Sewage treatment method and system based on simulation analysis

Abstract

The invention discloses a sewage treatment method and system based on simulation analysis, and the method comprises the steps: firstly, dividing a polluted water body region into K sub-regions, carrying out the microalgae putting and pollution monitoring of each sub-region based on a preset microalgae regulation and control scheme in a measurement time period, and collecting measurement data and pollution condition data; migration coefficients, growth coefficients and pollution change rates of the sub-regions are calculated by periodically analyzing migration, growth and pollution changes of the microalgae. Performing linear fitting by taking the migration coefficient and the growth coefficient as independent variables and the pollution change rate as a dependent variable, and searching an optimal fitting parameter through a gradient descent optimization algorithm to obtain a fitting equation of each sub-region; further, the sub-regions are grouped based on migration and growth characteristics. And searching local and global optimal solutions by taking pollution change rate minimization as a target through a Bayesian optimization algorithm, and setting an optimal microalgae regulation and control scheme for each region group in combination with microalgae resources so as to realize efficient treatment of polluted water.

Description

Technical Field

[0001] The present invention relates to the field of sewage data analysis, and more specifically, to a sewage treatment method and system based on simulation analysis. Background Art

[0002] With the acceleration of the industrialization process and the improvement of the urbanization level, the problem of water pollution has become increasingly serious, posing a huge threat to the environment and human health. Traditional sewage treatment methods often have problems such as low efficiency, high cost, and large resource consumption, and it is difficult to meet the growing environmental protection requirements. In recent years, microalgae have attracted wide attention in the field of water pollution treatment due to their high-efficiency sewage purification ability and potential for biomass energy production.

[0003] However, in traditional water pollution and microalgae treatment analysis technologies, there is often a lack of correlation analysis of the migration and growth characteristics of microalgae, a lack of regional pollution change analysis for water body areas, etc., and there is no local plan layout of microalgae plans for different small-scale areas, and a lack of global plan layout for the overall area, resulting in insufficient microalgae regulation ability. Therefore, there is an urgent need for an efficient and intelligent sewage treatment method based on microalgae at present. Summary of the Invention

[0004] The present invention overcomes the defects of the prior art and provides a sewage treatment method and system based on simulation analysis.

[0005] The first aspect of the present invention provides a sewage treatment method based on simulation analysis, including: Based on the basic information of the polluted water body area, divide the polluted water body area into K water body sub-areas; In a measurement time period, based on a preset microalgae regulation plan, carry out microalgae injection and pollution monitoring on each water body sub-area, collect the microalgae measurement data and pollution situation data of each water body sub-area, periodically analyze the microalgae measurement data and pollution situation data, and conduct microalgae migration analysis, microalgae growth analysis and pollution change analysis on the water body sub-areas, and calculate the microalgae-based migration coefficient, growth coefficient and pollution change rate in multiple cycles; Set the migration coefficient and growth coefficient as independent variables, the pollution change rate as the dependent variable, set weight coefficients Q1 and Q2 to be applied to the independent variables and conduct linear fitting, and based on the gradient descent optimization algorithm, search for the best fitting values of Q1 and Q2, and obtain the pollution fitting equation of each water body sub-area; Vectorize the data through the microalgae migration coefficient and growth coefficient in multiple cycles to obtain the migration feature vector and growth feature vector of each water body sub-area, and use the migration feature vector and growth feature vector as the clustering input for regional clustering grouping to form multiple regional groups; Based on the Bayesian optimization algorithm, in the fitting equation, the minimization of the pollution change rate is used as the objective function, and the migration coefficient and the growth coefficient are used as decision variables. Local optimal searches are performed for each regional group, and a global optimal search is performed for the overall polluted water body area to search for multiple local optimal solutions and one global optimal solution based on the migration coefficient and the growth coefficient. Based on the multiple local optimal solutions and one global optimal solution, multiple microalgae solutions are set. The pollution situation of each regional group is simulated and predicted through pollution situation data, and corresponding microalgae solutions are set for each regional group in combination with microalgae resources.

[0006] In this solution, based on the basic information of the polluted water body area, the polluted water body area is divided into K water body sub-areas, specifically: Obtain the basic information of the polluted water body area, where the basic information includes water body area, water body map contour, water body depth information, and water body pollution information. According to the basic information, the polluted water body area is divided to obtain K water body sub-areas. Each of the water body sub-areas is within a preset spatial range, and the water body characteristics within one water body sub-area are consistent.

[0007] In this solution, during a measurement time period, based on a preset microalgae regulation plan, microalgae are put into each water body sub-area and pollution is monitored. Microalgae measurement data and pollution situation data of each water body sub-area are collected, the microalgae measurement data and the pollution situation data are analyzed periodically, and microalgae migration analysis, microalgae growth analysis, and pollution change analysis are performed on the water body sub-areas to calculate the migration coefficient, growth coefficient, and pollution change rate based on microalgae in multiple cycles, specifically: During a measurement time period, based on a preset microalgae regulation plan, microalgae are put into each water body sub-area and pollution is monitored. Microalgae measurement data and pollution situation data of each water body sub-area are collected. The microalgae measurement data includes microalgae species, the quantity of various microalgae, and the total microalgae quantity, and the pollution situation data includes the concentrations of a preset variety of water body pollutants. The measurement time period is divided into multiple analysis cycles. Taking one water body sub-area as the analysis unit, based on each analysis cycle, calculate the change rates of the microalgae species quantity and the quantity of various microalgae between the analysis cycles to obtain P1 and P2 respectively. P1 represents the change rate of the microalgae species quantity, and P2 represents the average change rate of the quantity of various microalgae. Based on P1 and P2, a two-dimensional vector is set to obtain the first vector, calculate the average distance between the first vector and the corresponding first vector of the adjacent water body sub-area, and take the average distance as the migration coefficient. The distance calculation is applied to the standard Euclidean distance calculation between vectors, and the adjacent water body sub-area is the area adjacent to the one water body sub-area in terms of geographical location. The weighted average of P1 and P2 is taken to obtain the growth coefficient; Based on the pollution situation data, the pollutant concentration change is analyzed for each analysis period, and the average value of the change rates of multiple pollutants is calculated to obtain the pollution change rate.

[0008] In this solution, the migration coefficient and the growth coefficient are set as independent variables, and the pollution change rate is used as the dependent variable. The weight coefficients Q1 and Q2 are set and applied to the independent variables for linear fitting. Based on the gradient descent optimization algorithm, the best fitting values of Q1 and Q2 are searched, and the pollution fitting equation for each water body sub-region is obtained. Specifically: The migration coefficient and the growth coefficient are set as independent variables, and the pollution change rate is used as the dependent variable. The weight coefficients Q1 and Q2 are set and applied to the independent variables to obtain a fitting equation based on linear regression; Based on the gradient descent optimization algorithm, taking the difference between the result value of the fitting equation and the pollution change rate under multiple analysis periods as the loss function, through gradient descent iterative calculation, the optimal weight coefficients Q1 and Q2 are searched until the loss function converges within a preset range; Record the best fitting values of Q1 and Q2 at this time, and obtain the pollution fitting equation; Perform fitting analysis on multiple water body sub-regions to obtain the corresponding pollution fitting equations.

[0009] In this solution, the data is vectorized through the microalgae migration coefficient and growth coefficient under multiple periods to obtain the migration feature vector and growth feature vector of each water body sub-region. Taking the migration feature vector and growth feature vector as the clustering input for regional clustering grouping to form multiple regional groups. Specifically: Based on one water body sub-region, the microalgae migration coefficient and growth coefficient under multiple analysis periods are vectorized to form multi-dimensional migration feature vectors and growth feature vectors; Based on the DBSCAN clustering algorithm, taking the migration feature vector and growth feature vector of each water body sub-region as the clustering input, and each water body sub-region as the clustering unit, clustering grouping is performed on K water body sub-regions. During the clustering process, the similarity of the migration feature vectors and growth feature vectors between water body sub-regions is comprehensively considered, and multiple regional groups are formed.

[0010] In this solution, based on the Bayesian optimization algorithm, in the fitting equation, minimizing the pollution change rate is used as the objective function, and the migration coefficient and growth coefficient are used as decision variables. Local optimal search is performed for each regional group, and global optimal search is performed for the overall polluted water body region to search for multiple local optimal solutions and one global optimal solution based on the migration coefficient and growth coefficient. Specifically: For a region group, randomly select the pollution fitting equation of a water body sub-region within the region group as the current fitting equation; Based on the Bayesian optimization algorithm, in the current fitting equation, minimize the pollution change rate as the objective function, use the migration coefficient and the growth coefficient as decision variables, and set the constraint conditions with the preset decision variable range to perform iterative search for the optimal parameters, and set the obtained optimal solution as the local optimal solution; Generate multiple local optimal solutions based on multiple region groups; For the overall polluted water body region, equalize the parameters of the pollution fitting equations of K water body sub-regions to generate a mean fitting equation; Based on the Bayesian optimization algorithm, in the mean fitting equation, minimize the pollution change rate as the objective function, use the migration coefficient and the growth coefficient as decision variables, and set the constraint conditions with the preset decision variable range to perform iterative search for the optimal parameters, and set the obtained optimal solution as the global optimal solution; Each optimal solution includes an optimal migration coefficient and an optimal growth coefficient.

[0011] In this solution, for the multiple microalgae solutions set based on the local optimal solution and a global optimal solution, simulate and predict the pollution situation of each region group through the pollution situation data, and combine the microalgae resources to set the corresponding microalgae solution for each region group. Specifically: For each local optimal solution and global optimal solution, obtain the optimal migration coefficient and the optimal growth coefficient, based on the optimal migration coefficient and the optimal growth coefficient, conduct analysis of the types of microalgae input and matching of the input amount, and combine the microalgae resources to set the microalgae solution; Each local optimal solution and global optimal solution corresponds to a microalgae solution; In the pollution situation data, periodically analyze the pollution change rate of the water body sub-region, serialize and simulate and predict the pollution change rate through the ARIMA model to generate a predicted pollution change rate; Apply the microalgae solution corresponding to the local optimal solution to the corresponding region group; If the predicted pollution change rate of a water body sub-region is lower than the preset pollution rate, mark it as a general sub-region, and apply the microalgae solution corresponding to the global optimal solution to the general sub-region.

[0012] In this solution, in each of the multiple region groups, each region group includes multiple water body sub-regions.

[0013] The second aspect of the present invention also provides a sewage treatment system based on simulation analysis. The system includes: a memory and a processor. The memory includes a sewage treatment program based on simulation analysis. When the sewage treatment program based on simulation analysis is executed by the processor, the following steps are implemented: Based on the basic information of the polluted water area, K water sub-areas are divided from the polluted water area; In a measurement time period, based on a preset microalgae regulation scheme, microalgae are put into and pollution is monitored for each water sub-area, microalgae measurement data and pollution situation data of each water sub-area are collected, the microalgae measurement data and pollution situation data are periodically analyzed, and microalgae migration analysis, microalgae growth analysis and pollution change analysis are carried out on the water sub-areas, and the migration coefficient, growth coefficient and pollution change rate based on microalgae in multiple cycles are calculated; The migration coefficient and growth coefficient are set as independent variables, the pollution change rate is used as the dependent variable, weight coefficients Q1 and Q2 are set and applied to the independent variables for linear fitting, and based on the gradient descent optimization algorithm, the best fitting values of Q1 and Q2 are searched, and the pollution fitting equation of each water sub-area is obtained; Data vectorization is carried out through the microalgae migration coefficient and growth coefficient in multiple cycles to obtain the migration feature vector and growth feature vector of each water sub-area, and the migration feature vector and growth feature vector are used as the clustering input for regional clustering grouping to form multiple regional groups; Based on the Bayesian optimization algorithm, in the fitting equation, minimizing the pollution change rate is used as the objective function, the migration coefficient and growth coefficient are used as decision variables, local optimal search is carried out for each regional group, and global optimal search is carried out for the overall polluted water area, and multiple local optimal solutions and one global optimal solution based on the migration coefficient and growth coefficient are searched; Based on multiple local optimal solutions and one global optimal solution, multiple microalgae schemes are set, the pollution situation of each regional group is simulated and predicted through the pollution situation data, and combined with microalgae resources, corresponding microalgae schemes are set for each regional group.

[0014] The third aspect of the present invention further provides a computer-readable storage medium, which includes a sewage treatment program based on simulation analysis. When the sewage treatment program based on simulation analysis is executed by a processor, the steps of the sewage treatment method based on simulation analysis as described in any one of the above are realized.

[0015] The present invention discloses a sewage treatment method and system based on simulation analysis. First, the polluted water body area is divided into K sub-areas, and within a measurement time period, based on a preset microalgae regulation scheme, microalgae are put into each sub-area and pollution monitoring is carried out, and measurement data and pollution situation data are collected. By periodically analyzing the migration, growth and pollution changes of microalgae, the migration coefficient, growth coefficient and pollution change rate of the sub-areas are calculated. Taking the migration coefficient and growth coefficient as independent variables and the pollution change rate as the dependent variable, linear fitting is carried out, and the best fitting parameters are searched through the gradient descent optimization algorithm to obtain the fitting equation of each sub-area. Further, the sub-areas are grouped based on their migration and growth characteristics. Through the Bayesian optimization algorithm, with the goal of minimizing the pollution change rate, local and global optimal solutions are searched, and combined with microalgae resources, an optimal microalgae regulation scheme is set for each area group to achieve efficient treatment of the polluted water body. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The flowchart of a sewage treatment method based on simulation analysis according to the present invention is shown; Figure 2 The flowchart for obtaining the water body sub-areas of the present invention is shown; Figure 3 The block diagram of a sewage treatment system based on simulation analysis according to the present invention is shown; Figure 4 The analysis schematic diagram of the microalgae microscopic image of the present invention is shown; Figure 5 The brief block diagram of the data processing flow of a sewage treatment system based on simulation analysis according to the present invention is shown; DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] In order to more clearly understand the above objects, features and advantages of the present invention, the present invention will be further described in detail below with reference to the drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0018] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0019] Figure 1 The flowchart of a sewage treatment method based on simulation analysis according to the present invention is shown.

[0020] As Figure 1 shown, in the first aspect of the present invention, a sewage treatment method based on simulation analysis is provided, including: S102, based on the basic information of the polluted water area, dividing the polluted water area into K water sub-areas; S104, in a measurement time period, based on a preset microalgae control scheme, microalgae release and pollution monitoring are performed on each water body sub-area, microalgae measurement data and pollution situation data of each water body sub-area are collected, the microalgae measurement data and pollution situation data are periodically analyzed, and microalgae migration analysis, microalgae growth analysis and pollution change analysis are performed on the water body sub-area, and a migration coefficient, growth coefficient and pollution change rate based on microalgae are calculated under multiple cycles; S106, setting the migration coefficient and the growth coefficient as independent variables, the pollution change rate as the dependent variable, setting the weight coefficients Q1 and Q2 to apply to the independent variables and performing linear fitting, searching for the best fitting values of Q1 and Q2 based on the gradient descent optimization algorithm, and obtaining the pollution fitting equation for each water body sub-area; S108, performing data vectorization through the migration coefficient and growth coefficient of microalgae under multiple cycles to obtain the migration characteristic vector and growth characteristic vector of each water body sub-region, and performing regional clustering grouping using the migration characteristic vector and the growth characteristic vector as clustering input to form multiple regional groups; S110, based on the Bayesian optimization algorithm, in the fitting equation, the minimization of the pollution change rate is used as the objective function, the migration coefficient and the growth coefficient are used as decision variables, a local optimal search is performed for each regional group, and a global optimal search is performed for the entire polluted water area, and multiple local optimal solutions and a global optimal solution based on the migration coefficient and the growth coefficient are searched out; S112, multiple microalgae solutions are set based on the local optimal solution and a global optimal solution, the pollution situation of each regional group is predicted through pollution situation data simulation, and the corresponding microalgae solution is set for each regional group in combination with the microalgae resources.

[0021] Figure 2 The flow chart of obtaining water body sub-regions of the present invention is shown; According to an embodiment of the present invention, the polluted water area is divided into K water body sub-areas based on the basic information of the polluted water area, specifically: S202, obtaining basic information of the polluted water area, the basic information including water area, water map outline, water depth information, and water pollution information; S204, dividing the polluted water area into regions according to the basic information to obtain K water body sub-regions; S206: Each of the water body sub-regions is within a preset spatial range, and water body characteristics within a water body sub-region are consistent.

[0022] It should be noted that the preset spatial range is specifically an area range. In addition, based on the needs of pollution research, areas with the same pollution characteristics can be grouped.

[0023] According to an embodiment of the present invention, in a measurement time period, based on a preset microalgae regulation scheme, microalgae are put and pollution is monitored for each water body sub-region, microalgae measurement data and pollution situation data of each water body sub-region are collected, the microalgae measurement data and the pollution situation data are periodically analyzed, microalgae migration analysis, microalgae growth analysis and pollution change analysis are performed on the water body sub-region, and a migration coefficient, a growth coefficient and a pollution change rate based on microalgae in multiple cycles are calculated. Specifically: In a measurement time period, based on a preset microalgae regulation scheme, microalgae are put and pollution is monitored for each water body sub-region, and microalgae measurement data and pollution situation data of each water body sub-region are collected; The microalgae measurement data includes microalgae species, the quantity of various microalgae, and the total quantity of microalgae, and the pollution situation data includes the concentrations of a preset variety of water body pollutants; The measurement time period is divided into multiple analysis cycles, with a water body sub-region as an analysis unit. Based on each analysis cycle, the change rates of the microalgae species quantity and the quantity of various microalgae between the analysis cycles are calculated to obtain P1 and P2 respectively. P1 represents the change rate of the microalgae species quantity, and P2 represents the average change rate of the quantity of various microalgae; Based on P1 and P2, a two-dimensional vector is set to obtain a first vector, and the average distance between the first vector and the corresponding first vector of the adjacent water body sub-region is calculated, and the average distance is used as the migration coefficient; The distance calculation is applied to the standard Euclidean distance calculation between vectors, and the adjacent water body sub-region is the region adjacent to the said water body sub-region in terms of geographical location; P1 and P2 are weighted and averaged to obtain the growth coefficient; Based on the pollution situation data, pollutant concentration change analysis is performed on each analysis cycle, and the average value of the change rates of various pollutants is calculated to obtain the pollution change rate.

[0024] It should be noted that the preset microalgae regulation scheme includes information such as microalgae resource input quantity, input species, input frequency, etc. The preset variety of water body pollutants includes a variety of preset pollutants such as ammonia nitrogen, nitrate, heavy metals, polycyclic aromatic hydrocarbons, etc., and these pollutants can be treated and degraded by microalgae. In the weighted average, the weight is a value set by the user. The migration coefficient can effectively reflect the migration trend of microalgae in a sub-region, and is obtained through the differential analysis of the microalgae quantity characteristics of relevant adjacent regions. The larger this value is, the stronger the migration trend is, and the lower the microalgae richness in this region will be over time.

[0025] Based on each analysis period, calculate the change rates of the number of microalgae species and the numbers of various microalgae between the analysis periods to obtain P1 and P2. Specifically, calculate the change rate of the number of microalgae species between adjacent analysis periods to obtain P1, and do the same for the numbers of microalgae. Moreover, finally average the change rates of multiple microalgae to obtain P2.

[0026] According to an embodiment of the present invention, set the migration coefficient and the growth coefficient as independent variables, and the pollution change rate as the dependent variable. Set the weight coefficients Q1 and Q2 and apply them to the independent variables for linear fitting. Based on the gradient descent optimization algorithm, search for the best fitting values of Q1 and Q2, and obtain the pollution fitting equation for each water body sub-region. Specifically: Set the migration coefficient and the growth coefficient as independent variables, and the pollution change rate as the dependent variable. Set the weight coefficients Q1 and Q2 and apply them to the independent variables to obtain a fitting equation based on linear regression; Based on the gradient descent optimization algorithm, use the difference between the result value of the fitting equation and the pollution change rate under multiple analysis periods as the loss function. Through gradient descent iterative calculation, search for the optimal weight coefficients Q1 and Q2 until the loss function converges within a preset range; Record the best fitting values of Q1 and Q2 at this time, and obtain the pollution fitting equation; Perform fitting analysis on multiple water body sub-regions to obtain corresponding pollution fitting equations.

[0027] It should be noted that the specific function of the pollution fitting equation is to explore the correlation between the migration trend and the growth trend with respect to the pollution change. And in the embodiment of the present invention, separate fitting analysis is performed on multiple sub-regions to explore the pollution characteristics and microalgae treatment characteristics of the water body region.

[0028] The pollution fitting equation is specifically: ; Wherein, is the pollution change rate, Q1 and Q2 are the fitting weight coefficients, is the migration coefficient, is the growth coefficient.

[0029] According to an embodiment of the present invention, vectorize the data through the microalgae migration coefficient and growth coefficient under multiple cycles to obtain the migration feature vector and the growth feature vector of each water body sub-region. Use the migration feature vector and the growth feature vector as the clustering input for regional clustering grouping to form multiple region groups. Specifically: Based on a water body sub-region, vectorize the microalgae migration coefficient and growth coefficient under multiple analysis periods to form multi-dimensional migration feature vectors and growth feature vectors; Based on the DBSCAN clustering algorithm, using the migration feature vector and growth feature vector of each water body sub-region as the clustering input, and each water body sub-region as the clustering unit, cluster and group the K water body sub-regions. During the clustering process, comprehensively consider the similarity of the migration feature vectors and growth feature vectors between water body sub-regions, and form multiple regional groups.

[0030] It should be noted that both the migration feature vector and the growth feature vector include data in multiple dimensions, and the numerical value of each dimension corresponds to a migration coefficient or a growth coefficient. In the clustering grouping, the similarity of the input feature vectors can be calculated by the standard Euclidean distance.

[0031] According to the embodiment of the present invention, for the Bayesian optimization algorithm, in the fitting equation, taking the minimization of the pollution change rate as the objective function, and the migration coefficient and growth coefficient as the decision variables, perform local optimal search for each regional group, and perform global optimal search for the overall polluted water body region, and search for multiple local optimal solutions and one global optimal solution based on the migration coefficient and growth coefficient. Specifically: For a regional group, randomly select the pollution fitting equation of a water body sub-region within the regional group as the current fitting equation; Based on the Bayesian optimization algorithm, in the current fitting equation, taking the minimization of the pollution change rate as the objective function, and the migration coefficient and growth coefficient as the decision variables, set the constraint conditions with the preset decision variable range to perform iterative search for the optimal parameters, and set the obtained optimal solution as the local optimal solution; Generate multiple local optimal solutions based on multiple regional groups; For the overall polluted water body region, perform parameter averaging on the pollution fitting equations of the K water body sub-regions to generate a mean fitting equation; Based on the Bayesian optimization algorithm, in the mean fitting equation, taking the minimization of the pollution change rate as the objective function, and the migration coefficient and growth coefficient as the decision variables, set the constraint conditions with the preset decision variable range to perform iterative search for the optimal parameters, and set the obtained optimal solution as the global optimal solution; Each optimal solution includes an optimal migration coefficient and an optimal growth coefficient.

[0032] It should be noted that the preset decision variable range includes the reasonable change range of the migration coefficient and the growth coefficient. The parameter averaging of the pollution fitting equations of the K water body sub-regions to generate a mean fitting equation means performing mean calculation on the corresponding weight coefficients Q1 and Q2, setting the averaged fitting equation, and analyzing the averaged fitting equation as the fitting equation of the overall water body region.

[0033] According to an embodiment of the present invention, for multiple microalgae schemes, they are set based on local optimal solutions and a global optimal solution. By simulating and predicting the pollution situation data of each regional group, combined with microalgae resources, corresponding microalgae schemes are set for each regional group. Specifically: For each local optimal solution and global optimal solution, obtain the optimal migration coefficient and optimal growth coefficient. Based on the optimal migration coefficient and optimal growth coefficient, conduct analysis on the types of microalgae input and matching of input amounts, and combined with microalgae resources, set the microalgae scheme; Each local optimal solution and global optimal solution corresponds to a microalgae scheme; In the pollution situation data, periodically analyze the pollution change rate of the water body sub-region, serialize and simulate the prediction of the pollution change rate through the ARIMA model, and generate the predicted pollution change rate; For the microalgae scheme corresponding to the local optimal solution, apply it to the corresponding regional group; If the predicted pollution change rate of a water body sub-region is lower than the preset pollution rate, mark it as a general sub-region, and apply the microalgae scheme corresponding to the global optimal solution to the general sub-region.

[0034] It should be noted that in the analysis of the types of microalgae input and matching of input amounts, based on the migration coefficient and growth coefficient, analyze the migration trend and growth requirements, and set the types, total amounts, release frequencies, etc. of the corresponding microalgae to form a microalgae scheme. Each regional group corresponds to a local optimal solution.

[0035] For each microalgae scheme corresponding to the generated local optimal solution, it can be applied to multiple water body sub-regions within the regional group. At the same time, based on the pollution situation, if the change rate of a certain sub-region is lower than the preset value, it can be applied based on the globally optimized microalgae scheme. The globally optimized microalgae scheme is a general scheme, and the cost of the microalgae scheme is often low. Therefore, it can be applied to regions with little pollution change to achieve cost reduction and efficiency improvement in microalgae treatment.

[0036] According to an embodiment of the present invention, in the multiple regional groups, each regional group includes multiple water body sub-regions.

[0037] It is worth mentioning here that in traditional water pollution and microalgae treatment analysis technologies, there is often a lack of correlation analysis of the migration and growth characteristics of microalgae, a lack of regional pollution change analysis for water body regions, etc., and there is no clear local scheme layout of microalgae schemes for different small-scale regions, and a lack of global scheme layout for the overall region, resulting in insufficient microalgae regulation ability. The embodiments of the present invention can effectively solve the above technical problems.

[0038] According to an embodiment of the present invention, in the pollution situation data, the pollution change rate of the water body sub-region is periodically analyzed, and the ARIMA model is used to serialize and simulate and predict the pollution change rate to generate a predicted pollution change rate. It further includes: Serialize the historical analyzed pollution change rate data of multiple water body sub-regions to form training data; Construct an ARIMA model, import the training data into the ARIMA model for prediction training, and determine the p, d, and q parameters of the model; Based on multiple analysis cycles, numerically serialize the pollution change rate of the water body sub-region to form a first sequence, import the first sequence into the ARIMA model for multiple predictions, and generate multiple predicted values; Respectively form a pollution change rate sequence with the multiple predicted values and the first sequence, perform a pollution change rate trend prediction based on the pollution fitting equation of the water body sub-region, and determine whether the prediction trend of the pollution change rate sequence is consistent with the prediction trend of the pollution fitting equation. If they are consistent, mark the corresponding predicted value as the predicted pollution change rate of the water body sub-region.

[0039] It should be noted that p represents the autoregressive order of the time series, d represents the differencing order of the time series, and q represents the moving average order of the time series. Whether the prediction trends are consistent is based on deviation analysis of the predicted values and the predicted data of the equation.

[0040] In a complex water body environment, in addition to predicting pollution changes through the ARIMA model, it is also necessary to screen the predicted data to effectively screen various change trends. Based on this, the present invention can initially generate multiple pollution change trends for sub-region prediction through the ARIMA model, screen the predicted values that converge to the relevant error range based on the fitting equation (i.e., the predicted values with consistent prediction trends), so as to obtain accurate multiple pollution change trends, and further apply them to the set microalgae plan to efficiently treat water body pollution. A predicted pollution change rate of a water body sub-region can include multiple.

[0041] Figure 3 Shows a block diagram of a sewage treatment system based on simulation analysis according to the present invention.

[0042] The second aspect of the present invention also provides a sewage treatment system 2 based on simulation analysis. The system includes: a memory 31 and a processor 32. The memory 31 includes a sewage treatment program based on simulation analysis. When the sewage treatment program based on simulation analysis is executed by the processor 32, the following steps are implemented: Based on the basic information of the polluted water body area, divide the polluted water body area into K water body sub-regions; During a measurement period, based on a preset microalgae regulation plan, microalgae are put into each water body sub-region and pollution monitoring is carried out. Microalgae measurement data and pollution situation data of each water body sub-region are collected, the microalgae measurement data and pollution situation data are periodically analyzed, and microalgae migration analysis, microalgae growth analysis and pollution change analysis are carried out on the water body sub-region. The migration coefficient, growth coefficient and pollution change rate based on microalgae under multiple cycles are calculated; The migration coefficient and growth coefficient are set as independent variables, and the pollution change rate is used as the dependent variable. Weight coefficients Q1 and Q2 are set and applied to the independent variables for linear fitting. Based on the gradient descent optimization algorithm, the best fitting values of Q1 and Q2 are searched, and the pollution fitting equation of each water body sub-region is obtained; Data vectorization is carried out through the microalgae migration coefficient and growth coefficient under multiple cycles to obtain the migration feature vector and growth feature vector of each water body sub-region. The migration feature vector and growth feature vector are used as clustering inputs for regional clustering grouping to form multiple regional groups; Based on the Bayesian optimization algorithm, in the fitting equation, the minimization of the pollution change rate is used as the objective function, and the migration coefficient and growth coefficient are used as decision variables. Local optimal search is carried out for each regional group, and global optimal search is carried out for the overall polluted water body region to search for multiple local optimal solutions and one global optimal solution based on the migration coefficient and growth coefficient; Based on the local optimal solutions and one global optimal solution, multiple microalgae plans are set. The pollution situation of each regional group is simulated and predicted through the pollution situation data, and combined with microalgae resources, corresponding microalgae plans are set for each regional group.

[0043] According to the embodiments of the present invention, based on the basic information of the polluted water body region, the polluted water body region is divided into K water body sub-regions, specifically: Obtain the basic information of the polluted water body region, and the basic information includes water body area, water body map contour, water body depth information, and water body pollution information; According to the basic information, the polluted water body region is divided to obtain K water body sub-regions; Each water body sub-region is within a preset spatial range, and the water body characteristics within one water body sub-region are consistent.

[0044] It should be noted that the preset spatial range is specifically an area range. In addition, based on the needs of pollution research, regions with the same pollution characteristics can be grouped.

[0045] According to an embodiment of the present invention, during a measurement time period, based on a preset microalgae regulation scheme, microalgae are put into each water body sub-region and pollution monitoring is carried out, microalgae measurement data and pollution situation data of each water body sub-region are collected, the microalgae measurement data and pollution situation data are periodically analyzed, microalgae migration analysis, microalgae growth analysis and pollution change analysis are carried out on the water body sub-region, and migration coefficients, growth coefficients and pollution change rates based on microalgae in multiple cycles are calculated. Specifically: During a measurement time period, based on a preset microalgae regulation scheme, microalgae are put into each water body sub-region and pollution monitoring is carried out, and microalgae measurement data and pollution situation data of each water body sub-region are collected; The microalgae measurement data includes microalgae species, the quantity of various microalgae, and the total quantity of microalgae, and the pollution situation data includes the concentrations of a preset variety of water body pollutants; The measurement time period is divided into multiple analysis cycles. Taking one water body sub-region as an analysis unit, based on each analysis cycle, the change rates of the microalgae species quantity and the quantity of various microalgae between the analysis cycles are calculated to obtain P1 and P2 respectively. P1 represents the change rate of the microalgae species quantity, and P2 represents the average change rate of the quantity of various microalgae; Based on P1 and P2, a two-dimensional vector is set to obtain a first vector, and the average distance between the first vector and the corresponding first vector of the adjacent water body sub-region is calculated, and the average distance is used as the migration coefficient; The distance calculation is applied to the standard Euclidean distance calculation between vectors. The adjacent water body sub-region is the region adjacent to the said one water body sub-region in terms of geographical location; P1 and P2 are weighted and averaged to obtain the growth coefficient; Based on the pollution situation data, the change analysis of the pollutant concentration is carried out for each analysis cycle, and the average value of the change rates of various pollutants is calculated to obtain the pollution change rate.

[0046] It should be noted that the preset microalgae regulation scheme includes information such as the microalgae resource input quantity, input species, input frequency, etc. The preset variety of water body pollutants includes a variety of preset pollutants such as ammonia nitrogen, nitrate, heavy metals, polycyclic aromatic hydrocarbons, etc., and these pollutants can be treated and degraded by microalgae. In the weighted average, the weight is a value set by the user. The migration coefficient can effectively reflect the migration trend of microalgae in a sub-region, and is obtained through the differential analysis of the microalgae quantity characteristics of relevant adjacent regions. The larger this value is, the stronger the migration trend is, and the longer the time is, the lower the microalgae richness in this region will be.

[0047] In the step of calculating the change rates of the microalgae species quantity and the quantity of various microalgae between the analysis cycles to obtain P1 and P2 based on each analysis cycle, specifically, the change rate of the microalgae species quantity between adjacent analysis cycles is calculated to obtain P1, and the same applies to the microalgae quantity. Finally, the change rates of various microalgae are averaged to obtain P2.

[0048] According to the embodiments of the present invention, the migration coefficient and the growth coefficient are set as independent variables, the pollution change rate is used as the dependent variable, weight coefficients Q1 and Q2 are set and applied to the independent variables for linear fitting. Based on the gradient descent optimization algorithm, the optimal fitting values of Q1 and Q2 are searched, and the pollution fitting equation for each water body sub-region is obtained. Specifically: The migration coefficient and the growth coefficient are set as independent variables, the pollution change rate is used as the dependent variable, and weight coefficients Q1 and Q2 are set and applied to the independent variables to obtain a fitting equation based on linear regression; Based on the gradient descent optimization algorithm, taking the difference between the result value of the fitting equation and the pollution change rate in multiple analysis periods as the loss function, through gradient descent iterative calculation, the optimal weight coefficients Q1 and Q2 are searched until the loss function converges within a preset range; Record the optimal fitting values of Q1 and Q2 at this time, and obtain the pollution fitting equation; Perform fitting analysis on multiple water body sub-regions to obtain corresponding pollution fitting equations.

[0049] It should be noted that the specific function of the pollution fitting equation is to explore the correlation between the migration trend and the growth trend with respect to pollution changes. And in the embodiments of the present invention, fitting analysis is performed separately on multiple sub-regions to explore the pollution characteristics and microalgae treatment characteristics of the water body region.

[0050] The pollution fitting equation is specifically: ; Wherein, is the pollution change rate, Q1 and Q2 are the fitting weight coefficients, is the migration coefficient, is the growth coefficient.

[0051] According to the embodiments of the present invention, the microalgae migration coefficient and growth coefficient in multiple periods are vectorized to obtain the migration feature vector and growth feature vector of each water body sub-region. Using the migration feature vector and growth feature vector as the clustering input for regional clustering grouping to form multiple regional groups. Specifically: Based on a water body sub-region, the microalgae migration coefficient and growth coefficient in multiple analysis periods are vectorized to form multi-dimensional migration feature vectors and growth feature vectors; Based on the DBSCAN clustering algorithm, using the migration feature vector and growth feature vector of each water body sub-region as the clustering input, and each water body sub-region as the clustering unit, clustering grouping is performed on K water body sub-regions. During the clustering process, the similarity of the migration feature vectors and growth feature vectors between water body sub-regions is comprehensively considered, and multiple regional groups are formed.

[0052] It should be noted that both the migration feature vector and the growth feature vector include data in multiple dimensions, and the value of each dimension corresponds to a migration coefficient or a growth coefficient. In the clustering grouping, the similarity of the input feature vectors can be calculated by the standard Euclidean distance.

[0053] According to an embodiment of the present invention, in the Bayesian optimization algorithm, in the fitting equation, minimizing the pollution change rate is used as the objective function, and the migration coefficient and the growth coefficient are used as decision variables. For each regional group, local optimal search is performed, and for the overall polluted water body area, global optimal search is performed to search for multiple local optimal solutions and one global optimal solution based on the migration coefficient and the growth coefficient. Specifically: For a regional group, randomly select the pollution fitting equation of a water body sub-region within the regional group as the current fitting equation; Based on the Bayesian optimization algorithm, in the current fitting equation, minimizing the pollution change rate is used as the objective function, the migration coefficient and the growth coefficient are used as decision variables, and the constraint conditions are set with a preset decision variable range to perform iterative search for optimal parameters, and the obtained optimal solution is set as the local optimal solution; Generate multiple local optimal solutions based on multiple regional groups; For the overall polluted water body area, parameter averaging is performed on the pollution fitting equations of K water body sub-regions to generate a mean fitting equation; Based on the Bayesian optimization algorithm, in the mean fitting equation, minimizing the pollution change rate is used as the objective function, the migration coefficient and the growth coefficient are used as decision variables, and the constraint conditions are set with a preset decision variable range to perform iterative search for optimal parameters, and the obtained optimal solution is set as the global optimal solution; Each optimal solution includes an optimal migration coefficient and an optimal growth coefficient.

[0054] It should be noted that the preset decision variable range includes the reasonable change range of the migration coefficient and the growth coefficient. The parameter averaging of the pollution fitting equations of K water body sub-regions to generate a mean fitting equation means that the corresponding weight coefficients Q1 and Q2 are averaged, a homogenized fitting equation is set, and the mean fitting equation is used as the fitting equation analysis of the overall water body area.

[0055] According to an embodiment of the present invention, based on the multiple microalgae schemes set by the local optimal solutions and one global optimal solution, the pollution situation of each regional group is simulated and predicted through pollution situation data, and combined with microalgae resources, the corresponding microalgae schemes are set for each regional group. Specifically: For each local optimal solution and global optimal solution, obtain the optimal migration coefficient and the optimal growth coefficient, and based on the optimal migration coefficient and the optimal growth coefficient, perform analysis on the types of microalgae input and matching of the input amount, and combine with microalgae resources to set the microalgae scheme; Each local optimal solution and the global optimal solution correspond to a microalgae solution; In the pollution situation data, the pollution change rate of the water body sub-region is analyzed periodically, and the pollution change rate is serialized and simulated and predicted through the ARIMA model to generate the predicted pollution change rate; For the microalgae solution corresponding to the local optimal solution, it is applied to the corresponding regional group; If the predicted pollution change rate of a water body sub-region is lower than the preset pollution rate, it is marked as a general sub-region, and the general sub-region is applied based on the microalgae solution corresponding to the global optimal solution.

[0056] It should be noted that in the analysis of the types of microalgae input and the matching of the input amount, based on the migration coefficient and the growth coefficient, the migration trend and growth requirements are analyzed, and the types, total amounts, release frequencies, etc. of the corresponding microalgae are set to form a microalgae solution. Each regional group corresponds to a local optimal solution.

[0057] For each microalgae solution corresponding to the generated local optimal solution, it can be applied to multiple water body sub-regions within the regional group. At the same time, based on the pollution situation, if the change rate of a certain sub-region is lower than the preset value, it can be applied based on the globally optimized microalgae solution. The globally optimized microalgae solution is a general solution, and the cost of the microalgae solution is often low. Therefore, it can be applied to regions with little pollution change to achieve cost reduction and efficiency improvement in microalgae treatment.

[0058] According to the embodiment of the present invention, in the multiple regional groups, each regional group includes multiple water body sub-regions.

[0059] It is worth mentioning here that in the traditional water pollution and microalgae treatment analysis technology, there is often a lack of correlation analysis of the migration and growth characteristics of microalgae, a lack of regional pollution change analysis for water body regions, etc., and there is no clear local solution layout of microalgae solutions for different small-scale regions, and a lack of global solution layout for the overall region, resulting in insufficient microalgae regulation ability. The embodiment of the present invention can effectively solve the above technical problems.

[0060] The third aspect of the present invention also provides a computer-readable storage medium, which includes a sewage treatment program based on simulation analysis. When the sewage treatment program based on simulation analysis is executed by a processor, the steps of the sewage treatment method based on simulation analysis as described in any one of the above are implemented.

[0061] Figure 4 The analysis schematic diagram of the microalgae microscopic image of the present invention is shown; As Figure 4 shown, the microalgae are measured and the quantity analysis and statistics are carried out based on the microscopic image.

[0062] Figure 5The figure shows a brief block diagram of the data processing flow of a sewage treatment system based on simulation analysis according to the present invention; The present invention discloses a sewage treatment method and system based on simulation analysis. First, a polluted water body area is divided into K sub-areas, and within a measurement time period, microalgae are put into and pollution is monitored in each sub-area based on a preset microalgae regulation scheme, and measurement data and pollution situation data are collected. By periodically analyzing the migration, growth, and pollution changes of microalgae, the migration coefficient, growth coefficient, and pollution change rate of the sub-areas are calculated. Taking the migration coefficient and growth coefficient as independent variables and the pollution change rate as the dependent variable, linear fitting is performed, and the best fitting parameters are searched through a gradient descent optimization algorithm to obtain the fitting equation of each sub-area. Further, the sub-areas are grouped based on their migration and growth characteristics. Through a Bayesian optimization algorithm, with the goal of minimizing the pollution change rate, local and global optimal solutions are searched, and combined with microalgae resources, an optimal microalgae regulation scheme is set for each area group to achieve efficient treatment of the polluted water body.

[0063] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical, or other forms.

[0064] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0065] In addition, each functional unit in the embodiments of the present invention can be all integrated in a processing unit, or each unit can be separately used as a unit, or two or more units can be integrated in a unit; the above integrated units can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0066] Those of ordinary skill in the art can understand that all or part of the steps to implement the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including the above method embodiments; and the foregoing storage medium includes: removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs and other various media that can store program codes.

[0067] Alternatively, if the above integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. And the foregoing storage medium includes: removable storage devices, ROM, RAM, magnetic disks, or optical discs and other various media that can store program codes.

[0068] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention.

Claims

1. A sewage treatment method based on simulation analysis, characterized in that Including: Based on the basic information of the polluted water body area, divide the polluted water body area into K water sub-areas; During a measurement period, based on a preset microalgae regulation scheme, conduct microalgae dosing and pollution monitoring for each water sub-area, collect the microalgae measurement data and pollution situation data of each water sub-area, periodically analyze the microalgae measurement data and pollution situation data, and conduct microalgae migration analysis, microalgae growth analysis and pollution change analysis for the water sub-areas, and calculate the microalgae-based migration coefficient, growth coefficient and pollution change rate in multiple cycles; Set the migration coefficient and growth coefficient as independent variables, and the pollution change rate as the dependent variable. Set the weight coefficients Q1 and Q2 and apply them to the independent variables for linear fitting. Based on the gradient descent optimization algorithm, search for the best fitting values of Q1 and Q2, and obtain the pollution fitting equation for each water sub-area; Vectorize the data through the microalgae migration coefficient and growth coefficient in multiple cycles to obtain the migration feature vector and growth feature vector of each water sub-area, and use the migration feature vector and growth feature vector as the clustering input for regional clustering grouping to form multiple regional groups; Based on the Bayesian optimization algorithm, in the fitting equation, minimize the pollution change rate as the objective function, and use the migration coefficient and growth coefficient as decision variables. Conduct local optimal search for each regional group and global optimal search for the overall polluted water body area to search for multiple local optimal solutions and one global optimal solution based on the migration coefficient and growth coefficient; Set multiple microalgae schemes based on the local optimal solutions and one global optimal solution, simulate and predict the pollution situation of each regional group through the pollution situation data, and combine the microalgae resources to set corresponding microalgae schemes for each regional group.

2. The sewage treatment method based on simulation analysis according to claim 1, characterized in that, The step of dividing the polluted water body area into K water sub-areas based on the basic information of the polluted water body area is specifically: Obtain the basic information of the polluted water body area, and the basic information includes water area, water body map contour, water depth information, and water body pollution information; According to the basic information, conduct regional division on the polluted water body area to obtain K water sub-areas; Each water sub-area is within a preset spatial range, and the water body characteristics within one water sub-area are consistent.

3. A sewage treatment method based on simulation analysis according to claim 1, characterized in that, The step of, during a measurement period, based on a preset microalgae regulation scheme, conducting microalgae dosing and pollution monitoring for each water sub-area, collecting the microalgae measurement data and pollution situation data of each water sub-area, periodically analyzing the microalgae measurement data and pollution situation data, and conducting microalgae migration analysis, microalgae growth analysis and pollution change analysis for the water sub-areas, and calculating the microalgae-based migration coefficient, growth coefficient and pollution change rate in multiple cycles is specifically: During a measurement period, based on a preset microalgae regulation scheme, conduct microalgae dosing and pollution monitoring for each water sub-area, and collect the microalgae measurement data and pollution situation data of each water sub-area; The microalgae measurement data includes microalgae species, the quantity of various microalgae, and the total microalgae quantity, and the pollution situation data includes the concentrations of preset multiple water pollutants. Divide the measurement time period into multiple analysis cycles, use a water body sub-region as the analysis unit, and based on each analysis cycle, calculate the number of microalgae species and the number of various microalgae, and obtain P1 and P2 respectively by calculating the change rates between the analysis cycles. P1 represents the change rate of the number of microalgae species, and P2 represents the average change rate of the number of various microalgae. Based on P1 and P2, set a two-dimensional vector to obtain the first vector, calculate the average distance between the first vector and the corresponding first vector of the adjacent water body sub-region, and use the average distance as the migration coefficient. The distance calculation is applied to the standard Euclidean distance calculation between vectors. The adjacent water body sub-region is the region adjacent to the said one water body sub-region in geographical location. Perform a weighted average of P1 and P2 to obtain the growth coefficient. Based on the pollution situation data, analyze the change in pollutant concentration for each analysis cycle, and calculate the mean value of the change rates of various pollutants to obtain the pollution change rate.

4. The sewage treatment method based on simulation analysis according to claim 3, characterized in that, Set the migration coefficient and the growth coefficient as independent variables, and the pollution change rate as the dependent variable. Set the weight coefficients Q1 and Q2 and apply them to the independent variables for linear fitting. Based on the gradient descent optimization algorithm, search for the best fitting values of Q1 and Q2, and obtain the pollution fitting equation for each water body sub-region. Specifically: Set the migration coefficient and the growth coefficient as independent variables, and the pollution change rate as the dependent variable. Set the weight coefficients Q1 and Q2 and apply them to the independent variables to obtain a fitting equation based on linear regression. Based on the gradient descent optimization algorithm, use the difference between the result value of the fitting equation and the pollution change rate under multiple analysis cycles as the loss function, and through gradient descent iterative calculation, search for the optimal weight coefficients Q1 and Q2 until the loss function converges within a preset range. Record the best fitting values of Q1 and Q2 at this time, and obtain the pollution fitting equation. Conduct fitting analysis on multiple water body sub-regions to obtain the corresponding pollution fitting equations.

5. A sewage treatment method based on simulation analysis according to claim 1, characterized in that, Through data vectorization of the microalgae migration coefficient and growth coefficient under multiple cycles, obtain the migration feature vector and growth feature vector of each water body sub-region, and use the migration feature vector and growth feature vector as the clustering input for regional clustering grouping to form multiple regional groups. Specifically: Based on one water body sub-region, vectorize the microalgae migration coefficient and growth coefficient under multiple analysis cycles to form multi-dimensional migration feature vectors and growth feature vectors. Based on the DBSCAN clustering algorithm, use the migration feature vector and growth feature vector of each water body sub-region as the clustering input, and use each water body sub-region as the clustering unit to cluster and group K water body sub-regions. During the clustering process, comprehensively consider the similarity of the migration feature vectors and growth feature vectors between water body sub-regions, and form multiple regional groups.

6. The sewage treatment method based on simulation analysis according to claim 1, wherein Based on the Bayesian optimization algorithm, in the fitting equation, use the minimization of the pollution change rate as the objective function, and the migration coefficient and growth coefficient as decision variables. Conduct local optimal search for each regional group and global optimal search for the overall polluted water body region, and search for multiple local optimal solutions and one global optimal solution based on the migration coefficient and growth coefficient. Specifically: For a regional group, randomly select the pollution fitting equation of a water body sub-region within the regional group as the current fitting equation; Based on the Bayesian optimization algorithm, in the current fitting equation, minimize the pollution change rate as the objective function, use the migration coefficient and the growth coefficient as decision variables, and set the constraint conditions with the preset decision variable range to perform iterative search for the optimal parameters, and set the obtained optimal solution as the local optimal solution; Generate multiple local optimal solutions based on multiple regional groups; For the overall polluted water body area, equalize the parameters of the pollution fitting equations of K water body sub-regions to generate a mean fitting equation; Based on the Bayesian optimization algorithm, in the mean fitting equation, minimize the pollution change rate as the objective function, use the migration coefficient and the growth coefficient as decision variables, and set the constraint conditions with the preset decision variable range to perform iterative search for the optimal parameters, and set the obtained optimal solution as the global optimal solution; Each optimal solution includes an optimal migration coefficient and an optimal growth coefficient.

7. The sewage treatment method based on simulation analysis according to claim 6, wherein Based on the local optimal solutions and a global optimal solution, set multiple microalgae schemes. By simulating and predicting the pollution situation data of each regional group, combined with the microalgae resources, set the corresponding microalgae scheme for each regional group, specifically: For each local optimal solution and the global optimal solution, obtain the optimal migration coefficient and the optimal growth coefficient. Based on the optimal migration coefficient and the optimal growth coefficient, conduct microalgae input type analysis and input amount matching, and combined with the microalgae resources, set the microalgae scheme; Each local optimal solution and the global optimal solution correspond to a microalgae scheme; In the pollution situation data, periodically analyze the pollution change rate of the water body sub-region. Serialize and simulate the pollution change rate through the ARIMA model to generate the predicted pollution change rate; Apply the microalgae scheme corresponding to the local optimal solution to the corresponding regional group; If the predicted pollution change rate of a water body sub-region is lower than the preset pollution rate, mark it as a general sub-region, and apply the microalgae scheme corresponding to the global optimal solution to the general sub-region.

8. A sewage treatment method based on simulation analysis according to claim 1, characterized in that In each of the multiple regional groups, each regional group includes multiple water body sub-regions.

9. A sewage treatment system based on simulation analysis, characterized in that, The system includes: a memory and a processor. The memory includes a sewage treatment program based on simulation analysis. When the sewage treatment program based on simulation analysis is executed by the processor, the following steps are implemented: Based on the basic information of the polluted water body area, divide the polluted water body area into K water body sub-regions; In a measurement time period, based on the preset microalgae regulation scheme, conduct microalgae dosing and pollution monitoring for each water body sub-region, collect the microalgae measurement data and pollution situation data of each water body sub-region, periodically analyze the microalgae measurement data and pollution situation data, and conduct microalgae migration analysis, microalgae growth analysis and pollution change analysis for the water body sub-region, and calculate the microalgae-based migration coefficient, growth coefficient and pollution change rate in multiple cycles; Set the migration coefficient and the growth coefficient as independent variables, and the pollution change rate as the dependent variable. Set the weight coefficients Q1 and Q2 to be applied to the independent variables and perform linear fitting. Based on the gradient descent optimization algorithm, search for the best fitting values of Q1 and Q2, and obtain the pollution fitting equation of each water body sub-region; Vectorize the data through the microalgae migration coefficient and growth coefficient under multiple cycles to obtain the migration feature vector and growth feature vector of each water body sub-region, and use the migration feature vector and growth feature vector as the clustering input to perform regional clustering and grouping to form multiple regional groups; Based on the Bayesian optimization algorithm, in the fitting equation, minimize the pollution change rate as the objective function, and use the migration coefficient and growth coefficient as decision variables. Conduct a local optimal search for each regional group and a global optimal search for the overall polluted water body area to search for multiple local optimal solutions and a global optimal solution based on the migration coefficient and growth coefficient; Set multiple microalgae schemes based on the local optimal solutions and a global optimal solution, simulate and predict the pollution situation of each regional group through the pollution situation data, and combine the microalgae resources to set corresponding microalgae schemes for each regional group.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a sewage treatment program based on simulation analysis. When the sewage treatment program based on simulation analysis is executed by a processor, the steps of the sewage treatment method based on simulation analysis according to any one of claims 1 to 8 are implemented.

Images