix based on the frequency band coupling coefficient, substituting the component concentration change matrix into the reaction rate equation to obtain a reaction rate value, and calculating the direct reaction amount of the pollutant based on the product of the reaction rate value and the time step;

[0097] constructing a component interaction matrix based on the component concentration change matrix, substituting the component interaction matrix into the reaction rate equation, and calculating the synergistic reaction amount of the pollutants;

[0098] Acquiring environmental monitoring data, and correcting the correction coefficient term in the reaction rate equation according to the environmental monitoring data to calculate the pollutant attenuation;

[0099] The pollutant direct reaction amount and the pollutant synergistic reaction amount are added to the standardized concentration data, and the pollutant attenuation amount is subtracted to generate corrected component concentration data.

[0100] For example, the system obtains the concentration data of the component in the first frequency band and the concentration data of the component in the second frequency band. In practical applications, the first frequency band can be the ultraviolet spectrum region (such as 240-320nm), and the second frequency band can be the visible spectrum region (such as 380-780nm). For example, when monitoring air samples in a certain city, the concentration of SO2 in the ultraviolet band is 120μg / m 3 , the concentration in the visible light band is 105μg / m 3 ; The concentration of NOx in the ultraviolet band is 85μg / m 3 , the concentration in the visible light band is 78μg / m 3 ; The concentration of PM2.5 in the ultraviolet band is 45μg / m 3 , the concentration in the visible light band is 42μg / m 3 .

[0101] Normalization is performed on the component concentration data for the first and second frequency bands to produce standardized concentration data. This normalization uses a maximum-minimum normalization method, mapping the concentration values ​​of each component to a range of 0-1. For example, after normalization, the standardized concentration of SO2 in the ultraviolet band is 1.0, and in the visible light band is 0.875; the standardized concentration of NOx in the ultraviolet band is 0.708, and in the visible light band is 0.65; and the standardized concentration of PM2.5 in the ultraviolet band is 0.375, and in the visible light band is 0.35.

[0102] A reaction network structure is constructed based on standardized concentration data, with each component serving as a node, to establish the substance conversion relationships between components. For example, a photochemical reaction relationship exists between SO2 and NOx, an adsorption relationship exists between SO2 and PM2.5, and a catalytic relationship exists between NOx and PM2.5. Reaction intensities are calculated by calculating the concentration gradients between components. For example, the reaction intensity between SO2 and NOx in the ultraviolet band is 0.292 (i.e., 1.0 minus 0.708), and the reaction intensity in the visible light band is 0.225 (i.e., 0.875 minus 0.65).

[0103] A reaction rate equation for the chemical reaction kinetic correction model was established based on the reaction intensity. This reaction rate equation includes a reactant concentration term, a reaction rate constant term, and a correction factor term. For the reaction between SO₂ and NO₂, the reactant concentration term in the reaction rate equation is the product of their standardized concentrations. The initial value of the reaction rate constant term is set to 0.02, and the initial value of the correction factor term is set to 1.0.

[0104] The reaction rate equation is solved using standardized concentration data to obtain the band coupling coefficient. In this example, the band coupling coefficient between SO2 and NOx, obtained through iterative calculation, is 0.85, indicating a high correlation between the data in the ultraviolet and visible light bands. Based on the band coupling coefficients, a component concentration change matrix is ​​constructed, which reflects the rate of change of different component concentrations over time. For example, the SO2 concentration change rate is -0.018, and the NOx concentration change rate is -0.015, indicating that the concentrations of both decrease during the reaction.

[0105] Substitute the component concentration change matrix into the reaction rate equation to obtain the reaction rate value. For the reaction between SO2 and NOx, the calculated reaction rate value is 0.022. The direct reaction amount of the pollutant is calculated by multiplying the reaction rate value by the time step. Assuming a time step of 1 hour, the direct reaction amount of SO2 is 0.022 × 1 = 0.022, which converts to an actual concentration of approximately 2.64 μg / m 3 .

[0106] Based on the component concentration change matrix, a component interaction matrix is ​​constructed. This matrix describes the degree of mutual influence between components. For example, the influence coefficient of SO2 on NOx is 0.8, and the influence coefficient of NOx on SO2 is 0.75. Substituting the component interaction matrix into the reaction rate equation, the synergistic reaction amount of pollutants is calculated. For SO2, for example, its synergistic reaction amount is 0.015, which converts to an actual concentration of approximately 1.8 μg / m3.

[0107] Obtain environmental monitoring data, such as temperature, humidity, light intensity, etc. In this embodiment, the ambient temperature is 25°C, the relative humidity is 65%, and the light intensity is 850lux. Correct the correction coefficient term in the reaction rate equation based on the environmental monitoring data. For every 10°C increase in temperature, the correction coefficient increases by 0.2; for every 10% increase in relative humidity, the correction coefficient decreases by 0.1; for every 100lux increase in light intensity, the correction coefficient increases by 0.05. The corrected coefficient calculated in this way is 1.225. Recalculate the reaction rate using the corrected coefficient to obtain the pollutant attenuation. Taking SO2 as an example, its attenuation is 0.008, which is equivalent to an actual concentration of approximately 0.96μg / m 3 .

[0108] The pollutant direct reaction amount and pollutant synergistic reaction amount are added to the standardized concentration data, and the pollutant attenuation amount is subtracted to generate the corrected component concentration data. Taking SO2 as an example, the corrected standardized concentration is 1.0+0.022+0.015-0.008=1.029, which exceeds the standardization range and needs to be renormalized. The final corrected SO2 concentration is 123.48μg / m 3 .

[0109] Through the above steps, a chemical reaction kinetics correction model was constructed based on multi-band component concentration data, and the corrected component concentration data was generated, thereby improving the accuracy of atmospheric pollutant concentration prediction.

[0110] Figure 2 This is an analysis diagram of the pollutant synergistic effect capture capability of an embodiment of the present invention, as shown in FIG. Figure 2 As shown in the figure, this compares the performance of different models in capturing the synergistic effects of pollutants. The X-axis represents different pollutant combinations, and the Y-axis represents the synergistic effect capture rate (%). This technical solution (◆) demonstrates excellent synergistic effect capture capabilities in all pollutant combinations, especially in complex multi-component mixtures. In the SO2-NO2 combination, the capture rate of this technical solution reached 85.7%, while the machine learning method (△) and the traditional box model (□) were only 62.3% and 48.5%, respectively. In the key photochemical reaction combination of NO2-O3-VOCs, the capture rate of this technical solution reached 89.3%, 23.6 percentage points higher than the machine learning method. In the complex SO2-NO2-PM2.5-O3 four-component system, this technical solution still maintained a high capture rate of 76.9%, while the other methods dropped significantly to below 40%. These data fully demonstrate that the chemical reaction kinetics correction model constructed by this technical solution can effectively identify and quantify the complex interactions between pollutants. In particular, through the construction of the component interaction matrix, it successfully captures the synergistic reaction pathways that are difficult to express with traditional methods. From the perspective of the number of components, as the complexity of the pollutant combination increases, the capture capacity of each method generally decreases, but the decline of this technical solution is the smallest, maintaining a high level of capture rate.

[0111] The existing technology usually uses simple statistical regression methods or empirical pollutant transformation models to estimate the reaction amount of pollutants, but these methods are difficult to accurately describe the complex reaction process of pollutants, ignore the dynamic coupling relationship between different pollutant components, resulting in deviations in the characterization of pollutant transformation laws, affecting the accuracy of pollution tracing and governance. The present application normalizes the component concentration data and constructs a reaction network structure based on the standardized data, so that the material transformation relationship between different components can be represented in a structured manner, thereby improving the expression ability of pollutant reaction characteristics. Compared with the existing methods, the present application introduces concentration gradient calculation reaction intensity and describes the pollutant transformation process through the reaction rate equation, so that the calculation of the direct reaction amount of pollutants can be combined with the actual reaction kinetics characteristics, avoiding the simplified assumptions of the reaction process in the traditional method. Furthermore, the present application calculates the synergistic reaction amount of pollutants through the component interaction matrix. Compared with calculating the reaction amount of each pollutant separately, it can more comprehensively consider the synergistic effect between pollutants and improve the accuracy of reaction simulation. In addition, the present application uses environmental monitoring data to correct the reaction rate equation, so that the calculation of pollutant attenuation can dynamically adapt to environmental changes, enhancing the adaptability and generalization ability of the model. Ultimately, this application generates corrected component concentration data by comprehensively calculating the direct reaction amount, synergistic reaction amount and attenuation amount of pollutants, so that the simulation of pollutant concentration change trends is more consistent with actual emissions and conversion conditions, thereby improving the scientificity and reliability of pollutant analysis.

[0112] In an optional embodiment, based on emission characteristic fingerprint data, meteorological data, and pollutant distribution weight coefficients, a bidirectional fluid-solid coupling calculation method is used to use the gas-liquid phase conversion rate, chemical reaction rate, and sedimentation rate of pollutants as calculation parameters to generate pollutant transmission path data. The management and control zones of industrial parks based on pollutant transmission path data include:

[0113] Analyze the concentration distribution characteristics of different pollutant components in the emission characteristic fingerprint data, calculate the mutual promotion and mutual inhibition strengths between pollutant components, and construct the interaction strength matrix between components;

[0114] The intercomponent interaction intensity matrix is ​​combined with the pollutant distribution weight coefficient, and the local pollutant concentration distribution characteristic value is calculated based on the temperature and humidity information in the meteorological data to obtain the local concentration correction coefficient. The mass transfer resistance at the gas-liquid interface is corrected based on the local concentration correction coefficient, and the phase conversion rate considering the interface resistance is calculated in combination with the intercomponent interaction intensity matrix;

[0115] Calculating a mass transfer flux at the gas-liquid interface based on the phase conversion rate, combining the mass transfer flux with a local concentration correction coefficient to calculate a chemical reaction rate that takes into account local distribution characteristics, and calculating a pollutant deposition rate that takes into account interfacial mass transfer characteristics based on the chemical reaction rate and the phase conversion rate;

[0116] Substituting the phase conversion rate, chemical reaction rate, and sedimentation rate into the bidirectional fluid-solid coupling governing equation, which includes the interaction term between gaseous pollutants and particulate matter, an adaptive parameter adjustment mechanism is established based on real-time changes in environmental monitoring data. The pollutant transmission flux at each grid point is calculated through iterative solution.

[0117] Analyzing the spatiotemporal variation characteristics of the transmission flux, identifying the main transmission channels and calculating the pollution load index of each transmission channel to generate pollutant transmission path data;

[0118] The diffusion risk coefficient of each grid point is calculated according to the pollutant transmission path data, and the industrial park is divided into control zones based on the pollution load index and the diffusion risk coefficient.

[0119] For example, the emission characteristic fingerprint data is analyzed and processed. Taking a chemical park as an example, the emission characteristic fingerprint data of 10 major pollutants such as SO2, NOx, and VOCs are collected, including concentration values, emission time, emission height and other information. By analyzing the concentration distribution characteristics of different pollutant components in these data, the mutual promotion intensity and mutual inhibition intensity between pollutant components are calculated. For example, SO2 and NOx will produce a synergistic effect under certain conditions, with a promotion intensity of 0.78; while there is a certain inhibitory effect between VOCs and PM2.5, with an inhibition intensity of 0.32. Based on these values, an inter-component interaction intensity matrix is ​​constructed. The matrix is ​​a 10×10 square matrix, and the values ​​on the diagonal are all 1, indicating the intensity of their own interaction.

[0120] The pollutant distribution weight coefficient is determined based on the importance of each pollutant's impact on the environment. For example, the weight coefficient for SO2 is 0.85, for NOx is 0.92, and for VOCs is 0.76. At the same time, the characteristic values ​​of the local pollutant concentration distribution are calculated based on the temperature and humidity information in the meteorological data. In practical applications, when the temperature is 25°C and the relative humidity is 65%, the local concentration correction coefficient for SO2 is 1.12, for NOx is 0.95, and for VOCs is 1.23. Based on these local concentration correction coefficients, the mass transfer resistance at the gas-liquid interface is corrected. For example, the corrected gas-liquid interface mass transfer resistance coefficient is 0.85 times the original value. The phase conversion rate taking into account the interface resistance is calculated in conjunction with the interaction intensity matrix between components.

[0121] The calculated phase conversion rate is used to calculate the mass transfer flux at the gas-liquid interface. The mass transfer flux is combined with the local concentration correction factor to calculate the chemical reaction rate, which accounts for local distribution characteristics. Based on the chemical reaction rate and phase conversion rate, the pollutant deposition rate is calculated, which accounts for interfacial mass transfer characteristics. For example, the deposition rate for SO2 is 0.008 m / s, for NOx is 0.006 m / s, and for VOCs is 0.004 m / s.

[0122] The phase conversion rate, chemical reaction rate, and sedimentation rate are substituted into the bidirectional fluid-solid coupling control equation. This equation contains the interaction term between gaseous pollutants and particulate matter. The industrial park is divided by setting a grid with a grid size of 50m×50m, which is divided into 80×60 grid points. An adaptive parameter adjustment mechanism is established based on the real-time changes in environmental monitoring data. When the deviation between the monitoring data and the calculated results exceeds 15%, the parameters are automatically adjusted, and the adjustment range is ±10% of the original parameters. The transmission flux of pollutants at each grid point is obtained by iterative solution. The number of iterations is set to 500 times, and the convergence accuracy is 10 -6 .

[0123] By analyzing the spatiotemporal variations in transmission flux, we identified key transmission channels and calculated the pollution load index for each channel. In practice, we identified five key transmission channels, with the pollution load index for channel 1 being 0.87, channel 2 0.65, channel 3 0.59, channel 4 0.42, and channel 5 0.38. Based on this data, we generated pollutant transmission path data, including information such as transmission direction, transmission rate, and impact range.

[0124] The diffusion risk coefficient of each grid point is calculated based on the pollutant transmission path data. For example, the diffusion risk coefficient of the central area of ​​the industrial park is 0.92, the eastern area is 0.78, the western area is 0.65, the southern area is 0.53, and the northern area is 0.81. The industrial park is divided into control zones based on the pollution load index and diffusion risk coefficient. Specifically, it is divided into four types of areas: strict control areas (diffusion risk coefficient>0.85 and pollution load index>0.7), key control areas (diffusion risk coefficient 0.7-0.85 or pollution load index 0.5-0.7), general control areas (diffusion risk coefficient 0.5-0.7 and pollution load index 0.3-0.5) and buffer zones (diffusion risk coefficient<0.5 and pollution load index<0.3).

[0125] Using this method, a chemical park was divided into control zones. The strict control zone occupied 15% of the park area, primarily located in the park's center and northeast; the key control zone occupied 35%, primarily located around the strict control zone; the general control zone occupied 40%, with a more dispersed distribution; and the buffer zone occupied 10%, primarily located on the park's periphery. Three months after implementing these zoning controls, average SO₂ concentrations within the park decreased by 23%, NOx by 18%, and VOCs by 25%, significantly improving ambient air quality and demonstrating the effectiveness of this method.

[0126] In this embodiment, by constructing an interaction intensity matrix between components, the mutual promotion and inhibition relationship between different pollutant components can be quantified, and the ability to characterize the complex interactions of pollutants can be improved. The local concentration correction coefficient is used to correct the mass transfer resistance of the gas-liquid interface, so that the phase conversion rate calculation is more accurate, thereby optimizing the simulation of the migration of pollutants between the gas and liquid phases. Combined with the calculation of the sedimentation rate of pollutants, the sedimentation process of pollutants takes into account the interfacial mass transfer characteristics, thereby improving the adaptability of the model to the actual environment. Using the bidirectional fluid-solid coupling method, the interaction between gas-phase pollutants and particulate matter is introduced to enhance the accurate simulation of the diffusion dynamics of pollutants. At the same time, the adaptive parameter adjustment mechanism is used to improve the model's response to environmental changes. Finally, based on the pollutant transmission path data, the main pollution transmission channels are accurately identified, and the pollution load index and diffusion risk coefficient are calculated, thereby realizing the intelligent management and control zoning of industrial parks, improving the refinement level of pollution control and the scientific nature of decision-making.

[0127] In an optional embodiment, analyzing the spatiotemporal variation characteristics of the transmission flux, identifying the main transmission channels, and calculating the pollution load index of each transmission channel to generate pollutant transmission path data includes:

[0128] The spatial gradient of pollutant concentration of the transmission flux is calculated using a sliding time window method. The length of the sliding time window is dynamically adjusted according to the rate of change of the pollutant concentration. The temporal characteristics of the spatial gradient are analyzed, and a gradient discrimination threshold is set according to the physicochemical properties of the pollutants. When the spatial gradient is greater than the gradient discrimination threshold, data sampling points are added to obtain transmission flux sampling data.

[0129] Performing spatiotemporal decomposition on the transmission flux sampling data to obtain the temporal evolution characteristics and spatial distribution characteristics of the transmission flux, performing multi-factor correlation analysis on the spatiotemporal variation characteristics with the temperature field, humidity field, and wind field, and establishing a quantitative correspondence between the spatiotemporal variation characteristics of the transmission flux and the environmental field;

[0130] An environmental stress index is constructed based on the quantitative correspondence, wherein the environmental stress index represents the comprehensive impact of the environmental field on the diffusion, deposition and accumulation of pollutants, and the environmental stress index is weightedly combined with the transmission flux to calculate the pollution load index of each transmission channel;

[0131] Construct an intensity-direction phase diagram of the transmission flux, extract the transmission flux intensity contour lines and direction field in the phase diagram, determine the main transmission channel based on the continuity of the contour lines and direction field, and integrate the spatial position, transmission flux and pollution load of the main transmission channel to generate pollutant transmission path data.

[0132] The present invention relates to a method for analyzing the spatiotemporal variation of transport flux, identifying key transport pathways, and calculating a pollution load index. This method achieves efficient monitoring and assessment of pollutant transport pathways through a series of steps, specifically as follows:

[0133] A sliding time window method is used to analyze pollutant concentrations in transport fluxes. The core of this method lies in dynamically adjusting the length of the sliding time window based on the rate of change of pollutant concentration. Specifically, a fixed-length time window is initially set, and the pollutant concentration within this window is calculated at each time point. As pollutant concentrations change, if the rate of change exceeds a preset threshold, the length of the time window is increased accordingly to more comprehensively capture the characteristics of concentration changes. This dynamic adjustment effectively identifies spatial gradients in pollutant concentrations.

[0134] Based on the physicochemical properties of the pollutants, a gradient discrimination threshold is set. When the spatial gradient exceeds this threshold, additional data sampling points are added to obtain more accurate transmission flux sampling data. This process ensures that sufficient sample data is obtained in areas with significant changes in pollutant concentration for subsequent analysis.

[0135] After obtaining the transport flux sampling data, a spatiotemporal decomposition is performed to extract the temporal evolution and spatial distribution characteristics of the transport flux. Multi-factor correlation analysis is then used to correlate the spatiotemporal variations of the transport flux with the temperature, humidity, and wind fields. By establishing quantitative correlations, the degree of influence of environmental factors on pollutant transport can be clarified. For example, by analyzing the changes in pollutant concentrations in a specific area under different temperature, humidity, and wind speed conditions, the combined impact of environmental factors on pollutant diffusion, deposition, and accumulation can be determined.

[0136] Based on this quantitative correspondence, an environmental stress index was constructed. This index comprehensively considers the impact of the environmental field on pollutant diffusion, deposition, and accumulation, effectively reflecting the environmental pressure on pollutant transmission. By weighting the environmental stress index with the transmission flux, a pollution load index for each transmission channel was calculated. The level of the pollution load index intuitively reflects the degree of impact of the channel on the environment, providing a scientific basis for subsequent environmental governance.

[0137] After calculating the pollution load index, a phase diagram of the transmission flux intensity and direction is constructed. This phase diagram clearly illustrates the main transmission pathways of pollutants by extracting the transmission flux intensity contours and direction fields. Based on the continuity of the contours and direction fields, the spatial location of the main transmission pathways, the transmission flux, and the corresponding pollution load are determined. Ultimately, this information is integrated to generate pollutant transmission path data.

[0138] Taking air pollutants from a specific city as the research object, the team first collected meteorological data and pollutant concentration data for the region. In a preliminary analysis, the initial sliding time window was set to 24 hours. After dynamic adjustment, it was found that the rate of change in pollutant concentrations was significant during certain periods, and the time window was increased to 48 hours. By performing a spatiotemporal decomposition of these data, it was found that pollutant concentrations increased significantly under conditions of high temperature, low humidity, and strong winds.

[0139] A multivariate correlation analysis revealed that pollutant concentrations increased by an average of 5 micrograms per cubic meter for every 1°C increase in temperature, and by 3 micrograms per cubic meter for every 1% decrease in humidity. Using these data, an environmental stress index of 0.75 was calculated, indicating high environmental pressure in the region. Combined with transmission flux, the pollution load index for the main transmission corridor was calculated to be 150, indicating a significant impact on the environment.

[0140] Ultimately, by constructing intensity-directional phase maps, we identified the primary pollutant transmission pathways, finding that pollutants primarily diffuse along the city's main roads and rivers. By integrating this data, we generated detailed pollutant transmission path data, providing a scientific basis for subsequent environmental governance and pollution control.

[0141] In summary, the present invention, through a series of systematic steps and methods, can effectively analyze the spatiotemporal variation characteristics of transmission flux, identify major transmission channels, and calculate the pollution load index, providing important technical support for environmental monitoring and governance.

[0142] Figure 3 This is a diagram of the spatiotemporal decomposition and multi-factor correlation analysis of the transmission flux according to an embodiment of the present invention. Figure 3 As shown in the figure, the quantitative correspondence between the transmission flux and the environmental stress index is shown. This technical solution constructs the environmental stress index through spatiotemporal decomposition and multi-factor association analysis, taking the temperature field, humidity field and wind field into consideration and assigning weights of 0.35, 0.25 and 0.40 respectively. The figure shows that when the environmental stress is 0.2, the transmission flux is 3.8 mg / m 2 / s (low stress area); when the environmental stress reaches 0.6, the transmission flux rises rapidly to 9.6 mg / m 2 / s (critical point); when the environmental stress level is 0.8, the transmission flux reaches a maximum value of 11.7 mg / m 2 / s; then under high stress environment (environmental stress degree 1.0), the transmission flux decreased slightly to 10.3 mg / m 2 / s. The multi-factor model of this technical solution achieved a determination coefficient (R2) of 0.93 and a mean square error (MSE) of 0.42. In contrast, the single-factor model (PMF source apportionment method) only estimated a flux of 8.2 mg / m2 / s at the peak, which was an underestimate of 29.9%. The linear regression model (diffusion coefficient method) showed a significant linear deviation and only predicted 6.4 mg / m2 / s under the same stress level. 2 The predicted flux of 100 km / s is 45.3% lower than the actual value. This technical solution significantly improves the accuracy of transmission flux prediction by considering the nonlinear interaction of environmental factors.

[0143] Existing technologies usually rely on fixed time windows or simple interpolation methods to calculate the spatiotemporal distribution of pollutant transmission fluxes, but these methods are difficult to adapt to the rapid changes in pollutant concentrations, resulting in low transmission path identification accuracy and affecting the accurate characterization of the main pollution transmission channels. The present application calculates the spatial gradient of pollutant concentrations through a sliding time window method and dynamically adjusts the window length according to the concentration change rate, making the sampling strategy more flexible, able to accurately capture areas with drastic changes in pollutant concentrations, and improving the effectiveness of data sampling. Compared with existing methods, the present application introduces a multi-factor correlation analysis of temperature field, humidity field and wind field when analyzing the spatiotemporal variation characteristics of transmission flux, establishes a quantitative correspondence between pollutant transmission flux and environmental factors, makes the simulation of pollutant diffusion and deposition more consistent with actual environmental conditions, and avoids the problem of insufficient consideration of external environmental factors by traditional methods. In addition, the present application constructs an environmental stress index to quantify the comprehensive impact of the environmental field on pollutant diffusion, deposition and accumulation, and calculates the pollution load index in combination with the transmission flux. Compared with the method of pollution load assessment based solely on concentration distribution, it can more comprehensively reflect the effect of environmental factors on pollutant migration and improve the accuracy of pollution risk assessment. Finally, this application uses the intensity-directional phase diagram of the transmission flux, combined with the continuity of contour lines and directional fields to accurately identify the main pollution transmission channels, and integrates spatial position, flux and pollution load information to generate pollutant transmission path data, so that the spatial diffusion process of pollutants can be clearly visualized, thereby improving the scientificity and accuracy of pollution monitoring and control.

[0144] In an optional embodiment, a pollutant migration and diffusion model is constructed based on the control zones and pollutant transmission path data, and the pollutant superposition influence coefficient between each pollution source is calculated to generate a pollution source correlation intensity matrix including:

[0145] Gridding the control zones based on pollutant transmission path data, adaptively adjusting the grid density using concentration gradients calculated based on pollutant concentration monitoring data, establishing mass and momentum conservation equations within the grid that include pollutant chemical reaction rates, gas-liquid phase conversion rates, and sedimentation rates, and constructing a pollutant migration and diffusion model;

[0146] The pollutant migration and diffusion model is used to solve the pollutant concentration field distribution data, and based on the pollutant concentration field distribution data, a sensitivity coefficient characterizing the impact of changes in pollution source emissions on receptor point concentration is calculated. The sensitivity coefficient is substituted into a nonlinear response function including gas phase oxidation, liquid phase oxidation, and heterogeneous reaction to calculate the pollutant superposition influence coefficient;

[0147] The single-source transmission influence coefficient is calculated based on the pollutant superposition influence coefficient, and the single-source transmission influence coefficient is input into the transitive closure algorithm for calculating the multi-source coupled transmission effect of pollutants to obtain the coupled transmission influence coefficient. The single-source transmission influence coefficient and the coupled transmission influence coefficient are combined based on a sliding window of a time series to generate a pollution source correlation intensity matrix.

[0148] Among them, the control zone is first gridded according to the pollutant transmission path data. Specifically, the geographical boundary data and pollutant transmission path data of the control zone are obtained, and the control zone is preliminarily divided into a uniform grid of 500 meters × 500 meters. Then, the concentration gradient is calculated based on the pollutant concentration monitoring data, and the grid division density is adaptively adjusted. In areas with large concentration gradients (such as gradient values ​​greater than 0.05μg / m3 / km), the grid is refined to 100 meters × 100 meters; in areas with medium concentration gradients (such as gradient values ​​between 0.01-0.05μg / m3 / km), the grid is refined to 200 meters × 200 meters; in areas with small concentration gradients (such as gradient values ​​less than 0.01μg / m 3 / km), maintaining a grid size of 500 m × 500 m.

[0149] In the divided grid, mass conservation equations and momentum conservation equations are established, which include the chemical reaction rate, gas-liquid phase conversion rate, and sedimentation rate of pollutants, to construct a pollutant migration and diffusion model. The mass conservation equation takes into account the emission, transmission, diffusion, chemical conversion, and sedimentation processes of pollutants. For PM2.5 pollutants, the chemical reaction rate is set to 0.01-0.05 / hour, the gas-liquid phase conversion rate is set to 0.005-0.02 / hour, the dry deposition rate is set to 0.1-0.5 cm / second, and the wet deposition rate is dynamically adjusted according to the precipitation intensity, ranging from 0.2-2.0 / hour. The momentum conservation equation takes into account the effects of wind field, temperature field, and pressure field on pollutant transmission.

[0150] Using the constructed pollutant migration and diffusion model, the pollutant concentration field distribution data is calculated using numerical solution methods (such as the finite difference method). The calculation time step is set to 1 hour, and the spatial resolution is consistent with the grid division. For example, in a typical case, the PM2.5 concentration range in the simulation area is 15-120μg / m 3 , among which the highest in industrial areas can reach 120μg / m 3 , 60-90 μg / m in the urban center 3 , in the suburbs it is 15-40 μg / m 3 .

[0151] Based on the pollutant concentration distribution data, we calculated the sensitivity coefficients that characterize the impact of changes in pollution source emissions on the concentration at the receptor site. Specifically, for each pollution source, we simulated a 10% increase and a 10% decrease in its emissions, and calculated the rate of change in the concentration at the receptor site. For example, if a 10% increase in emissions from an industrial pollution source causes a 4.2% increase in PM2.5 concentration at a receptor site 3 kilometers away, the sensitivity coefficient for that pollution source at that receptor site would be 0.42.

[0152] Substituting the sensitivity coefficient into the nonlinear response function including gas-phase oxidation, liquid-phase oxidation and heterogeneous reactions, the pollutant superposition influence coefficient is calculated. The nonlinear response function takes into account the synergistic and antagonistic effects between different pollutants. For PM2.5, gas-phase oxidation mainly considers reactions with NOx, SO2, and VOCs, liquid-phase oxidation mainly considers reactions with soluble components in cloud droplets, and heterogeneous reactions mainly consider reactions with the surface of particulate matter. Through these reaction paths, the pollutant superposition influence coefficient matrix is ​​calculated. For example, in one case, the superposition influence coefficient of two industrial pollution sources A and B, which are 5 kilometers apart, is 1.2, indicating that their joint impact is 20% greater than the sum of their individual impacts.

[0153] Based on the pollutant superposition influence coefficient, the single source transmission influence coefficient is calculated. The single source transmission influence coefficient indicates the degree of influence of a single pollution source on each receptor point. The calculation method is to multiply the emission intensity of the pollution source by the corresponding superposition influence coefficient, and then divide it by the square of the distance between the receptor point and the pollution source. For example, the single source transmission influence coefficient of pollution source A with an emission intensity of 100 tons / year on the receptor point 2 kilometers away is 15μg / m 3 .

[0154] The single-source transmission influence coefficient is input into the transitive closure algorithm used to calculate the coupled transmission effects of multiple pollutants, resulting in the coupled transmission influence coefficient. The transitive closure algorithm uses iterative calculations to account for multiple interactions among pollutants during transmission. For example, within a given area with five major pollution sources, the coupled transmission influence coefficient matrix calculated using the transitive closure algorithm shows that the coupled transmission influence coefficient between sources A and C is 2.3, significantly higher than their direct influence coefficient of 1.5, indicating a significant indirect coupling effect.

[0155] The single-source transmission influence coefficients and coupled transmission influence coefficients were combined using a sliding window based on a time series to generate a pollution source correlation strength matrix. The sliding window size was set to 24 hours with a step size of 6 hours. The influence coefficients within each time window were weighted averaged, with the weights proportional to the pollutant concentration. For example, during the winter heating period, the correlation strength matrix for the five major pollution sources in an industrial zone showed that the correlation strength between pollution sources A and B was 0.85 (out of a maximum score of 1), indicating a strong mutual influence between them; while the correlation strength between pollution sources A and E was only 0.12, indicating a weaker mutual influence.

[0156] Through the above steps, the entire process of building a pollutant migration and diffusion model based on control zones and pollutant transmission path data, calculating the pollutant superposition impact coefficient between pollution sources, and generating a pollution source correlation intensity matrix was completed, providing a scientific basis for joint prevention and control of regional air pollution.

[0157] In this embodiment, adaptive grid division based on pollutant concentration gradient is used to improve the calculation accuracy of areas with drastic changes in pollutant concentration, avoiding the problems of insufficient resolution or waste of computing resources caused by existing fixed grid methods. By using the mass conservation and momentum conservation equations that include chemical reaction rate, phase conversion rate and sedimentation rate, a pollutant migration and diffusion model that is more consistent with the actual physical process is established, so that the transmission dynamics of pollutants under different environmental conditions can be accurately simulated. Compared with the limitations of traditional methods that ignore the nonlinear reactions of pollutants, the accuracy and adaptability of the model are enhanced. In addition, the present application calculates the sensitivity coefficient based on the pollutant concentration field and calculates the pollutant superposition influence coefficient in combination with the nonlinear response function. Compared with the single pollution source analysis method, it can more comprehensively reflect the changes in pollutant concentration under the joint action of multiple pollution sources. Furthermore, the coupled transmission influence coefficient is calculated by the transitive closure algorithm, and the sliding window is used to combine data from different time periods, so that the pollution source correlation intensity matrix can dynamically reflect the transmission relationship and time evolution characteristics of the pollution source, thereby improving the ability to analyze the causes of pollution and providing a more scientific decision-making basis for accurate source tracing and regional pollution control.

[0158] In an optional embodiment, the optimal emission reduction ratio of each pollution source is calculated based on the pollution source correlation intensity matrix and the pollutant distribution weight coefficient, the dynamic emission control parameters of each pollution source are calculated based on the optimal emission reduction ratio, and a multi-pollution source linkage control strategy is established based on the dynamic emission control parameters and pollutant transmission path data. The generation of coordinated control instructions for each pollution source includes:

[0159] The pollution source correlation intensity matrix and the pollutant distribution weight coefficient are input into a nonlinear programming model, wherein the nonlinear programming model includes objective functions of maximizing pollutant reduction and minimizing economic costs, and the optimal emission reduction ratio of each pollution source is obtained by solving the model through a genetic algorithm;

[0160] A state space model is established based on the optimal emission reduction ratio, including pollution source characteristics, meteorological conditions, and environmental capacity. A Kalman filter algorithm is used to estimate the system state in real time. The state estimation results are input into a model predictive controller to calculate the dynamic emission control parameters of each pollution source.

[0161] A weighted directed graph of pollution sources is constructed based on the dynamic emission control parameters and pollutant transmission path data, a community discovery algorithm is used to identify strongly correlated pollution source groups in the weighted directed graph, and differentiated group control strategies are generated according to the dynamic emission control parameters of each group to establish a multi-pollution source linkage control strategy;

[0162] A hierarchical control structure is constructed based on the multi-pollution source linkage control strategy, a feedback compensation mechanism is set in the hierarchical control structure, actual pollutant concentration change data is input into the feedback compensation mechanism for dynamic correction, and coordinated control instructions for each pollution source are generated.

[0163] For example, the optimal emission reduction ratio for each pollution source is calculated based on the pollution source correlation intensity matrix and the pollutant distribution weight coefficient. The pollution source correlation intensity matrix represents the degree of mutual influence between different pollution sources and can be constructed through historical monitoring data and diffusion models. For example, there are five major pollution sources in a certain area. The correlation intensity matrix obtained by analyzing historical data shows that the correlation intensity between pollution source 1 and pollution source 2 is 0.75, indicating that the emission change of pollution source 1 will have a strong impact on the area where pollution source 2 is located. The pollutant distribution weight coefficient reflects the contribution of each pollutant to environmental quality. For example, the weight coefficient of PM2.5 is 0.4, the weight coefficient of SO2 is 0.3, and the weight coefficient of NOx is 0.3.

[0164] The above data was input into a nonlinear programming model, which incorporates two objective functions: maximizing pollutant reduction and minimizing economic costs. The maximization objective is to maximize the reduction in pollutant concentrations within the region; the minimization objective is to minimize the economic costs of emission reduction measures. Constraints in the model include: an upper limit of 80% for emission reductions from each pollution source, a minimum 20% improvement in regional environmental quality, and a maximum economic impact of 2% of regional GDP.

[0165] A genetic algorithm was used to solve the nonlinear programming model, with the following parameters: population size 100, maximum number of iterations 500, crossover probability 0.8, and mutation probability 0.1. Through iterative optimization, the optimal emission reduction ratios for each pollution source were determined: 35% for pollution source 1, 42% for pollution source 2, 28% for pollution source 3, 50% for pollution source 4, and 20% for pollution source 5.

[0166] A state-space model is established that incorporates pollution source characteristics, meteorological conditions, and environmental capacity. Pollution source characteristics include parameters such as emission height, emission temperature, and emission rate; meteorological conditions include wind direction, wind speed, and atmospheric stability; and environmental capacity is determined based on regional environmental quality standards.

[0167] Taking an industrial zone as an example, pollution source 1 is a thermal power plant with an emission height of 120 meters and an emission temperature of 85°C. The initial emission rate is 200 kg / h for SO2 and 150 kg / h for NOx. The weather conditions on that day are northeasterly wind with a speed of 3.5 m / s and atmospheric stability of Class D. The regional SO2 environmental capacity is 150 μg / m 3 , NOx environmental capacity is 100μg / m 3 .

[0168] A Kalman filter algorithm is used to estimate the system state in real time, addressing both process and observation noise to improve state estimation accuracy. The algorithm's initial parameters are set as follows: the state estimation error covariance matrix P is initialized to the identity matrix, the process noise covariance matrix Q is set to 0.01, and the observation noise covariance matrix R is set to 0.05. By continuously updating observation data, the optimal estimate of the system state is obtained.

[0169] The state estimation results are fed into a model predictive controller with a 24-hour prediction horizon, an 8-hour control horizon, and a 1-hour sampling period. The controller calculates dynamic emission control parameters for each pollution source based on the predicted pollutant diffusion trends and environmental capacity constraints. For example, the SO2 emission control parameters for pollution source 1 over the next 8 hours are: 130 kg / h, 120 kg / h, 140 kg / h, 150 kg / h, 130 kg / h, 120 kg / h, 110 kg / h, and 100 kg / h.

[0170] A multi-source linkage control strategy is established based on dynamic emission control parameters and pollutant transmission path data. A weighted directed graph of pollution sources is constructed, where nodes represent pollution sources, edge weights represent pollutant transmission intensity, and directions represent transmission paths. For example, a weight of 0.65 for the edge from source 1 to source 3 indicates that 65% of the pollutants emitted by source 1 will affect the area where source 3 is located.

[0171] Alternatively, the Louvain community discovery algorithm was used to identify strongly connected groups of pollution sources in a weighted directed graph, with the algorithm resolution parameter set to 1.0. Through algorithmic analysis, the five pollution sources were divided into two groups: Group 1 included pollution sources 1, 2, and 3, and Group 2 included pollution sources 4 and 5. The average correlation strength within Group 1 was 0.72, the average correlation strength within Group 2 was 0.68, and the average correlation strength between groups was 0.31.

[0172] Differentiated group control strategies are generated based on the dynamic emission control parameters of each group. For Group 1, which includes high-emission thermal power plants, a "gradient emission reduction" strategy is adopted, reducing emissions in advance of peak pollution periods. For Group 2, which primarily consists of intermittent emission sources, a "peak-shifting emission" strategy is adopted to avoid high-intensity emissions during the same period.

[0173] Based on a multi-source linkage control strategy, a hierarchical control structure is constructed, comprising three levels: regional, group, and source. The regional level is responsible for decomposing overall targets, the group level coordinates the linkage of pollution sources within the group, and the source level executes specific control instructions. A feedback compensation mechanism is incorporated into the hierarchical control structure, collecting pollutant concentration data from environmental monitoring stations in real time. Compensation adjustments are triggered when actual concentrations deviate from the target by more than 10%.

[0174] For example, on a certain day, the PM2.5 concentration in the area was found to be 75 μg / m 3 , exceeding the expected target of 65μg / m 3 The feedback compensation mechanism automatically adjusts the emission parameters of each pollution source: SO2 emissions from Pollution Source 1 are adjusted from the original 130kg / h to 110kg / h, a 15.4% reduction; NOx emissions from Pollution Source 2 are adjusted from the original 90kg / h to 75kg / h, a 16.7% reduction. Through this dynamic adjustment, coordinated control instructions are ultimately generated for each pollution source, effectively controlling regional pollutant concentrations.

[0175] Through the above technical solution, the present invention realizes the precise coordinated regulation of multiple pollution sources, maximizes the improvement of environmental quality while ensuring economic development, and has significant practical value.

[0176] In this embodiment, a nonlinear programming model is constructed by using the pollution source correlation intensity matrix and the pollutant distribution weight coefficient to optimize the emission reduction ratio, maximize the pollutant reduction effect, and reduce the emission reduction cost. Compared with the traditional fixed ratio emission reduction method, it is more targeted and adaptable. The Kalman filter algorithm is combined with the state space model to achieve real-time estimation of the emission state of the pollution source, and the emission control parameters are dynamically adjusted through the model predictive controller, so that the pollution control strategy can adapt to the real-time changes in environmental conditions, overcoming the problem of the existing method's untimely response to sudden pollution events. In addition, the present application uses pollutant transmission path data to construct a weighted directed graph and uses a community discovery algorithm to identify strongly associated pollution source groups, so that pollution control can be differentiated based on the actual impact relationship of the pollution source, avoiding the limitations of independent regulation of each pollution source in traditional methods. Finally, the present application uses a hierarchical control structure and feedback compensation mechanism to dynamically modify the pollution control strategy, so that the control instructions can adapt to the actual changes in pollutant concentration, thereby improving control accuracy, ensuring the stability and sustainability of pollution control effects, and optimizing regional pollution prevention and control decisions.

[0177] In an optional embodiment, a weighted directed graph of pollution sources is constructed based on the dynamic emission control parameters and pollutant transmission path data, a community discovery algorithm is used to identify strongly correlated pollution source groups in the weighted directed graph, and differentiated group control strategies are generated based on the dynamic emission control parameters of each group. Establishing a multi-pollution source linkage control strategy includes:

[0178] Dynamic emission control parameters are used as node eigenvalues, node connection relationships are constructed based on pollutant transmission path data, and the transmission volume between nodes is updated using an exponential decay method to obtain edge eigenvalues. A weighted directed graph of pollution sources is constructed based on the node eigenvalues ​​and edge eigenvalues.

[0179] Calculating the actual transmission strength between nodes and the network benchmark transmission strength based on the pollution source weighted directed graph, inputting the actual transmission strength and the network benchmark transmission strength into a community discovery algorithm, and obtaining an initial group division scheme by iteratively optimizing the group division index;

[0180] Calculating an inter-group transmission distance coefficient and a meteorological similarity coefficient based on the initial group division scheme, combining the transmission distance coefficient and meteorological similarity coefficient with a group division index to construct a group optimization criterion, optimizing the initial group division scheme according to the group optimization criterion to obtain a target pollution source group, constructing a group control model including pollutant reduction amounts and control costs for the target pollution source group, and obtaining a pollution source group control target by solving the group control model;

[0181] Calculating the connectivity coefficient, transmission flux coefficient, and position correlation coefficient of the nodes in each pollution source group, combining the connectivity coefficient, transmission flux coefficient, and position correlation coefficient to obtain a node priority coefficient, and grading the nodes in the pollution source group based on the node priority coefficient to obtain an intra-group grading scheme;

[0182] A group game model including pollutant reduction amounts and control costs is constructed based on the intra-group grading scheme and pollution source group control targets. The group game model is solved to obtain differentiated group control strategies, and real-time monitoring data is collected to calculate control correction amounts. The control correction amounts are input into the compensation model to make real-time adjustments to the differentiated group control strategies, thereby establishing a multi-pollution source linkage control strategy.

[0183] For example, a weighted directed graph of pollution sources is constructed based on dynamic emission control parameters and pollutant transmission path data. Specifically, each pollution source is treated as a node in the graph, and the dynamic emission control parameters are used as node eigenvalues. These parameters include the pollution source's emission intensity, emission height, flue gas temperature, and so on. For example, the emission intensity of a steel plant is 200 tons / year, the emission height is 80 meters, and the flue gas temperature is 150°C. These values ​​together constitute the eigenvalues ​​of the pollution source node.

[0184] Based on pollutant transmission path data, connections between nodes are constructed, essentially defining edges in a directed graph. For example, if an atmospheric diffusion model calculates that pollution source A contributes 15% of the pollutants in the area where source B is located, a directed edge from A to B is established. Inter-node transmission quantities are updated using an exponential decay method, meaning that the transmission effect decreases exponentially over time or as distance increases. For example, when the transmission distance is 10 kilometers, the transmission coefficient might be 0.8; when the distance increases to 20 kilometers, the transmission coefficient might drop to 0.64. These transmission quantities serve as edge eigenvalues, ultimately forming a complete weighted directed graph of pollution sources.

[0185] It identifies groups of strongly connected pollution sources based on a constructed weighted directed graph of pollution sources. It calculates the actual transmission intensity between nodes. For example, the actual transmission intensity from source A to source B is A's emissions multiplied by the transmission coefficient, resulting in a specific value such as 30 tons / year. It also calculates the network's baseline transmission intensity, which is the average transmission intensity between all nodes in the entire network. For example, if a network has 100 nodes and a total transmission volume of 2,000 tons / year, the baseline transmission intensity is 20 tons / year.

[0186] The actual transmission intensity and the network benchmark transmission intensity are input into a community discovery algorithm, such as the Louvain algorithm or the InfoMap algorithm. An initial grouping scheme is then obtained by iteratively optimizing the grouping metric (such as the modularity Q value). For example, the initial grouping scheme might divide 100 pollution sources into five groups, with dense connections within each group and relatively sparse connections between groups.

[0187] Based on the initial grouping scheme, the transmission distance coefficient and meteorological similarity coefficient between groups were calculated. The transmission distance coefficient reflects the geographical distance between groups. For example, the average distance between Group A and Group B is 15 kilometers, corresponding to a transmission distance coefficient of 0.7. The meteorological similarity coefficient reflects the similarity of meteorological conditions in the areas where the groups are located. For example, the wind direction similarity between Groups C and D is 85%, and the wind speed similarity is 90%, resulting in a meteorological similarity coefficient of 0.87.

[0188] The transmission distance coefficient and meteorological similarity coefficient are combined with the grouping index to construct a grouping optimization criterion. For example, the optimization criterion can be set as: modularity Q value × 0.5 + transmission distance coefficient × 0.3 + meteorological similarity coefficient × 0.2. By optimizing the initial grouping scheme based on this criterion, it is possible to adjust the original five groups to six, thus obtaining the target pollution source group.

[0189] For target pollution source groups, a group control model is constructed that includes pollutant reduction targets and control costs. For example, Group E needs to reduce pollutant emissions by 100 tons, with a total control cost of no more than 5 million yuan. By solving this model, the control targets for the pollution source groups are obtained. For example, the pollution sources in Group E need to reduce sulfur dioxide by 80 tons and nitrogen oxides by 120 tons, with a total cost of 4.5 million yuan.

[0190] Calculate the connectivity coefficient, transmission flux coefficient, and position correlation coefficient of the nodes within each pollution source group. The connectivity coefficient reflects the degree of connection between the node within the group. For example, if the number of connections between a node and other nodes in the group is 8 and the average number of connections within the group is 5, then the connectivity coefficient of the node is 1.6. The transmission flux coefficient reflects the total amount of pollutants transmitted by the node. For example, if the outward transmission volume of a node is 40 tons / year, the incoming transmission volume is 20 tons / year, the total flux is 60 tons / year, and the group average flux is 40 tons / year, then the transmission flux coefficient of the node is 1.5. The position correlation coefficient reflects the importance of the node in terms of its geographical location. For example, if a node is located in the upwind area and has a significant impact on the downwind area, its position correlation coefficient may be 1.8.

[0191] The node priority coefficient is calculated by combining the connectivity coefficient, the transmission flux coefficient, and the position correlation coefficient. For example, the priority coefficient can be set as: connectivity coefficient × 0.4 + transmission flux coefficient × 0.4 + position correlation coefficient × 0.2. Nodes within the pollution source group are classified based on the node priority coefficient. For example, a priority coefficient greater than 1.5 is considered a first-level node, 1.0-1.5 is considered a second-level node, and less than 1.0 is considered a third-level node, thus forming a grading scheme within the group.

[0192] Based on the internal group classification scheme and the pollution source group control targets, a group game model was constructed that incorporates pollutant reduction targets and control costs. In this model, nodes at different levels bear different proportions of the emission reduction task, for example, first-level nodes bear 50% of the emission reduction, second-level nodes bear 30%, and third-level nodes bear 20%. Solving this game model yields differentiated group control strategies, such as an average emission reduction of 40 tons for first-level nodes, 20 tons for second-level nodes, and 10 tons for third-level nodes.

[0193] Real-time monitoring data is collected to calculate control corrections. For example, if real-time monitoring reveals that pollutant concentrations in a certain area exceed the standard by 20%, an additional 15 tons of emission reductions are required. This control correction is then input into the compensation model, allowing real-time adjustments to differentiated group control strategies. For example, the emission reduction at the first-level node can be adjusted from 40 tons to 46 tons, at the second-level node from 20 tons to 23 tons, and at the third-level node from 10 tons to 11.5 tons. Ultimately, a complete multi-pollution source linkage control strategy is established.

[0194] Through the above methods, group division based on pollution source correlation, hierarchical control based on node importance, and dynamic adjustment based on real-time data are achieved, providing scientific and effective technical support for the joint prevention and control of regional air pollution.

[0195] Figure 4 This is a simulation diagram of the real-time monitoring effect of the multi-pollution source linkage control strategy in an embodiment of the present invention. The diagram shows the real-time air quality change trend. This technical solution (solid line) keeps the pollutant concentration at 100μg / m throughout the day. 3 Below the standard line, the highest is only 95μg / m 3 The traditional method (dashed line) exceeded the pollutant concentration limit during the 8-20 hour period, with the highest concentration reaching 135 μg / m 3 During critical periods, this technical solution reduced pollutant concentrations by an average of 28.3%. By adjusting the differentiated group control strategy in real time through a compensation model, this technical solution achieved dynamic linkage control based on real-time monitoring data, significantly improving pollutant control efficiency and achieving environmental goals.

[0196] Existing technologies usually adopt the method of independent regulation of single sources or fixed-proportion reduction in the control of multiple pollution sources, ignoring the mutual influence between pollution sources, resulting in a lack of precision in the control strategy and limited emission reduction effects. This application constructs a weighted directed graph of pollution sources, combines pollutant transmission path data and dynamic emission control parameters, and accurately describes the transmission relationship between pollution sources. Compared with traditional methods, it can more finely characterize the pollution diffusion characteristics and improve the accuracy of pollution source identification. The community discovery algorithm is used to optimize the division of pollution source groups, and the group optimization criteria are adjusted based on transmission distance and meteorological similarity, making the pollution source classification more scientific and overcoming the errors caused by the single indicator division of traditional methods. Further, through the group game model, combined with the pollutant reduction amount and control cost, differentiated group control strategies are formulated, avoiding a one-size-fits-all emission reduction approach and improving the flexibility of pollution control. At the same time, this application uses real-time monitoring data to calculate the control correction amount, and dynamically adjusts the control strategy through a compensation model, so that the control scheme can adapt to environmental changes and improve the real-time response capability of pollution control. Compared with the existing technology, this application has achieved an upgrade from static reduction to dynamic optimization, improved the accuracy and adaptability of coordinated regulation of multiple pollution sources, and ensured the stability and integrity of pollutant reduction effects while reducing governance costs.

[0197] According to a second aspect of the embodiments of the present invention,

[0198] An electronic device is provided, comprising:

[0199] processor;

[0200] a memory for storing processor-executable instructions;

[0201] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0202] According to a third aspect of the embodiments of the present invention,

[0203] A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described above is implemented.

[0204] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0205] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for collaboratively controlling multiple pollution sources and optimizing emissions in industrial parks, characterized by: include: Obtain real-time monitoring data and meteorological data for multiple pollution sources within the industrial park; Based on real-time monitoring data, by analyzing the concentration of characteristic pollutant components and the ratio of characteristic pollutant component concentrations of each pollution source, the emission characteristic fingerprint data of each pollution source is generated, and the pollutant distribution weight coefficient is calculated based on the emission characteristic fingerprint data; Based on emission fingerprint data, meteorological data, and pollutant distribution weight coefficients, a two-way fluid-solid coupling calculation method is used to take the gas-liquid phase conversion rate, chemical reaction rate, and sedimentation rate of pollutants as calculation parameters to generate pollutant transmission path data. Based on this pollutant transmission path data, the industrial park is divided into control zones. A pollutant migration and diffusion model is constructed based on the control zoning and pollutant transmission path data, the pollutant superposition impact coefficients between pollution sources are calculated, and a pollution source correlation intensity matrix is ​​generated. The optimal emission reduction ratio of each pollution source is calculated based on the pollution source correlation intensity matrix and the pollutant distribution weight coefficient. The dynamic emission control parameters of each pollution source are calculated based on the optimal emission reduction ratio. Based on the dynamic emission control parameters and pollutant transmission path data, a multi-pollution source linkage control strategy is established to generate coordinated control instructions for each pollution source.

2. The method according to claim 1, characterized in that Based on real-time monitoring data, by analyzing the concentration of characteristic pollutant components and the ratio of characteristic pollutant component concentrations of each pollution source, the emission characteristic fingerprint data of each pollution source is generated. The pollutant distribution weight coefficients calculated based on the emission characteristic fingerprint data include: Acquire real-time monitoring data of multiple pollution sources in the industrial park, the real-time monitoring data including characteristic pollutant component concentration data, perform wavelet transform decomposition on the characteristic pollutant component concentration data to obtain first frequency band component concentration data and second frequency band component concentration data; constructing a chemical reaction kinetics correction model based on the component concentration data of the first frequency band and the component concentration data of the second frequency band, calculating the direct reaction amount of pollutants, the synergistic reaction amount of pollutants, and the attenuation amount of pollutants through the chemical reaction kinetics correction model, and generating corrected component concentration data; The attention mechanism is used to perform time series analysis on the corrected component concentration data to extract the time distribution characteristics of the component concentrations and generate time characteristic data. The transformation relationship between the pollutant components is calculated based on the time characteristic data to generate component transformation characteristic data. Calculate the correlation between pollutant components based on the time characteristic data and the component conversion characteristic data to generate a component action coefficient, and use the component action coefficient to perform weighted fusion on the time characteristic data and the component conversion characteristic data to obtain pollution source emission characteristic fingerprint data; Based on the emission characteristic fingerprint data of the pollution sources, the fluctuation pattern of the component concentration of each pollution source in different time periods is analyzed, the mean value, fluctuation amplitude and fluctuation period of the pollutant concentration in each time period are calculated, and the pollutant distribution weight coefficient is obtained. The pollutant distribution weight coefficient is used to characterize the pollutant emission contribution of each pollution source.

3. The method according to claim 2, characterized in that A chemical reaction kinetics correction model is constructed based on the component concentration data of the first frequency band and the component concentration data of the second frequency band. The direct reaction amount, synergistic reaction amount, and attenuation amount of pollutants are calculated using the chemical reaction kinetics correction model to generate the corrected component concentration data. Normalizing the concentration data of the components in the first frequency band and the concentration data of the components in the second frequency band to obtain standardized concentration data, constructing a reaction network structure based on the standardized concentration data, establishing a substance conversion relationship between the components using the components as nodes, and calculating the concentration gradient between the components to obtain the reaction intensity; Establishing a reaction rate equation of a chemical reaction kinetics correction model according to the reaction intensity, wherein the reaction rate equation includes a reactant concentration term, a reaction rate constant term, and a correction coefficient term; Solving the reaction rate equation using the standardized concentration data to obtain a frequency band coupling coefficient, establishing a component concentration change matrix based on the frequency band coupling coefficient, substituting the component concentration change matrix into the reaction rate equation to obtain a reaction rate value, and calculating the direct reaction amount of the pollutant based on the product of the reaction rate value and the time step; constructing a component interaction matrix based on the component concentration change matrix, substituting the component interaction matrix into the reaction rate equation, and calculating the synergistic reaction amount of the pollutants; Acquiring environmental monitoring data, and correcting the correction coefficient term in the reaction rate equation according to the environmental monitoring data to calculate the pollutant attenuation; The pollutant direct reaction amount and the pollutant synergistic reaction amount are added to the standardized concentration data, and the pollutant attenuation amount is subtracted to generate corrected component concentration data.

4. The method according to claim 1, wherein Based on emission characteristic fingerprint data, meteorological data, and pollutant distribution weight coefficients, a two-way fluid-solid coupling calculation method is used to take the gas-liquid phase conversion rate, chemical reaction rate, and sedimentation rate of pollutants as calculation parameters to generate pollutant transmission path data. Based on the pollutant transmission path data, the control zones of the industrial park are divided into the following: Analyze the concentration distribution characteristics of different pollutant components in the emission characteristic fingerprint data, calculate the mutual promotion and mutual inhibition strengths between pollutant components, and construct the interaction strength matrix between components; The intercomponent interaction intensity matrix is ​​combined with the pollutant distribution weight coefficient, and the local pollutant concentration distribution characteristic value is calculated based on the temperature and humidity information in the meteorological data to obtain the local concentration correction coefficient. The mass transfer resistance at the gas-liquid interface is corrected based on the local concentration correction coefficient, and the phase conversion rate considering the interface resistance is calculated in combination with the intercomponent interaction intensity matrix; Calculating a mass transfer flux at the gas-liquid interface based on the phase conversion rate, combining the mass transfer flux with a local concentration correction coefficient to calculate a chemical reaction rate that takes into account local distribution characteristics, and calculating a pollutant deposition rate that takes into account interfacial mass transfer characteristics based on the chemical reaction rate and the phase conversion rate; Substituting the phase conversion rate, chemical reaction rate, and sedimentation rate into the bidirectional fluid-solid coupling governing equation, which includes the interaction term between gaseous pollutants and particulate matter, an adaptive parameter adjustment mechanism is established based on real-time changes in environmental monitoring data. The pollutant transmission flux at each grid point is calculated through iterative solution. Analyzing the spatiotemporal variation characteristics of the transmission flux, identifying the main transmission channels and calculating the pollution load index of each transmission channel to generate pollutant transmission path data; The diffusion risk coefficient of each grid point is calculated according to the pollutant transmission path data, and the industrial park is divided into control zones based on the pollution load index and the diffusion risk coefficient.

5. The method according to claim 4, characterized in that Analyzing the spatiotemporal variation characteristics of the transmission flux, identifying the main transmission channels and calculating the pollution load index of each transmission channel to generate pollutant transmission path data includes: The spatial gradient of pollutant concentration of the transmission flux is calculated using a sliding time window method. The length of the sliding time window is dynamically adjusted according to the rate of change of the pollutant concentration. The temporal characteristics of the spatial gradient are analyzed, and a gradient discrimination threshold is set according to the physicochemical properties of the pollutants. When the spatial gradient is greater than the gradient discrimination threshold, data sampling points are added to obtain transmission flux sampling data. Performing spatiotemporal decomposition on the transmission flux sampling data to obtain the temporal evolution characteristics and spatial distribution characteristics of the transmission flux, performing multi-factor correlation analysis on the spatiotemporal variation characteristics with the temperature field, humidity field, and wind field, and establishing a quantitative correspondence between the spatiotemporal variation characteristics of the transmission flux and the environmental field; An environmental stress index is constructed based on the quantitative correspondence, wherein the environmental stress index represents the comprehensive impact of the environmental field on the diffusion, deposition and accumulation of pollutants, and the environmental stress index is weightedly combined with the transmission flux to calculate the pollution load index of each transmission channel; Construct an intensity-direction phase diagram of the transmission flux, extract the transmission flux intensity contour lines and direction field in the phase diagram, determine the main transmission channel based on the continuity of the contour lines and direction field, and integrate the spatial position, transmission flux and pollution load of the main transmission channel to generate pollutant transmission path data.

6. The method according to claim 1, characterized in that Based on the control zones and pollutant transmission path data, a pollutant migration and diffusion model is constructed to calculate the pollutant superposition impact coefficient between pollution sources and generate a pollution source correlation intensity matrix including: Gridding the control zones based on pollutant transmission path data, adaptively adjusting the grid density using concentration gradients calculated based on pollutant concentration monitoring data, establishing mass and momentum conservation equations within the grid that include pollutant chemical reaction rates, gas-liquid phase conversion rates, and sedimentation rates, and constructing a pollutant migration and diffusion model; The pollutant migration and diffusion model is used to solve the pollutant concentration field distribution data, and based on the pollutant concentration field distribution data, a sensitivity coefficient characterizing the impact of changes in pollution source emissions on receptor point concentration is calculated. The sensitivity coefficient is substituted into a nonlinear response function including gas phase oxidation, liquid phase oxidation, and heterogeneous reaction to calculate the pollutant superposition influence coefficient; The single-source transmission influence coefficient is calculated based on the pollutant superposition influence coefficient, and the single-source transmission influence coefficient is input into the transitive closure algorithm for calculating the multi-source coupled transmission effect of pollutants to obtain the coupled transmission influence coefficient. The single-source transmission influence coefficient and the coupled transmission influence coefficient are combined based on a sliding window of a time series to generate a pollution source correlation intensity matrix.

7. The method according to claim 1, characterized in that The optimal emission reduction ratio for each pollution source is calculated based on the pollution source correlation intensity matrix and the pollutant distribution weight coefficient. The dynamic emission control parameters for each pollution source are calculated based on the optimal emission reduction ratio. Based on the dynamic emission control parameters and pollutant transmission path data, a multi-pollution source linkage control strategy is established to generate coordinated control instructions for each pollution source, including: The pollution source correlation intensity matrix and the pollutant distribution weight coefficient are input into a nonlinear programming model, wherein the nonlinear programming model includes objective functions of maximizing pollutant reduction and minimizing economic costs, and the optimal emission reduction ratio of each pollution source is obtained by solving the model through a genetic algorithm; A state space model is established based on the optimal emission reduction ratio, including pollution source characteristics, meteorological conditions, and environmental capacity. A Kalman filter algorithm is used to estimate the system state in real time. The state estimation results are input into a model predictive controller to calculate the dynamic emission control parameters of each pollution source. A weighted directed graph of pollution sources is constructed based on the dynamic emission control parameters and pollutant transmission path data, a community discovery algorithm is used to identify strongly correlated pollution source groups in the weighted directed graph, and differentiated group control strategies are generated according to the dynamic emission control parameters of each group to establish a multi-pollution source linkage control strategy; A hierarchical control structure is constructed based on the multi-pollution source linkage control strategy, a feedback compensation mechanism is set in the hierarchical control structure, actual pollutant concentration change data is input into the feedback compensation mechanism for dynamic correction, and coordinated control instructions for each pollution source are generated.

8. The method according to claim 7, characterized in that A weighted directed graph of pollution sources is constructed based on the dynamic emission control parameters and pollutant transmission path data. A community discovery algorithm is used to identify strongly correlated pollution source groups in the weighted directed graph. Differentiated group control strategies are generated based on the dynamic emission control parameters of each group. Establishing a multi-pollution source linkage control strategy includes: Dynamic emission control parameters are used as node eigenvalues, node connection relationships are constructed based on pollutant transmission path data, and the transmission volume between nodes is updated using an exponential decay method to obtain edge eigenvalues. A weighted directed graph of pollution sources is constructed based on the node eigenvalues ​​and edge eigenvalues. Calculating the actual transmission strength between nodes and the network benchmark transmission strength based on the pollution source weighted directed graph, inputting the actual transmission strength and the network benchmark transmission strength into a community discovery algorithm, and obtaining an initial group division scheme by iteratively optimizing the group division index; Calculating an inter-group transmission distance coefficient and a meteorological similarity coefficient based on the initial group division scheme, combining the transmission distance coefficient and meteorological similarity coefficient with a group division index to construct a group optimization criterion, optimizing the initial group division scheme according to the group optimization criterion to obtain a target pollution source group, constructing a group control model including pollutant reduction amounts and control costs for the target pollution source group, and obtaining a pollution source group control target by solving the group control model; Calculating the connectivity coefficient, transmission flux coefficient, and position correlation coefficient of the nodes in each pollution source group, combining the connectivity coefficient, transmission flux coefficient, and position correlation coefficient to obtain a node priority coefficient, and grading the nodes in the pollution source group based on the node priority coefficient to obtain an intra-group grading scheme; A group game model including pollutant reduction amounts and control costs is constructed based on the intra-group grading scheme and pollution source group control targets. The group game model is solved to obtain differentiated group control strategies, and real-time monitoring data is collected to calculate control correction amounts. The control correction amounts are input into the compensation model to make real-time adjustments to the differentiated group control strategies, thereby establishing a multi-pollution source linkage control strategy.

9. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 8.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images