Method, device and server for planning the placement of drugs for treating blue algae blooms
By constructing mathematical models of hydrodynamics, water quality and cyanobacteria migration, optimizing the drug delivery strategy, solving the problem of inaccurate drug delivery in the existing technology, and improving the treatment effect of cyanobacteria blooms and the utilization rate of drug.
Patent Information
- Application Number
- CN202411281693.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-13
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-09-13
AI Technical Summary
When preventing cyanobacteria blooms, the drug delivery plan cannot accurately determine the optimal drug delivery route and dose, resulting in low drug utilization rate and insufficient consideration of the impact of water flow on drug diffusion, and poor treatment effect.
By constructing a mathematical model of hydrodynamic, water quality and cyanobacterial migration, combining calculation modules and optimization modules, dynamically couple the drug administration strategy, determine the target drug administration strategy, and refine the drug administration.
It significantly improves the treatment effect of cyanobacteria blooms, improves the utilization rate of drugs, ensures even distribution of drugs, and avoids excessive local concentrations or missing drugs.
Smart Images

Figure CN118780216B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of water environment treatment, and in particular to a method, a device and a server for planning the placement of a medicament for treating blue algae blooms. Background Art
[0002] At present, in order to prevent the sudden growth and reproduction of large numbers of cyanobacterial cells in water bodies and the formation of cyanobacterial blooms, relevant technologies have proposed that water quality monitoring and early warning can be carried out, and the dosage of a single agent can be determined based on the early warning signal and linear relationship, thereby combining the early warning technology with the algae inhibition technology to achieve autonomous quantitative dosage based on the early warning signal.
[0003] However, the above-mentioned drug delivery plan only considers the influencing factors of water quality and delivers the drug based on the predicted concentration. Its control is relatively simple and it is unable to accurately determine the optimal route and amount of drug delivery. Therefore, it is easy for local concentration to be too high or drug leakage to occur, resulting in low drug utilization rate. In addition, the above-mentioned plan does not fully consider the impact of water flow on drug diffusion, and is unable to provide a refined and locally adapted drug delivery strategy, resulting in poor control effect on cyanobacteria blooms. Summary of the invention
[0004] In view of this, the purpose of the present invention is to provide a method, device and server for planning the placement of pesticides for the control of cyanobacteria blooms. The dosing strategy is determined by constructing a mathematical model of hydrodynamics, water quality and cyanobacteria migration, and the dosing strategy is optimized through the coupling of a calculation module and an optimization module. This can significantly improve the control effect of cyanobacteria blooms and improve the utilization rate of pesticides.
[0005] In a first aspect, an embodiment of the present invention provides a method for planning the placement of an agent for controlling blue-green algae blooms, the method being applied to a drug placement planning system, the drug placement planning system comprising: a water quality detection device, a calculation module and an optimization module, the method comprising: obtaining real-time water quality data through a water quality detection device, wherein the real-time water quality data comprises: water pH value, dissolved oxygen concentration, nutrient concentration and light intensity; sending the water quality data to a calculation module, and through the calculation module, performing data model construction processing on the water quality data to determine a hydrodynamic model, a water quality model and a blue-green algae diffusion model, wherein the hydrodynamic model is used to simulate the flow field distribution of the water body, the water quality model is used to simulate the water quality distribution, and the blue-green algae diffusion model is used to simulate the blue-green algae concentration distribution; through the optimization module, optimizing and analyzing the water flow field distribution, the water quality distribution and the blue-green algae concentration distribution to determine the initial dosing strategy, and dynamically coupling the calculation module and the optimization module to optimize the initial dosing strategy and determine the target dosing strategy.
[0006] In one embodiment, after the steps of constructing a data model for water quality data and determining a hydrodynamic model, a water quality model and a cyanobacteria diffusion model through a calculation module, the method includes: discretizing the hydrodynamic model, the water quality model and the cyanobacteria diffusion model to convert the model from a continuous partial differential equation into a group of algebraic equations; utilizing the interaction relationship between the hydrodynamic model, the water quality model and the cyanobacteria diffusion model, coupling the hydrodynamic model, the water quality model and the cyanobacteria diffusion model to organically combine the solution process of the group of algebraic equations, and determining the solution results of the group of algebraic equations as the water flow field distribution, the water quality distribution and the cyanobacteria concentration distribution.
[0007] In one embodiment, after the step of coupling the hydrodynamic model, the water quality model and the cyanobacteria diffusion model, the method includes: setting the boundary conditions of the hydrodynamic model according to the inflow and outflow of the water body and the shear stress of the fluid wall; setting the boundary conditions of the water quality model according to the initial distribution of nutrients and cyanobacteria; setting the boundary conditions of the cyanobacteria diffusion model according to the adsorption and drift effect of cyanobacteria at the water body boundary; substituting the boundary conditions of the hydrodynamic model, the boundary conditions of the water quality model and the boundary conditions of the cyanobacteria diffusion model as well as the source and sink terms fed back by the optimization module into the coupled algebraic equation group for solving, and determining the water flow field distribution, water quality distribution and cyanobacteria concentration distribution.
[0008] In one embodiment, after the step of determining the solution results of the algebraic equation group as the water flow field distribution, water quality distribution and cyanobacteria concentration distribution, it includes: sending the water flow field distribution, water quality distribution and cyanobacteria concentration distribution to an optimization module, and visualizing the water flow field distribution, water quality distribution and cyanobacteria concentration distribution to generate a water flow field image, a water quality distribution image and a cyanobacteria concentration image.
[0009] In one embodiment, the calculation module and the optimization module are dynamically coupled to optimize the initial dosing strategy, and the step of determining the target dosing strategy includes: combining the initial dosing strategy as a source-sink term with the hydrodynamic model, water quality model and cyanobacteria diffusion model constructed by the calculation module to determine an updated model group, and solving the updated model group through the calculation module to determine the water flow field distribution, water quality distribution and cyanobacteria concentration distribution corresponding to each moment after the update; constructing a local optimization model using the source-sink term, the water flow field distribution, the water quality distribution and the cyanobacteria concentration distribution, and solving the local optimization model through a preset standard solver to end the iterative optimization of this round of dosing strategy and determine the updated dosing strategy.
[0010] In one embodiment, the step of constructing a local optimization model using source-sink terms, water flow field distribution, water quality distribution and cyanobacteria concentration distribution includes: performing local sensitivity analysis on the source-sink terms, determining changes in water flow field distribution, water quality distribution and cyanobacteria concentration distribution as the source-sink terms change, and establishing a sensitivity matrix based on the changes; obtaining the objective function of the optimization module, and constructing a local optimization model using the sensitivity matrix and the objective function.
[0011] In one embodiment, after solving the local optimization model by a preset standard solver to end the iterative optimization of the dosing strategy of this round and determine the updated dosing strategy, the method includes: when the difference between the dosing strategies obtained by two adjacent iterative optimizations is less than a preset threshold, or the number of iterative optimizations reaches a preset maximum number of iterations, stopping the iterative optimization process and determining the dosing strategy updated by the last iterative update as the target dosing strategy.
[0012] In a second aspect, an embodiment of the present invention further provides a device for planning the administration of pesticides for the treatment of cyanobacteria blooms. The device is applied to a pesticide administration planning system. The pesticide administration planning system includes: water quality detection equipment, a calculation module and an optimization module. The device includes: a data acquisition unit. The data acquisition module acquires real-time water quality data through the water quality detection equipment, wherein the real-time water quality data includes: water pH value, dissolved oxygen concentration, nutrient concentration and light intensity; a model construction unit, which sends the water quality data to the calculation module, and through the calculation module, performs data model construction processing on the water quality data to determine a hydrodynamic model, a water quality model and a cyanobacteria diffusion model, wherein the hydrodynamic model is used to simulate the flow field distribution of the water body, the water quality model is used to simulate the water quality distribution, and the cyanobacteria diffusion model is used to simulate the cyanobacteria concentration distribution; a strategy optimization unit, through the optimization module, optimizes and analyzes the water flow field distribution, the water quality distribution and the cyanobacteria concentration distribution, determines the initial dosing strategy, and dynamically couples the calculation module and the optimization module to optimize the initial dosing strategy and determine the target dosing strategy.
[0013] In a third aspect, an embodiment of the present invention further provides a server, comprising a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement any one of the methods provided in the first aspect.
[0014] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement any one of the methods provided in the first aspect.
[0015] The embodiments of the present invention bring the following beneficial effects:
[0016] The embodiment of the present invention provides a method, device and server for planning the placement of a drug for controlling blue algae blooms. After obtaining real-time water quality data through a water quality detection device, the method sends the water quality data to a calculation module, and through the calculation module, performs data model construction processing on the water quality data to determine a hydrodynamic model, a water quality model and a blue algae diffusion model. Then, through the optimization module, the water flow field distribution, the water quality distribution and the blue algae concentration distribution are optimized and analyzed to determine the initial drug dosing strategy, and the calculation module and the optimization module are dynamically coupled to optimize the initial drug dosing strategy and determine the target drug dosing strategy. The embodiment of the present invention determines the drug dosing strategy by constructing a mathematical model of hydrodynamics, water quality and blue algae migration, and optimizes the drug dosing strategy through the coupling of the calculation module and the optimization module, which can significantly improve the control effect of blue algae blooms and improve the drug utilization rate.
[0017] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.
[0018] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0020] Figure 1 A schematic diagram of a flow chart of a method for planning the placement of a drug for treating blue algae blooms provided by an embodiment of the present invention;
[0021] Figure 2 A schematic diagram of a specific process of a method for planning the placement of a drug for treating blue algae blooms provided by an embodiment of the present invention;
[0022] Figure 3 A schematic diagram of the structure of a drug delivery planning device for treating blue algae blooms provided by an embodiment of the present invention;
[0023] Figure 4 A schematic diagram of the structure of a server provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0024] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described in combination with the embodiments below. Obviously, the described embodiments are 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.
[0025] At present, in order to prevent the sudden growth and reproduction of a large number of cyanobacterial cells in water bodies and the formation of cyanobacterial blooms, relevant technologies have proposed that water quality monitoring and early warning can be carried out, and the dosage of a single agent can be determined based on the early warning signal and the linear relationship, so as to combine the early warning technology with the algae inhibition technology to achieve autonomous quantitative dosage based on the early warning signal. However, the above-mentioned agent delivery scheme only considers the influencing factors of water quality and delivers the agent based on the predicted concentration. Its control is relatively simple and it is impossible to accurately determine the optimal dosage route and dosage. Therefore, it is easy to have local excessive concentration or drug leakage, resulting in low agent utilization rate. In addition, the above-mentioned scheme does not fully consider the impact of water flow on the diffusion of the agent, and cannot provide a refined and adapted agent delivery strategy, resulting in poor control effect on cyanobacterial blooms.
[0026] Compared with the existing agent delivery strategies, the present invention introduces a hydrodynamic model, an intelligent optimization algorithm and source term coupling optimization, solves the flow field through partial differential equations, and determines the delivery route and delivery amount through an optimization algorithm. It can dynamically plan routes based on real-time data and optimize the delivery of multiple agents, and optimize the delivery based on multiple factors, thereby achieving complex and precise control of water quality monitoring, hydrodynamic simulation and intelligent optimization of drug delivery. Based on this, the present invention implements a method, device and server for planning agent delivery for the control of cyanobacteria blooms, determines the drug delivery strategy by constructing a mathematical model of hydrodynamics, water quality and cyanobacteria migration, and optimizes the drug delivery strategy through the coupling of a calculation module and an optimization module, which can significantly improve the control effect of cyanobacteria blooms and improve the utilization rate of agents.
[0027] See also Figure 1 The flow chart of a method for planning the placement of a medicament for treating blue algae blooms is shown. The method is applied to a medicament placement planning system. The medicament placement planning system includes: water quality detection equipment, a calculation module and an optimization module. The method mainly includes the following steps S102 to S106:
[0028] Step S102, real-time water quality data is obtained through water quality detection equipment, wherein the real-time water quality data includes: water body pH value, dissolved oxygen concentration, nutrient concentration and light intensity. In one embodiment, it is also necessary to detect the basic data of the target water area and the biological characteristic parameters of cyanobacteria through the detection equipment. The basic data of the target water area includes: water body shape, water depth distribution, inflow and outflow conditions, wind field data, etc. The basic data of the target water area is the basis for the calculation module to construct a hydrodynamic model. The biological characteristic parameters of cyanobacteria include: growth rate, mortality rate, migration rate, etc. The biological characteristic parameters of cyanobacteria are used to construct a cyanobacteria diffusion model.
[0029] Step S104, sending the water quality data to the calculation module, and through the calculation module, constructing a data model for the water quality data to determine the hydrodynamic model, water quality model and cyanobacteria diffusion model, wherein the hydrodynamic model is used to simulate the flow field distribution of the water body, the water quality model is used to simulate the water quality distribution, and the cyanobacteria diffusion model is used to simulate the cyanobacteria concentration distribution. In one embodiment, the calculation module can construct a hydrodynamic model, a water quality model and a cyanobacteria diffusion model according to the real-time water quality data, the basic data of the target water area and the biological characteristic parameters of the cyanobacteria, so as to simulate the flow field and the cyanobacteria concentration distribution, and provide necessary data support for subsequent optimization control. Specifically, the calculation process of the calculation module includes: constructing control equations for hydrodynamics, water quality and cyanobacteria migration; setting boundary conditions in combination with measured river inflow conditions, wind field conditions, etc.; importing the path planning and delivery amount of the optimization module as source and sink terms; discretizing the equations to obtain a group of algebraic equations; and solving the group of algebraic equations. After obtaining the flow field, water quality and cyanobacteria concentration distribution data, the calculation ends.
[0030] Step S106, through the optimization module, the water flow field distribution, water quality distribution and cyanobacteria concentration distribution are optimized and analyzed to determine the initial dosing strategy, and the calculation module and the optimization module are dynamically coupled to optimize the initial dosing strategy and determine the target dosing strategy, wherein the target dosing strategy includes: a target dosing route and a target dosage. In one embodiment, the optimization module is used to solve the optimal dosing route and the optimal dosage of each agent based on the flow field and cyanobacteria distribution data, combined with the description of each dosage, using an optimization algorithm to obtain the best dosing route and the best dosage of each agent, so that the distribution of all agents in the target water area covers the cyanobacteria outbreak area. According to the calculation of the optimization module, the target dosage of various agents can be determined, so that different agents can be dosed in batches according to the target dosage. The drugs dosed include organic acids, oxygenators, probiotics (such as lactic acid bacteria, Bacillus, nitrifying bacteria), sodium humate and blue water spirit, etc. The specific dosage of the agent depends on the pH value of the water body, dissolved oxygen concentration, nutrient salt concentration and light intensity.
[0031] Furthermore, determining the target dosing route and target dosage through the optimization module is a key link in algal bloom control, which aims to determine the optimal delivery route for the unmanned boat and the optimal delivery amount of each type of agent, so that the agents are distributed in the target waters to cover the cyanobacteria outbreak area, thereby achieving the goal of effectively controlling cyanobacteria blooms. Among them, the optimization module needs to comprehensively consider multiple factors, including the selection of objective function, the setting of constraints, the selection of optimization algorithm and parameter adjustment.
[0032] The above-mentioned agent placement planning method for controlling cyanobacterial blooms provided in an embodiment of the present invention determines the dosing strategy by constructing a mathematical model of hydrodynamics, water quality and cyanobacterial migration, and optimizes the dosing strategy through the coupling of a calculation module and an optimization module, formulates the optimal dosing route and release amount, so that the agent is evenly distributed in the target water area, and there will be no local excessive concentration or drug leakage. The control effect of cyanobacterial blooms can be significantly improved, and the utilization rate of the agent is improved.
[0033] See also Figure 2 The specific flow diagram of a method for planning the administration of a drug for treating blue algae blooms is shown. The embodiment of the present invention also provides an implementation method for determining a target administration strategy, as shown in (A) to (D) below:
[0034] (A) The hydrodynamic model, water quality model and cyanobacteria diffusion model are constructed through the calculation module, and the models are solved to determine the water flow field distribution, water quality distribution and cyanobacteria concentration distribution. For details, see (a) to (c) below:
[0035] (a) Discretize the hydrodynamic model, water quality model and cyanobacteria diffusion model, transform the model from a continuous partial differential equation into a set of algebraic equations, and utilize the interaction between the hydrodynamic model, water quality model and cyanobacteria diffusion model to couple the hydrodynamic model, water quality model and cyanobacteria diffusion model so that the solution process of the algebraic equations can be organically combined, and the solution results of the algebraic equations can be determined as the water flow field distribution, water quality distribution and cyanobacteria concentration distribution. Discretize the model and transform the continuous partial differential equation into a set of algebraic equations, so that the model can be solved on a computer. Solution, this process needs to pay attention to numerical stability and convergence issues, and reasonably select parameters such as calculation grid and time step to ensure the reliability of the calculation results. In addition, due to the strong interaction and feedback mechanism between the above three models, changes in the flow field will affect the diffusion of nutrients and cyanobacteria, and the presence of cyanobacteria will consume nutrients and dissolved oxygen in the water body. Therefore, it is necessary to couple the hydrodynamic model, water quality model and cyanobacteria migration model, and by designing a reasonable time stepping strategy, iterate the calculation multiple times in each time step until the convergence condition is reached, thereby organically combining the solution process of the above three models.
[0036] (b) In the process of solving the model, the present invention also needs to consider the processing of boundary conditions. The boundary conditions of the hydrodynamic model are set according to the inflow and outflow of the water body and the shear stress of the fluid wall. The boundary conditions of the water quality model are set according to the initial distribution of nutrients and cyanobacteria. The boundary conditions of the cyanobacteria diffusion model are set according to the adsorption and drift effect of cyanobacteria at the water body boundary. The boundary conditions of the hydrodynamic model, the boundary conditions of the water quality model and the boundary conditions of the cyanobacteria diffusion model, as well as the source and sink terms fed back by the optimization module, are substituted into the coupled algebraic equation group for solution processing to determine the water flow field distribution, water quality distribution and cyanobacteria concentration distribution.
[0037] (c) The calculation module needs to have visualization and post-processing functions, and perform visualization processing on the water flow field distribution, water quality distribution and cyanobacteria concentration distribution, generate water flow field images, water quality distribution images and cyanobacteria concentration images to facilitate subsequent analysis and optimization, and provide data export interface and data import interface to send the water flow field distribution, water quality distribution and cyanobacteria concentration distribution to the optimization module, and read the path planning and release amount set in the optimization module to provide a basis for path planning and release amount determination.
[0038] (B) The initial dosing strategy is combined as a source-sink term with the hydrodynamic model, water quality model and cyanobacteria diffusion model constructed by the calculation module to determine the updated model group, and the updated model group is solved by the calculation module to determine the water flow field distribution, water quality distribution and cyanobacteria concentration distribution corresponding to each time after the update. In one embodiment, the initial dosing strategy The optimization module can also be used to determine the initial cyanobacteria distribution and flow field (which may be measured data or simple model predictions). Since the source and sink terms represent external factors that affect the system during the simulation, in partial differential equations (such as convection-diffusion equations), the source and sink terms are usually directly added to the right side of the equation. The initial dosing strategy is input into the partial differential equation of the calculation module as the source and sink terms, and the updated model group obtained can be expressed as:
[0039]
[0040] Where C is the cyanobacteria concentration, V is the velocity field, D is the diffusion coefficient, is the source and sink term of the drug administration. By solving this equation, the distribution of cyanobacteria at time t1 can be obtained. and flow field .
[0041] In addition, the addition of chemicals is a typical external influence, which will change the state of the water body (such as pH value, dissolved oxygen, etc.) at a specific location and time. Taking the addition of chemicals as a source and sink term can more accurately simulate the distribution process of chemicals in time and space. For example, the control equation can be added with the form The source-sink term represents the dosage of the drug at the position (x, y) and time t. The source-sink term can take effect at any time, so that the system can dynamically adjust the dosing strategy according to the real-time monitored water quality data without resetting the initial conditions and starting the simulation from scratch.
[0042] Furthermore, by treating dosing as a source-sink term, the coupling of the computational module and the optimization module can be realized more naturally. The optimization module can adjust the dosing strategy according to the simulation results of the computational module (such as the distribution of cyanobacteria), while the computational module updates the simulation according to the adjusted dosing strategy. This feedback mechanism is particularly important when dealing with dynamically changing environments (such as changes in flow fields and cyanobacteria distribution).
[0043] (C) Use source and sink items, water flow field distribution, water quality distribution and cyanobacteria concentration distribution to build a local optimization model. Specifically, it is necessary to conduct local sensitivity analysis on the source and sink items to determine the changes in water flow field distribution, water quality distribution and cyanobacteria concentration distribution with the change of source and sink items, and establish a sensitivity matrix based on the changes, and obtain the objective function of the optimization module. Use the sensitivity matrix and objective function to build a local optimization model. For details, see (1) to (3) below:
[0044] (1) Sensitivity analysis: Perform local sensitivity analysis, that is, at each dosing point Nearby, slightly change the dosage ±δS, run the calculation module again to observe the distribution of cyanobacteria The change of , thus we can get a sensitivity matrix J, whose elements It indicates the influence of the dosage change at dosing point i on the concentration of cyanobacteria in area j.
[0045] (2) Objective function construction: The objective function can be set to minimize the evaluation of the cyanobacteria control effect of the agent in the target waters, or to minimize the total amount of drug release. The former focuses on ensuring that the agent covers the distribution of the cyanobacteria outbreak area in the waters, that is, precise drug release, while the latter focuses more on reducing the cost of control, that is, economical drug release. In addition, these two objective functions can also be weighted to weigh the importance of the evaluation of the cyanobacteria control effect and the total amount of drug release. In practical applications, the objective function F(C) can be defined as:
[0046] Spatial variance of cyanobacteria concentration (covering regional indicators of cyanobacteria outbreaks): ;
[0047] Total cyanobacteria (effect index): F2(C) = ∫∫C(x, y)dxdy;
[0048] Total dosage (cost index): F3(S) = ∫∫∫S(x, y, t)dxdydt;
[0049] Comprehensive objective function: ,in , , is the weight.
[0050] (3) Dosage strategy optimization: Using the sensitivity matrix J and the objective function F, a local optimization problem can be constructed:
[0051]
[0052] Where ΔS is the dosage adjustment, and λ‖ΔS‖² is a regularization term to prevent excessive adjustments. This is a quadratic programming problem that can be quickly solved using a standard solver to obtain ΔS. Update the dosing strategy: S1(x, y, t) = S0(x, y, t) + ΔS.
[0053] (D) Solve the local optimization model by using the preset standard solver to end the iterative optimization of the dosing strategy, determine the updated dosing strategy, and use S1(x, y, t) as the new source and sink term for the next round of iterative optimization to obtain S2(x, y, t). Then repeat the iterative optimization process until the difference between the dosing strategies obtained from two adjacent iterative optimizations is , that is, When it is less than a preset threshold, or the number of iterative optimizations reaches a preset maximum number of iterations, the iterative optimization process is stopped, and the dosing strategy updated in the last iteration is determined as the target dosing strategy.
[0054] In practical applications, the optimization module also needs to work closely with the calculation module and the control module. On the one hand, it needs to obtain the flow field and cyanobacteria concentration distribution data from the calculation module as the basis for optimization; on the other hand, it needs to output the optimized delivery route and delivery amount to the control module to guide the actual operation of the unmanned boat. In addition, the optimization module also needs to have a certain degree of adaptive ability and be able to dynamically adjust the optimization strategy according to real-time monitoring data. Since the flow field and cyanobacteria concentration distribution will change over time, fixed delivery routes and delivery amounts may not achieve the best results. Therefore, the optimization module needs to connect with the monitoring system, obtain the latest data in real time, and re-optimize the delivery plan based on the new data to adapt to the dynamically changing environment. Since the water environment is dynamically changing, the boundary conditions and initial conditions in the calculation module can be updated by obtaining the input of real-time monitoring data, so as to repeat the above process at each critical moment tᵢ (for example, every hour) to obtain a time-varying optimal dosing strategy S*(x, y, t), and send the optimized S*(x, y, t) to the control module to control the navigation path of the unmanned boat and the delivery amount of the dosing device.
[0055] For the above steps (B) to (D), an optimization module can be determined to be used to solve the optimal delivery route and the optimal delivery amount of each agent based on the flow field and cyanobacteria distribution data using an optimization algorithm, and the dosage and delivery route output by the optimization module are used as the source and sink terms of the equation group in the calculation module, where the source and sink terms represent external factors that affect the system during the simulation process (for example, a term of the form The source-sink term represents the dosage of medicine at the position (x, y) and time t. The source-sink term can take effect at any time. Using the drug administration as the source-sink term can more naturally realize the coupling of the calculation module and the optimization module. The optimization module can adjust the drug administration strategy according to the simulation results of the calculation module (such as the distribution of cyanobacteria), and the calculation module updates the simulation according to the adjusted drug administration strategy.
[0056] The optimization module designs an iterative optimization strategy, so that the optimization module dynamically adjusts S(x, y, t) according to the output of the calculation module, thereby achieving further optimization of the dosage and route of dosing. This process can be divided into the following steps: First, the optimization module uses the optimization algorithm and other methods to obtain the initial dosing strategy based on the initial cyanobacteria distribution and flow field (which may be measured data or simple model predictions). .Will As the source and sink terms, it is input into the partial differential equation of the calculation module. By solving this equation, the distribution of cyanobacteria at time t1 is obtained. and flow field .right Perform local sensitivity analysis. That is, slightly change the dosage near each dosing point. ± δS, run the calculation module again to observe the distribution of cyanobacteria The change of , thus we can get a sensitivity matrix J, whose elements It represents the influence of the dosage change at the dosing point i on the concentration of cyanobacteria in area j. Then, the objective function is constructed, and the optimized S(x, y, t) is sent to the control module to control the navigation path of the unmanned boat and the dosage of the dosing device.
[0057] In summary, the present invention establishes a mathematical model of hydrodynamics, water quality and cyanobacteria migration to simulate the water flow field and cyanobacteria concentration distribution. By constructing an accurate mathematical model, the flow field and cyanobacteria diffusion are accurately simulated to provide reliable data support for subsequent optimization. In addition, a variety of influencing factors are comprehensively considered in the modeling process, and the model is coupled to solve the problem, which has a high technical difficulty. This delivery strategy fully considers the influence of water flow on the diffusion of the agent, is more refined and adapted to local conditions, and can improve the uniform distribution of the agent in the water area, thereby improving the treatment effect.
[0058] In addition, the present invention also uses an optimization module to obtain an initial dosing strategy based on the initial cyanobacteria distribution and flow field (which may be measured data or simple model prediction) using optimization algorithms and other methods. , and As the source and sink terms, it is input into the partial differential equation of the calculation module. Conduct local sensitivity analysis, define the objective function F(C), and use the sensitivity matrix J and the objective function F to construct a local optimization problem, so as to use the intelligent optimization algorithm to determine the optimal delivery route and the delivery amount of each agent.
[0059] For the method for planning the administration of a medicament for treating blue algae blooms provided in the above-mentioned embodiment, an embodiment of the present invention provides a device for planning the administration of a medicament for treating blue algae blooms. The device is applied to a medicament administration planning system. The medicament administration planning system includes: a water quality detection device, a calculation module and an optimization module. Figure 3 The schematic diagram of the structure of a drug delivery planning device for treating blue algae blooms is shown, and the device includes the following parts:
[0060] The data acquisition unit 302, the data acquisition module acquires real-time water quality data through water quality detection equipment, wherein the real-time water quality data includes: water pH value, dissolved oxygen concentration, nutrient salt concentration and light intensity;
[0061] The model building unit 304 sends the water quality data to the calculation module, and performs data model building processing on the water quality data through the calculation module to determine the hydrodynamic model, the water quality model and the cyanobacteria diffusion model, wherein the hydrodynamic model is used to simulate the flow field distribution of the water body, the water quality model is used to simulate the water quality distribution, and the cyanobacteria diffusion model is used to simulate the cyanobacteria concentration distribution;
[0062] The strategy optimization unit 306 optimizes and analyzes the water flow field distribution, water quality distribution and cyanobacteria concentration distribution through the optimization module to determine the initial dosing strategy, and dynamically couples the calculation module and the optimization module to optimize the initial dosing strategy and determine the target dosing strategy, wherein the target dosing strategy includes: target dosing route and target dosage.
[0063] The above-mentioned agent placement planning device for controlling cyanobacterial blooms provided in the embodiment of the present application determines the dosing strategy by constructing a mathematical model of hydrodynamics, water quality and cyanobacterial migration, and optimizes the dosing strategy through the coupling of a calculation module and an optimization module, which can significantly improve the control effect of cyanobacterial blooms and improve the utilization rate of the agent.
[0064] In one embodiment, after the steps of constructing a data model for water quality data through a calculation module to determine a hydrodynamic model, a water quality model and a cyanobacteria diffusion model, the model construction unit 304 is further used to: discretize the hydrodynamic model, the water quality model and the cyanobacteria diffusion model to convert the model from a continuous partial differential equation into a set of algebraic equations; utilize the interaction relationship between the hydrodynamic model, the water quality model and the cyanobacteria diffusion model to couple the hydrodynamic model, the water quality model and the cyanobacteria diffusion model so as to organically combine the solution process of the set of algebraic equations, and determine the solution results of the set of algebraic equations as the water flow field distribution, the water quality distribution and the cyanobacteria concentration distribution.
[0065] In one embodiment, after the step of coupling the hydrodynamic model, the water quality model and the cyanobacteria diffusion model, the model construction unit 304 is further used to: set the boundary conditions of the hydrodynamic model according to the inflow and outflow of the water body and the shear stress of the fluid wall; set the boundary conditions of the water quality model according to the initial distribution of nutrients and cyanobacteria; set the boundary conditions of the cyanobacteria diffusion model according to the adsorption and drift effect of cyanobacteria at the water body boundary; substitute the boundary conditions of the hydrodynamic model, the boundary conditions of the water quality model and the boundary conditions of the cyanobacteria diffusion model as well as the source and sink terms fed back by the optimization module into the coupled algebraic equation group for solution processing to determine the water flow field distribution, water quality distribution and cyanobacteria concentration distribution.
[0066] In one embodiment, after the step of determining the solution results of the algebraic equation group as the water flow field distribution, water quality distribution and cyanobacteria concentration distribution, the above-mentioned model building unit 304 is also used to: send the water flow field distribution, water quality distribution and cyanobacteria concentration distribution to the optimization module, and visualize the water flow field distribution, water quality distribution and cyanobacteria concentration distribution to generate a water flow field image, a water quality distribution image and a cyanobacteria concentration image.
[0067] In one embodiment, when dynamically coupling the calculation module and the optimization module to optimize the initial dosing strategy and determine the target dosing strategy, the strategy optimization unit 306 is also used to: combine the initial dosing strategy as a source-sink term with the hydrodynamic model, water quality model and cyanobacteria diffusion model constructed by the calculation module to determine an updated model group, and solve the updated model group through the calculation module to determine the water flow field distribution, water quality distribution and cyanobacteria concentration distribution corresponding to each moment after the update; construct a local optimization model using the source-sink term, water flow field distribution, water quality distribution and cyanobacteria concentration distribution, and solve the local optimization model through a preset standard solver to end the iterative optimization of this round of dosing strategy and determine the updated dosing strategy.
[0068] In one embodiment, when performing the step of constructing a local optimization model using source-sink terms, water flow field distribution, water quality distribution, and cyanobacteria concentration distribution, the strategy optimization unit 306 is also used to: perform local sensitivity analysis on the source-sink terms, determine the changes in the water flow field distribution, water quality distribution, and cyanobacteria concentration distribution as the source-sink terms change, and establish a sensitivity matrix based on the changes; obtain the objective function of the optimization module, and construct a local optimization model using the sensitivity matrix and the objective function.
[0069] In one embodiment, after solving the local optimization model through a preset standard solver to end the iterative optimization of the dosing strategy of this round and determine the updated dosing strategy, the above-mentioned strategy optimization unit 306 is also used to: when the difference between the dosing strategies obtained by two adjacent iterative optimizations is less than a preset threshold, or the number of iterative optimizations reaches a preset maximum number of iterations, stop the iterative optimization process, and determine the dosing strategy updated by the last iterative update as the target dosing strategy.
[0070] The device provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.
[0071] An embodiment of the present invention provides a server. Specifically, the server includes a processor and a storage device. The storage device stores a computer program, and when the computer program is executed by the processor, it executes the method described in any one of the above-mentioned embodiments.
[0072] Figure 4 A structural diagram of a server provided in an embodiment of the present invention, the server 100 includes: a processor 40, a memory 41, a bus 42 and a communication interface 43, wherein the processor 40, the communication interface 43 and the memory 41 are connected via the bus 42; the processor 40 is used to execute an executable module stored in the memory 41, such as a computer program.
[0073] The memory 41 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 43 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.
[0074] The bus 42 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0075] Among them, the memory 41 is used to store programs, and the processor 40 executes the program after receiving the execution instruction. The method executed by the device for flow process definition disclosed in any embodiment of the above-mentioned embodiment of the present invention can be applied to the processor 40 or implemented by the processor 40.
[0076] The processor 40 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 40. The above processor 40 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiment of the present invention can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 41, and the processor 40 reads the information in the memory 41 and completes the steps of the above method in combination with its hardware.
[0077] The computer program product of the readable storage medium provided in the embodiment of the present invention includes a computer-readable storage medium storing program code, and the instructions included in the program code can be used to execute the methods described in the previous method embodiments. The specific implementation can be referred to the previous method embodiments, which will not be repeated here.
[0078] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.
[0079] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims
1. A method for planning the use of a drug for controlling blue algae blooms, characterized in that: The method is applied to a drug delivery planning system, which includes: water quality detection equipment, a calculation module and an optimization module. The method includes: Acquire real-time water quality data through the water quality detection equipment, wherein the real-time water quality data includes: water pH value, dissolved oxygen concentration, nutrient salt concentration and light intensity; The water quality data is sent to the calculation module, and the calculation module is used to construct a data model for the water quality data to determine a hydrodynamic model, a water quality model and a cyanobacteria diffusion model, wherein the hydrodynamic model is used to simulate the flow field distribution of the water body, the water quality model is used to simulate the water quality distribution, and the cyanobacteria diffusion model is used to simulate the cyanobacteria concentration distribution; Through the optimization module, the water flow field distribution, the water quality distribution and the cyanobacteria concentration distribution are optimized and analyzed to determine the initial dosing strategy, and the calculation module and the optimization module are dynamically coupled to optimize the initial dosing strategy and determine the target dosing strategy, wherein the target dosing strategy includes: a target dosing route and a target dosing amount; Among them, the step of dynamically coupling the calculation module and the optimization module to optimize the initial dosing strategy and determine the target dosing strategy includes: combining the initial dosing strategy as a source-sink term with the hydrodynamic model, the water quality model and the cyanobacteria diffusion model constructed by the calculation module to determine an updated model group, and solving the updated model group through the calculation module to determine the water flow field distribution, the water quality distribution and the cyanobacteria concentration distribution corresponding to each moment after the update; constructing a local optimization model using the source-sink term, the water flow field distribution, the water quality distribution and the cyanobacteria concentration distribution, and solving the local optimization model through a preset standard solver to end the iterative optimization of this round of dosing strategy and determine the updated dosing strategy; Among them, the updated model group is: ; Where C is the cyanobacteria concentration, V is the velocity field, D is the diffusion coefficient, is the source and sink term of the drug administration. By solving this equation, the distribution of cyanobacteria at time t1 is obtained. and flow field ; The step of constructing a local optimization model using the source-sink term, the water flow field distribution, the water quality distribution and the cyanobacteria concentration distribution includes: performing local sensitivity analysis on the source-sink term to determine the changes of the water flow field distribution, the water quality distribution and the cyanobacteria concentration distribution with the change of the source-sink term, and establishing a sensitivity matrix according to the changes; obtaining the objective function of the optimization module, and constructing the local optimization model using the sensitivity matrix and the objective function; Wherein, the sensitivity matrix and the objective function are used to construct a local optimization problem: ; Where J is the sensitivity matrix, F is the objective function, ΔS is the dosage adjustment, and λ‖ΔS‖² is the regularization term used to prevent excessive adjustments. The local optimization problem is quickly solved using a standard solver to obtain ΔS and determine the updated dosing strategy: S1(x, y, t) = S0(x, y, t) + ΔS. Among them, after the step of solving the local optimization model by a preset standard solver to end the iterative optimization of the dosing strategy of this round and determine the updated dosing strategy, it includes: when the difference between the dosing strategies obtained by two adjacent iterative optimizations is less than a preset threshold, or the number of iterative optimizations reaches a preset maximum number of iterations, the iterative optimization process is stopped, and the dosing strategy updated by the last iterative update is determined as the target dosing strategy.
2. The method for planning the use of a pharmaceutical agent for controlling blue algae blooms according to claim 1, characterized in that: After the step of constructing a data model for the water quality data by the calculation module to determine a hydrodynamic model, a water quality model and a blue algae diffusion model, the method includes: Discretization processing is performed on the hydrodynamic model, the water quality model and the cyanobacteria diffusion model, and the models are converted from continuous partial differential equations into a group of algebraic equations; By utilizing the interaction relationship among the hydrodynamic model, the water quality model and the cyanobacteria diffusion model, the hydrodynamic model, the water quality model and the cyanobacteria diffusion model are coupled to organically combine the solution process of the algebraic equations, and the solution results of the algebraic equations are determined as the water flow field distribution, the water quality distribution and the cyanobacteria concentration distribution.
3. The method for planning the use of a pharmaceutical agent for controlling blue algae blooms according to claim 2, characterized in that: After the step of coupling the hydrodynamic model, the water quality model and the cyanobacteria diffusion model, the method further comprises: Set the boundary conditions of the hydrodynamic model according to the water inflow, outflow and fluid wall shear stress; Setting the boundary conditions of the water quality model according to the initial distribution of nutrients and cyanobacteria; The boundary conditions of the cyanobacteria diffusion model are set according to the adsorption and drift effects of cyanobacteria at the water body boundary; The boundary conditions of the hydrodynamic model, the boundary conditions of the water quality model, the boundary conditions of the cyanobacteria diffusion model, and the source and sink terms fed back by the optimization module are substituted into the coupled algebraic equation group for solving to determine the water flow field distribution, the water quality distribution, and the cyanobacteria concentration distribution.
4. The method for planning the use of a pharmaceutical agent for controlling blue algae blooms according to claim 2, characterized in that: After the step of determining the solution results of the algebraic equation group as the water flow field distribution, the water quality distribution and the cyanobacteria concentration distribution, the method further comprises: The water flow field distribution, the water quality distribution and the cyanobacteria concentration distribution are sent to the optimization module, and the water flow field distribution, the water quality distribution and the cyanobacteria concentration distribution are visualized to generate a water flow field image, a water quality distribution image and a cyanobacteria concentration image.
5. A device for planning the use of a drug for treating blue algae blooms, characterized in that: The device is applied to a drug delivery planning system, which includes: water quality detection equipment, a calculation module and an optimization module. The device includes: A data acquisition unit, wherein the data acquisition module acquires real-time water quality data through the water quality detection equipment, wherein the real-time water quality data includes: water pH value, dissolved oxygen concentration, nutrient salt concentration and light intensity; A model building unit sends the water quality data to the calculation module, and performs data model building processing on the water quality data through the calculation module to determine a hydrodynamic model, a water quality model and a cyanobacteria diffusion model, wherein the hydrodynamic model is used to simulate the flow field distribution of the water body, the water quality model is used to simulate the water quality distribution, and the cyanobacteria diffusion model is used to simulate the cyanobacteria concentration distribution; The strategy optimization unit optimizes and analyzes the water flow field distribution, the water quality distribution and the cyanobacteria concentration distribution through the optimization module to determine an initial dosing strategy, and dynamically couples the calculation module with the optimization module to optimize the initial dosing strategy and determine a target dosing strategy, wherein the target dosing strategy includes: a target dosing route and a target dosing amount; Among them, the step of dynamically coupling the calculation module and the optimization module to optimize the initial dosing strategy and determine the target dosing strategy includes: combining the initial dosing strategy as a source-sink term with the hydrodynamic model, the water quality model and the cyanobacteria diffusion model constructed by the calculation module to determine an updated model group, and solving the updated model group through the calculation module to determine the water flow field distribution, the water quality distribution and the cyanobacteria concentration distribution corresponding to each moment after the update; constructing a local optimization model using the source-sink term, the water flow field distribution, the water quality distribution and the cyanobacteria concentration distribution, and solving the local optimization model through a preset standard solver to end the iterative optimization of this round of dosing strategy and determine the updated dosing strategy; Among them, the updated model group is: ; Where C is the cyanobacteria concentration, V is the velocity field, D is the diffusion coefficient, is the source and sink term of the drug administration. By solving this equation, the distribution of cyanobacteria at time t1 is obtained. and flow field ; The step of constructing a local optimization model using the source-sink term, the water flow field distribution, the water quality distribution and the cyanobacteria concentration distribution includes: performing local sensitivity analysis on the source-sink term to determine the changes of the water flow field distribution, the water quality distribution and the cyanobacteria concentration distribution with the change of the source-sink term, and establishing a sensitivity matrix according to the changes; obtaining the objective function of the optimization module, and constructing the local optimization model using the sensitivity matrix and the objective function; Wherein, the sensitivity matrix and the objective function are used to construct a local optimization problem: ; Where J is the sensitivity matrix, F is the objective function, ΔS is the dosage adjustment, and λ‖ΔS‖² is the regularization term used to prevent excessive adjustments. The local optimization problem is quickly solved using a standard solver to obtain ΔS and determine the updated dosing strategy: S1(x, y, t) = S0(x, y, t) + ΔS. Among them, after the step of solving the local optimization model by a preset standard solver to end the iterative optimization of the dosing strategy of this round and determine the updated dosing strategy, it includes: when the difference between the dosing strategies obtained by two adjacent iterative optimizations is less than a preset threshold, or the number of iterative optimizations reaches a preset maximum number of iterations, the iterative optimization process is stopped, and the dosing strategy updated by the last iterative update is determined as the target dosing strategy.
6. A server, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method according to any one of claims 1 to 4.
7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method according to any one of claims 1 to 4.
