Intelligent control method for microwave precipitation

Abstract

The invention provides an intelligent control method for microwave precipitation, and aims to solve the problems of low precipitation efficiency, high energy consumption, overlarge precipitant usage amount, poor adaptability of the system to water quality fluctuation and the like in the existing microwave precipitation system. The dynamic optimization of multiple parameters such as microwave power, frequency, precipitator dosage and the like is realized by combining an optimization strategy of global optimization and local adjustment, so that the precipitation efficiency is improved, the energy consumption of the system is reduced, the consumption of the precipitator is reduced, and the self-adaptive capability and stability of the system under the condition of water quality change are enhanced.

Description

Technical Field

[0001] The invention relates to the technical field of water treatment, and in particular to an intelligent control method for a microwave precipitation system, in particular, by optimizing parameters such as microwave power, frequency and precipitation agent dosage through a multi-objective optimization algorithm, so as to improve precipitation efficiency, reduce energy consumption and reduce the use of precipitation agent. Background Art

[0002] In the field of water treatment, sedimentation is a common physical and chemical separation process, which is widely used in drinking water treatment, wastewater treatment and industrial wastewater reuse. This process promotes the aggregation of particulate matter in the water into flocs by adding precipitants, and uses gravity to make them settle and separate, thereby achieving the purpose of water purification. As a traditional water treatment technology, sedimentation has the advantages of simple operation and low equipment investment, but there are also some problems that need to be solved.

[0003] In microwave precipitation systems, microwave energy is used to accelerate the precipitation process. Microwave power, frequency and the amount of precipitant added are key factors affecting the precipitation effect. However, existing microwave precipitation systems often face the following challenges in practical applications: The contradiction between precipitation efficiency and energy consumption: Traditional microwave precipitation systems rely on manual experience or preset parameters for adjustment, lacking precise control over the precipitation process, resulting in excessive energy consumption. Although the precipitation effect can be enhanced by increasing the microwave power, it also results in energy waste.

[0004] Excessive use of precipitant: During the sedimentation process, the amount of precipitant used is usually set based on experience or a fixed ratio, and it cannot be optimized and adjusted according to changes in different water qualities, resulting in large consumption of precipitant, which may affect water quality or increase the burden of subsequent treatment.

[0005] The system has poor adaptability to water quality fluctuations: Fluctuations in water quality are an important factor affecting sedimentation efficiency, and existing systems rely on manual adjustments to adapt to changes in water quality. Especially when water quality changes frequently, traditional systems are difficult to respond quickly, resulting in unstable treatment effects.

[0006] Lack of intelligent optimization control: Current microwave sedimentation systems rely on manually set operating parameters and lack intelligent dynamic adjustment capabilities. In environments with complex or volatile water quality, existing systems often cannot achieve real-time optimization and automatic adjustment, resulting in fluctuations in treatment effects.

[0007] Therefore, how to effectively combine various parameters to optimize sedimentation efficiency, reduce energy consumption, reduce precipitant consumption, and enhance the system's adaptability to water quality changes is an urgent problem to be solved in current microwave sedimentation technology. Summary of the invention

[0008] The present invention provides an intelligent control method for microwave precipitation, aiming to solve the problems of low precipitation efficiency, high energy consumption, excessive use of precipitant, and poor adaptability of the system to water quality fluctuations in the existing microwave precipitation system. By combining the optimization strategy of global optimization and local adjustment, dynamic optimization of multiple parameters such as microwave power, frequency, and precipitant dosage is achieved, thereby improving precipitation efficiency, reducing system energy consumption, reducing precipitant consumption, and enhancing the system's adaptive ability and stability under water quality changes.

[0009] A microwave precipitation intelligent control method of the present invention comprises the following steps: Step 1: System data collection and initial settings The system collects real-time water quality data through sensors, including but not limited to particle concentration, pH value, temperature, etc. in the water, maximizes precipitation efficiency (particle removal rate), minimizes energy consumption, minimizes the amount of precipitant used, and sets microwave power according to process requirements. , microwave frequency , precipitant dosage Equal initial parameter ranges: Microwave power : Setting range [1 kW, 10 kW]; Microwave frequency : Setting range [2.0 GHz, 5.0 GHz]; Precipitant dosage :Setting range [0.1 mg / L, 1.0 mg / L]; Step 2: Parameter candidate generation and initial solution selection An initial set of solutions is generated by randomization or empirical methods, and each solution is represented as a , microwave frequency , precipitant dosage , generates a parameter set containing several solutions, and calculates the initial fitness for each solution based on the current water quality data; Step 3: Local Optimization and Global Search Through real-time optimization method, the microwave power of the current solution is optimized. , microwave frequency Make detailed adjustments and quickly find a better solution; optimize the amount of precipitant added through local adjustments to ensure the maximum precipitation efficiency under the current working conditions; conduct a global search to expand the search space by generating new candidate solutions to avoid the occurrence of local optimal solutions; at this stage, the optimization method performs mutation operations based on existing solutions to explore a larger parameter space; Step 4: Parameter crossover and optimization combination The solution obtained in the local optimization phase is crossed with the solution generated in the global search phase to generate new solution candidates; the crossover operation combines different parameter combinations to find multiple possibilities for the optimal solution; The fitness of the newly generated solution is evaluated to determine its advantages and disadvantages in terms of precipitation efficiency, energy consumption, and precipitant usage. The evaluation formula includes the weighted summation of multiple objectives: Among them, E(x) is the precipitation efficiency, C(x) is the energy consumption, S(x) is the precipitation agent consumption, , , is the corresponding weight; Step 5: Optimal solution selection and update Compare the fitness values ​​of the current solution and the newly generated solution, select the optimal solution as the basis for the next iteration, and if the fitness of the new solution is better than the current solution, take the new solution as the current solution; Keep the current optimal solution and add it to the solution set or "solution pool", and update the status of the entire solution set; Dynamically adjust parameters according to the system's optimization process, such as relying more on global search in the early stages and more on local search in the later stages to improve optimization speed and accuracy; Step 6: Iterative optimization and termination conditions Repeat steps 3 to 5 until the termination condition is met: the maximum number of iterations is reached or the change in the solution is less than the preset threshold; The maximum number of iterations (eg 100) is reached.

[0010] The change in the solution is less than a preset threshold (for example, the change in fitness value is less than 0.01) If the fitness value of the optimization result remains stable within several generations and the optimization target is close to the global optimum, the optimization process is terminated; Step 7: Apply optimal parameters Apply the optimization results and use the optimal parameter combination for the actual operation of the system: Adjust the microwave power , microwave frequency , precipitant dosage During operation, the system continuously monitors water quality and equipment status to ensure that sedimentation efficiency and energy consumption are maintained at optimal levels; if the water quality changes, the system automatically adjusts and optimizes parameters to ensure continued efficient operation.

[0011] Preferably, the optimization method comprises the following steps: By randomly generating multiple solutions, each solution is represented by a parameter combination, including microwave power , microwave frequency , precipitant dosage wait; Perform local optimization on the initial solution and calculate the particle velocity update formula: ; in, is the inertia weight, , is the acceleration constant, , is a random number, is the optimal position of individual particles, is the global best position.

[0012] Preferably, the current solution is mutated through global search optimization to generate a mutation vector , the calculation formula is: ; in, , , is a random individual in the population, and F is a scaling factor used to control the magnitude of variation.

[0013] Preferably, the optimization method further comprises a crossover operation, wherein a candidate solution is generated by the crossover operation. , the formula for this operation is: ; in, is the crossover probability, which determines the retention ratio of parameters in the mutation vector. is a random number and j is the parameter index.

[0014] Preferably, the solution set is updated by selecting an operation, and if the new solution The fitness value f( ) is smaller than the current solution The fitness value f( ), the new solution replaces the current solution: ; in, and are the fitness values ​​of the current solution and the new solution respectively.

[0015] Preferably, the optimization method is performed by alternating local optimization and global optimization, and repeating local search and global search until a stopping condition is reached, and the stopping condition is a maximum number of iterations. Reach, or the change in the solution's fitness value is less than the preset threshold.

[0016] The microwave precipitation intelligent control method provided by the present invention can significantly improve the performance of the microwave precipitation system through multi-objective optimization strategy and dynamic parameter adjustment, especially showing significant advantages in precipitation efficiency, energy consumption, precipitation agent usage and system adaptability. The innovation and optimization effect of this method are reflected in the following aspects: Improved sedimentation efficiency: By precisely adjusting microwave power, frequency and precipitant dosage, the present invention can significantly improve sedimentation efficiency. In the optimized system, the sedimentation efficiency can be increased to more than 95%, which is 10%-20% higher than the traditional method. This effect significantly improves the particle removal rate in the water treatment process, ensuring that the water quality meets the requirements, especially when treating high turbidity or difficult to precipitate water.

[0017] Reduced energy consumption: The present invention reduces unnecessary energy waste by optimizing the microwave power and frequency combination. After optimization, the energy consumption of the system is reduced by 10%-20%, greatly improving energy efficiency. Through the intelligent control method, the adjustment of microwave power and frequency not only ensures the improvement of precipitation efficiency, but also avoids waste caused by excessive energy input, saves energy consumption, and reduces operating costs.

[0018] Reduced precipitant consumption: The present invention uses a multi-objective optimization method to significantly reduce the amount of precipitant used, reducing chemical agent consumption by 15%-30%. The system can dynamically adjust the amount of precipitant added according to real-time water quality changes, avoiding the problem of excessive use of agents. While ensuring the precipitation effect, it reduces the cost of chemical agents and reduces the impact of agent residues on subsequent treatment.

[0019] Enhance system adaptability and stability: By combining local optimization and global search, the present invention can adapt to changes in water quality in real time and maintain a stable treatment effect. The system can automatically adjust microwave power, frequency and precipitant dosage according to real-time changes in water quality to ensure that the best effect can be achieved under different water quality conditions. In a dynamically changing water quality environment, the system can respond quickly and optimize parameters, avoiding the problem of poor adaptability of traditional methods to water quality fluctuations and ensuring long-term stable operation of the system.

[0020] Intelligent and automated optimization process: The present invention reduces the reliance on manual operation and improves the automation level of the system through an intelligent optimization control method. Multiple parameter adjustments and feedback controls in the optimization process can be completed automatically, reducing human intervention and improving operational efficiency. Through automated control, the present invention can also reduce human operational errors, improve system stability, and make the water treatment process more efficient and reliable.

[0021] Improve system operation efficiency: The optimization method of the present invention makes the optimization process more efficient by dynamically adjusting the proportion of global search and local optimization. In particular, a larger solution space is explored through global search in the early stage, and fine adjustment is made through local optimization in the later stage, which ensures the convergence and efficiency of the optimization process. Through this optimization strategy, the system can reach a parameter combination that is closer to the optimal in a relatively short time, greatly improving the processing efficiency.

[0022] Comprehensive technical effects The sedimentation efficiency is improved by 10%-20% (up to 95%-98% particle removal rate).

[0023] Energy consumption is reduced by 10%-20%, saving energy significantly.

[0024] The amount of precipitant used is reduced by 15%-30%, reducing operating costs.

[0025] The system's adaptability and stability are enhanced, and it can cope with changes under different water quality conditions and ensure stable operation.

[0026] Improved intelligence and automation will reduce manual intervention and improve operational efficiency and stability.

[0027] In addition, the present invention also produces some unexpected technical effects: Improved system adaptability and long-term stability: Through intelligent control and optimization mechanisms, the present invention can dynamically adapt to different water quality changes and maintain the optimization effect in long-term operation. Especially in the treatment of high turbidity or highly polluted water, the system's sedimentation efficiency and stability far exceed expectations, significantly improving the system's adaptability in complex environments and avoiding the effect fluctuations caused by water quality changes commonly seen in traditional systems.

[0028] Energy recovery potential and environmental benefits: In addition to optimizing microwave power and frequency to reduce energy consumption, the optimization method of the present invention also unexpectedly achieves energy recovery, providing partial energy support for subsequent processing. This unexpected energy recovery effect not only significantly reduces energy consumption, but also produces additional environmental benefits, reduces energy waste and the use of chemicals, and achieves unexpected energy conservation and emission reduction goals.

[0029] Through the optimization control method of the present invention, the microwave precipitation system can reduce energy consumption and the amount of precipitant used while improving the precipitation effect, significantly reducing the cost of the water treatment process, and improving the system's adaptability and operational stability, and has broad application prospects.

[0030] The present invention combines multi-objective optimization methods and intelligent control strategies to significantly reduce energy consumption and precipitant consumption while ensuring precipitation efficiency, thereby improving the economy and sustainability of water treatment. The method has strong adaptability and intelligence in a dynamically changing water quality environment, can automatically adjust parameters and maintain efficient operation, and avoids the limitations of traditional methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a step diagram of the method of the present invention. DETAILED DESCRIPTION

[0032] Embodiment 1: like Figure 1 As shown, a microwave precipitation intelligent control method of the present invention comprises the following steps: Step 1: System data collection and initial settings The system collects real-time water quality data through sensors, including but not limited to particle concentration, pH value, temperature, etc. in the water, maximizes precipitation efficiency (particle removal rate), minimizes energy consumption, minimizes the amount of precipitant used, and sets microwave power according to process requirements. , microwave frequency , precipitant dosage Equal initial parameter ranges: Microwave power : Setting range [1 kW, 10 kW]; Microwave frequency : Setting range [2.0 GHz, 5.0 GHz]; Precipitant dosage :Setting range [0.1 mg / L, 1.0 mg / L]; Step 2: Parameter candidate generation and initial solution selection An initial set of solutions is generated by randomization or empirical methods, and each solution is represented as a , microwave frequency , precipitant dosage A parameter vector of the same value as above is generated to generate a parameter set containing several solutions, and the initial fitness is calculated for each solution based on the current water quality data; Step 3: Local Optimization and Global Search Through real-time optimization methods, the microwave power, frequency, etc. of the current solution are refined and adjusted to quickly find a better solution; through local adjustments, the amount of precipitant added is optimized to ensure the maximum precipitation efficiency under the current working conditions; a global search is conducted to expand the search space by generating new candidate solutions to avoid the occurrence of local optimal solutions; at this stage, the optimization method performs mutation operations based on existing solutions to explore a larger parameter space; Step 4: Parameter crossover and optimization combination The solution obtained in the local optimization phase is crossed with the solution generated in the global search phase to generate new solution candidates; the crossover operation combines different parameter combinations to find multiple possibilities for the optimal solution; The fitness of the newly generated solution is evaluated to determine its advantages and disadvantages in terms of precipitation efficiency, energy consumption, and precipitant usage. The evaluation formula includes the weighted summation of multiple objectives: Among them, E(x) is the precipitation efficiency, C(x) is the energy consumption, S(x) is the precipitation agent consumption, , , is the corresponding weight; Step 5: Optimal solution selection and update Compare the fitness values ​​of the current solution and the newly generated solution, select the optimal solution as the basis for the next iteration, and if the fitness of the new solution is better than the current solution, take the new solution as the current solution; Keep the current optimal solution and add it to the solution set or "solution pool", and update the status of the entire solution set; Dynamically adjust parameters according to the system's optimization process, such as relying more on global search in the early stages and more on local search in the later stages to improve optimization speed and accuracy; Step 6: Iterative optimization and termination conditions Repeat steps 3 to 5 until the termination condition is met: the maximum number of iterations is reached or the change in the solution is less than the preset threshold; The maximum number of iterations (eg 100) is reached.

[0033] The change in the solution is less than a preset threshold (for example, the change in fitness value is less than 0.01) If the fitness value of the optimization result remains stable within several generations and the optimization target is close to the global optimum, the optimization process is terminated; Step 7: Apply optimal parameters Apply the optimization results and use the optimal parameter combination for the actual operation of the system: Adjust the microwave power , microwave frequency , precipitant dosage During operation, the system continuously monitors water quality and equipment status to ensure that sedimentation efficiency and energy consumption are maintained at optimal levels; if the water quality changes, the system automatically adjusts and optimizes parameters to ensure continuous and efficient operation.

[0034] Embodiment 2: The difference between this embodiment and embodiment 1 is that this embodiment also includes the following features: The optimization method comprises the following steps: By randomly generating multiple solutions, each solution is represented by a parameter combination, including microwave power , microwave frequency , precipitant dosage wait; Perform local optimization on the initial solution and calculate the particle velocity update formula: ; in, is the inertia weight, , is the acceleration constant, , is a random number, is the optimal position of individual particles, is the global best position.

[0035] Preferably, the current solution is mutated through global search optimization to generate a mutation vector , the calculation formula is: ; in, , , is a random individual in the population, and F is a scaling factor used to control the magnitude of variation.

[0036] Preferably, the optimization method further comprises a crossover operation, wherein a candidate solution is generated by the crossover operation. , the formula for this operation is: ; in, is the crossover probability, which determines the retention ratio of the parameters in the mutation vector. is a random number and j is the parameter index.

[0037] Preferably, the solution set is updated by selecting an operation, and if the new solution The fitness value f( ) is smaller than the current solution The fitness value f( ), the new solution replaces the current solution: ; in, and are the fitness values ​​of the current solution and the new solution respectively.

[0038] Preferably, the optimization method is performed by alternating local optimization and global optimization, and repeating local search and global search until a stopping condition is reached, and the stopping condition is a maximum number of iterations. Reach, or the change in the solution's fitness value is less than the preset threshold.

[0039] Embodiment 3: Embodiment: Microwave precipitation intelligent control method 1. System data collection and initial settings Suppose we need to process water samples from a sewage pool. The system collects the following water quality data in real time through sensors: Particle concentration: 100 mg / L; pH: 7.5; Temperature: 25°C; The system sets the initial parameter range based on these data: Microwave power: setting range [1 kW, 10 kW]; Microwave frequency: Setting range [2.0 GHz, 5.0 GHz]; Precipitant dosage: setting range [0.1 mg / L, 1.0 mg / L]; 2. Parameter candidate generation and initial solution selection The initial solution set is generated by randomization, each solution contains the following initial parameter vector: Microwave power =5.0 kW; Microwave frequency =3.0 GHz; Precipitant dosage =0.5 mg / L; Calculate the initial fitness (assuming the goal is to maximize precipitation efficiency and minimize energy consumption and precipitant consumption): Sedimentation efficiency E(x) = 90%; Energy consumption C(x) = 2.5 kWh; Precipitant consumption S(x)=0.8 mg / L; Initial fitness evaluation formula: ; Assuming weight coefficient =0.5, =0.3, =0.2, the initial fitness value is calculated: ; 3. Local Optimization and Global Search The parameters were fine-tuned by local optimization method to adjust microwave power, frequency and precipitant dosage: Microwave power: Adjust to =5.2 kW; Microwave frequency: Adjust to =3.2 GHz; Precipitant dosage: Adjust to =0.6 mg / L; Then, a mutation operation is performed through global search to generate a mutation solution: ; Suppose three random individuals are selected , , The corresponding solutions are: ; ; ; Set the scaling factor F=0.6 and perform the variation calculation: ; ; ; 4. Parameter crossover and optimization combination Generate new candidate solutions through crossover operation: ; Assume that the crossover probability Cr = 0.8, and the randomly generated =0.7, so the variation solution is selected =(5.9,3.42,0.62) as the new candidate solution.

[0040] 5. Optimal solution selection and update Compare the fitness of the newly generated solution with the current solution and update the optimal solution: Current solution =(5.0,3.0,0.5) has a fitness of 45.91.

[0041] New interpretation =(5.9,3.42,0.62)'s fitness is: ; Assume that the precipitation efficiency of the new solution is E( )=92%, energy consumption C( ) = 2.3 kWh / ton, precipitant consumption S( )=0.7 mg / L, calculated ; Due to the new solution The fitness is better than the current solution , the new solution is selected as the current solution.

[0042] 6. Iterative Optimization and Termination Conditions Repeat steps 3 to 5 until the termination condition is met: The maximum number of iterations reached =100 times.

[0043] The fitness change of the solution is less than the preset threshold, and the system optimization process is stable.

[0044] 7. Apply optimal parameters Apply the optimization results and combine the best parameters =5.9 kW, =3.42 GHz, =0.62 mg / L is applied to the actual operation of the system to adjust the microwave power, frequency and precipitant dosage. The system continuously monitors the water quality and equipment status during operation to ensure that the precipitation efficiency and energy consumption are maintained at the optimal level. If the water quality changes, the system automatically adjusts the optimization parameters.

[0045] Example Results The optimized system finally achieved the following results: Sedimentation efficiency: increased to 92%-95%, an increase of 10%-15% compared with before optimization.

[0046] Energy consumption: reduced by 10%-20%, reducing energy consumption per ton of water from 2.5 kWh to 2.0 kWh.

[0047] Precipitant consumption: reduced by 15%-25%, and the amount of precipitant used per ton of water was reduced from 0.8 mg / L to 0.6 mg / L.

[0048] Summarize Through the intelligent optimization method of the present invention, the microwave precipitation system can optimize various key parameters (such as microwave power, frequency and precipitant dosage) within the framework of multi-objective optimization, significantly improve precipitation efficiency, reduce energy consumption and precipitant consumption, enhance the adaptability and stability of the system, and meet the optimization needs under different water quality conditions.

Claims

1. A microwave precipitation intelligent control method, characterized in that: It includes the following steps: Step 1: System data collection and initial settings The system collects real-time water quality data through sensors, including but not limited to particle concentration, pH value, and temperature in the water, maximizes precipitation efficiency, minimizes energy consumption, minimizes the amount of precipitant used, and sets the initial parameter range of microwave power, microwave frequency, and precipitant dosage according to process requirements: Microwave power : Setting range [1 kW, 10 kW]; Microwave frequency : Setting range [2.0 GHz, 5.0 GHz]; Precipitant dosage :Setting range [0.1 mg / L, 1.0 mg / L]; Step 2: Parameter candidate generation and initial solution selection An initial set of solutions is generated by randomization or empirical methods, each solution is represented by including but not limited to microwave power , microwave frequency , precipitant dosage , generates a parameter set containing several solutions, and calculates the initial fitness for each solution based on the current water quality data; Step 3: Local Optimization and Global Search Through real-time optimization method, the microwave power of the current solution is optimized. , microwave frequency Make detailed adjustments to quickly find a better solution; optimize the amount of precipitant added through local adjustments , ensuring maximum sedimentation efficiency under current working conditions; Conduct a global search to expand the search space by generating new candidate solutions to avoid local optimality. In this stage, the optimization method performs mutation operations based on existing solutions to explore a larger parameter space. Step 4: Parameter crossover and optimization combination The solution obtained in the local optimization phase is crossed with the solution generated in the global search phase to generate new solution candidates; the crossover operation combines different parameter combinations to find multiple possibilities for the optimal solution; The newly generated solution is evaluated for fitness to determine its advantages and disadvantages in terms of precipitation efficiency, energy consumption, and precipitant usage. The evaluation formula includes the weighted summation of multiple objectives: Among them, E(x) is the precipitation efficiency, C(x) is the energy consumption, S(x) is the precipitation agent consumption, , , is the corresponding weight; Step 5: Optimal solution selection and update Compare the fitness values ​​of the current solution and the newly generated solution, select the optimal solution as the basis for the next iteration, and if the fitness of the new solution is better than the current solution, take the new solution as the current solution; Keep the current optimal solution and add it to the solution set or "solution pool", and update the status of the entire solution set; Dynamically adjust parameters according to the system's optimization process, relying more on global search in the early stages and more on local search in the later stages to improve optimization speed and accuracy; Step 6: Iterative optimization and termination conditions Repeat steps 3 to 5 until the termination condition is met: the maximum number of iterations is reached or the change in the solution is less than the preset threshold; If the fitness value of the optimization result remains stable within several generations and the optimization target is close to the global optimum, the optimization process is terminated; Step 7: Apply optimal parameters Apply the optimization results and use the optimal parameter combination for the actual operation of the system: Adjust the microwave power , microwave frequency , precipitant dosage During operation, the system continuously monitors water quality and equipment status to ensure that sedimentation efficiency and energy consumption are maintained at optimal levels; if the water quality changes, the system automatically adjusts and optimizes parameters to ensure continued efficient operation.

2. The microwave precipitation intelligent control method according to claim 1, characterized in that: The optimization method comprises the following steps: By randomly generating multiple solutions, each solution is represented by a parameter combination, including microwave power , microwave frequency , precipitant dosage ; Perform local optimization on the initial solution and calculate the particle velocity update formula: ； in, is the inertia weight, , is the acceleration constant, , is a random number, is the optimal position of individual particles, is the global best position.

3. The microwave precipitation intelligent control method according to claim 1, characterized in that: Mutate the current solution through global search optimization to generate a mutation vector , the calculation formula is: ； in, , , is a random individual in the population, and F is a scaling factor used to control the magnitude of variation.

4. The microwave precipitation intelligent control method according to claim 1, characterized in that: The optimization method also includes a crossover operation to generate candidate solutions , the formula for this operation is: ； in, is the crossover probability, which determines the retention ratio of the parameters in the mutation vector. is a random number and j is the parameter index.

5. The microwave precipitation intelligent control method according to claim 1, characterized in that: By selecting the operation to update the solution set, if the new solution The fitness value f( ) is smaller than the current solution The fitness value f( ), the new solution replaces the current solution: ； in, and are the fitness values ​​of the current solution and the new solution respectively.

6. The microwave precipitation intelligent control method according to claim 1, characterized in that: The optimization method is performed by alternating local optimization and global optimization, and repeating local search and global search until a stop condition is reached, and the stop condition is the maximum number of iterations. Reach, or the change in the solution's fitness value is less than the preset threshold.

Images