Pollution treatment result evaluation method and system based on big data

Abstract

The invention discloses a pollution abatement result evaluation method and system based on big data, and relates to the technical field of pollution abatement. The method comprises the following steps: acquiring removal rates of different pollutants according to multi-modal data of sewage, acquiring a first evaluation coefficient, acquiring a historical data set of a river, acquiring influence degrees of different environmental conditions on different pollutants in combination with the first evaluation coefficient, constructing an interference analysis model, acquiring a real-time influence degree according to a real-time data set, and analyzing the real-time influence degree according to the real-time influence degree. Obtaining a second evaluation coefficient according to the removal rates and the real-time influence degrees of the different pollutants, obtaining a prediction influence degree according to the prediction data set, and obtaining the optimized removal rates of the different pollutants in combination with an evaluation coefficient threshold value; the pollution condition of the treated pollutants in the diffusion process can be continuously monitored, the limitation that pollution treatment result evaluation only stays in the discharging process in the past is solved, and the treatment results of different pollutants can be evaluated more accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of pollution control, and in particular to a pollution control result evaluation method and system based on big data. Background Art

[0002] By integrating IoT sensor data, enterprise emission data, pipe network topology information, meteorological and hydrological data, and combining deep learning models with dynamic causal analysis, it is possible to quantitatively evaluate the effect of sewage treatment. This is already a relatively mature technical means, but existing technologies often rely on traditional water quality monitoring station data and lack technical solutions for the fusion of multi-dimensional data such as pipe network pressure, real-time enterprise emissions, and surface runoff. Moreover, the existing technology for pollution control often only stays at the stage of discharge from sewage treatment plants, but fails to continue to evaluate its subsequent diffusion. Under actual environmental conditions, different rainfall and runoff will indirectly affect the concentration changes of pollutants, and even meet the standards when discharged but exceed the standards in the river, resulting in unstable pollution control. In view of the shortcomings of the existing technology, the present invention provides a pollution control result evaluation method and system based on big data. Summary of the invention

[0003] The purpose of the present invention is to provide a pollution control result evaluation method and system based on big data.

[0004] The purpose of the present invention can be achieved through the following technical solutions: A pollution control result evaluation system based on big data, comprising the following modules: A first evaluation module is used to deploy a distributed sensor network, use the distributed sensor network to obtain multimodal data of sewage, obtain removal rates of different pollutants according to the multimodal data, and obtain corresponding first evaluation coefficients; A data analysis module is used to construct a distribution map of rivers and obtain a historical data set of rivers, combine the first evaluation coefficient in the distribution map, obtain the influence of different environmental conditions on different pollutants, and construct a corresponding interference analysis model; A second evaluation module is used to obtain a real-time impact degree according to a real-time data set of a river using an interference analysis model, and obtain a second evaluation coefficient according to the removal rates of different pollutants and their real-time impact degrees; The data optimization module is used to obtain the predicted impact based on the predicted data set of the river, and to obtain the optimized removal rate of different pollutants in combination with the evaluation coefficient threshold.

[0005] Furthermore, the distributed sensor network is deployed, and the process of using the distributed sensor network to obtain multimodal data of sewage includes: The distributed sensor network includes a water quality detection unit and a flow detection unit at the water inlet and the water outlet, and the multimodal data includes water quality parameters and flow parameters at the water inlet and the water outlet; The water quality parameters of the water inlet and the water outlet are collected respectively through the water quality detection unit, and the flow rate parameters of the water inlet and the water outlet are collected respectively through the flow rate detection unit; The water quality parameters include total nitrogen, total phosphorus, chemical oxygen demand, biochemical oxygen demand, suspended solids, turbidity, dissolved oxygen, ammonia nitrogen, and heavy metals; the flow parameters include flow rate, flow velocity, and water level.

[0006] Furthermore, the process of obtaining the removal rates of different pollutants according to the multimodal data and obtaining the corresponding first evaluation coefficients includes: Set a treatment cycle, treat a single water quality parameter as a pollutant, and obtain the removal rate P of the single water quality parameter in the single treatment cycle every time a treatment cycle is reached;

[0007] Q in and C in are the flow rate of the water inlet and the value of the single water quality parameter at the same time in the single treatment cycle, Q out and C out are the flow rate at the water outlet and the value of the single water quality parameter at the same time in the single treatment cycle; It represents the sum of the products of the flow rate at the water inlet and the value of the single water quality parameter at all times during the single treatment cycle. It represents the sum of the products of the flow rate at the water outlet at all times during the single treatment cycle and the value of the single water quality parameter; The removal rates of other water quality parameters in the single treatment cycle are obtained respectively, and used as the first evaluation coefficients in the single treatment cycle, and the first evaluation coefficients in different treatment cycles are obtained respectively.

[0008] Furthermore, the process of constructing a river distribution map and obtaining a historical data set of the river includes: Obtain the distribution information of all rivers downstream of the sewage treatment plant, use GIS technology to construct a distribution map of all rivers based on the obtained distribution information, and set up several monitoring points in each river; The water quality parameters and environmental parameters of a single monitoring point in a single treatment cycle are taken as a historical data set, wherein the environmental parameters refer to the rainfall and runoff of the single monitoring point in the single treatment cycle; The diffusion distance of each monitoring point is bound to its historical data set. The diffusion distance refers to the length of the river between each monitoring point and the outlet of the sewage treatment plant. The historical data set and diffusion distance of each monitoring point in different treatment cycles are obtained respectively.

[0009] Furthermore, the process of combining the first evaluation coefficient in the distribution map to obtain the influence of different environmental conditions on different pollutants and constructing a corresponding interference analysis model includes: According to a single historical data set of a single monitoring point and a first evaluation coefficient in a corresponding processing period, the influence degree Y of the single monitoring point on a single water quality parameter in the corresponding processing period is obtained;

[0010] J a and J b are the rainfall and runoff at the monitoring point at the same time in the corresponding treatment period, respectively, and C r is the value of the single water quality parameter at the monitoring point at the same time during the corresponding treatment cycle; S c is the diffusion distance of the single monitoring point, It represents the sum of the products of the sum of rainfall and runoff at the monitoring point at all times during the corresponding treatment period and the value of the single water quality parameter; Obtain the influence degree of other water quality parameters in the single treatment cycle, and the influence degree of each monitoring point on each water quality parameter in different treatment cycles; Generate an interference analysis set based on the historical data set, diffusion distance, first evaluation coefficient and its influence on various water quality parameters of each monitoring point in different processing cycles, and divide the interference analysis set into a training set and a test set; Construct a convolutional neural network, use different historical data sets, diffusion distances, and first evaluation coefficients in the training set as input data of the convolutional neural network, and use the corresponding influence in the training set as output data of the convolutional neural network; The convolutional neural network is trained using the training set to obtain an initial convolutional neural network, the initial convolutional neural network is model verified using the test set, and an initial convolutional neural network that is less than or equal to a preset test error threshold is output as an interference assessment model.

[0011] Furthermore, the interference analysis model is used to obtain the real-time impact according to the real-time data set of the river, and the process of obtaining the second evaluation coefficient according to the removal rates of different pollutants and their real-time impacts includes: The current water quality parameters and environmental parameters of a single monitoring point are used as a real-time data set, combined with the first evaluation coefficient and its diffusion distance in the current processing cycle, and input into the interference analysis model to obtain the real-time influence of the single monitoring point on various water quality parameters; According to the removal rate P of a single water quality parameter in the current treatment cycle d Its real-time impact Y d Obtain the corrected removal rate E;

[0012] P max The theoretical maximum removal rate of the single water quality parameter of the sewage treatment plant is obtained by respectively obtaining the corrected removal rates of other water quality parameters of the single monitoring point in the current treatment cycle, and using them as the second evaluation coefficient of the single monitoring point in the current treatment cycle.

[0013] Furthermore, the process of obtaining the predicted impact according to the predicted data set of the river and obtaining the optimized removal rate of different pollutants in combination with the evaluation coefficient threshold includes: Obtain the predicted rainfall and predicted runoff of a single monitoring point in the next processing cycle through the hydrological and meteorological station, and use the current water quality parameters of the single monitoring point and the predicted rainfall and predicted runoff of the next processing cycle as a prediction data set; The predicted data set, the first evaluation coefficient, and the diffusion distance of the single monitoring point in the current treatment cycle are input into the interference analysis model to obtain the predicted influence of the single monitoring point on each water quality parameter, and the corrected removal rate obtained according to the removal rate of the single water quality parameter in the current treatment cycle and its predicted influence is used as its predicted evaluation coefficient; Set corresponding evaluation coefficient thresholds for different water quality parameters, compare the predicted evaluation coefficient of each water quality parameter with its evaluation coefficient threshold to obtain the parameter to be optimized, adjust the treatment process of the sewage treatment plant until the predicted evaluation coefficient of the parameter to be optimized is less than or equal to its evaluation coefficient threshold, and use the removal rate at this time as the optimized removal rate and feed it back to relevant personnel.

[0014] A pollution control result evaluation method based on big data comprises the following steps: Step S1: deploying a distributed sensor network, using the distributed sensor network to obtain multimodal data of sewage, obtaining removal rates of different pollutants according to the multimodal data, and obtaining corresponding first evaluation coefficients; Step S2: construct a distribution map of rivers, obtain a historical data set of rivers, combine the first evaluation coefficient in the distribution map, obtain the influence of different environmental conditions on different pollutants, and construct a corresponding interference analysis model; Step S3: using the interference analysis model to obtain the real-time impact according to the real-time data set of the river, and obtaining the second evaluation coefficient according to the removal rates of different pollutants and their real-time impacts; Step S4: Obtain the predicted impact according to the predicted data set of the river, and obtain the optimized removal rate of different pollutants in combination with the evaluation coefficient threshold.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention obtains the removal rates of different pollutants when they are discharged from the sewage treatment plant and uses them as the first evaluation coefficient. In combination with the water quality parameters, environmental parameters and diffusion distances at different monitoring points in the downstream river, the influence of different environmental conditions on the diffusion of different pollutants can be obtained, and then the second evaluation coefficient can be obtained, which is conducive to continuing to monitor the pollution situation of the treated pollutants during the diffusion process, and solves the limitation that the evaluation of pollution control results in the past only stays at the time of discharge, and can more accurately evaluate the control results of different pollutants. By constructing an interference analysis model, we can directly obtain the interference of different environmental conditions on the concentrations of different pollutants. According to the subsequent changes in rainfall and runoff, we can judge in advance whether the concentrations of different pollutants will be too high, and adjust the sewage treatment process in advance to avoid this situation. This can more effectively ensure that the sewage treatment results are always up to standard. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0017] like Figure 1 As shown, a pollution control result evaluation system based on big data includes the following modules: A first evaluation module is used to deploy a distributed sensor network, use the distributed sensor network to obtain multimodal data of sewage, obtain removal rates of different pollutants according to the multimodal data, and obtain corresponding first evaluation coefficients; A data analysis module is used to construct a distribution map of rivers and obtain a historical data set of rivers, combine the first evaluation coefficient in the distribution map, obtain the influence of different environmental conditions on different pollutants, and construct a corresponding interference analysis model; A second evaluation module is used to obtain a real-time impact degree according to a real-time data set of a river using an interference analysis model, and obtain a second evaluation coefficient according to the removal rates of different pollutants and their real-time impact degrees; The data optimization module is used to obtain the predicted impact based on the predicted data set of the river, and to obtain the optimized removal rate of different pollutants in combination with the evaluation coefficient threshold.

[0018] It should be further explained that, in the embodiment of the present invention, the process of deploying a distributed sensor network and obtaining multimodal data of sewage using the distributed sensor network includes: Corresponding water quality detection units are respectively set at the water inlet and the water outlet of the sewage treatment plant, and the water quality parameters of the water inlet and the water outlet are respectively collected through the water quality detection units, and the water quality parameters of the water inlet and the water outlet are respectively marked as inlet water quality parameters and outlet water quality parameters; Corresponding flow detection units are respectively arranged at the water inlet and the water outlet of the sewage treatment plant, and the flow parameters of the water inlet and the water outlet are respectively collected through the flow detection units, and the flow parameters of the water inlet and the water outlet are respectively marked as inflow flow parameters and outflow flow parameters; The water quality parameters include total nitrogen, total phosphorus, chemical oxygen demand, biochemical oxygen demand, suspended solids, turbidity, dissolved oxygen, ammonia nitrogen, heavy metals, etc. The flow parameters include flow rate, flow velocity, water level, etc., which are expressed by specific values; The distributed sensing network includes water quality detection units and flow detection units at the water inlet and the water outlet, and the multimodal data includes inlet water quality parameters and inlet flow parameters of the water inlet and outlet water quality parameters and outlet flow parameters of the water outlet.

[0019] It should be further explained that, in an embodiment of the present invention, the process of obtaining the removal rates of different pollutants according to the multimodal data and obtaining the corresponding first evaluation coefficients includes: Set a treatment cycle, take a single water quality parameter (such as total nitrogen) as an example, and analyze it as a pollutant. When each treatment cycle is reached, obtain the removal rate of the single water quality parameter in the single treatment cycle, which is recorded as P;

[0020] Among them, Q in and C in are the flow rate and total nitrogen value of the water inlet at the same time in the single treatment cycle, Q out and C out are the flow rate and total nitrogen values ​​at the outlet at the same time in the single treatment cycle; It represents the sum of the products of the flow rate at the water inlet and the total nitrogen value at all times during the single treatment cycle. It represents the sum of the products of the outlet flow rate and the total nitrogen value at all times in the single treatment cycle; The same method is adopted to obtain the removal rates of other water quality parameters in the single treatment cycle, and they are collectively used as the first evaluation coefficient in the single treatment cycle. The same method is adopted to obtain the first evaluation coefficients in different treatment cycles.

[0021] It should be further explained that, in the embodiment of the present invention, the process of constructing a river distribution map and obtaining a historical data set of the river includes: Obtaining the distribution information of all rivers downstream of the sewage treatment plant, wherein the distribution information refers to the geographical distribution of each river, and constructing a distribution map of all rivers downstream of the sewage treatment plant based on the obtained distribution information using GIS technology; A number of monitoring points are randomly set in each river, and the water quality parameters and environmental parameters of a single monitoring point in a single treatment cycle are used as its historical data set, wherein the environmental parameters refer to the rainfall and runoff of the single monitoring point in the single treatment cycle; The diffusion distance of each monitoring point is bound to its historical data set. The diffusion distance refers to the length of the river between each monitoring point and the outlet of the sewage treatment plant. The same method is used to obtain the historical data set of each monitoring point in different treatment cycles and its corresponding diffusion distance.

[0022] It should be further explained that, in the embodiment of the present invention, the process of combining the first evaluation coefficient in the distribution map, obtaining the influence of different environmental conditions on different pollutants, and constructing the corresponding interference analysis model includes: Taking a single monitoring point as an example, according to a single historical data set of the single monitoring point and the first evaluation coefficient in the corresponding processing period, the influence of the single monitoring point on a single water quality parameter (such as total nitrogen) in the corresponding processing period is obtained, which is recorded as Y;

[0023] Among them, J a and J b are the rainfall and runoff at the monitoring point at the same time in the corresponding treatment period, respectively, and C r is the value of total nitrogen at the monitoring point at the same time during the corresponding treatment cycle; S c is the diffusion distance corresponding to the single monitoring point, It represents the sum of the products of the sum of rainfall and runoff at the monitoring point at all times during the corresponding treatment period and the value of total nitrogen; The same method is used to obtain the influence degree of other water quality parameters in the single treatment cycle, as well as the influence degree of each monitoring point on each water quality parameter in different treatment cycles; Generate an interference analysis set based on the historical data set, diffusion distance, first evaluation coefficient and its influence on various water quality parameters of each monitoring point in different processing cycles, and divide the interference analysis set into a training set and a test set; Construct a convolutional neural network, use different historical data sets, diffusion distances, and first evaluation coefficients in the training set as input data of the convolutional neural network, and use the corresponding influence in the training set as output data of the convolutional neural network; The convolutional neural network is trained using the training set to obtain an initial convolutional neural network, the initial convolutional neural network is model verified using the test set, and an initial convolutional neural network that is less than or equal to a preset test error threshold is output as the corresponding interference assessment model.

[0024] It should be further explained that, in the embodiment of the present invention, the process of obtaining the real-time impact degree according to the real-time data set of the river by using the interference analysis model and obtaining the second evaluation coefficient according to the removal rates of different pollutants and their real-time impact degrees includes: Taking a single monitoring point as an example, the current water quality parameters and environmental parameters of the single monitoring point are used as the corresponding real-time data set, combined with the first evaluation coefficient and its diffusion distance in the current processing cycle, and input into the interference analysis model to obtain the real-time influence of the single monitoring point on various water quality parameters; According to the removal rate P of a single water quality parameter (such as total nitrogen) in the current treatment cycle d Its real-time impact Y d Get the corrected removal rate, denoted as E;

[0025] Among them, P max In order to obtain the theoretical maximum removal rate of the single water quality parameter of the sewage treatment plant, the same method is used to obtain the corrected removal rates of other water quality parameters at the single monitoring point in the current treatment cycle, and they are used together as the second evaluation coefficient of the single monitoring point in the current treatment cycle.

[0026] It should be further explained that, in the embodiment of the present invention, the process of obtaining the predicted influence according to the predicted data set of the river and obtaining the optimized removal rate of different pollutants in combination with the evaluation coefficient threshold includes: Taking a single monitoring point as an example, the current water quality parameters of the single monitoring point and the predicted rainfall and predicted runoff in the next processing cycle are used as the corresponding prediction data set, and the predicted rainfall and predicted runoff are directly obtained through the local hydrological and meteorological station; The predicted data set, the first evaluation coefficient, and the diffusion distance of the single monitoring point in the current treatment cycle are input into the interference analysis model to obtain the predicted influence of the single monitoring point on each water quality parameter, and the corrected removal rate obtained according to the removal rate of the single water quality parameter in the current treatment cycle and its predicted influence is used as its predicted evaluation coefficient; Set corresponding evaluation coefficient thresholds for different water quality parameters, compare the obtained predicted evaluation coefficient with its evaluation coefficient threshold, if the predicted evaluation coefficient is greater than the evaluation coefficient threshold, mark the water quality parameter as a parameter to be optimized, if the predicted evaluation coefficient is less than or equal to the evaluation coefficient threshold, do not perform any other operations on it; For the parameters to be optimized, the treatment process of the sewage treatment plant is adjusted until the predicted evaluation coefficient of the parameter to be optimized is less than or equal to its evaluation coefficient threshold, and the removal rate at this time is used as the corresponding optimized removal rate, and it is fed back to the relevant personnel to prompt them to adjust the treatment process of the next treatment cycle based on this standard.

[0027] The embodiment of the present invention also includes a pollution control result evaluation method based on big data, comprising the following steps: Step S1: deploying a distributed sensor network, using the distributed sensor network to obtain multimodal data of sewage, obtaining removal rates of different pollutants according to the multimodal data, and obtaining corresponding first evaluation coefficients; Step S2: construct a distribution map of rivers, obtain a historical data set of rivers, combine the first evaluation coefficient in the distribution map, obtain the influence of different environmental conditions on different pollutants, and construct a corresponding interference analysis model; Step S3: using the interference analysis model to obtain the real-time impact according to the real-time data set of the river, and obtaining the second evaluation coefficient according to the removal rates of different pollutants and their real-time impacts; Step S4: Obtain the predicted impact according to the predicted data set of the river, and obtain the optimized removal rate of different pollutants in combination with the evaluation coefficient threshold.

[0028] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A pollution control result evaluation system based on big data, characterized in that: Includes the following modules: A first evaluation module is used to deploy a distributed sensor network, use the distributed sensor network to obtain multimodal data of sewage, obtain removal rates of different pollutants according to the multimodal data, and obtain corresponding first evaluation coefficients; A data analysis module is used to construct a distribution map of rivers and obtain a historical data set of rivers, combine the first evaluation coefficient in the distribution map, obtain the influence of different environmental conditions on different pollutants, and construct a corresponding interference analysis model; A second evaluation module is used to obtain a real-time impact degree according to a real-time data set of a river using an interference analysis model, and obtain a second evaluation coefficient according to the removal rates of different pollutants and their real-time impact degrees; The data optimization module is used to obtain the predicted impact based on the predicted data set of the river, and to obtain the optimized removal rate of different pollutants in combination with the evaluation coefficient threshold.

2. According to the big data-based pollution control result evaluation system of claim 1, it is characterized in that: The process of obtaining multimodal data of sewage includes: The distributed sensor network includes a water quality detection unit and a flow detection unit at the water inlet and the water outlet, and the multimodal data includes water quality parameters and flow parameters at the water inlet and the water outlet; The water quality parameters of the water inlet and the water outlet are collected respectively through the water quality detection unit, and the flow rate parameters of the water inlet and the water outlet are collected respectively through the flow rate detection unit; The water quality parameters include total nitrogen, total phosphorus, chemical oxygen demand, biochemical oxygen demand, suspended solids, turbidity, dissolved oxygen, ammonia nitrogen, and heavy metals; the flow parameters include flow rate, flow velocity, and water level.

3. A pollution control result evaluation system based on big data according to claim 2, characterized in that: The process of obtaining the removal rates and first evaluation coefficients of different pollutants includes: Set a treatment cycle, treat a single water quality parameter as a pollutant, and obtain the removal rate P of the single water quality parameter in the single treatment cycle every time a treatment cycle is reached; Q in and C in are the flow rate of the water inlet and the value of the single water quality parameter at the same time in the single treatment cycle, Q out and C out are the flow rate at the water outlet and the value of the single water quality parameter at the same time in the single treatment cycle; It represents the sum of the products of the flow rate at the water inlet and the value of the single water quality parameter at all times during the single treatment cycle. It represents the sum of the products of the flow rate at the water outlet at all times during the single treatment cycle and the value of the single water quality parameter; The removal rates of other water quality parameters in the single treatment cycle are obtained respectively, and used as the first evaluation coefficients in the single treatment cycle, and the first evaluation coefficients in different treatment cycles are obtained respectively.

4. A pollution control result evaluation system based on big data according to claim 3, characterized in that: The process of obtaining a historical data set for a river includes: Obtain the distribution information of all rivers downstream of the sewage treatment plant, use GIS technology to construct a distribution map of all rivers based on the obtained distribution information, and set up several monitoring points in each river; The water quality parameters and environmental parameters of a single monitoring point in a single treatment cycle are taken as a historical data set, wherein the environmental parameters refer to the rainfall and runoff of the single monitoring point in the single treatment cycle; The diffusion distance of each monitoring point is bound to its historical data set. The diffusion distance refers to the length of the river between each monitoring point and the outlet of the sewage treatment plant. The historical data set and diffusion distance of each monitoring point in different treatment cycles are obtained respectively.

5. A pollution control result evaluation system based on big data according to claim 4, characterized in that: The process of obtaining the impact of different pollutants and building an interference analysis model includes: According to a single historical data set of a single monitoring point and a first evaluation coefficient in a corresponding processing period, the influence degree Y of the single monitoring point on a single water quality parameter in the corresponding processing period is obtained; J a and J b are the rainfall and runoff at the monitoring point at the same time in the corresponding treatment period, respectively, and C r is the value of the single water quality parameter at the monitoring point at the same time during the corresponding treatment cycle; S c is the diffusion distance of the single monitoring point, It represents the sum of the products of the sum of rainfall and runoff at the monitoring point at all times during the corresponding treatment period and the value of the single water quality parameter; Obtain the influence degree of other water quality parameters in the single treatment cycle, and the influence degree of each monitoring point on each water quality parameter in different treatment cycles; Generate an interference analysis set based on the historical data set, diffusion distance, first evaluation coefficient and its influence on various water quality parameters of each monitoring point in different processing cycles, and divide the interference analysis set into a training set and a test set; Construct a convolutional neural network, use different historical data sets, diffusion distances, and first evaluation coefficients in the training set as input data of the convolutional neural network, and use the corresponding influence in the training set as output data of the convolutional neural network; The convolutional neural network is trained using the training set to obtain an initial convolutional neural network, the initial convolutional neural network is model verified using the test set, and an initial convolutional neural network that is less than or equal to a preset test error threshold is output as an interference assessment model.

6. A pollution control result evaluation system based on big data according to claim 5, characterized in that: The process of obtaining the real-time impact and the second evaluation coefficient includes: The current water quality parameters and environmental parameters of a single monitoring point are used as a real-time data set, combined with the first evaluation coefficient and its diffusion distance in the current processing cycle, and input into the interference analysis model to obtain the real-time influence of the single monitoring point on various water quality parameters; According to the removal rate P of a single water quality parameter in the current treatment cycle d Its real-time impact Y d Obtain the corrected removal rate E; P max The theoretical maximum removal rate of the single water quality parameter of the sewage treatment plant is obtained by respectively obtaining the corrected removal rates of other water quality parameters of the single monitoring point in the current treatment cycle, and using them as the second evaluation coefficient of the single monitoring point in the current treatment cycle.

7. A pollution control result evaluation system based on big data according to claim 6, characterized in that: The process of obtaining the predicted impact and optimizing the removal rate includes: Obtain the predicted rainfall and predicted runoff of a single monitoring point in the next processing cycle through the hydrological and meteorological station, and use the current water quality parameters of the single monitoring point and the predicted rainfall and predicted runoff of the next processing cycle as a prediction data set; The predicted data set, the first evaluation coefficient, and the diffusion distance of the single monitoring point in the current treatment cycle are input into the interference analysis model to obtain the predicted influence of the single monitoring point on each water quality parameter, and the corrected removal rate obtained according to the removal rate of the single water quality parameter in the current treatment cycle and its predicted influence is used as its predicted evaluation coefficient; Set corresponding evaluation coefficient thresholds for different water quality parameters, compare the predicted evaluation coefficient of each water quality parameter with its evaluation coefficient threshold to obtain the parameter to be optimized, adjust the treatment process of the sewage treatment plant until the predicted evaluation coefficient of the parameter to be optimized is less than or equal to its evaluation coefficient threshold, and use the removal rate at this time as the optimized removal rate and feed it back to relevant personnel.

8. A pollution control result evaluation method based on big data, which is implemented based on the pollution control result evaluation system according to any one of claims 1 to 7, characterized in that: The method comprises: Step S1: deploying a distributed sensor network, using the distributed sensor network to obtain multimodal data of sewage, obtaining removal rates of different pollutants according to the multimodal data, and obtaining corresponding first evaluation coefficients; Step S2: construct a distribution map of rivers, obtain a historical data set of rivers, combine the first evaluation coefficient in the distribution map, obtain the influence of different environmental conditions on different pollutants, and construct a corresponding interference analysis model; Step S3: using the interference analysis model to obtain the real-time impact according to the real-time data set of the river, and obtaining the second evaluation coefficient according to the removal rates of different pollutants and their real-time impacts; Step S4: Obtain the predicted impact according to the predicted data set of the river, and obtain the optimized removal rate of different pollutants in combination with the evaluation coefficient threshold.

Images