Sewage treatment facility site selection and scale optimization method and system

Abstract

The invention relates to the field of sewage treatment, in particular to a sewage treatment facility site selection and scale optimization method and system, and the method comprises the steps: obtaining sewage treatment facility site selection and scale related data, carrying out the preprocessing, and carrying out the domestic sewage fine space distribution simulation; according to the to-be-optimized sewage treatment area and the treated data, the site selection of the to-be-constructed sewage treatment facility is obtained, and finally the scale of the to-be-constructed sewage treatment facility is obtained. According to the method, domestic sewage fine spatial distribution simulation is firstly carried out, and then a to-be-optimized sewage treatment area is obtained, so that theoretical support is provided for facility layout optimization, and a more accurate to-be-built sewage treatment facility site selection is obtained; and finally, the scale of the sewage treatment facility to be constructed is obtained according to the data, so that the capacity of the facility is flexibly adjusted according to service requirements of different regions, and the service efficiency is maximized and the cost is minimized.

Description

Technical Field

[0001] The present invention relates to the field of sewage treatment, and more specifically, to a method and system for optimizing the location and scale of sewage treatment facilities. Background Art

[0002] The accessibility of public service facilities is the most direct and representative tool for evaluating the planning of public service facilities and social fairness. Currently, many studies are based on this for layout optimization. At present, in the evaluation of public facility accessibility, the gravity model, potential model, two-step floating catchment area method, etc. are the most widely used. The optimal supply-demand allocation model has a more explicit physical meaning than the two-step floating catchment area method and can be flexibly used to statistically analyze public facility service indicators (such as per capita service travel time, service travel time at each demand point, average travel time of each facility user, service coverage within a specific radius, etc.). It has application prospects in the existing public facility optimization. In the planning of sewage treatment facilities, using the optimal supply-demand allocation model to evaluate the service capacity of sewage treatment facilities can more accurately reflect the spatial distribution of sewage emissions and demand points, thereby providing theoretical support for facility layout optimization. However, this sewage treatment facility optimization method fails to evaluate the service level of sewage treatment facilities and comprehensively consider the refined demand for future domestic sewage emissions to optimize the facility scale.

[0003] The prior art discloses a method and device for spatially locating a sewage treatment station. The method includes: dividing the optional range of construction land into multiple spatial units, and according to a site selection analysis evaluation system including various factors related to site selection analysis, using hierarchical analysis software to calculate the weights of the various factors in the form of group decision-making expert data aggregation to form a factor weight matrix, where the factors include condition factors and dynamic correction evaluation factors; retrieving the factor data corresponding to the factors from the basic geographic information spatial database, and performing standardization processing on the factor data; substituting the standardized factor data and the factor weight matrix into the site selection analysis formula to obtain the suitability index for setting a sewage treatment station in each spatial unit. However, this method does not further optimize the facility scale, resulting in the service efficiency not reaching the maximum, and the cost is relatively high. Summary of the Invention

[0004] The purpose of the present invention is to disclose a method and system for optimizing the location and scale of sewage treatment facilities with higher service efficiency.

[0005] To achieve the above purpose, the present invention provides a method and system for optimizing the location and scale of sewage treatment facilities, including:

[0006] S1: Obtain data related to the location and scale of sewage treatment facilities, and perform preprocessing to obtain preprocessed data;

[0007] S2: Simulate the refined spatial distribution of domestic sewage based on the processed data to obtain the refined spatial distribution map of sewage;

[0008] S3: Obtain the sewage treatment area to be optimized based on the refined spatial distribution map of sewage and the processed data;

[0009] S4: Obtain the location selection of the sewage treatment facilities to be constructed based on the sewage treatment area to be optimized and the processed data;

[0010] S5: Obtain the scale of the sewage treatment facilities to be constructed based on the sewage treatment area to be optimized, the processed data and the location selection of the sewage treatment facilities to be constructed.

[0011] Furthermore, in step S1, the data related to the location selection and scale of sewage treatment facilities include: demographic data, district and county administrative boundary data, land use data, DEM data, road data, POI data, building outline data, Tencent location big data, night light data, wind direction data, settlement data, slope data, river distance data.

[0012] Furthermore, in step S1, after preprocessing, the obtained processed data include:

[0013] Demographic data: Obtain the population number, age-specific fertility rate and total fertility rate of women of childbearing age, male and female mortality rates, and migration rates;

[0014] Land use type data: Use the projection coordinate system WGS84-UTM to reclassify 25 land use types into 6 categories;

[0015] DEM data: Use the projection coordinate system WGS84-UTM and resample the raster size to 100m×100m using the nearest neighbor method;

[0016] Road data: Clip the vector layer of provincial road data at a scale of 1:1,000,000 to obtain the road data in the study area, and obtain the Euclidean distance raster layer of the nearest road from the vector layer through the Euclidean distance tool. The raster size is resampled to 100m×100m using the nearest neighbor method;

[0017] Building outline: Convert the surface elements into point elements through ArcGIS tools;

[0018] POI data, Tencent location big data and building points: Through the kernel density analysis tool, convert the 14-class POI vector point layer, Tencent location big data layer and building points into 16 density raster layers. The raster size is resampled to 100m×100m using the nearest neighbor method;

[0019] Nighttime light data: The light data of the study area is obtained by splicing and clipping. The raster size is resampled to 100m×100m using the nearest neighbor method, and the projected coordinate system WGS84-UTM is used at the same time;

[0020] Clean the wind direction data and vectorize it.

[0021] Further, in step S2, it includes:

[0022] Construct an XGBoost model and a multi-source data feature library; input the multi-source data feature library into the XGBoost model to obtain the weight values of the population distribution indicative factors;

[0023] Couple the multi-objective optimization model of land use, set the objective function and constraints, and use the multi-objective genetic algorithm (NSGA-II) to optimize the quantity structure of land use; calculate the transfer matrix based on the optimized land use structure, and construct a suitability atlas in combination with the local land use characteristics and references. Input the transfer matrix and the suitability atlas into the CA-Markov model to finally simulate the multi-objective optimized land use layout

[0024] Use the Leslie model to predict the future population size

[0025] After determining the weight values of the population distribution indicative factors, the land use layout, and the population distribution indicative factor layer, use the ArcGIS tool to generate a refined future population spatial distribution map of the coupled multi-objective optimization model of land use through the zonal density method; combine the future per capita comprehensive domestic sewage, and make the predicted per capita sewage production into raster data and multiply it with the refined future population spatial distribution layer to obtain the refined sewage spatial distribution map.

[0026] Further, the multi-source data feature library includes: feature data and label data; the feature data consists of 19 population distribution indicative factors, covering Tencent location big data, 14 types of POIs data, nighttime light data, road data, elevation, and building outlines; the label data is composed of the logarithm of the predicted population in the study area.

[0027] Further, in step S3, it includes: evaluating the service capacity of existing sewage treatment facilities based on the optimal supply-demand allocation model: input the refined spatial distribution data of domestic sewage and the sewage volume at each point as demand point data into the optimal supply-demand allocation model, and input the existing sewage treatment facilities and their scales as supply point data; use the Euclidean distance for analysis with the objective of minimizing pipeline costs; finally obtain the coverage of the service capacity of existing sewage treatment facilities, identify the areas with supply-demand imbalance, and obtain the areas of sewage treatment to be optimized.

[0028] Further, in step S4, it includes:

[0029] First, select settlement points, slope, wind direction, road distance, river distance, the optimized water bodies and construction land after multi-objective optimization to produce a suitability atlas for the siting of sewage treatment facilities; set prohibited construction areas, including areas with a slope greater than 15°, within 50 m of the road, within 300 m of the settlement point, within 100 m of the river, water bodies and existing construction land as prohibited construction areas; combine the slope, wind direction, distance from the river and the road, determine the weights of each factor according to the analytic hierarchy process, sort the suitability of the siting of sewage treatment facilities, and set the prohibited construction areas as areas where it is "not suitable" to build sewage treatment facilities. Finally, a suitability atlas for the siting of sewage treatment facilities is obtained. According to the suitability atlas, alternative points for sewage treatment facilities are selected from the areas of the two levels of "suitable" and "very suitable", and the siting of the sewage treatment facilities to be built is respectively selected from the alternative points through two location models, namely the P-median model and the maximum covering model.

[0030] Furthermore, it includes:

[0031] Through the quadratic programming model, based on the area of sewage treatment to be optimized, the processed data, and the siting of the sewage treatment facilities to be built, with the minimization of the standard deviation of accessibility as the optimization goal, the scale of the sewage treatment facilities to be built is obtained.

[0032] Furthermore, in step S5, it includes: predicting the future per capita comprehensive domestic sewage, calculating the total sewage volume generated in the predicted year, and the difference between the sewage volume in the predicted year and the scale of the existing sewage treatment facilities is the sewage volume not covered by the existing sewage treatment facilities; taking the sewage volume not covered by the existing sewage treatment facilities as the average distribution to the two sewage treatment facilities to be built as the initial scale; then, calculating the distance and demand between each sewage treatment facility to be built and the uncovered demand points, inputting them into the programming tool, and optimizing the scale through the quadratic programming model; finally, respectively optimizing the initial scales of the sewage treatment facilities P1, P2 and M1, M2 selected by the P-median model and the maximum covering model; the optimized results are verified through the optimal supply-demand allocation model, the accessibility analysis of the optimized sewage treatment facilities is obtained, and finally a visual result is generated; by comparing different layout and scale schemes, the most suitable facility configuration scheme is selected to obtain the scale of the sewage treatment facilities to be built.

[0033] In addition, the present invention also provides a system for optimizing the siting and scale of sewage treatment facilities, including:

[0034] An acquisition and preprocessing module: acquiring data related to the siting and scale of sewage treatment facilities and performing preprocessing to obtain preprocessed data;

[0035] A sewage distribution module: simulating the refined spatial distribution of domestic sewage according to the processed data to obtain a refined spatial distribution map of sewage;

[0036] Module for sewage treatment area to be optimized: Obtain the sewage treatment area to be optimized according to the refined spatial distribution map of sewage and the processed data;

[0037] Siting module: Obtain the siting of sewage treatment facilities to be constructed according to the sewage treatment area to be optimized and the processed data;

[0038] Scale module: Obtain the scale of sewage treatment facilities to be constructed according to the sewage treatment area to be optimized, the processed data, and the siting of sewage treatment facilities to be constructed.

[0039] Compared with the prior art, the beneficial effects of the technical solution of the present invention are:

[0040] The present invention first conducts a refined spatial distribution simulation of domestic sewage, and then obtains the sewage treatment area to be optimized, thereby providing a theoretical support for the optimization of facility layout and obtaining a more accurate siting of sewage treatment facilities to be constructed; finally, the scale of sewage treatment facilities to be constructed is obtained according to the above data, so as to realize the flexible adjustment of the capacity of facilities according to the service needs of different regions, thereby maximizing the service efficiency and minimizing the cost. Description of the Drawings

[0041] Figure 1 Flowchart of a method for siting and scale optimization of sewage treatment facilities according to Embodiment 1;

[0042] Figure 2 Block diagram of a system for siting and scale optimization of sewage treatment facilities according to Embodiment 3; Detailed Description of the Invention

[0043] The drawings are only for illustrative purposes and should not be construed as a limitation of this patent;

[0044] The technical solution of the present invention will be further described below with reference to the drawings and embodiments.

[0045] Embodiment 1:

[0046] This embodiment provides a method for siting and scale optimization of sewage treatment facilities as shown in Figure 1 and includes:

[0047] S1: Obtain data related to the siting and scale of sewage treatment facilities, and perform preprocessing to obtain preprocessed data;

[0048] S2: Conduct a refined spatial distribution simulation of domestic sewage according to the processed data to obtain a refined spatial distribution map of sewage;

[0049] S3: Obtain the sewage treatment area to be optimized according to the refined spatial distribution map of sewage and the processed data;

[0050] S4: Based on the sewage treatment area to be optimized and the processed data, obtain the location of the sewage treatment facility to be built;

[0051] S5: Based on the sewage treatment area to be optimized, the processed data, and the location of the sewage treatment facility to be built, obtain the scale of the sewage treatment facility to be built.

[0052] In this embodiment, the refined spatial distribution of domestic sewage is simulated first, and then the sewage treatment area to be optimized is obtained, thereby providing theoretical support for the optimization of facility layout and obtaining a more accurate location of the sewage treatment facility to be built; finally, the scale of the sewage treatment facility to be built is obtained based on the above data, so as to flexibly adjust the capacity of the facility according to the service needs of different regions, thereby maximizing the service efficiency and minimizing the cost.

[0053] Embodiment Two:

[0054] This embodiment further discloses on the basis of Embodiment One:

[0055] Further, in step S1, the data related to the location and scale of the sewage treatment facility includes: demographic data, district and county administrative boundary data, land use data, DEM data, road data, POI data, building outline data, Tencent location big data, night light data, wind direction data, settlement data, slope data, river distance data.

[0056] Further, in step S1, after preprocessing, the obtained preprocessed data includes:

[0057] Demographic data: Obtain the population, age-specific fertility rate and total fertility rate of women of childbearing age, male and female mortality rates, and migration rates;

[0058] Land use type data: Use the projection coordinate system WGS84-UTM to reclassify 25 land use types into 6 categories;

[0059] DEM data: Use the projection coordinate system WGS84-UTM, and resample the raster size to 100m×100m using the nearest neighbor method;

[0060] Road data: Clip the vector layer of the road data of a certain province at a scale of 1:1,000,000 to obtain the road data of the research area, and obtain the Euclidean distance raster layer of the nearest road from the vector layer through the Euclidean distance tool, and resample the raster size to 100m×100m using the nearest neighbor method;

[0061] Building outline: Convert the surface elements into point elements through ArcGIS tools;

[0062] POI data, Tencent location big data, and building points: Through the kernel density analysis tool, convert 14 types of POI vector point layers, Tencent location big data layers, and building points into 16 density raster layers, and resample the raster size to 100m × 100m using the nearest neighbor method;

[0063] Nighttime light data: Perform mosaicking and clipping to obtain the light data of the study area, resample the raster size to 100m × 100m using the nearest neighbor method, and use the projection coordinate system WGS84 - UTM at the same time;

[0064] Clean the wind direction data and vectorize it.

[0065] Furthermore, in step S2, it includes:

[0066] Construct an XGBoost model and a multi - source data feature library; input the multi - source data feature library into the XGBoost model to obtain the weight values of the population distribution indicative factors;

[0067] Couple the multi - objective optimization model of land use, set the objective function and constraint conditions, and use the multi - objective genetic algorithm (NSGA - Ⅱ) to optimize the land use quantity structure; calculate the transfer matrix based on the optimized land use structure, and construct a suitability atlas in combination with the local land use characteristics and references. Input the transfer matrix and the suitability atlas into the CA - Markov model to finally simulate the multi - objective optimized land use layout

[0068] Use the Leslie model to predict the future population size

[0069] After determining the weight values of the population distribution indicative factors, the land use layout, and the population distribution indicator factor layer, use the ArcGIS tool to generate a refined future population spatial distribution map coupling the multi - objective optimization model of land use through the zonal density method; combine with the future per capita comprehensive domestic sewage, multiply the predicted per capita sewage generation amount to make raster data and multiply it with the refined future population spatial distribution layer to obtain the refined sewage spatial distribution map.

[0070] Furthermore, the multi - source data feature library includes: feature data and label data; the feature data consists of 19 population distribution indicative factors covering Tencent location big data, 14 types of POIs data, nighttime light data, road data, elevation, and building outlines; the label data is composed of the logarithm of the predicted population in the study area.

[0071] Further, in step S3, it includes: evaluating the service capacity of existing sewage treatment facilities based on the optimal supply-demand allocation model: inputting the refined spatial distribution data of domestic sewage and the sewage volume at each point as demand point data into the optimal supply-demand allocation model, and inputting the existing sewage treatment facilities and their scales as supply point data; taking the minimization of pipeline cost as the objective function and using the Euclidean distance for analysis; finally obtaining the coverage of the service capacity of existing sewage treatment facilities, identifying the areas with supply-demand imbalance, and obtaining the sewage treatment areas to be optimized.

[0072] Further, in step S4, it includes:

[0073] First, select residential areas, slope, wind direction, road distance, river distance, the water bodies and construction land after multi-objective optimization to make an atlas of the suitability for the location of sewage treatment facilities; set no-construction areas, including areas with a slope greater than 15°, within 50 m of the road, within 300 m of residential areas, within 100 m of rivers, water bodies and existing construction land as no-construction areas; combine the slope, wind direction, and distances from rivers and roads, determine the weights of each factor according to the analytic hierarchy process, sort the suitability for the location of sewage treatment facilities, and set the no-construction areas as areas where it is "not suitable" to build sewage treatment facilities. Finally, an atlas of the suitability for the location of sewage treatment facilities is obtained. According to the suitability atlas, select alternative points for sewage treatment facilities from the areas of the two levels of "suitable" and "very suitable", and respectively select the locations for the sewage treatment facilities to be built from the alternative points through two location models, namely the P-median model and the maximum coverage model.

[0074] Further, it includes:

[0075] Through the quadratic programming model, according to the sewage treatment areas to be optimized, the processed data, and the locations for the sewage treatment facilities to be built, with the minimization of the standard deviation of accessibility as the optimization objective, obtain the scale of the sewage treatment facilities to be built.

[0076] Further, in step S5, it includes: predicting the future per capita comprehensive domestic sewage, calculating the total generated sewage volume in the predicted year, and the difference between the sewage volume in the predicted year and the scale of the existing sewage treatment facilities is the sewage volume not covered by the existing sewage treatment facilities; taking the sewage volume not covered by the existing sewage treatment facilities as the scale of the sewage treatment facilities to be constructed and evenly distributing it to the two sewage treatment facilities to be constructed as the initial scale; then, calculating the distance and demand between each sewage treatment facility to be constructed and the uncovered demand points, inputting them into the programming tool, and optimizing the scale through the quadratic programming model; finally, optimizing the initial scales of the sewage treatment facilities P1, P2 and M1, M2 selected by the P-median model and the maximum coverage model respectively; verifying the optimized results through the optimal supply-demand allocation model, obtaining the accessibility analysis of the optimized sewage treatment facilities, and finally generating a visual result; by comparing different layout and scale schemes, selecting the most suitable facility configuration scheme to obtain the scale of the sewage treatment facilities to be constructed.

[0077] In this embodiment, the refined spatial distribution simulation of domestic sewage is first carried out, and then the sewage treatment area to be optimized is obtained, so as to provide theoretical support for the facility layout optimization and obtain a more accurate location of the sewage treatment facilities to be constructed; finally, the scale of the sewage treatment facilities to be constructed is obtained based on the above data, so as to flexibly adjust the capacity of the facilities according to the service requirements of different regions, thereby maximizing the service efficiency and minimizing the cost.

[0078] This embodiment provides a Figure 2 sewage treatment facility location and scale optimization system as shown in

[0079] Acquisition and preprocessing module: acquiring data related to the location and scale of sewage treatment facilities and performing preprocessing to obtain preprocessed data;

[0080] Sewage distribution module: performing refined spatial distribution simulation of domestic sewage according to the processed data to obtain a refined spatial distribution map of sewage;

[0081] Sewage treatment area to be optimized module: obtaining the sewage treatment area to be optimized according to the refined spatial distribution map of sewage and the processed data;

[0082] Location module: obtaining the location of the sewage treatment facilities to be constructed according to the sewage treatment area to be optimized and the processed data;

[0083] Scale module: obtaining the scale of the sewage treatment facilities to be constructed according to the sewage treatment area to be optimized, the processed data and the location of the sewage treatment facilities to be constructed.

[0084] In this embodiment, the refined spatial distribution of domestic sewage is simulated first, and then the sewage treatment area to be optimized is obtained, so as to provide theoretical support for the optimization of facility layout and obtain a more accurate location for the sewage treatment facilities to be built. Finally, the scale of the sewage treatment facilities to be built is obtained based on the above data, so as to flexibly adjust the capacity of the facilities according to the service requirements of different regions, thereby maximizing the service efficiency and minimizing the cost.

[0085] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, rather than limiting the implementation manners of the present invention. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to enumerate all the implementation manners here. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the claims of the present invention.

Claims

1. A method for optimizing the location and scale of sewage treatment facilities, characterized in that, Including: S1: Obtain data related to the location and scale of sewage treatment facilities, and perform preprocessing to obtain preprocessed data; S2: Based on the processed data, conduct a refined spatial distribution simulation of domestic sewage to obtain a refined spatial distribution map of sewage; S3: Based on the refined spatial distribution map of sewage and the processed data, obtain the sewage treatment area to be optimized; S4: Based on the sewage treatment area to be optimized and the processed data, obtain the location of the sewage treatment facility to be constructed; S5: Based on the sewage treatment area to be optimized, the processed data, and the location of the sewage treatment facility to be constructed, obtain the scale of the sewage treatment facility to be constructed.

2. The sewage treatment facility site selection and scale optimization method according to claim 1, wherein In step S1, the data related to the location and scale of sewage treatment facilities include: demographic data, district- and county-level administrative boundary data, land use data, DEM data, road data, POI data, building outline data, Tencent location big data, night light data, wind direction data, settlement data, slope data, and river distance data.

3. The method for optimizing the location and scale of a sewage treatment facility according to claim 2, wherein, In step S1, when performing preprocessing, the preprocessed data obtained include: Demographic data: Obtain the population number, age-specific fertility rate and total fertility rate of women of childbearing age, male and female mortality rates, and migration rates; Land use type data: Use the projection coordinate system WGS84-UTM to reclassify 25 land use types into 6 categories; DEM data: Use the projection coordinate system WGS84-UTM, and resample the raster size to 100m×100m using the nearest neighbor method; Road data: Clip the vector layer of provincial road data at a scale of 1:1,000,000 to obtain the road data of the study area. Use the Euclidean distance tool to obtain the Euclidean distance raster layer of the nearest road from the vector layer, and resample the raster size to 100m×100m using the nearest neighbor method; Building outline: Convert the surface elements into point elements through ArcGIS tools; POI data, Tencent location big data, and building points: Use the kernel density analysis tool to convert the vector point layers of 14 types of POIs, the Tencent location big data layer, and building points into 16 density raster layers, and resample the raster size to 100m×100m using the nearest neighbor method; Night light data: Perform stitching and clipping to obtain the light data of the study area, resample the raster size to 100m×100m using the nearest neighbor method, and at the same time use the projection coordinate system WGS84-UTM; Clean the wind direction data and vectorize it.

4. The method for optimizing the location and scale of a sewage treatment facility according to claim 2, characterized in that, In step S2, it includes: Construct an XGBoost model and a multi-source data feature library; input the multi-source data feature library into the XGBoost model to obtain the weight values of the population distribution indicative factors; Couple the land use multi-objective optimization model, set the objective function and constraints, and use the multi-objective genetic algorithm (NSGA-II) to optimize the land use quantity structure; calculate the transfer matrix based on the optimized land use structure, and combine the local land use characteristics and references to construct a suitability atlas. Input the transfer matrix and the suitability atlas into the CA-Markov model to finally simulate the multi-objective optimized land use layout; Use the Leslie model to predict the future population size; After determining the weight values of the indicative factors of population distribution, the land use layout, and the layer of indicative factors of population distribution, use ArcGIS tools to generate a refined future population spatial distribution map that couples with the multi-objective optimization model of land use through the zonal density method; combine the future per capita comprehensive domestic sewage, and multiply the predicted per capita sewage generation amount made into raster data by the refined future population spatial distribution layer to obtain the refined spatial distribution map of sewage.

5. A method for optimizing the location and scale of sewage treatment facilities according to claim 4, characterized in that, The multi-source data feature library includes: feature data and label data; the feature data consists of 19 indicative factors of population distribution, covering Tencent location big data, 14 types of POIs data, night light data, road data, elevation, and building outlines; the label data is composed of the logarithm of the predicted population in the study area.

6. The method for optimizing the location and scale of a sewage treatment facility according to claim 1, wherein In step S3, it includes: evaluating the service capacity of existing sewage treatment facilities based on the optimal supply-demand allocation model: input the refined spatial distribution data of comprehensive domestic sewage and the sewage volume at each point as demand point data into the optimal supply-demand allocation model, and input the existing sewage treatment facilities and their scales as supply point data; take minimizing the pipeline cost as the objective function and use the Euclidean distance for analysis; finally, obtain the coverage of the service capacity of existing sewage treatment facilities, identify the areas with unbalanced supply and demand, and obtain the sewage treatment areas to be optimized.

7. A method for optimizing the site selection and scale of sewage treatment facilities according to claim 2, characterized in that, In step S4, it includes: First, select settlement points, slope, wind direction, road distance, river distance, water bodies and construction land after multi-objective optimization to make an atlas of the suitability of sewage treatment facility siting; set prohibited construction areas, including areas with a slope greater than 15°, within 50m of the road, within 300m of the settlement point, within 100m of the river, water bodies and existing construction land as prohibited construction areas; combine the slope, wind direction, and distances from the river and the road, determine the weights of each factor according to the analytic hierarchy process, sort the suitability of sewage treatment facility siting, and set the prohibited construction areas as areas "unsuitable" for building sewage treatment facilities. Finally, obtain the atlas of the suitability of sewage treatment facility siting. According to the suitability atlas, select alternative points for sewage treatment facilities from the areas of the two levels of "suitable" and "very suitable", and select the siting of the sewage treatment facilities to be built from the alternative points through two location models, namely the P-median model and the maximum coverage model.

8. A method for optimizing the location and scale of a sewage treatment facility according to claim 1, characterized in that, In step S5, it includes: Through the quadratic programming model, according to the sewage treatment areas to be optimized, the processed data, and the siting of the sewage treatment facilities to be built, with minimizing the standard deviation of accessibility as the optimization objective, obtain the scale of the sewage treatment facilities to be built.

9. The method for optimizing the site selection and scale of a sewage treatment facility according to claim 8, wherein, In step S5, it includes: predicting the future per capita comprehensive domestic sewage, calculating the total generated sewage volume in the predicted year, and the difference between the sewage volume in the predicted year and the scale of the existing sewage treatment facilities is the sewage volume not covered by the existing sewage treatment facilities; taking the sewage volume not covered by the existing sewage treatment facilities as the scale of the sewage treatment facilities to be built and evenly distributing it to the two sewage treatment facilities to be built as the initial scale; then, calculating the distance and demand volume between each sewage treatment facility to be built and the uncovered demand points, inputting them into the programming tool, and optimizing the scale through the quadratic programming model; finally, respectively optimizing the initial scale of the sewage treatment facilities to be built selected by the P-median model; verifying the optimized results through the optimal supply-demand allocation model, obtaining the accessibility analysis of the optimized sewage treatment facilities, and finally generating the visualization results; by comparing different layout and scale schemes, preferentially selecting the most suitable facility configuration scheme to obtain the scale of the sewage treatment facilities to be built.

10. A sewage treatment facility location and scale optimization system, characterized in that, It includes: Acquisition and preprocessing module: acquiring the data related to the location selection and scale of sewage treatment facilities, and performing preprocessing to obtain the preprocessed data; Sewage distribution module: simulating the refined spatial distribution of domestic sewage according to the processed data to obtain the refined spatial distribution map of sewage; Sewage treatment area to be optimized module: obtaining the sewage treatment area to be optimized according to the refined spatial distribution map of sewage and the processed data; Location selection module: obtaining the location selection of the sewage treatment facilities to be built according to the sewage treatment area to be optimized and the processed data; Scale module: obtaining the scale of the sewage treatment facilities to be built according to the sewage treatment area to be optimized, the processed data, and the location selection of the sewage treatment facilities to be built.

Images