Multi-objective optimization water pollution load distribution method and system

Abstract

The invention provides a multi-objective optimization water pollution load distribution method and system, and relates to the technical field of water pollution load distribution.The method comprises the steps that a target water body is divided into a plurality of pollution areas, and historical pollution discharge data of pollution discharge ports are obtained; respectively constructing a water pollutant concentration prediction model and a treatment cost prediction model through a deep neural network for predicting the water pollution concentration and the treatment cost; according to the pollutant discharge distribution amount, the pollutant discharge flow and the like, calculating the actual pollutant discharge amount, the pollutant reduction amount and the treatment load of the sewage outlet; and finally, by taking minimization of the total treatment cost, minimization of the water pollutant concentration and minimization of the pollutant treatment load as targets and combining constraint conditions, determining an optimal distribution scheme of pollutant discharge through a genetic algorithm, thereby realizing efficient optimization of water pollution treatment.

Description

Technical Field

[0001] The present invention relates to the technical field of water pollution load allocation, and specifically to a multi-objective optimization method and system for water pollution load allocation. Background Art

[0002] With the rapid development of social economy, the processes of industrialization and urbanization have accelerated, and the problem of water body pollution has become increasingly prominent. The treatment of water body pollution has become an important task for achieving sustainable development and ensuring ecological environment safety. However, due to the wide distribution of water pollution sources, significant differences in pollution levels among regions, and significant differences in treatment capabilities and costs among different pollution sources, traditional water pollution treatment methods often struggle to effectively reduce pollutant concentrations while taking into account treatment costs and the fairness of resource allocation. Therefore, how to achieve a reasonable balance among pollutant concentration reduction, treatment cost control, and treatment fairness during the water pollution treatment process has become an important technical problem in current water pollution load allocation research.

[0003] In current research, some methods tend to single-objective optimization, such as reducing the pollutant concentration in a certain region, but ignore the economic efficiency of costs or the fairness among different regions; other methods overly focus on cost control and pay insufficient attention to the improvement effect of water environment quality. At the same time, traditional optimization algorithms also have certain limitations in terms of efficiency and accuracy in dealing with complex multi-objective problems. Therefore, there is an urgent need for a multi-objective optimization method for water pollution load allocation that can simultaneously meet the requirements of reducing pollutant concentrations, controlling treatment costs, and achieving fair distribution of treatment resources, and improve the calculation efficiency and decision-making quality through an effective optimization algorithm.

[0004] In the prior art, the published patent No. CN110619435A discloses a two-layer multi-objective optimization method for water pollution load allocation. According to the environmental Gini coefficient index and the weights of each environmental Gini coefficient index, the environmental Gini coefficient is determined; according to the two-layer multi-objective optimization water pollution load allocation model based on the minimum environmental Gini coefficient and the minimum unit pollutant emission cost, the upper-layer load allocation is carried out; according to the two-layer multi-objective optimization water pollution load allocation model based on the maximum industrial total output value and the minimum unevenness of reduction rates at each sewage outlet, the lower-layer load allocation is carried out.

[0005] The main problems of the above method are as follows: The two-layer optimization method processes the objectives in the upper and lower layers. The upper layer focuses on the environmental Gini coefficient and unit sewage discharge cost, and the lower layer focuses on industrial total output value and unevenness of reduction rates. To a certain extent, this leads to conflicts or compromises between the upper and lower layer objectives, thereby affecting the overall optimization result; the treatment fairness is mainly reflected by the environmental Gini coefficient, but the environmental carrying capacity, economic development level, and pollution treatment capacity of different regions are difficult to be fully reflected by the Gini coefficient, resulting in limited applicability of the actual allocation scheme.

[0006] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0007] The purpose of the present invention is to provide a multi-objective optimized water pollution load allocation method and system to solve the problems raised in the above background art.

[0008] To achieve the above purpose, the present invention provides the following technical solutions:

[0009] A multi-objective optimized water pollution load allocation method, the specific steps include:

[0010] Step 1: Divide the equal-area regions of the target water body into multiple pollution regions, and obtain the pollutant emission allocation amounts, treatment costs, sewage discharge flows, and pollutant emission concentrations of each sewage outlet during the previous sewage discharge time period, as well as the maximum value of the water body pollutant concentration in each pollution region during the corresponding sewage discharge time period;

[0011] Step 2: Build a water body pollutant concentration prediction model based on a deep neural network, using the sewage discharge flows and pollutant emission concentrations of all sewage outlets during the same sewage discharge time period as inputs and the maximum value of the water body pollutant concentration at the pollution region as the label to train the water body pollutant concentration prediction model;

[0012] Step 3: Calculate the actual pollutant emissions, pollutant reduction amounts, and pollutant treatment loads of each sewage outlet during the sewage discharge time period based on the pollutant emission allocation amounts, sewage discharge flows, and pollutant concentrations;

[0013] Step 4: Build a treatment cost prediction model based on a deep neural network, using the pollutant reduction amounts, sewage discharge flows, and pollutant emission concentrations of each sewage outlet during the sewage discharge time period as inputs and the treatment cost as the label to train the treatment cost prediction model;

[0014] Step 5: Obtain the total pollutant emission allocation amount during the future sewage discharge time period, generate a fitness function with the minimization of the total treatment cost, the minimization of the water body pollutant concentration, and the minimization of the pollutant treatment load as the optimization objectives, and with the constraints that the maximum value of the water body pollutant concentration in each pollution region is less than the pollutant concentration standard, the sum of the pollutant emission allocation amounts of each sewage outlet is equal to the total pollutant emission allocation amount, and the pollutant treatment load of each sewage outlet is not greater than the maximum design load. Based on the genetic algorithm, the water body pollutant concentration prediction model, and the treatment cost prediction model, obtain the optimal water pollution load allocation plan, and the optimal water pollution load allocation plan is the pollutant emission allocation amounts, sewage discharge flows, and pollutant emission concentrations of each sewage outlet during the future sewage discharge time period.

[0015] Further, the pollutant emission allocation amount is the amount of pollutants allocated to each sewage outlet; the treatment cost represents the economic cost generated by the sewage outlet reducing the pollutant emission concentration during the sewage discharge period, and is determined by collecting the historical details of sewage treatment financial expenditures; the sewage discharge flow represents the sewage discharge volume containing pollutants at each sewage outlet per unit time, and an ultrasonic flowmeter is installed at the sewage outlet for real-time monitoring; the pollutant emission concentration represents the concentration of the pollutant with the highest proportion in the wastewater at the sewage outlet during the sewage discharge period, and real-time data is obtained by installing an on-line pollutant concentration monitoring instrument at the sewage outlet. The on-line monitoring instrument includes a COD monitor and an ammonia nitrogen analyzer; the maximum value of the water body pollution concentration represents the maximum concentration of pollutants in the water body during the sewage discharge period.

[0016] Further, the principles for calculating the actual pollutant emissions, pollutant reduction amounts, and pollutant treatment loads of each sewage outlet during the sewage discharge period are as follows:

[0017] The formula for calculating the actual pollutant emissions is:

[0018] M i =Q i ·C i ·T

[0019] Wherein, M i represents the pollutant emissions of the i-th sewage outlet during the sewage discharge period, i represents the index of the sewage outlet, Q i represents the sewage discharge flow of the i-th sewage outlet, C i represents the average pollutant concentration of the i-th sewage outlet during the sewage discharge period, and T represents the duration of the sewage discharge period;

[0020] The formula for calculating the pollutant reduction amount is:

[0021] D i =F i -M i

[0022] Wherein, D i represents the pollutant reduction amount of the i-th sewage outlet, and F i represents the pollutant emission allocation amount of the i-th sewage outlet;

[0023] The formula for calculating the pollutant treatment load is:

[0024]

[0025] Wherein, L i represents the treatment load of the i-th sewage outlet per unit time.

[0026] Furthermore, with the goal of minimizing the total treatment cost, minimizing the concentration of water pollutants, and minimizing the treatment load of pollutants, the fitness function generated is as follows:

[0027]

[0028] Among them, X represents the total treatment cost, i represents the index of the sewage outlet, and i ∈ [1, N], where N represents the number of sewage outlets, S i represents the treatment cost of the i-th sewage outlet output by the treatment cost prediction model, X max represents the upper limit of the total treatment cost, j represents the index of the pollution area, and j ∈ [1, H], where H represents the number of pollution areas divided in the water body, P j represents the maximum value of the pollutant concentration in the j-th pollution area output by the water pollutant concentration prediction model, P j,std represents the expected value of the pollutant concentration in the j-th pollution area, L i,max represents the maximum design load of the i-th sewage outlet, w 1 、w 2 、w 3 respectively represent the weight coefficients, and w 1 +w 2 +w 3 =1, w 2 >w 3 >w 1 .

[0029] Furthermore, based on the genetic algorithm, the water pollutant concentration prediction model, and the treatment cost prediction model, the principle for obtaining the optimal water pollution load allocation plan is as follows:

[0030] Based on the genetic algorithm, the pollutant discharge allocation amount, sewage flow rate, and pollutant discharge concentration are encoded into chromosomes, and an initial population is randomly generated. Each individual in the population represents a set of pollutant discharge allocation amounts, sewage flow rates, and pollutant discharge concentrations, and the pollutant concentration and treatment cost are generated based on the water pollutant concentration prediction model and the treatment cost prediction model, and then the fitness function of each individual is generated;

[0031] Based on tournament selection, the individuals in the initial population are randomly arranged. After the arrangement, individuals are selected pairwise from the front and back of the initial population, the fitness function values of the individuals are calculated, and the individual with the smaller fitness function value between the two is selected as the parent. The above process is repeated until all individuals in the initial population are traversed, which is regarded as completing one round of selection. Then, crossover and mutation are randomly performed among the selected parent individuals to generate new offspring. The offspring and the parents are combined to form a new population, and the fitness function values of each individual are calculated. The individual with the lowest fitness function value is recorded as the current optimal solution. The above operations are regarded as one iteration. The maximum number of iterations is set to 100. When the number of iterations reaches 100, or the decrease amplitude of the fitness function value in 10 consecutive iterations is less than 5%, the iteration is terminated, and the individual with the lowest current fitness function value is output. The corresponding pollutant emission allocation, sewage discharge flow, and pollutant emission concentration are the allocation schemes for each sewage outlet during the future sewage discharge period.

[0032] The present invention also provides a multi-objective optimization water pollution load allocation system, which is used to implement the above multi-objective optimization water pollution load allocation method, and specifically includes:

[0033] A data acquisition module, which is used to divide the equal-area region of the target water body into multiple pollution regions, and obtain the pollutant emission allocation, treatment cost, sewage discharge flow, and pollutant emission concentration of each sewage outlet during the previous sewage discharge period, as well as the maximum value of the water body pollutant concentration in each pollution region during the corresponding sewage discharge period.

[0034] A concentration prediction module, which is used to construct a water body pollutant concentration prediction model based on a deep neural network, using the sewage discharge flow and pollutant emission concentration of all sewage outlets during the same sewage discharge period as the input, and the maximum value of the water body pollutant concentration in the pollution region as the label to train the water body pollutant concentration prediction model.

[0035] An emission calculation module, which is used to calculate the actual pollutant emissions, pollutant reduction amounts, and pollutant treatment loads of each sewage outlet during the sewage discharge period based on the pollutant emission allocation, sewage discharge flow, and pollutant concentration.

[0036] A cost prediction module, which is used to construct a treatment cost prediction model based on a deep neural network, using the pollutant reduction amounts, sewage discharge flow, and pollutant emission concentration of each sewage outlet during the sewage discharge period as the input, and the treatment cost as the label to train the treatment cost prediction model.

[0037] The comprehensive optimization module is used to obtain the total pollutant emission allocation within the future sewage discharge time period, generate a fitness function with the minimization of the total treatment cost, the minimization of the water body pollutant concentration, and the minimization of the pollutant treatment load as the optimization objectives. With the maximum water body pollutant concentration in each polluted area being less than the pollutant concentration standard, the sum of the pollutant emission allocation amounts at each sewage outlet being equal to the total pollutant emission allocation, and the pollutant treatment load at each sewage outlet not being greater than the maximum design load as the constraint conditions, based on the genetic algorithm, the water body pollutant concentration prediction model, and the treatment cost prediction model, an optimal water pollution load allocation plan is obtained. The optimal water pollution load allocation plan is the pollutant emission allocation amount, sewage discharge flow, and pollutant emission concentration of each sewage outlet within the future sewage discharge time period.

[0038] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0039] The present invention comprehensively considers the pollutant emission allocation amount, sewage discharge flow, and pollutant emission concentration; through the comprehensive utilization of regional division and historical data, the spatio-temporal variation characteristics of water body pollution can be captured more accurately, providing support for dynamic optimization. Through regional division and data collection, the treatment requirements and characteristics of each polluted area can be clarified, providing reliable inputs and constraint conditions for subsequent optimization algorithms, and contributing to the realization of systematic optimization of multiple objectives; and by comprehensively considering the pollutant emission allocation amount, sewage discharge flow, and pollutant concentration, the actual pollutant emissions, pollutant reduction amounts, and pollutant treatment loads of each sewage outlet can be accurately calculated, thus comprehensively reflecting the actual treatment capacity of the sewage outlet.

[0040] The present invention also trains the water body pollutant concentration prediction model and the treatment cost prediction model through a deep learning network, can accurately capture the complex dynamic relationship between the sewage discharge flow, pollutant concentration, and the target water body pollutant concentration, with higher prediction accuracy. The pollutant concentration and treatment cost data predicted by the model can directly guide the sewage load allocation, providing an intuitive reference basis for decision-makers, and avoiding the governance mistakes or resource waste that may be caused by uncertainties in traditional methods; by simultaneously optimizing the total treatment cost, water body pollutant concentration, and pollutant treatment load, taking into account both environmental and economic benefits, and introducing the genetic algorithm, it can efficiently converge to the optimal solution under multi-variable and non-linear conditions, making full use of historical data and real-time monitoring data to achieve the optimization of each sewage outlet. Description of the Drawings

[0041] Figure 1 It is a schematic flow chart of the method in the embodiment of the present invention;

[0042] Figure 2 It is a schematic diagram of the system module in the embodiment of the present invention. Detailed Embodiments

[0043] To make the objectives, technical solutions, and advantages of the present invention more clear and understandable, the following further elaborates on the present invention in detail with reference to specific embodiments.

[0044] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those with ordinary skills in the field to which the present invention pertains. The "first", "second", and similar terms used in the present invention do not denote any order, quantity, or importance, but are only used to distinguish different components. The terms such as "comprising" or "including" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. The terms such as "connected" or "linked" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left", "right", etc. are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0045] Embodiment:

[0046] Please refer to Figure 1 , the present invention provides a technical solution:

[0047] A multi-objective optimization method for water pollution load allocation, the specific steps include:

[0048] Step 1: Divide the equal-area regions of the target water body into multiple pollution regions, and obtain the pollutant emission allocation amounts, treatment costs, sewage discharge flows, and pollutant emission concentrations of each sewage outlet during the previous sewage discharge time period, as well as the maximum value of the water body pollutant concentration in each pollution region during the corresponding sewage discharge time period;

[0049] In this embodiment, the pollutant emission allocation amount represents the allocation value of the total pollution emission to each sewage outlet, describes the actual pollutant emission situation of each sewage outlet during the previous sewage discharge time period, and is used to evaluate the emission capacity of the sewage outlet; the treatment cost represents the economic cost generated by the sewage outlet to reduce the pollutant emission concentration during the sewage discharge time period, and is determined by collecting the details of historical sewage treatment financial expenditures; the sewage discharge flow represents the sewage discharge amount containing pollutants of each sewage outlet per unit time, and an ultrasonic flowmeter is installed at the sewage outlet for real-time monitoring; the pollutant emission concentration represents the concentration of the pollutant with the highest proportion in the wastewater at the sewage outlet during the sewage discharge time period, and real-time data is obtained by installing an on-line pollutant concentration monitoring instrument at the sewage outlet. The on-line monitoring instrument includes a COD monitor and an ammonia nitrogen analyzer; the maximum value of the water body pollution concentration represents the maximum concentration of pollutants in the water body during the sewage discharge time period.

[0050] Step 2: Build a water pollutant concentration prediction model based on a deep neural network. Use the sewage discharge flow and pollutant emission concentration of all sewage outlets during the same sewage discharge period as inputs, and the maximum value of the water pollutant concentration in the polluted area as the label to train the water pollutant concentration prediction model.

[0051] In this embodiment, the deep learning network structure for building the water pollutant concentration prediction model is as follows:

[0052] Output layer: It contains 2N neurons and is used to input the sewage discharge flow and pollutant emission concentration of each sewage outlet, where N represents the number of sewage outlets.

[0053] First hidden layer: It contains 64 neurons and is activated using the ReLU activation function.

[0054] Second hidden layer: It contains 32 neurons and is activated using the ReLU activation function.

[0055] Third hidden layer: It contains 16 neurons and is activated using the ReLU activation function.

[0056] Output layer: It contains N neurons and is used to output the maximum value of the water pollutant concentration in each polluted area.

[0057] Collect historical sewage discharge flow and pollutant emission concentration data. Randomly select 80% of the historical data as the training set to train the water pollutant concentration prediction model, and 20% as the validation set. Build a mean squared error function to compare the error between the predicted water pollutant concentration and the actual water pollutant concentration, and verify the prediction accuracy of the model. The smaller the mean squared error function value, the closer the predicted value of the model is to the true value, and the better the model performance.

[0058] Step 3: Calculate the actual pollutant emissions, pollutant reduction amounts, and pollutant treatment loads of each sewage outlet during the sewage discharge period based on the pollutant emission allocation, sewage discharge flow, and pollutant concentration.

[0059] In this embodiment, the principles for calculating the actual pollutant emissions, pollutant reduction amounts, and pollutant treatment loads of each sewage outlet during the sewage discharge period are as follows:

[0060] The formula for calculating the actual pollutant emissions is:

[0061] M i =Q i ·C i ·T

[0062] Where, M i represents the pollutant emissions of the i-th sewage outlet during the sewage discharge period, i represents the index of the sewage outlet, Q iDenote the sewage discharge flow rate of the $i$-th sewage outfall, $C$ i Denote the average pollutant concentration of the $i$-th sewage outfall during the sewage discharge period, and $T$ denote the duration of the sewage discharge period;

[0063] The sewage discharge flow rate represents the amount of sewage discharged per unit time, and the pollutant concentration represents the mass of pollutants contained in the sewage per unit volume. The product of the two represents the pollutant discharge amount per unit time, and multiplying by the discharge time generates the actual pollutant discharge amount during this period.

[0064] The formula for calculating the pollutant reduction amount is:

[0065] $D$ i $=$ i $F$ i

[0066] where $D$ i denotes the pollutant reduction amount of the $i$-th sewage outfall, and $F$ i denotes the pollutant discharge allocation amount of the $i$-th sewage outfall;

[0067] The pollutant reduction amount represents the reduced pollutant discharge amount after treatment at the sewage outfall. Subtracting the actual discharge amount from the pollutant discharge allocation amount, their difference is the reduced pollutant discharge amount after treatment at the sewage outfall.

[0068] The formula for calculating the pollutant treatment load is:

[0069]

[0070] where $L$ i denotes the treatment load of the $i$-th sewage outfall per unit time.

[0071] The pollutant treatment load represents the rate of reducing pollutants per unit time. The pollutant reduction amount represents the total amount during the entire sewage discharge time, and dividing by the sewage discharge time represents the treatment load.

[0072] Step 4: Construct a governance cost prediction model based on a deep neural network, using the pollutant reduction amount, sewage discharge flow rate, and pollutant discharge concentration of each sewage outfall during the sewage discharge period as inputs and the governance cost as the label to train the governance cost prediction model;

[0073] In this embodiment, the deep neural network structure for constructing the governance cost prediction model is:

[0074] Input layer: It contains 3N neurons and is used to input the pollutant reduction amount, sewage discharge flow rate, and pollutant discharge concentration of each sewage outfall;

[0075] The first hidden layer: It contains 64 neurons and is activated using the ReLU activation function;

[0076] The second hidden layer: contains 32 neurons and is activated using the ReLU activation function;

[0077] The third hidden layer: contains 16 neurons and is activated using the ReLU activation function;

[0078] The output layer: contains N neurons and is used to output the treatment cost of each sewage outlet during the sewage discharge period.

[0079] Collect historical pollutant reduction amounts, sewage discharge flows, and pollutant emission concentration data. Randomly select 80% of the historical data as the training set to train the treatment cost prediction model, and use the remaining 20% of the data as the validation set. Construct the mean squared error function to compare the error between the predicted treatment cost and the actual treatment cost. The smaller the value of the mean squared error function, the closer the predicted value is to the true value, and the better the model performance.

[0080] The pollution treatment cost is not completely linear but shows the characteristic of decreasing marginal cost. As the pollutant reduction amount increases, the treatment cost will go through the following stages:

[0081] Initial stage: low-cost area. A large amount of pollutants can be reduced through simple measures such as basic wastewater treatment and reducing emission concentration. The treatment cost increases linearly with the reduction amount.

[0082] Transition stage: increasing cost area. Further reducing pollutants requires more complex technologies, and the unit reduction cost increases, showing a non-linear growth trend.

[0083] Deep treatment stage: high-cost area. When the reduction approaches the limit, the cost rises sharply and may even exceed economic feasibility.

[0084] Step 5: Obtain the total amount of pollutant emissions allocated during the future sewage discharge period. Generate a fitness function with the minimization of the total treatment cost, the minimization of the water body pollutant concentration, and the minimization of the pollutant treatment load as the optimization objectives. With the maximum value of the water body pollutant concentration in each pollution area being less than the pollutant concentration standard, the sum of the pollutant emission allocation amounts of each sewage outlet being equal to the total amount of pollutant emissions allocated, and the pollutant treatment load of each sewage outlet not being greater than the maximum design load as the constraint conditions, based on the genetic algorithm, the water body pollutant concentration prediction model, and the treatment cost prediction model, obtain the optimal water pollution load allocation plan. The optimal water pollution load allocation plan is the pollutant emission allocation amount, sewage discharge flow, and pollutant emission concentration of each sewage outlet during the future sewage discharge period.

[0085] In this embodiment, with the minimization of the total treatment cost, the minimization of the water body pollutant concentration, and the minimization of the pollutant treatment load as the optimization objectives, the generated fitness function is:

[0086]

[0087] Among them, X represents the total governance cost, i represents the index of the sewage outlet, and i ∈ [1, N], where N represents the number of sewage outlets, and S i represents the governance cost of the i-th sewage outlet output by the governance cost prediction model, and X max represents the upper limit of the total governance cost, j represents the index of the pollution area, and j ∈ [1, H], where H represents the number of pollution areas divided from the water body, and P j represents the maximum value of the pollutant concentration in the j-th pollution area output by the water body pollutant concentration prediction model, and P j,std represents the expected value of the pollutant concentration in the j-th pollution area, and L i,max represents the maximum design load of the i-th sewage outlet, and w 1 、w 2 、w 3 represent weight coefficients respectively, and w 1 +w 2 +w 3 = 1, w 2 > w 3 > w 1 .

[0088] represents the normalization processing of the total governance cost, and X max represents the total governance cost generated when all sewage outlets bear the maximum design load, and max(0, P j -P j,std ) represents the excess of the water body pollutant concentration in each pollution area relative to the expected value of the pollutant concentration. If it does not exceed the standard, the value is 0. If it exceeds the standard, the excess amounts of all areas are normalized and accumulated to obtain the optimization target of the overall concentration of the pollution area; max(0, L i -L i,max ) represents the excess of the treatment load of each sewage outlet relative to the maximum design load. If the load does not exceed the amount, the value is 0. If it exceeds the amount, the excess amounts are normalized and accumulated as the optimization target of the treatment load of the sewage outlet.

[0089] In the water pollution distribution and governance, the most important goal is to reduce the pollutant concentration. It is necessary to give priority to ensuring that the water body pollutant concentration in the pollution area is lower than the expected value. Therefore, w 2 takes the highest value; and the pollutant treatment load directly determines the working pressure of the sewage outlet. If the load exceeds the standard, it may lead to a decrease in the sewage discharge operation efficiency, thus affecting the actual treatment effect. Therefore, w 3 takes the second highest value; the total governance cost is a relatively flexible goal, which can be adjusted through different governance technologies, optimization schemes and capital allocation strategies, and has a certain flexibility. It can be gradually optimized through long-term planning. Therefore, w 1takes the minimum value, and the specific weights are: w 1 = 0.2, w 2 = 0.5, w 3 = 0.3.

[0090] Based on the genetic algorithm, the water pollutant concentration prediction model, and the treatment cost prediction model, the principle for obtaining the optimal water pollution load allocation scheme is as follows:

[0091] Based on the genetic algorithm, the pollutant discharge allocation amount, the sewage discharge flow rate, and the pollutant discharge concentration are encoded into chromosomes, and an initial population is randomly generated. Each individual in the population represents a set of pollutant discharge allocation amounts, sewage discharge flow rates, and pollutant discharge concentrations. Based on the water pollutant concentration prediction model and the treatment cost prediction model, the pollutant concentration and the treatment cost are generated, and then the fitness function of each individual is generated;

[0092] Based on tournament selection, the individuals in the initial population are randomly arranged. After the arrangement, the individuals are selected pairwise before and after the initial population, the fitness function values of the individuals are calculated, and the individual with the smaller fitness function value between the two is selected as the parent. The above process is repeated until all the individuals in the initial population are traversed, which is regarded as completing one round of selection. Then, crossover and mutation are randomly performed among the selected parent individuals to generate new offspring. The offspring and the parents are combined to form a new population, and the fitness function values of each individual are calculated. The individual with the lowest fitness function value is recorded as the current optimal solution; the above operations are regarded as one iteration. The maximum number of iterations is set to 100. When the number of iterations reaches 100, or the decrease in the fitness function value is less than 5% in 10 consecutive iterations, the iteration is terminated, and the individual with the lowest current fitness function value is output. The corresponding pollutant discharge allocation amount, sewage discharge flow rate, and pollutant discharge concentration are the allocation schemes for each sewage outfall during the future sewage discharge period.

[0093] Please refer to Figure 2 , the present invention also provides a multi-objective optimization water pollution load allocation system, which is used to implement the above multi-objective optimization water pollution load allocation method, and specifically includes:

[0094] A data acquisition module, which is used to divide the equal-area regions of the target water body into multiple pollution regions, and obtain the pollutant discharge allocation amounts, treatment costs, sewage discharge flow rates, and pollutant discharge concentrations of each sewage outfall during the previous sewage discharge period, as well as the maximum water pollutant concentration in each pollution region during the corresponding sewage discharge period;

[0095] A concentration prediction module, which is used to construct a water pollutant concentration prediction model based on a deep neural network, take the sewage discharge flow rate and pollutant discharge concentration of all sewage outfalls during the same sewage discharge period as inputs, and the maximum water pollutant concentration in the pollution region as a label to train the water pollutant concentration prediction model;

[0096] An emission calculation module, configured to calculate the actual emissions, pollutant reduction amounts, and pollutant treatment loads of each sewage outlet during the sewage discharge period based on the pollutant emission allocation amounts, sewage discharge flows, and pollutant concentrations.

[0097] A cost prediction module, configured to construct a governance cost prediction model based on a deep neural network, using the pollutant reduction amounts, sewage discharge flows, and pollutant emission concentrations of each sewage outlet during the sewage discharge period as inputs and the governance cost as labels to train the governance cost prediction model.

[0098] A comprehensive optimization module, configured to obtain the total pollutant emission allocation amount during a future sewage discharge period, generate a fitness function with the minimization of the total governance cost, the minimization of the water body pollutant concentration, and the minimization of the pollutant treatment load as optimization objectives, and based on the genetic algorithm, the water body pollutant concentration prediction model, and the governance cost prediction model, obtain an optimal water pollution load allocation plan under the constraint conditions that the maximum value of the water body pollutant concentration in each pollution area is less than the pollutant concentration standard, the sum of the pollutant emission allocation amounts of each sewage outlet is equal to the total pollutant emission allocation amount, and the pollutant treatment load of each sewage outlet is not greater than the maximum design load. The optimal water pollution load allocation plan is the pollutant emission allocation amounts, sewage discharge flows, and pollutant emission concentrations of each sewage outlet during the future sewage discharge period.

[0099] The above formulas are all calculated by taking the numerical values after dimensionless. The formula is obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0100] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0101] The units described as separate components may or may not be physically separated. 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.

[0102] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application.

Claims

1. A multi-objective optimization method for water pollution load distribution, characterized in that: The specific steps include: Step 1: Divide the target water body into multiple pollution areas, and obtain the pollutant emission distribution, treatment cost, discharge flow and pollutant emission concentration of each sewage outlet in the previous discharge time period, as well as the maximum water pollutant concentration of each pollution area in the corresponding discharge time period; Step 2: Build a water pollutant concentration prediction model based on a deep neural network, taking the discharge flow and pollutant emission concentration of all sewage outlets in the same sewage discharge time period as input, and the maximum water pollutant concentration in the polluted area as the label to train the water pollutant concentration prediction model; Step 3: Based on the pollutant emission allocation, discharge flow and pollutant concentration, calculate the actual pollutant emission, pollutant reduction and pollutant treatment load of each discharge outlet during the discharge time period; Step 4: Build a governance cost prediction model based on a deep neural network, taking the pollutant reduction, discharge flow rate and pollutant emission concentration of each sewage outlet during the sewage discharge period as input and the governance cost as a label to train the governance cost prediction model; Step 5: Obtain the total amount of pollutant emission allocation in the future pollution discharge period, and generate a fitness function with minimization of total governance cost, minimization of water pollutant concentration, and minimization of pollutant treatment load as optimization objectives. The maximum water pollutant concentration in each polluted area is less than the pollutant concentration standard, the sum of the pollutant emission allocation of each sewage outlet is equal to the total amount of pollutant emission allocation, and the pollutant treatment load of each sewage outlet is not greater than the maximum design load as constraints. Based on genetic algorithms, water pollutant concentration prediction models, and governance cost prediction models, the optimal water pollution load allocation scheme is obtained. The optimal water pollution load allocation scheme is the pollutant emission allocation, discharge flow, and pollutant emission concentration of each sewage outlet in the future pollution discharge period.

2. A multi-objective optimization method for water pollution load distribution according to claim 1, characterized in that: The pollutant emission allocation in step 1 is the pollutant value allocated to each sewage outlet; the treatment cost represents the economic cost incurred by reducing the pollutant emission concentration at the sewage outlet during the sewage discharge time period, which is determined by collecting historical sewage treatment financial expenditure details; the sewage flow rate represents the sewage discharge volume containing pollutants at each sewage outlet per unit time, and an ultrasonic flow meter is installed at the sewage outlet for real-time monitoring; the pollutant emission concentration represents the concentration of the pollutant with the highest proportion in the wastewater at the sewage outlet during the sewage discharge time period, and an online pollutant concentration monitoring instrument is installed at the sewage outlet to obtain real-time data, and the online monitoring instrument includes a COD monitor and an ammonia nitrogen analyzer; the maximum water pollution concentration represents the maximum concentration of pollutants in the water body during the sewage discharge time period.

3. A multi-objective optimization method for water pollution load distribution according to claim 1, characterized in that: The principle for calculating the actual pollutant discharge, pollutant reduction and pollutant treatment load of each sewage outlet during the sewage discharge period in step 3 is: The formula used to calculate the actual amount of pollutant emissions is: M i =Q i ·C i · Among them, M i represents the pollutant emission of the i-th sewage outlet during the sewage discharge period, i represents the index of the sewage outlet, Q i represents the discharge flow of the ith sewage outlet, C i represents the average pollutant concentration of the ith sewage outlet during the sewage discharge time period, and T represents the duration of the sewage discharge time period; The formula used to calculate pollutant reductions is: D i =F i -M i Among them, D i represents the pollutant reduction of the i-th sewage outlet, F i represents the pollutant emission allocation of the ith sewage outlet; The formula used to calculate the pollutant treatment load is: Among them, L i Represents the treatment load of the ith sewage outlet per unit time.

4. A multi-objective optimization method for water pollution load distribution according to claim 1, characterized in that: In step 5, the optimization objectives are to minimize the total cost of treatment, minimize the concentration of water pollutants, and minimize the pollutant treatment load, and the fitness function generated is: Where X represents the total cost of treatment, i represents the index of the sewage outlet, and i∈[1,N], N represents the number of sewage outlets, S i represents the governance cost of the ith sewage outlet output by the governance cost prediction model, X max represents the upper limit of the total cost of governance, j represents the index of the polluted area, and j∈[1,H], H represents the number of polluted areas divided into water bodies, P j represents the maximum value of pollutant concentration in the jth polluted area output by the water pollutant concentration prediction model, P j,std represents the expected value of pollutant concentration in the jth polluted area, L i,max represents the maximum design load of the ith sewage outlet, w1, w2, w3 represent weight coefficients respectively, and w1+w2+w3=1, w2>w3>w1.

5. The multi-objective optimization method for water pollution load distribution according to claim 1 is characterized in that: The principle for obtaining the optimal water pollution load distribution scheme in step 5 based on the genetic algorithm, the water pollutant concentration prediction model and the treatment cost prediction model is as follows: Based on the genetic algorithm, the pollutant emission allocation, discharge flow and pollutant emission concentration are encoded into chromosomes, and the initial population is randomly generated. Each individual in the population represents a set of pollutant emission allocation, discharge flow and pollutant emission concentration. The pollutant concentration and treatment cost are generated based on the water pollutant concentration prediction model and the treatment cost prediction model, and then the fitness function of each individual is generated; Based on the tournament selection, the individuals of the initial population are randomly arranged, and individuals are selected in pairs before and after the initial population after the arrangement, and the fitness function values ​​of the individuals are calculated. The individual with the smaller fitness function value between the two is selected as the parent generation, and the process is repeated until all individuals of the initial population are traversed, which is regarded as completing a round of selection, and random crossover and mutation are performed among the selected parent individuals to generate new offspring, and the offspring and the parent generation are combined to form a new population, and the fitness function value of each individual is calculated, and the individual with the lowest fitness function value is recorded as the current optimal solution; the above operation is regarded as one iteration, and the maximum number of iterations is set to 100. When the number of iterations reaches 100, or the fitness function value decreases by less than 5% in 10 consecutive iterations, the iteration is terminated, and the individual with the lowest current fitness function value is output. The corresponding pollutant emission allocation, sewage discharge flow rate and pollutant emission concentration are the allocation plans of each sewage outlet in the future sewage discharge time period.

6. A multi-objective optimization water pollution load distribution system, characterized by: The system is used to implement the multi-objective optimization water pollution load distribution method according to any one of claims 1 to 5, specifically comprising: The data acquisition module is used to divide the target water body into multiple pollution areas, and obtain the pollutant emission distribution, treatment cost, sewage flow rate and pollutant emission concentration of each sewage outlet in the previous sewage discharge time period, as well as the maximum water pollutant concentration of each pollution area in the corresponding sewage discharge time period; The concentration prediction module is used to build a water pollutant concentration prediction model based on a deep neural network. The discharge flow and pollutant emission concentration of all sewage outlets in the same sewage discharge time period are used as input, and the maximum water pollutant concentration in the polluted area is used as a label to train the water pollutant concentration prediction model. The emission calculation module is used to calculate the actual pollutant emission, pollutant reduction and pollutant treatment load of each sewage outlet during the sewage discharge time period based on the pollutant emission allocation, sewage discharge flow and pollutant concentration; The cost prediction module is used to build a governance cost prediction model based on a deep neural network. The pollutant reduction, discharge flow rate and pollutant emission concentration of each sewage outlet during the sewage discharge period are used as inputs, and the governance cost is used as a label to train the governance cost prediction model. The comprehensive optimization module is used to obtain the total amount of pollutant emission allocation in the future pollution discharge period, and to generate a fitness function with minimization of total governance cost, minimization of water pollutant concentration, and minimization of pollutant treatment load as optimization objectives. The maximum water pollutant concentration in each polluted area is less than the pollutant concentration standard, the sum of the pollutant emission allocation of each sewage outlet is equal to the total amount of pollutant emission allocation, and the pollutant treatment load of each sewage outlet is not greater than the maximum design load as constraints. Based on genetic algorithms, water pollutant concentration prediction models and governance cost prediction models, the optimal water pollution load allocation scheme is obtained. The optimal water pollution load allocation scheme is the pollutant emission allocation, discharge flow and pollutant emission concentration of each sewage outlet in the future pollution discharge period.

Images