Simulation-optimization method of polluted site underground water pumping-injection-treatment pollution remediation system

Abstract

The invention discloses a simulation-optimization method for a pollution site groundwater pumping-injection-treatment pollution remediation system based on a multiform evolution search normal form. The method comprises the following steps: constructing a groundwater flow model and a pollutant solute transport model; the method comprises the following steps: determining a management objective function and constraint conditions of hydraulic control of an underground water pollution range, establishing an underground water pollutant treatment model, optimizing underground water pumping and injection treatment of a pollution site by adopting BLMFO, solving the problem of interdependence between an upper-layer global target and a lower-layer local target through nested optimization, and constructing an auxiliary task by utilizing MFO; state variables are updated through the groundwater flow model and the pollutant solute transport model, a management objective function value of the groundwater pollutant treatment model is calculated, and whether constraint conditions are met or not is judged; meanwhile, decision variables are selected by optimizing the groundwater pollutant treatment model, and state variables are updated by returning to the groundwater flow model and the pollutant solute transport model.

Description

Technical Field

[0001] The present invention relates to the field of groundwater pollution control engineering and environmental science applications, and in particular to a simulation-optimization method for a groundwater pumping-treatment pollution remediation system in a contaminated site based on a multi-form evolutionary search paradigm. Background Art

[0002] In the field of groundwater pollution control engineering and environmental science applications, certain progress has been made in the decision-making management of groundwater remediation for contaminated sites. For example, patent application CN102992417A discloses a decision-making method for in-situ remediation of petroleum-contaminated groundwater. The method is based on in-situ extraction and treatment technology. By collecting relevant parameters of the contaminated site, numerical simulation, regression methods and nonlinear optimization techniques are used to obtain a proxy simulation model of the remediation plan, and then the optimal groundwater remediation plan is produced. Patent application CN105718632A proposes a multi-objective optimization management method for uncertain groundwater remediation, based on the multi-objective random taboo search algorithm PEMOTS with elite retention strategy, combined with sequential Gaussian condition simulation SGSIM to reduce the uncertainty of water system parameters, coupled with the groundwater flow program MODFLOW and the solute transport program MT3DMS, with strong reliability and robustness. Patent application CN105819616A relates to an integrated remediation system for shallow groundwater pollutants under multi-objective conditions, including a groundwater pollution migration monitoring system, a diagnostic system, a groundwater remediation system, and a post-processing and maintenance system. By real-time monitoring of pollutant data, simulating and calculating pollutant migration and transformation paths, etc., a groundwater pollution remediation management plan is established. Patent application CN113240282A discloses a multi-objective hierarchical method for determining mercury-contaminated soil remediation standards. Based on human health risk assessment theory and soil pollution evaluation theory, it calculates soil mercury remediation target values ​​at different levels, providing a basis for selecting soil mercury remediation target values. Patent application CN115659719A is an optimization method for in-situ bioremediation schemes for chlorinated hydrocarbon contamination in aquifers. By constructing a simulation model and a multi-objective optimization model, and solving it using the NSGA-II algorithm, the optimal remediation scheme set is obtained, the simulation accuracy is improved, and the contradictory relationship between remediation cost and remediation effect is weighed.

[0003] These existing technologies have played an important role in the field of groundwater pollution remediation and have certain advantages. For example, some technologies can combine a variety of advanced technologies, such as numerical simulation, optimization algorithms, etc., to provide a scientific basis for the formulation of remediation plans and improve the reliability and efficiency of remediation decisions; some methods take into account the complexity and uncertainty of groundwater pollution, and by introducing corresponding models and algorithms, reduce the uncertainty of the model and enhance the adaptability and robustness of the remediation plan; there are also technologies that build a relatively complete groundwater pollution remediation system, covering multiple links such as monitoring, diagnosis, remediation and post-maintenance, and realize all-round control and remediation of groundwater pollution.

[0004] However, the existing technology also has some shortcomings. In terms of algorithm applicability, the optimization algorithms used in some methods may have problems with the diversity of solutions and insufficient convergence when dealing with complex multi-objective optimization problems such as the groundwater extraction-treatment pollution remediation system of chlorinated hydrocarbon contaminated sites. Although the NSGA-II algorithm performs well in general multi-objective optimization problems, it may be difficult to effectively explore the solution space and maintain the diversity of solutions for the multiple decision variables and complex constraints involved in the system, and it is easy to fall into the local optimal solution.

[0005] In terms of the difficulty of convergence and solution, some technologies have slow convergence speed and high solution difficulty due to the complexity of the model and the large amount of calculation. For example, the optimization method of in-situ bioremediation scheme for chlorinated hydrocarbon pollution in aquifers mentioned in patent application CN115659719A involves the coupling of multiple models, including the simulation model of in-situ bioremediation of chlorinated hydrocarbon pollution in aquifers, the multi-objective optimization model of in-situ bioremediation scheme for chlorinated hydrocarbon pollution in aquifers, etc. Although this coupling method can improve the simulation accuracy and optimization effect, in actual applications, the model coupling is more complex, the amount of calculation is large, and the requirements for computing resources and time are also high, which affects the practicality and promotion of the method.

[0006] In terms of high simulation-optimization coupling complexity, some methods in the prior art have the problem of high coupling complexity when coupling the simulation model with the optimization model. For example, the uncertain groundwater remediation multi-objective optimization management method mentioned in patent application CN105718632A, although coupled with the groundwater flow program MODFLOW and the solute transport program MT3DMS, has strong reliability and robustness, but in the coupling process, it is necessary to process a large amount of data and complex model relationships, which increases the difficulty and complexity of the coupling.

[0007] In terms of high system integration complexity, although the groundwater pollution remediation systems constructed by some technologies are comprehensive in functions, the system integration complexity is high. For example, the integrated remediation system for shallow groundwater pollutants under multi-target conditions mentioned in patent application CN105819616A covers multiple links such as monitoring, diagnosis, remediation and post-maintenance, forming a relatively complete system. However, this system integration involves a variety of different treatment processes and equipment, such as coagulation and sedimentation, heavy metal separation, biological denitrification, ultrafiltration and reverse osmosis, etc. In actual applications, the coordination between these processes and equipment may be difficult, and it is necessary to further optimize the system integration solution to reduce complexity and improve the stability and reliability of the system. Summary of the invention

[0008] The present invention aims to solve the various deficiencies in the existing simulation-optimization method of groundwater extraction-treatment pollution remediation system in contaminated sites such as chlorinated hydrocarbons. In the prior art, when the optimization algorithm processes complex multi-objective problems, the diversity and convergence of the solution are insufficient, and it is easy to fall into the local optimal solution, and it is impossible to provide a comprehensive and reasonable remediation plan for decision makers. At the same time, the simulation-optimization method has a high model complexity and a large amount of calculation, resulting in a slow convergence speed and high difficulty in solving, which is difficult to meet the needs of fast and efficient decision-making in actual engineering. In addition, when the prior art couples the groundwater flow and pollutant migration simulation model with the optimization management model, the coupling complexity is high, and data interaction and collaborative work are difficult, which affects the reliability and stability of the model. In terms of system integration, it involves a variety of processing processes and equipment, which are difficult to coordinate and cooperate, and the integration complexity is high, which reduces the stability and reliability of the system. In the actual remediation process, there is a lack of real-time feedback and adjustment mechanism, and the remediation plan cannot be adjusted in time according to the real-time monitoring data, which affects the remediation effect and resource utilization efficiency. In terms of multi-objective coordinated optimization, the prior art does not fully balance and coordinate between different objectives, and it is difficult to effectively control the remediation cost and resource consumption while meeting the remediation effect. In view of these shortcomings, the present invention proposes a simulation-optimization method for the contaminated site groundwater injection-treatment pollution remediation system based on a multi-form evolutionary search paradigm. By introducing a multi-form evolutionary search paradigm (MFO) and a double-layer multi-objective optimization framework (BLMFO), the optimization efficiency and solution diversity are improved, the model coupling complexity is reduced, the real-time feedback and adjustment capabilities of the system are enhanced, and coordinated optimization among multiple objectives is achieved, providing scientific, efficient and economical decision-making support for groundwater remediation in contaminated sites.

[0009] The specific technical solutions are as follows: A simulation-optimization method for groundwater pumping-treatment pollution remediation system of contaminated sites based on a multi-form evolutionary search paradigm, comprising: Construct a groundwater flow model for the contaminated site, set up an initial pumping and injection well plan based on it, and establish a solute transport model for groundwater pollutants in the contaminated site; Determine the management objective function and constraints of hydraulic control of groundwater pollution range in contaminated sites, establish a groundwater pollutant treatment model with pumping and injection water treatment as the core, and use a double-layer multi-objective optimization framework (BLMFO) to optimize groundwater pumping and injection treatment in contaminated sites. The interdependence problem between the upper global objective and the lower local objective is solved through nested optimization, and the auxiliary tasks are constructed using the multi-form evolutionary search paradigm (MFO); the upper global objective, i.e., the management objective function, includes minimizing the remediation cost and maximizing the pollutant removal efficiency; the lower local objectives include the pumping and injection volume and the operating time of each well; The state variables are updated through the groundwater flow model of the contaminated site and the solute transport model of groundwater pollutants in the contaminated site, the management objective function value of the groundwater pollutant treatment model is calculated, and it is determined whether the constraints are met; at the same time, the decision variables are selected by optimizing the groundwater pollutant treatment model, and the state variables are returned to the groundwater flow model of the contaminated site and the solute transport model of groundwater pollutants in the contaminated site to update.

[0010] In some embodiments, the simulation-optimization method of groundwater pumping-treatment and pollution remediation system for contaminated sites based on a multi-form evolutionary search paradigm, the construction of a groundwater flow model for contaminated sites includes: statistically analyzing the drilling stratigraphic data of the contaminated site and the distribution data of pollutants in the groundwater, using the MODFLOW (seepage) module of the GMS (Groundwater Modeling Systems) software to determine the aquifer structure, source and sink terms and boundary conditions of the contaminated site, constructing a groundwater flow model for the contaminated site, and adjusting the groundwater flow model parameters to the optimal level through groundwater observation data.

[0011] In some embodiments, the contaminated site groundwater injection-treatment pollution remediation system simulation-optimization method based on the multi-form evolutionary search paradigm utilizes the MT3DMS (modular three-dimensional solute transport model) module to establish a solute transport model of groundwater pollutants in the contaminated site.

[0012] In some embodiments, the simulation-optimization method of the contaminated site groundwater pumping-treatment and pollution remediation system based on the multi-form evolutionary search paradigm, the state variables in the contaminated site groundwater pumping-treatment and pollution remediation system are the groundwater level and the pollutant concentration value in the contaminated site, and the decision variables include any one or more of the following: the pumping and injection volume of the pumping and injection wells, the location and number of the pumping and injection wells, the operating time and scheduling, which determine the specific timing of pumping and injection.

[0013] In some embodiments, the simulation-optimization method for groundwater pumping-treatment pollution remediation system of contaminated sites based on the multi-form evolutionary search paradigm, the decision variables include the amount of water pumped and injected into the pumping wells, and the following groundwater pollutant treatment model is established: ; ; ; ; in: is the cost of repair; represents minimizing the cost of repair; It is the pumping and injection cost coefficient of the pumping and injection well, for example, it can be set to 0.15 yuan / (m 3 m), etc. It is The water volume of the pumping and injection wells (unit can be m 3 / d); It is The continuous pumping and injection time of the pumping and injection well (the unit can be d); It is the pump-injection-treatment pollution remediation system that controls the number of pump-injection wells; is the number of iterative optimizations, It is The quality of residual pollutants in groundwater after the first iteration optimization (Unit can be kg) and the initial pollutant mass of groundwater (the unit can be kg) percentage; It represents iterative optimization to maximize pollutant removal efficiency; It is The concentration of pollutants in groundwater at the contaminated site after the first iteration of optimization; is the maximum permissible concentration of pollutants in groundwater at a contaminated site; It is the area of ​​pollutants in groundwater where the concentration exceeds the standard after pumping and injection treatment and remediation; It is the initial area of ​​the polluted site where the groundwater concentration exceeds the standard pollutant concentration; Optimize pumping and injection volumes to meet groundwater flow field and pollutant concentration constraints.

[0014] In some embodiments, the simulation-optimization method of groundwater pumping-treatment pollution remediation system of contaminated sites based on the multi-form evolutionary search paradigm generates multiple groups of initial pumping and injection well schemes as initial solutions in the upper layer, and each solution in the upper layer, i.e., each group of pumping and injection well schemes corresponding to the lower layer, is independently optimized, and the MT3DMS module is called to simulate the migration of groundwater pollutants; The lower layer optimizes the water pumping and injection volume, generates the optimal lower layer solution set (Pareto frontier) corresponding to the upper layer solution, and feeds it back to the upper layer to calculate the global fitness value.

[0015] Furthermore, the lower layer uses the NSGA-II algorithm to optimize the water injection and pumping volume. The NSGA-II algorithm randomly initializes the population Individual, each of which Represents the water extraction and injection volume vector group of all water extraction and injection wells: ; ; in, Represents the total number of individuals in the population generated by NSGA-II. represents a pumping scheme, .

[0016] In some embodiments, the method for simulating and optimizing the contaminated site groundwater pumping-treatment pollution remediation system based on the multi-form evolutionary search paradigm, the auxiliary task constructed by using the multi-form evolutionary search paradigm includes: Construct auxiliary task 1: Ignore the lower-level optimization constraints, simplify the multi-objective problem, and treat the lower-level optimization as a penalty term and add it to the upper-level objective function: ; ; in: represents the objective function of auxiliary task 1; represents the upper objective function, i.e., minimizing the remediation cost and maximizing the pollutant removal efficiency; is the cost of repair; It is the percentage of the mass of residual pollutants in groundwater after pumping and injection treatment and remediation to the mass of initial pollutants in groundwater; represents the decision variable vector; is the penalty coefficient, which is used to control the degree of penalty for violating the constraint. For example, it can be set to 0.1 in the initial stage, increase by 0.1 every 50 generations, and finally stabilize at 1.0; represents the violation degree of the lower constraint, , is the single well pumping and injection volume constraint, is the hydraulic gradient constraint; Construct auxiliary task 2: Integrate the lower-level local objectives into the upper-level to form a single-level multi-objective optimization problem. Through this task, the trade-off between the amount of pumping and injection water and the efficiency of groundwater pollutant removal is discovered; the lower-level objectives include the relationship between the amount of pumping and injection water and the concentration of groundwater pollutants; The lower optimization problem is used to simulate the migration of groundwater pollutants to calculate the final residual amount of groundwater pollutants: ; in: is the pollutant degradation rate, is the hydrodynamic dispersion coefficient, is the groundwater flow velocity, and The pollutant concentrations are The second-order gradient term (diffusion term) and the first-order gradient term (convection term) of represents the total number of grid cells after the contaminated site is discretized. represents the grid cell number, , Indicates that given the upper decision variable The optimal set of lower-level decision variables under ; The two-layer multi-objective optimization framework uses explicit knowledge transfer (KT) to perform data interaction between the two auxiliary tasks and the original problem to enhance the optimization effect. That is, after a certain number of iterations (such as 10 times), an explicit knowledge transfer across tasks is performed to ensure the co-evolution of the main task and the auxiliary task.

[0017] In some embodiments, the simulation-optimization method of the contaminated site groundwater pumping-treatment pollution remediation system based on the multi-form evolutionary search paradigm gives priority to the solution belonging to the Pareto frontier in the auxiliary task, and the fitness of the solution of the auxiliary task in the main task must be higher than the current population mean. The solution is screened by crowding distance to avoid population aggregation and ensure that the layout of the pumping and injection wells covers different sub-areas of the contaminated site; When the solution of the auxiliary task is transferred to the main task, the lower-level decision variables including the amount of water pumped and injected are supplemented, and the expansion is completed by randomly extracting the lower-level parameters of the historical optimal solution; The feasible solution of the main task is fed back to the auxiliary task to guide its search direction, including initializing the auxiliary population using the verified well location scheme.

[0018] A computer device includes a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory. When the computer program is running, the processor executes the simulation-optimization method of groundwater pumping-treatment pollution remediation system of contaminated sites based on a multi-form evolutionary search paradigm.

[0019] A computer-readable storage medium stores a program or instruction. When the program or instruction is executed by a computer device, the computer device executes the simulation-optimization method of groundwater pumping-treatment pollution remediation system of contaminated sites based on a multi-form evolutionary search paradigm.

[0020] The present invention solves the key problems existing in the traditional groundwater remediation optimization method by introducing the double-layer multi-objective optimization framework (BLMFO) and the multi-form evolutionary search paradigm (MFO), significantly improves the remediation efficiency, reduces the cost, and overcomes many technical obstacles in the prior art. Compared with the prior art, the present invention has achieved breakthrough innovations in the following aspects: (1) The contradiction between diversity of solutions and convergence When dealing with complex multi-objective problems, traditional methods often find it difficult to balance the diversity and convergence of solutions and are prone to falling into local optimal solutions. The present invention quickly generates a diverse solution set in a low-complexity space by constructing auxiliary tasks (such as ignoring lower-level optimization or converting it into a single-level problem), and combines the knowledge transfer mechanism to dynamically feed back the non-dominated solutions in the auxiliary tasks to the main task to ensure the global distribution of solutions. For example, in the case of a chlorinated hydrocarbon contaminated site in Jiangsu, the Pareto solution set generated by the present invention contains 6 differentiated solutions, while the traditional method only generates 3 homogeneous solutions, which significantly improves the flexibility of decision-making and the remediation effect.

[0021] (2) High computational cost of simulation-optimization coupling In the simulation-optimization coupling process, traditional methods need to repeatedly call complex numerical simulation modules (such as MT3DMS), resulting in high computational cost and slow convergence. The present invention does not rely on proxy models (such as Kriging models), but uses a multi-form evolutionary search paradigm and knowledge transfer mechanism to replace part of the simulation calculations, and only calls numerical simulation (MT3DMS) for potential solutions, avoiding repeated calls in the global scope, and combining with the parallel optimization architecture to significantly reduce the amount of calculation. In the same case, the present invention achieves a 3×10 5 The sub-function evaluation converges to the optimal solution, while the traditional method requires 1.5×10 6 times, and the computing efficiency is improved by 80%. In addition, the present invention supports real-time feedback and dynamic adjustment. The traditional method has high computing cost. Each optimization requires iterative calling of the numerical model thousands to millions of times, and each round of calculation cycle takes more than ten hours to dozens of hours. The present invention adopts a knowledge transfer mechanism and uses explicit knowledge transfer to exchange data between the main task and the auxiliary task. High-quality solutions can be delivered to the main task through the auxiliary task, and the calculation cycle is within a few hours. If a well location plan cannot effectively reduce the pollution concentration, the optimization process can support manual input of information and parameters for adjustment, and update the repair plan once, which greatly improves the real-time and adaptability of the repair.

[0022] (3) Optimization of remediation costs and pollutant removal efficiency The present invention uses a two-layer optimization framework to select low-well-position solutions (referring to the optimization solutions with relatively few pumping and injection wells selected in the upper global optimization process) in the upper global optimization, and accurately control the pumping and injection volume in the lower local optimization, thereby achieving dual optimization of remediation costs and pollutant removal efficiency. In a case of a chlorinated hydrocarbon contaminated site in Jiangsu, the present invention reduced the number of pumping wells from 23 to 13, the total pumping volume from 1150 m³ / d to 392 m³ / d, and the remediation cost by 70%. At the same time, the proportion of residual pollutants was reduced from 12.5% ​​to 0.25%, which is significantly better than traditional methods.

[0023] (4) Innovation in dynamic penalty coefficient and constraint processing The present invention proposes an adaptive penalty coefficient mechanism, which allows mild constraint violations in the initial stage to explore diversity, and imposes strict restrictions in the later stage to ensure the feasibility of the solution. This innovation effectively solves the shortcomings of traditional methods in constraint processing and significantly increases the proportion of feasible solutions. In the test problem, the proportion of feasible solutions of the present invention increased from 65% of traditional methods to 92%, further verifying its technical advantages.

[0024] In summary, the present invention has achieved a breakthrough improvement in core indicators such as remediation cost, pollutant removal efficiency, and computational efficiency through a dual-layer coupled optimization architecture, a multi-form search synergy mechanism, and a dynamic knowledge transfer strategy. Compared with traditional methods, the present invention has significant advantages in terms of solution diversity, computational efficiency, real-time performance, and remediation effect, and the technical solution is irreplaceable and meets the requirements of invention creativity. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 The present invention is a flow chart of a simulation-optimization method for a groundwater injection-treatment pollution remediation system of a chlorinated hydrocarbon contaminated site based on a multi-form evolutionary search paradigm in a specific implementation method.

[0026] Figure 2 for Figure 1 The solution diagram shown is when the simulation-optimization method of groundwater injection-treatment pollution remediation system of chlorinated hydrocarbon contaminated sites was run for 100 generations. DETAILED DESCRIPTION

[0027] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not used to limit the scope of the present invention.

[0028] The specific solution process of the BLMFO algorithm used in the present invention is as follows: (a) Problem definition and initialization The upper problem is defined as a global goal, that is, minimizing the extraction cost and maximizing the pollution treatment efficiency; the lower problem is positioned as a specific goal, that is, the layout of the pumping and injection wells, the amount of pumping and injection, etc. The upper decision sets the boundary conditions for the lower layer, but the optimization results of the lower layer will be fed back to the upper layer. The initialization of BLMFO is divided into two parts: the upper layer and the lower layer. Random generation N L The upper solution and N F To ensure the optimization efficiency and diversity of the solution set, the initial population needs to be quality controlled. Through random generation and fitness screening, solutions that significantly violate the constraints are eliminated, and the solution distribution is ensured to evenly cover the search space. The fitness value of the upper solution depends on the optimization result of the lower layer.

[0029] (b) Introducing auxiliary tasks to simplify the two-layer problem The core of BLMFO's optimization process is to reduce the complexity of two-layer optimization by introducing auxiliary tasks through multiform optimization (MFO). MFO constructs multiple auxiliary tasks to simplify the original two-layer problem and improves the efficiency of the algorithm through parallel optimization. First, a complete two-layer optimization is performed in the main task. For the upper-layer solution, the lower-layer optimization is called to find the corresponding optimal lower-layer solution. The main task needs to handle the interdependence between the upper and lower layers through nested optimization.

[0030] Auxiliary task A: Ignore the lower-level optimization problem and directly optimize the upper-level objective function, but ignore the optimization of the lower-level objective and only indirectly constrain the feasibility of the lower layer through the penalty function.

[0031] Auxiliary Task B: Convert the two-layer problem into a single-layer problem by directly integrating the feedback objectives of the lower layer into the upper layer objectives to form a new single-layer multi-objective problem.

[0032] And decompose the complex two-level multi-objective optimization problem into several sub-objectives, such as optimizing the pollutant removal or pumping cost separately.

[0033] The population is optimized in parallel in the main task and auxiliary task, and the multi-objective evolutionary algorithm (NSGA-II) is used for population evolution, combining crossover, mutation and selection operations to explore the search space. The auxiliary task quickly provides high-quality candidate solutions on sub-problems with lower computational complexity, and these solutions will be fed back to the main task through the knowledge transfer mechanism.

[0034] (c) Information transfer mechanism By dynamically exchanging solutions between the main task and the auxiliary task, the diversity of the solution set and the global search capability are enhanced. Knowledge transfer mainly includes two directions: solution transfer from the auxiliary task to the main task, and solution feedback from the main task to the auxiliary task. Solution transfer from the auxiliary task to the main task: After every fixed number of generations (such as 10 generations), the best performing solution is selected from the auxiliary task and transferred to the main task. These solutions are selected according to the following rules: Non-dominance: The solutions belonging to the Pareto front in the auxiliary task solution set will be selected first.

[0035] Fitness improvement: The fitness value of the auxiliary task solution in the main task population is higher than the average fitness of the current population.

[0036] Diversity maintenance: Crowding distance is used to ensure that the transfer solution does not cause the population to be overly concentrated in a local area.

[0037] Feedback of solutions from the main task to the auxiliary task: The solution with the largest crowding distance is selected from the Pareto frontier solution set of the main task and fed back to the auxiliary task to optimize the diversity of the auxiliary task population. After the auxiliary task receives the main task solution, it uses these solutions as guidance for population initialization or directly replaces part of the population, promoting the auxiliary task to explore the search space more comprehensively.

[0038] Formation of Pareto solution set: After each population evolution, all solutions in the main task are sorted by non-dominated order to generate the Pareto frontier solution set. The solution set is finally formed by selecting non-dominated solutions and combining crowding distance to retain diversity. The high-quality solutions provided by the auxiliary tasks will also be gradually added to the Pareto solution set of the main task through knowledge transfer.

[0039] Compared with traditional optimization, the BLMFO algorithm is particularly suitable for complex problems that require hierarchical decision-making, where the upper and lower layers have different objectives and constraints. It searches in the original problem space and the auxiliary task space simultaneously, and uses knowledge transfer to improve search efficiency and optimization performance. The multi-form search framework (BLMFO) accelerates and simplifies the optimization process by generating auxiliary tasks (such as ignoring the lower-level optimization problem or converting the problem into a single-layer multi-objective optimization). This method can generate alternative models in groundwater pollution management to simulate different remediation strategies or pollution propagation scenarios, thereby providing additional information support for the original optimization.

[0040] The core of the proposed multi-form evolutionary search paradigm (MFO) is to explore the search space in parallel by constructing multiple optimization tasks (main tasks and auxiliary tasks), thereby improving the efficiency of solving complex optimization problems. Its characteristics are: 1) Construct auxiliary tasks that are related to the main task but have lower complexity; 2) Each task occupies a different local area in the original search space; 3) Perform search in parallel between the main task and auxiliary tasks; 4) Auxiliary tasks help the main task improve convergence speed through knowledge transfer; 5) Transfer high-quality solutions obtained in auxiliary tasks to the main task; 6) The solution in the main task can also be fed back to the auxiliary task to improve search diversity.

[0041] MFO is not directly equivalent to a replacement model, nor does it completely replace the original problem. Instead, it optimizes multiple problem perspectives simultaneously to reduce complexity and improve efficiency.

[0042] A simulation-optimization method for groundwater pumping-treatment pollution remediation system of contaminated sites based on a multi-form evolutionary search paradigm, comprising: Construct a groundwater flow model for the contaminated site, set up an initial pumping and injection well plan based on it, and establish a solute transport model for groundwater pollutants in the contaminated site; Determine the management objective function and constraints of hydraulic control of groundwater pollution range in contaminated sites, establish a groundwater pollutant treatment model with pumping and injection water treatment as the core, and use a two-layer multi-objective optimization framework to optimize groundwater pumping and injection treatment in contaminated sites. The interdependence problem between the upper global objective and the lower local objective is solved through nested optimization, and auxiliary tasks are constructed using a multi-form evolutionary search paradigm; the upper global objective, i.e., the management objective function, includes minimizing the remediation cost and maximizing the pollutant removal efficiency; the lower local objectives include the amount of pumping and injection water and the operating time of each well; The state variables are updated through the groundwater flow model of the contaminated site and the solute transport model of groundwater pollutants in the contaminated site, the management objective function value of the groundwater pollutant treatment model is calculated, and it is determined whether the constraints are met; at the same time, the decision variables are selected by optimizing the groundwater pollutant treatment model, and the state variables are returned to the groundwater flow model of the contaminated site and the solute transport model of groundwater pollutants in the contaminated site to update.

[0043] See also Figure 1 A simulation-optimization method for groundwater pumping-treatment pollution remediation system of chlorinated hydrocarbon contaminated sites based on a multi-form evolutionary search paradigm is proposed. It is based on a groundwater solute transport simulation model and aims to design the most efficient groundwater pollutant extraction and treatment system. The following takes a groundwater chlorobenzene contaminated site in a chemical park as an example to illustrate the specific implementation steps of this method: Step (1) is to collect data on the formation of boreholes and the distribution of pollutants in groundwater. The MODFLOW module of GMS software is used to determine the aquifer structure, source and sink terms, and boundary conditions of the study area, and to construct a groundwater flow model for the study area. The parameters of the groundwater flow model are adjusted to the optimal value through groundwater observation data. The permeability coefficient of each formation ranges from 1×10 -5 -1.1×10 -3 cm / s, and the porosity is 0.3. On this basis, an initial pumping and injection well plan is set up, with 23 pumping wells and 10 injection wells. The maximum pumping and injection volume of the injection wells and pumping wells is taken, and the pumping well is 50 m 3 / d, injection well is 100m 3 / d, and the MT3DMS module was used to establish the pollutant solute transport model in the study area. The vertical diffusion coefficient was set to 0.076, while the horizontal diffusion coefficient was determined to be 0.76, and the simulated repair period was 6 months.

[0044] Step (2) determines the management objective function and constraints of the hydraulic control of the groundwater pollution range of the site. In the pumping and injection water treatment system, the decision variables usually involve the following aspects: the pumping and injection rate of the pumping and injection wells, the location and number of wells, the operation time and scheduling, and the specific timing of pumping and injection and treatment. In this case, the optimization decision variable is the pumping and injection volume of the pumping and injection wells, and the state variables are the groundwater level and pollutant concentration values ​​in the site. A mathematical model of the groundwater pollutant treatment model with pumping and injection water treatment as the core is established.

[0045] ; ; ; ; in: is the cost of repair; represents minimizing the cost of repair; is the pumping and injection cost coefficient of the pumping and injection well, which is set to 0.15 yuan / (m 3 m); It is The water volume of the pumping and injection wells (in m 3 / d); It is The continuous pumping and injection time of the pumping and injection well (in days); It is the pump-injection-treatment pollution remediation system that controls the number of pump-injection wells; is the number of iterative optimizations, It is The quality of residual pollutants in groundwater after the first iteration optimization (Unit: kg) and the initial mass of groundwater pollutants (unit: kg) as a percentage; It represents iterative optimization to maximize pollutant removal efficiency; It is The concentration of pollutants in groundwater at the contaminated site after the first iteration of optimization; is the maximum permissible concentration of pollutants in groundwater at a contaminated site; It is the area of ​​pollutants in groundwater where the concentration exceeds the standard after pumping and injection treatment and remediation; It is the initial area where the concentration of pollutants in groundwater exceeds the standard.

[0046] Step (3): In order to optimize the treatment of groundwater pumping and injection at the chlorinated hydrocarbon contaminated site, a two-layer multi-objective optimization framework (BLMFO) was used for optimization calculation. The interdependence problem between the upper layer (global goal: minimizing the remediation cost and maximizing the pollutant removal efficiency) and the lower layer (local goal: pumping and injection volume) was solved through nested optimization, and the multi-form evolutionary search paradigm (MFO) was used to construct auxiliary tasks to simplify complexity and improve optimization efficiency.

[0047] The upper layer goal is to minimize the cost of remediation and maximize the efficiency of pollutant removal. The decision variables include the location, number and operation time of the pumping and injection wells. After fixing the upper layer variables (such as the well location), the pumping and injection volume is optimized to meet the constraints of the groundwater flow field and pollutant concentration (such as the pollutant concentration is lower than the safety threshold). The upper layer generates the initial solution (such as randomly generating 10 groups of pumping and injection well layout plans), and each solution corresponding to the lower layer needs to be optimized independently (calling the MT3DMS module to simulate pollutant migration). The lower layer uses the NSGA-II algorithm to optimize the pumping and injection volume, generates the optimal lower layer solution set (Pareto frontier) corresponding to the upper layer solution, and feeds back to the upper layer to calculate the global fitness value.

[0048] The NSGA-II algorithm initializes the population randomly Individual, each of which Represents the water extraction and injection volume vector group of all water extraction and injection wells: ; ; in, Represents the total number of individuals in the population generated by NSGA-II. represents a pumping scheme, .

[0049] BLMFO uses explicit knowledge transfer (KT) to perform data interaction between the two auxiliary tasks and the original problem to enhance the optimization effect.

[0050] At the same time, we construct the auxiliary tasks of the Multi-Form Evolutionary Search Paradigm (MFO): Construct auxiliary task 1: Ignore the lower-level optimization constraints first, simplify the multi-objective problem, and treat the lower-level optimization as a penalty term and add it to the upper-level objective function.

[0051] ; ; in: represents the objective function of auxiliary task 1; represents the upper objective function, i.e., minimizing the remediation cost and maximizing the pollutant removal efficiency; is the cost of repair; It is the percentage of the mass of residual pollutants in groundwater after pumping and injection treatment and remediation to the mass of initial pollutants in groundwater; represents the decision variable vector; It is the penalty coefficient, which is used to control the degree of penalty for violating the constraint. It can be set to 0.1 in the initial stage, and increase by 0.1 every 50 generations, and finally stabilize at 1.0; represents the violation degree of the lower constraint, , is the single well pumping and injection volume constraint, is the hydraulic gradient constraint.

[0052] Directly optimize the upper layer objectives and ignore the lower layer independence. Through this task, a low-cost layout plan for water injection and extraction wells can be quickly screened out (fewer wells can be set up while meeting the removal efficiency, but the feasibility needs to be verified later).

[0053] Construct auxiliary task 2: Integrate the lower-level objectives (such as the relationship between water injection volume and pollutant concentration) into the upper layer to form a single-layer multi-objective optimization problem. Through this task, the trade-off relationship between water injection volume and pollutant removal efficiency is discovered, providing decision makers with a variety of options.

[0054] The lower optimization problem is used to simulate the transport of pollutants to calculate the final residual amount of pollutants: ; in: is the pollutant degradation rate, is the hydrodynamic dispersion coefficient, is the groundwater flow velocity, and The pollutant concentrations are The second-order gradient term (diffusion term) and the first-order gradient term (convection term) of represents the total number of grid cells after the contaminated site is discretized. represents the grid cell number, , Indicates that given the upper decision variable The optimal set of lower-level decision variables under .

[0055] It is also necessary to set a cross-task knowledge transfer (KT) after a certain number of iterations (10 times) to ensure the co-evolution of the main task and the auxiliary task. The solution selection should give priority to the solution belonging to the Pareto frontier in the auxiliary task. The fitness of the auxiliary solution in the main task must be higher than the current population mean. The solution is screened by the crowding distance to avoid population aggregation (such as ensuring that the layout of the pumping and injection wells covers different sub-areas of the polluted area). When the solution of the auxiliary task is transferred to the main task, the lower-level variables (such as the amount of pumping and injection water) need to be supplemented, and the expansion is completed by randomly extracting the lower-level parameters of the historical optimal solution. The feasible solution of the main task is fed back to the auxiliary task to guide its search direction (such as initializing the auxiliary population using a verified well location plan).

[0056] The algorithm terminates when the following conditions are met: 1. The number of iterations reaches the set upper limit (such as 100 generations).

[0057] 2. The non-dominated solution converges to a stable Pareto front.

[0058] The main purpose of constructing auxiliary task 1 is to reduce the computational complexity by expanding the search space, but it may not fully satisfy the optimal solution of the lower layer. Constructing auxiliary task 2 directly converts the original two-layer multi-objective optimization problem into a single-layer multi-objective optimization problem, reducing the computational complexity, but increasing the number of objectives and the difficulty of optimization. During the optimization and solution process, auxiliary task 1, auxiliary task 2 and the knowledge transfer mechanism are carried out in parallel, which ultimately improves the optimization quality and solution efficiency.

[0059] Step (4) couples the simulation model of groundwater flow and reaction and migration of polluted components in the polluted area with the hydraulic control optimization management model: the groundwater level and the pollutant concentration of each grid are used as state variables, and the pumping flow rate of each well is used as a decision variable. The simulation model constructed in step (1) continuously updates the state variables, calculates the objective function value of the optimization management model constructed in step (2), and determines whether the constraints are met; at the same time, the decision variables are selected through the optimization management model, and returned to the simulation model to update the state variables.

[0060] Step (5): Select the extraction treatment scheme corresponding to the optimal solution obtained by optimizing step (4), substitute it into the numerical simulation model, and predict the pollutant control effect in the polluted area. Combined with the simulation results, verify the reliability of the optimized solution, and adjust the pumping well layout and pumping and injection strategy according to the actual situation to form a more scientific and effective remediation plan.

[0061] See also Figure 2, select the remediation scheme in the Pareto frontier. From left to right and from top to bottom in the figure, they are marked as Scheme 1, Scheme 2, Scheme 3, Scheme 4, Scheme 5, and Scheme 6. Through analysis, it can be seen that Scheme 1 and Scheme 2 have low pumping volume and high residual pollution. The advantage is that the cost may be low, which is suitable for situations with limited budgets or occasions with low environmental interference requirements. The disadvantage is that the residual amount of pollutants is large, the remediation effect is not ideal, and the long-term environmental and health risks may be greater. Scheme 3 and Scheme 4 represent medium pumping volume and medium residual pollution, achieving a balance between cost and remediation effect, and are suitable for scenes seeking medium governance levels. However, it may take longer to achieve the ideal pollutant removal effect. Scheme 5 and Scheme 6 have the best remediation effect and the smallest residual pollution, which are most suitable for situations where pollution needs to be reduced urgently to meet safety standards. At the same time, the cost is very high, the requirements for facilities are also higher, and they are not suitable for projects with limited budgets. These six schemes represent different trade-offs. Which one to choose depends on which goal is more important and the degree of compromise you are willing to accept between the two.

[0062] A computer device comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory. When the computer program is running, the processor executes the above-mentioned simulation-optimization method of groundwater injection-treatment pollution remediation system in a chlorinated hydrocarbon contaminated site based on a multi-form evolutionary search paradigm.

[0063] A computer-readable storage medium stores a program or instruction. When the program or instruction is executed by a computer device, the computer device executes the above-mentioned simulation-optimization method for groundwater injection-treatment pollution remediation system of chlorinated hydrocarbon contaminated sites based on a multi-form evolutionary search paradigm.

[0064] In addition, it should be understood that after reading the above description of the present invention, those skilled in the art may make various changes or modifications to the present invention, and these equivalent forms also fall within the scope defined by the claims attached to this application.

Claims

1. A simulation-optimization method for groundwater pumping-treatment pollution remediation system in contaminated sites based on a multi-form evolutionary search paradigm, characterized in that: include: Construct a groundwater flow model for the contaminated site, set up an initial pumping and injection well plan based on it, and establish a solute transport model for groundwater pollutants in the contaminated site; Determine the management objective function and constraints of hydraulic control of groundwater contamination range at contaminated sites, establish a groundwater pollutant treatment model with pumping and injection water treatment as the core, use a two-layer multi-objective optimization framework to optimize groundwater pumping and injection treatment at contaminated sites, solve the interdependence problem between the upper global objective and the lower local objective through nested optimization, and use a multi-form evolutionary search paradigm to construct auxiliary tasks; The upper-level global objectives, i.e., the management objective function, include minimizing the cost of remediation and maximizing the efficiency of pollutant removal; Lower local objectives include the amount of water pumped and injected and the operating time of each well; The state variables are updated through the groundwater flow model of the contaminated site and the solute transport model of groundwater pollutants in the contaminated site, the management objective function value of the groundwater pollutant treatment model is calculated, and it is determined whether the constraints are met; at the same time, the decision variables are selected by optimizing the groundwater pollutant treatment model, and the state variables are returned to the groundwater flow model of the contaminated site and the solute transport model of groundwater pollutants in the contaminated site to update.

2. The method for simulating and optimizing the contaminated site groundwater pumping-treatment pollution remediation system based on a multi-form evolutionary search paradigm according to claim 1 is characterized in that: The construction of the groundwater flow model of the contaminated site includes: collecting data on the borehole formation of the contaminated site and the distribution data of pollutants in the groundwater, using the MODFLOW module of the GMS software to determine the aquifer structure, source and sink items and boundary conditions of the contaminated site, constructing the groundwater flow model of the contaminated site, and adjusting the parameters of the groundwater flow model to the optimum through groundwater observation data; The MT3DMS module is used to establish a solute transport model of groundwater pollutants in contaminated sites.

3. The method for simulating and optimizing the groundwater pumping and treatment pollution remediation system of a contaminated site based on a multi-form evolutionary search paradigm according to claim 1 is characterized in that: The state variables in the contaminated site groundwater pumping and injection-treatment pollution remediation system are the groundwater level and the pollutant concentration in the contaminated site. The decision variables include any one or more of the following: the amount of water pumped and injected from the pumping and injection wells, the location and number of the pumping and injection wells, the operating time and scheduling, which determine the specific timing of pumping and injection.

4. The method for simulating and optimizing the groundwater pumping and treatment pollution remediation system of a contaminated site based on a multi-form evolutionary search paradigm according to claim 3 is characterized in that: The decision variables include the water injection volume of the pumping and injection wells, and the following groundwater pollutant treatment model is established: ； ； ； ； in: is the cost of repair; represents minimizing the cost of repair; is the pumping and injection cost coefficient of the pumping and injection well; It is The water extraction and injection volume of the pumping and injection wells; It is The continuous pumping and injection time of the pumping and injection wells; It is the pump-injection-treatment pollution remediation system that controls the number of pump-injection wells; is the number of iterative optimizations, It is The quality of residual pollutants in groundwater after the first iteration optimization Initial contaminant quality in groundwater percentage of It represents iterative optimization to maximize pollutant removal efficiency; It is The concentration of pollutants in groundwater at the contaminated site after the first iteration of optimization; is the maximum permissible concentration of pollutants in groundwater at a contaminated site; It is the area of ​​pollutants in groundwater where the concentration exceeds the standard after pumping and injection treatment and remediation; It is the initial area of ​​the polluted site where the groundwater concentration exceeds the standard pollutant concentration; Optimize pumping and injection volumes to meet groundwater flow field and pollutant concentration constraints.

5. The method for simulating and optimizing the groundwater pumping and treatment pollution remediation system of a contaminated site based on a multi-form evolutionary search paradigm according to claim 1 is characterized in that: The upper layer generates multiple groups of initial pumping and injection well schemes as initial solutions. Each solution of the upper layer, i.e., the lower layer corresponding to each group of pumping and injection well schemes, is optimized independently, and the MT3DMS module is called to simulate the migration of groundwater pollutants. The lower layer optimizes the water pumping and injection volume, generates the optimal lower layer solution set corresponding to the upper layer solution, and feeds it back to the upper layer to calculate the global fitness value.

6. The method for simulating and optimizing the groundwater pumping and treatment pollution remediation system of a contaminated site based on a multi-form evolutionary search paradigm according to claim 5 is characterized in that: The lower layer uses the NSGA-II algorithm to optimize the water pumping and injection volume. The NSGA-II algorithm randomly initializes the population Individual, each of which Represents the water extraction and injection volume vector group of all water extraction and injection wells: ； ； in, Represents the total number of individuals in the population generated by NSGA-II. represents a pumping scheme, .

7. The method for simulating and optimizing the groundwater pumping and treatment pollution remediation system of a contaminated site based on a multi-form evolutionary search paradigm according to claim 1, characterized in that: The auxiliary tasks constructed by using the multi-form evolutionary search paradigm include: Construct auxiliary task 1: Ignore the lower-level optimization constraints, simplify the multi-objective problem, and treat the lower-level optimization as a penalty term and add it to the upper-level objective function: ； ； in: represents the objective function of auxiliary task 1; represents the upper objective function, i.e., minimizing the remediation cost and maximizing the pollutant removal efficiency; is the cost of repair; It is the percentage of the mass of residual pollutants in groundwater after pumping and injection treatment and remediation to the mass of initial pollutants in groundwater; represents the decision variable vector; is the penalty coefficient; represents the violation degree of the lower constraint, , is the single well water injection and extraction capacity constraint, is the hydraulic gradient constraint; Construct auxiliary task 2: Integrate the lower-level local objectives into the upper-level to form a single-level multi-objective optimization problem. Through this task, the trade-off between the amount of pumping and injection water and the efficiency of groundwater pollutant removal is discovered; the lower-level objectives include the relationship between the amount of pumping and injection water and the concentration of groundwater pollutants; The lower optimization problem is used to simulate the migration of groundwater pollutants to calculate the final residual amount of groundwater pollutants: ； in: is the pollutant degradation rate, is the hydrodynamic dispersion coefficient, is the groundwater flow velocity, and The pollutant concentrations are The second-order gradient term and the first-order gradient term of represents the total number of grid cells after the contaminated site is discretized. represents the grid cell number, , Indicates that given the upper decision variable The optimal set of lower-level decision variables under ; The two-layer multi-objective optimization framework uses explicit knowledge transfer to perform data interaction between the two auxiliary tasks and the original problem to enhance the optimization effect. That is, after a certain number of iterations, an explicit knowledge transfer across tasks is performed to ensure the co-evolution of the main task and the auxiliary task.

8. The method for simulating and optimizing the groundwater pumping and treatment pollution remediation system of a contaminated site based on a multi-form evolutionary search paradigm according to claim 1 or 7, characterized in that: Prioritize solutions that belong to the Pareto front in the auxiliary task. The fitness of the solution of the auxiliary task in the main task must be higher than the current population mean. The solution is screened by crowding distance to avoid population aggregation and ensure that the layout of the pumping and injection wells covers different sub-areas of the contaminated site. When the solution of the auxiliary task is transferred to the main task, the lower-level decision variables including the amount of water pumped and injected are supplemented, and the expansion is completed by randomly extracting the lower-level parameters of the historical optimal solution; The feasible solution of the main task is fed back to the auxiliary task to guide its search direction, including initializing the auxiliary population using the verified well location scheme.

9. A computer device comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, wherein: When the computer program is running, the processor executes the simulation-optimization method for groundwater injection-treatment pollution remediation system of contaminated sites based on a multi-form evolutionary search paradigm as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores programs or instructions, and when the programs or instructions are executed by a computer device, the computer device executes the simulation-optimization method for groundwater pumping-treatment pollution remediation system of contaminated sites based on a multi-form evolutionary search paradigm as described in any one of claims 1-8.

Images