Method, device and system for repairing nitrogen and phosphorus polluted water and storage medium

Abstract

The invention discloses a method, a device and a system for repairing a nitrogen and phosphorus polluted water body and a storage medium. The method comprises the following steps: acquiring historical experimental data of nitrogen and phosphorus absorption of plants; constructing a multi-target plant configuration optimization model according to historical experimental data; based on real-time experimental data, dynamically adjusting input parameters of the multi-target plant configuration optimization model to obtain an optimal multi-target plant configuration optimization model; the to-be-processed environment data is input into the optimal multi-target plant configuration optimization model for comprehensive scoring, the optimal scheme for repairing the nitrogen and phosphorus polluted water is determined, and by adopting the technical scheme, the nitrogen and phosphorus polluted water repairing effect is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of ecological restoration, and in particular relates to a method and device, a system, and a storage medium for repairing nitrogen and phosphorus polluted water. Background Art

[0002] Wetland is an ecosystem that transitions from terrestrial to aquatic, i.e. natural or artificially constructed swamps, peatlands, water areas, static or flowing freshwater, brackish water, salt water, including seawater with a depth of no more than 6m at low tide. Artificial wetlands are complex ecosystems composed of specific substrates, aquatic plants, microorganisms, animals and water bodies, which are artificially designed and constructed by simulating natural wetlands. Artificial wetland technology has entered the field of water pollution control as a new and unique sewage treatment technology. Its purification mechanism includes substrate filtration, adsorption, sedimentation, ion exchange, antagonism, redox reaction, plant absorption and microbial degradation to achieve the degradation and removal of pollutants.

[0003] Plants are an indispensable part of the wetland system, and the growth of plants directly affects the sewage purification effect of the wetland system. The growth of plants themselves requires direct adsorption of pollutants in the water as nutrients, while delivering oxygen to the matrix layer to create a good aerobic environment for root microorganisms. Plants can also maintain and enhance the hydraulic transmission of the matrix. Common wetland plants include cattail, iris, wild rice, rush, etc. The planting density generally needs to be adjusted according to the actual project, which often requires a lot of experimental experiments. Most wetland plants are herbaceous plants. The cold weather in winter will cause some plants to die. The plant humus will re-enter the water body and return the absorbed nitrogen and phosphorus to the water body. At the same time, it will breed a large number of bacteria to destroy the ecological balance of the wetland. Therefore, a more scientific plan needs to be specified for regular cleaning and maintenance.

[0004] With the rapid development of agriculture and industry, the problem of nitrogen and phosphorus pollution in water bodies has become increasingly serious, causing frequent eutrophication of water bodies, which not only destroys the balance of aquatic ecosystems, but also poses a potential threat to human health. In the years of development and application, although artificial wetland technology has played an important role in removing nitrogen and phosphorus from water bodies, it also faces some challenges and problems. In particular, management, maintenance and design standardization need further optimization and improvement.

[0005] With the long-term operation of artificial wetlands, the lack of effective maintenance and management measures has gradually become the main factor restricting their long-term stable operation. For example, the management and maintenance of plants, the formation of wetland dead zones, and the calculation of economic costs all need to be given sufficient attention and timely treatment. At present, most artificial wetlands lack timely, scientific and reasonable maintenance, which not only affects the purification effect of the wetlands, but also shortens their service life. In addition, there are still some problems in the design process of artificial wetland technology. Current designs are mostly based on experience and statistical data, lacking sufficient scientific basis and standardized guidance. Although traditional wetland plant restoration technology provides a natural and sustainable solution, its experience-based method has obvious deficiencies in scientific basis. It is difficult to fully consider a variety of key factors including plant species selection, planting density, water depth and water flow rate, and lacks the ability to dynamically adjust with environmental changes. Summary of the invention

[0006] The technical problem to be solved by the present invention is to provide a method and device, system, and storage medium for repairing nitrogen and phosphorus polluted water bodies, and to optimize the wetland plant configuration using a genetic programming algorithm (GP) to improve the repair effect of nitrogen and phosphorus polluted water bodies.

[0007] To achieve the above object, the present invention adopts the following technical solution:

[0008] A method for repairing nitrogen and phosphorus polluted water, comprising:

[0009] Obtain historical experimental data on plant nitrogen and phosphorus absorption;

[0010] Based on historical experimental data, a multi-objective plant configuration optimization model is constructed;

[0011] Based on real-time experimental data, the input parameters of the multi-objective plant configuration optimization model are dynamically adjusted to obtain the optimal multi-objective plant configuration optimization model;

[0012] The environmental data to be processed are input into the optimal multi-objective plant configuration optimization model for comprehensive scoring to determine the best solution for repairing nitrogen and phosphorus polluted water bodies.

[0013] Preferably, the wetland plant configuration is optimized by a genetic programming algorithm based on real-time experimental data to obtain a multi-objective plant configuration optimization model; wherein the input data of the multi-objective plant configuration optimization model includes: plant species, planting density, water depth, and water flow velocity; the output data of the multi-objective plant configuration optimization model includes: nitrogen and phosphorus removal rate, plant growth status, economic cost, and ecological functional diversity; the multi-objective fitness function of the multi-objective plant configuration optimization model is used to evaluate the overall performance of each individual in the multi-objective optimization.

[0014] Preferably, the input parameters of the dynamic adjustment multi-objective plant configuration optimization model include:

[0015] Collect water quality and meteorological data in real time;

[0016] The optimization results of the multi-objective optimization model are used as part of the initial population to generate new individuals;

[0017] Evaluate the performance of each individual in the initial population under the current environment;

[0018] According to the changes in real-time data, the parameters of genetic operations such as selection, crossover, and mutation are dynamically adjusted to generate new offspring;

[0019] Evaluate the performance of the newly generated offspring in the current environment;

[0020] Repeat the above steps until the predetermined number of iterations is reached.

[0021] The present invention also provides a device for repairing nitrogen and phosphorus polluted water, comprising:

[0022] The acquisition module is used to obtain the historical experimental data of nitrogen and phosphorus absorption by plants;

[0023] A construction module is used to construct a multi-objective plant configuration optimization model based on historical experimental data;

[0024] An optimization module is used to dynamically adjust the input parameters of the multi-objective plant configuration optimization model based on real-time experimental data to obtain the optimal multi-objective plant configuration optimization model;

[0025] The restoration module is used to input the environmental data to be processed into the optimal multi-objective plant configuration optimization model for comprehensive scoring, and determine the best solution for repairing nitrogen and phosphorus polluted water bodies.

[0026] Preferably, the construction module optimizes the wetland plant configuration through a genetic programming algorithm based on real-time experimental data to obtain a multi-objective plant configuration optimization model.

[0027] Preferably, the input data of the multi-objective plant configuration optimization model include: plant species, planting density, water depth, and water flow velocity; the output data of the multi-objective plant configuration optimization model include: nitrogen and phosphorus removal rate, plant growth status, economic cost, and ecological functional diversity; the multi-objective fitness function of the multi-objective plant configuration optimization model is used to evaluate the overall performance of each individual in the multi-objective optimization.

[0028] The present invention also provides a system for repairing nitrogen and phosphorus polluted water bodies, comprising: a memory and a processor, wherein the memory stores a computer program run by the processor, and the computer program executes a method for repairing nitrogen and phosphorus polluted water bodies when run by the processor.

[0029] The present invention also provides a storage medium, on which a computer program is stored, and when the computer program is run, a method for repairing a water body polluted by nitrogen and phosphorus is executed.

[0030] The present invention realizes dynamic environmental adaptability optimization by combining genetic programming algorithms and real-time data monitoring, ensuring that plant configuration schemes are efficient, economical and eco-friendly under different environmental conditions, thereby improving the effect of wetland plants in repairing nitrogen and phosphorus polluted water bodies. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0032] Figure 1 The present invention is a flowchart of a method for repairing nitrogen and phosphorus polluted water bodies according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0035] Embodiment 1:

[0036] like Figure 1 As shown, the embodiment of the present invention provides a method for optimizing wetland plant restoration of nitrogen and phosphorus polluted water bodies based on a genetic programming algorithm. By combining the genetic programming algorithm and real-time data monitoring, dynamic environmental adaptability optimization is achieved to ensure that the plant configuration scheme is efficient, economical and eco-friendly under different environmental conditions, thereby improving the effect of wetland plant restoration of nitrogen and phosphorus polluted water bodies. The method comprises the following steps:

[0037] S100, plant selection and preliminary experiments

[0038] In this step, appropriate plant species are selected and preliminary experiments are conducted to verify their performance under specific environmental conditions, and the performance data of different plants (nitrogen and phosphorus removal rates, biomass, economic costs, etc.) are output to provide basic data for the next step.

[0039] S101 Water sample collection:

[0040] Take samples of target water bodies, measure nitrogen and phosphorus concentrations, and assess the degree of pollution. For example, the nitrogen and phosphorus concentrations of a lake are 20 mg / L and 10 mg / L, respectively, which is considered lightly polluted.

[0041] S102 Plant Selection:

[0042] We screened out wetland plant species with strong absorption capacity for nitrogen and phosphorus, such as cattail, reed and rush as candidate plants.

[0043] S103 Preliminary Experiment:

[0044] Under laboratory conditions, selected plants are cultivated on a small scale to measure their nitrogen and phosphorus absorption efficiency and obtain basic data.

[0045] Under laboratory conditions, cattail, reed and rush were planted separately, and their nitrogen and phosphorus absorption efficiency was recorded at different planting densities. 2 When the planting density of reed is 15 plants / m 2 When the planting density of rush is 20 plants / m 2 The nitrogen and phosphorus removal rate was 60%.

[0046] Through this step, the nitrogen and phosphorus absorption efficiency of different plants under different conditions was obtained, providing basic data for subsequent optimization.

[0047] S200, building a multi-objective plant configuration optimization model

[0048] In this step, a multi-objective plant configuration optimization model is established, and based on the plant species, planting density, water depth, water flow velocity, etc. obtained in the previous step, a set of optimization schemes is generated, which comprehensively considers multiple objectives (such as nitrogen and phosphorus removal rate, plant growth conditions, economic costs, and ecological functional diversity).

[0049] S201 defines input variables:

[0050] Plant species (multiple plant combinations), planting density (number of plants per square meter), water depth (cm), and water velocity (m / s). For example, input variables include plant species (cattail, reed, rush), planting density (10-20 plants / m 2 ), water depth (20-50cm), water flow velocity (0.1-0.5m / s).

[0051] S202 defines output variables:

[0052] Nitrogen and phosphorus removal rate (%), plant growth conditions (such as biomass, root system development, etc.), economic cost (yuan / m2), ecological functional diversity (such as biodiversity index, carbon sink, etc.). For example: output variables include nitrogen and phosphorus removal rate (%), biomass (kg / m 2 ), economic cost (yuan / m 2 ), biodiversity index.

[0053] S203 initializes the population:

[0054] Generate an initial population, each individual represents a plant configuration scheme. Suppose 100 initial populations are generated, each individual represents a specific plant configuration scheme, for example:

[0055] Individual1=[Typha, 10 plants / m 2 ,30cm,0.2m / s]

[0056] Indicates that each individual is composed of 4 genes (plant species, planting density, water depth, water flow speed). S204 defines a multi-objective fitness function:

[0057] F i =w1·f 1i +w2·f 2i -w3·f 3i +w4·f 4i

[0058] Among them, F i is the fitness value of the ith individual. Each individual has a plant configuration scheme and a corresponding fitness value. i It is used to evaluate the overall performance of the i-th individual in multi-objective optimization. The higher the fitness value, the better the performance of the individual after comprehensively considering all objectives. 1i is the nitrogen and phosphorus removal rate of the ith individual, f 2i is the plant growth status of the ith individual, f 3i is the economic cost of the ith individual, f 4i is the ecological functional diversity of the ith individual, w1, w2, w3, and w4 are weight coefficients, which can be adjusted according to actual needs.

[0059] S205 fitness value calculation:

[0060] Based on the above F i =w1·f 1i +w2·f 2i -w3·f 3i +w4·f 4i , calculate the fitness value F of each individual i .

[0061] S206 Genetic Operations:

[0062] ①Selection operation: Use roulette selection, as follows:

[0063]

[0064] Among them, P i is the probability that the ith individual is selected, F i is the fitness value of the ith individual, N is the population size, if the initial population is 100, then N = 100.

[0065] ②Crossover operation: Use single-point crossover, as follows:

[0066] Child1=Parent1[0:k]+Parent2[k+1:n]

[0067] Child2=Parent2[0:k]+Parent2[k+1:n]

[0068] Where k is a randomly selected crossover point and n is the length of the individual.

[0069] Assume Parent1 = [Cattail, 10 plants / m 2 ,30cm,0.2m / s] and Parent2=[reed,15 plants / m 2 ,40cm,0.3m / s], randomly select the intersection point k=2, then the generated children are:

[0070] Child1=[Typha, 10 plants / m 2 ,40cm,0.3m / s]

[0071] Child2=[Reed, 15 plants / m 2 ,30cm,0.2m / s]

[0072] In this example, the length of the individual n=4 means that each individual consists of 4 genes (plant species, planting density, water depth, water flow speed). The crossover point k=2 means that the crossover is performed at the second gene. Therefore, Child1 inherits the first two genes (plant species and planting density) from Parent1 and the last two genes (water depth and water flow speed) from Parent2. Similarly, Child2 inherits the first two genes from Parent2 and the last two genes from Parent1.

[0073] ③ Mutation operation: Use bit flip mutation, as follows:

[0074]

[0075] Among them, p m is the probability of mutation, which is a value between 0 and 1, indicating the probability of each gene mutation. It is usually set to a smaller value (such as 0.01 to 0.1) to maintain the diversity of the population. Rand is a random number generated between 0 and 1 to determine whether a mutation occurs. i For each gene in an individual, such as plant species, planting density, water depth, water flow speed, etc. i For mutation operation: If the random number rand is less than the mutation probability p m , then the gene mutates. The mutation can be a random change in the value of the gene, or a fine-tuning within a certain range.

[0076] Assume Child1 = [Cattail, 10 plants / m 2 ,40cm,0.3m / s], randomly select gene positions as planting density, random number rand=0.03 <p m =0.05, the planting density is 10 plants / m 2 Change to 15 plants / m 2 , the new individual generated is: Mutated i =[Typha, 15 plants / m 2 ,40cm,0.3m / s]

[0077] ④ Iterative optimization: Repeat the selection, crossover, and mutation operations until the predetermined number of iterations is reached or the fitness value no longer increases significantly.

[0078] For example, after 100 iterations, 100 optimization schemes are generated, and the fitness value of each scheme gradually increases, and finally the optimal plant configuration scheme is found.

[0079] Therefore, in this step, 100 optimization schemes were generated by constructing a multi-objective optimization model, taking multiple factors into consideration.

[0080] S300, Dynamic Environmental Adaptability Plant Configuration Optimization

[0081] This step outputs a dynamically adjusted optimization plan based on the optimization results of the multi-objective optimization model in the previous step and real-time water quality data and meteorological data. In other words, the optimization plan is dynamically adjusted in the case of real-time environmental changes to ensure that the best results can be achieved under different environmental conditions.

[0082] S301 Real-time Data Integration:

[0083] Combined with Internet of Things technology, water quality and meteorological data are collected in real time, and the input parameters of the optimization model are adjusted dynamically.

[0084] Data collection: Install water quality monitoring equipment and weather stations to collect water quality data (such as nitrogen and phosphorus concentrations, dissolved oxygen, etc.) and meteorological data (such as temperature, humidity, light, etc.) in real time. For example, the water quality data collected in real time is that the nitrogen and phosphorus concentrations are 18mg / L and 9mg / L respectively, and the meteorological data is 25℃, 70% humidity, and 500lux light intensity.

[0085] Data processing: Preprocess the collected data, such as denoising and normalization, to ensure the accuracy and usability of the data. For example, use a filter to remove noise and normalize the data to between 0 and 1.

[0086] S302 Initialize the population:

[0087] The optimization results of the multi-objective optimization model are used as part of the initial population to generate new individuals. Here, the optimization results of the multi-objective optimization model are used as part of the initial population to ensure that there are known high-quality individuals in the new population. The details are as follows:

[0088] Select high-quality individuals: From the 100 optimization schemes of the multi-objective optimization model, select the top 50 individuals with higher fitness values ​​as part of the initial population. Assume that the optimal individual generated by the multi-objective optimization model is Optimal1 = [Cattail, 15 plants / m 2 ,35cm,0.25m / s] and add it directly into the initial population.

[0089] Generate new individuals: Generate 50 new individuals based on real-time data to supplement the initial population. For example, based on real-time water quality data and meteorological data, generate 50 new individuals to ensure the diversity of the initial population. For example, new individual New1 = [reed, 12 plants / m 2 ,32cm,0.28m / s].

[0090] S303 first fitness evaluation:

[0091] Evaluate the performance of each individual in the initial population under the current environment. Use real-time data and machine learning models to predict the fitness value F of each individual i , evaluate the performance of each individual in the current environment.

[0092] Data prediction: Use machine learning models to predict the nitrogen and phosphorus removal rate, plant growth status, economic cost, and ecological functional diversity of each individual. Use historical data (such as water quality data and plant growth data from the past few years) to train machine learning models (such as neural networks, support vector machines, etc.) to predict the nitrogen and phosphorus removal effects of different plant configurations. For example, based on real-time data, the machine learning model predicts that the nitrogen and phosphorus removal rate of individual Optimal1 is 72%, and the biomass is S202 kg / m 2 , the economic cost is 52 yuan / m2 , the biodiversity index is 0.85.

[0093] According to F i =w1·f 1i +w2·f 2i -w3·f 3i +w4·f 4i , calculate the fitness value F of each individual i .

[0094] S304 Adaptive Genetic Operation:

[0095] According to the changes in real-time data, the parameters of genetic operations such as selection, crossover, and mutation are dynamically adjusted to generate new offspring.

[0096] Selection operation: Use roulette selection method, according to the fitness value F i Select individuals.

[0097] Crossover operation: Use the single-point crossover method to generate new offspring.

[0098] Mutation operation: Use bit flipping mutation to randomly change the values ​​of certain genes.

[0099] These steps are consistent with the corresponding parts in constructing the multi-objective plant configuration optimization model above.

[0100] S305 Second fitness evaluation

[0101] Evaluate the performance of the newly generated offspring in the current environment. Re-evaluate the fitness value F of the newly generated offspring i , ensuring the continuity and effectiveness of the optimization process. Because adaptive genetic operations generate new offspring, the gene combinations and parameters of these offspring may be different from those of individuals in the initial population. Since environmental conditions are changing dynamically, new offspring need to be evaluated in the current environment to ensure that their fitness values ​​are accurate. That is, the first fitness evaluation is to ensure the performance of individuals in the initial population in the current environment, while the second fitness evaluation is to ensure the performance of new offspring generated after adaptive genetic operations in the current environment.

[0102] Moreover, the second fitness assessment will also evaluate the ecological functional diversity of the optimization scheme to ensure that the optimization scheme is not only efficient but also eco-friendly.

[0103] F i =w1·f 1i +w2·f 2i -w3·f 3i +w4·f 4i +w5·f 5i

[0104] Among them, f5i is the ecological function diversity index of the i-th individual, that is, f 5i Integrate into the fitness evaluation, w5 is the corresponding weight coefficient.

[0105] Relying solely on the biodiversity index 4i It cannot fully reflect the functional diversity of the ecosystem. Increasing can more comprehensively evaluate the ecological benefits of the optimization scheme. For example, an ecosystem may have high biodiversity, but if the plants in it perform poorly in terms of carbon sequestration capacity, soil and water conservation, etc., the overall ecological benefit is still not high. Therefore, f 5i The carbon sink is defined as an indicator of ecological functional diversity to assess the carbon fixation capacity of plants and reduce greenhouse gas emissions.

[0106] S306 Iteration Optimization:

[0107] Repeat the above operation until the predetermined number of iterations is reached or the fitness value no longer increases significantly. For example, if the number of iterations is set to 50, 50 dynamically adjusted optimization schemes are generated after 50 iterations, and the fitness value of each scheme gradually increases, ensuring that the best results can be achieved under different environmental conditions.

[0108] Therefore, this step uses the optimization results of the multi-objective optimization model in the initialization of the population to ensure that there are known high-quality individuals in the new population. Fitness evaluation is performed once before and after the adaptive genetic operation to ensure that each generated offspring can be effectively evaluated in the current environment. The combination of adaptive genetic operation and fitness evaluation ensures the effectiveness and real-time performance of the optimization scheme. Finally, through iterative optimization, 50 dynamically adjusted optimization schemes were generated to ensure the best results under different environmental conditions.

[0109] S400, Field Application and Monitoring

[0110] In this step, the optimization schemes generated by the dynamic environmental adaptability optimization step, for example, 50 optimization schemes, are applied to the actual environment, and field monitoring (nitrogen and phosphorus removal effects, biomass, economic costs, ecological functional diversity, etc.) is carried out to evaluate their actual effects.

[0111] S401 Program Implementation:

[0112] Selection of test area: Select a representative test area to ensure that the test results are universal and generalizable.

[0113] Scheme layout: Plant configurations were arranged in the test area according to 50 optimized schemes to ensure that each scheme had an independent test area.

[0114] Implementation cycle: Set a reasonable implementation cycle, such as 3 or 6 months, to ensure sufficient data for evaluation.

[0115] S402 Data Collection:

[0116] Water quality monitoring: Regularly collect water quality data in the test area, including nitrogen and phosphorus concentrations, dissolved oxygen, etc.

[0117] Plant growth monitoring: Regularly measure plant growth conditions, such as biomass, plant height, etc.

[0118] Economic cost record: Record the economic cost of each plan, including the cost of plant procurement, planting, maintenance, etc.

[0119] Ecological function monitoring: Evaluate the ecological function diversity of each plan, such as carbon sequestration, soil and water conservation capacity, etc.

[0120] S403 data analysis:

[0121] Performance evaluation: Based on the collected data, each scheme is evaluated in terms of nitrogen and phosphorus removal effect, biomass, economic cost, ecological function diversity and other performance indicators.

[0122] S404 Comprehensive scoring: Based on the evaluation results, each plan is comprehensively scored to determine the best plan.

[0123] The present invention achieves comprehensive, efficient and flexible optimization of plant configuration schemes by combining genetic programming algorithms, multi-objective optimization and dynamic optimization, ensuring the best results under different environmental conditions. Specifically:

[0124] 1. Application of genetic programming algorithm: Genetic programming algorithm is used to generate a diverse initial population. Each individual can be a complex expression describing different plant configuration schemes. Through selection, crossover and mutation operations, new optimization schemes are continuously generated to ensure the dynamics and flexibility of the plant configuration optimization process.

[0125] 2. Integration of multi-objective optimization: It comprehensively considers multiple objectives such as nitrogen and phosphorus removal rate, biomass, economic cost and ecological functional diversity. It not only performs well in environmental governance, but also achieves a balance between economic and ecological benefits, ensuring the healthy growth of plants and the overall restoration effect.

[0126] 3. Implementation of dynamic optimization: Through dynamic environmental adaptability optimization, using genetic programming algorithms and real-time data, the plant configuration plan is continuously adjusted and optimized to generate the final dynamically adjusted optimization plan, ensuring the efficiency and adaptability of the optimization plan under different environmental conditions.

[0127] Embodiment 2:

[0128] The embodiment of the present invention further provides a device, including:

[0129] The acquisition module is used to obtain the historical experimental data of nitrogen and phosphorus absorption by plants;

[0130] A construction module is used to construct a multi-objective plant configuration optimization model based on historical experimental data;

[0131] An optimization module is used to dynamically adjust the input parameters of the multi-objective plant configuration optimization model based on real-time experimental data to obtain the optimal multi-objective plant configuration optimization model;

[0132] The restoration module is used to input the environmental data to be processed into the optimal multi-objective plant configuration optimization model for comprehensive scoring, and determine the best solution for repairing nitrogen and phosphorus polluted water bodies.

[0133] As an implementation method of the embodiment of the present invention, the construction module optimizes the wetland plant configuration through a genetic programming algorithm based on real-time experimental data to obtain a multi-objective plant configuration optimization model.

[0134] As an implementation method of an embodiment of the present invention, the input data of the multi-objective plant configuration optimization model includes: plant species, planting density, water depth, and water flow velocity; the output data of the multi-objective plant configuration optimization model includes: nitrogen and phosphorus removal rate, plant growth status, economic cost, and ecological functional diversity; the multi-objective fitness function of the multi-objective plant configuration optimization model is used to evaluate the overall performance of each individual in the multi-objective optimization.

[0135] Embodiment 3:

[0136] An embodiment of the present invention also provides a system for repairing nitrogen and phosphorus polluted water bodies, including: a memory and a processor, wherein the memory stores a computer program run by the processor, and the computer program executes a method for repairing nitrogen and phosphorus polluted water bodies when run by the processor.

[0137] Embodiment 4:

[0138] An embodiment of the present invention further provides a storage medium, on which a computer program is stored, and when the computer program is run, a method for repairing a water body polluted by nitrogen and phosphorus is executed.

[0139] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A method for repairing nitrogen and phosphorus polluted water, characterized in that: include: Obtain historical experimental data on plant nitrogen and phosphorus absorption; Based on historical experimental data, a multi-objective plant configuration optimization model is constructed; Based on real-time experimental data, the input parameters of the multi-objective plant configuration optimization model are dynamically adjusted to obtain the optimal multi-objective plant configuration optimization model; The environmental data to be processed are input into the optimal multi-objective plant configuration optimization model for comprehensive scoring to determine the best solution for repairing nitrogen and phosphorus polluted water bodies.

2. The method for repairing nitrogen and phosphorus polluted water according to claim 1, characterized in that: According to real-time experimental data, the wetland plant configuration is optimized through the genetic programming algorithm to obtain a multi-objective plant configuration optimization model; among them, the input data of the multi-objective plant configuration optimization model includes: plant species, planting density, water depth, and water flow velocity; the output data of the multi-objective plant configuration optimization model includes: nitrogen and phosphorus removal rate, plant growth status, economic cost, and ecological functional diversity; the multi-objective fitness function of the multi-objective plant configuration optimization model is used to evaluate the overall performance of each individual in the multi-objective optimization.

3. The method for repairing nitrogen and phosphorus polluted water according to claim 2, characterized in that: The input parameters of the dynamic adjustment multi-objective plant configuration optimization model include: Collect water quality and meteorological data in real time; The optimization results of the multi-objective optimization model are used as part of the initial population to generate new individuals; Evaluate the performance of each individual in the initial population under the current environment; According to the changes in real-time data, the parameters of genetic operations such as selection, crossover, and mutation are dynamically adjusted to generate new offspring; Evaluate the performance of the newly generated offspring in the current environment; Repeat the above steps until the predetermined number of iterations is reached.

4. A device for repairing nitrogen and phosphorus polluted water, characterized in that: include: The acquisition module is used to obtain the historical experimental data of nitrogen and phosphorus absorption by plants; A construction module is used to construct a multi-objective plant configuration optimization model based on historical experimental data; An optimization module is used to dynamically adjust the input parameters of the multi-objective plant configuration optimization model based on real-time experimental data to obtain the optimal multi-objective plant configuration optimization model; The restoration module is used to input the environmental data to be processed into the optimal multi-objective plant configuration optimization model for comprehensive scoring, and determine the best solution for repairing nitrogen and phosphorus polluted water bodies.

5. The device for repairing nitrogen and phosphorus polluted water as claimed in claim 4, characterized in that: The construction module optimizes the wetland plant configuration through genetic programming algorithm according to real-time experimental data to obtain a multi-objective plant configuration optimization model.

6. The device for repairing nitrogen and phosphorus polluted water as claimed in claim 5, characterized in that: The input data of the multi-objective plant configuration optimization model include: plant species, planting density, water depth, and water flow velocity; the output data of the multi-objective plant configuration optimization model include: nitrogen and phosphorus removal rate, plant growth status, economic cost, and ecological functional diversity; the multi-objective fitness function of the multi-objective plant configuration optimization model is used to evaluate the overall performance of each individual in the multi-objective optimization.

7. A system for repairing nitrogen and phosphorus polluted water, characterized in that: include: A memory and a processor, wherein the memory stores a computer program executed by the processor, and when the computer program is executed by the processor, the method for repairing nitrogen and phosphorus polluted water as described in any one of claims 1 to 3 is executed.

8. A storage medium, characterized in that: The storage medium stores a computer program, which, when running, executes the method for repairing nitrogen and phosphorus polluted water as described in any one of claims 1 to 3.

Images