An Adaptive Regulation Method for a Fishery Oxygen Regulation Control System

Abstract

The present invention discloses an adaptive adjustment method for a fishery oxygen regulation control system, belonging to the technical field of PID control optimization. The specific steps are as follows: Step 1, construct a fishery oxygen regulation control system; Step 2, improve the football team training optimization algorithm. The specific improvement strategies include: S1, use a dynamic multi-dimensional weight update strategy to improve the update strategy of followers in the collective training stage; S2, use a distance-based optimal learning strategy to improve the optimal learning strategy in group training; Step 3, use the improved football team training optimization algorithm to optimize the PID control in the fishery oxygen regulation control system; Step 4, input a set of optimal parameters obtained in Step 3 into the PID controller in the fishery oxygen regulation control system. By optimizing the PID controller in the fishery oxygen regulation control system with the improved football team training optimization algorithm, the dynamic response speed and steady-state accuracy of the entire control system can be significantly improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of PID control optimization, and particularly relates to an adaptive adjustment method for a fishery oxygen regulation control system. Background Art

[0002] With the continuous development of modern fishery aquaculture, the control of water quality in aquaculture ponds has become a key factor in ensuring the healthy growth of aquaculture organisms. Especially in the regulation of oxygen concentration in water, establishing an effective oxygen regulation control system to dynamically adjust the oxygen concentration in the pond has become an important task in pond management. By precisely controlling the operating state of oxygenation equipment to ensure that the oxygen concentration in the water body remains near the target value helps to optimize the aquaculture environment and improve aquaculture efficiency.

[0003] Traditional PID controllers (Proportional, Integral, Derivative controllers) are widely used in many industrial control systems. Its basic principle is to adjust the control signal according to the current value, cumulative value, and change rate of the error, thereby achieving stable regulation of the system. In the oxygen regulation of fishery aquaculture ponds, the PID controller can adjust the oxygenation equipment in real time according to the error of oxygen concentration, so as to achieve the purpose of stabilizing at the target concentration. However, traditional PID controllers have certain limitations. In the case of large environmental changes or disturbances, fixed parameters are difficult to adapt to, and the control effect may be affected. Secondly, the adjustment process of PID controller parameters requires manual setting and is unstable under different working conditions. To solve these drawbacks, in recent years, intelligent optimization algorithms have gradually been introduced into the parameter optimization of PID controllers, and the PID parameters are adjusted in real time according to environmental feedback through the algorithm, so as to improve the adaptability of the system to dynamic changes.

[0004] The football team training optimization algorithm is a meta-heuristic optimization algorithm inspired by the football team training process, which simulates the three stages of team training: collective training, group training, and individual extra training. By simulating the phased cooperation mechanism of football team training, it shows significant advantages in global optimization and engineering applications. Its core lies in the phased dynamic balance between exploration and exploitation, and the flexibility of the model is enhanced through an unconstrained weight strategy, providing an efficient solution for complex optimization problems. Summary of the Invention

[0005] The object of the invention is to improve the standard football team training optimization algorithm, improve the optimization speed and accuracy of the algorithm in the optimization process, and increase the adaptive ability and stability of the algorithm, so that it is more suitable for the application scenario of fishery oxygen regulation control. The improved football team training optimization algorithm is used to optimize the parameters of the PID controller in the fishery oxygen regulation control system, improve the overall control performance of the system through algorithm optimization, reduce the complexity of manual parameter adjustment, and improve the stability of oxygen concentration regulation, so as to improve the fishery breeding environment and breeding efficiency.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions.

[0007] An adaptive adjustment method for a fishery oxygen regulation control system, the specific steps are as follows.

[0008] Step 1: Construct a fishery oxygen regulation control system, convert the fishery oxygen regulation control problem into a mathematical model to be optimized. The fishery oxygen regulation control system includes: an error calculation module, a PID controller, an improved football team training optimization algorithm module, a real-time detection module, and an oxygen regulation control module.

[0009] Step 2: Improve the football team training optimization algorithm, and the specific improvements include:

[0010] S1: Use a dynamic multi-dimensional weight update strategy to improve the update strategy of followers in the collective training stage of the football team training optimization algorithm. A dynamic multi-dimensional weight update strategy is to select the top 6 individuals with the best fitness values in the search population. The weight of the individual in the first position increases non-linearly with the increase of the algorithm iteration times. The position vectors of the remaining 5 individuals are decomposed according to different dimensions and randomly combined into three new individuals according to different dimensions. The weights of these three new individuals are dynamically allocated from the remaining weights, and the sum of all weights is 1;

[0011] S2: Use a distance-based optimal learning strategy to improve the optimal learning strategy in the group training of the football team training optimization algorithm. A distance-based optimal learning strategy is to guide the current individual by means of the position of the optimal individual in the population, and adjust the position of the current individual through the distance between the optimal individual and the current individual, so as to achieve position update.

[0012] Step 3: Use the improved football team training optimization algorithm to optimize the PID control in the fishery oxygen regulation control system, and obtain the optimal values of a set of PID control parameters Kp, Ki, and Kd through iterative optimization of the algorithm.

[0013] Step 4: Input the set of optimal Kp, Ki, and Kd parameters obtained in Step 3 into the PID controller in the fishery oxygen regulation control system to optimize the control effect of the entire fishery oxygen regulation control system.

[0014] Preferably, in step one, the execution process of each module in the constructed fishery oxygen regulation control system is as follows: by inputting the given target oxygen regulation concentration and the actual oxygen concentration obtained by the real-time detection module into the error calculation module, the real-time error e(t) is calculated, and then this error is input into the PID controller. The PID controller uses the improved football team training optimization algorithm module to optimize it to obtain the optimal parameters. The optimized PID controller calculates and outputs the control quantity u(t) according to these optimal parameters. This control quantity is then transmitted to the oxygen regulation control module, and further adjusts the oxygen supply quantity to achieve the required oxygen concentration. The mathematical model of the oxygen regulation control module is shown in Equation (1):

[0015] (1);

[0016] In Equation (1), O(t) represents the oxygen concentration in water, Kc represents the oxygen consumption coefficient, which is related to the biomass and temperature in water, Nc represents the biological quantity coefficient in water, O_min represents the lowest oxygen concentration in water, which is related to water quality, and u(t) represents the control quantity output by the PID controller. The specific formula is shown in Equation (2):

[0017] (2);

[0018] In Equation (2), Kp represents the proportional gain, Ki represents the integral gain, Kd represents the derivative gain, and e(t) represents the real-time error.

[0019] Preferably, in S1, a dynamic multi-dimensional weight update strategy is used to improve the update strategy of the followers in the collective training stage of the football team training optimization algorithm. The improved specific mathematical model is shown in Equation (3):

[0020] (3);

[0021] In Equation (3), represents the position of the updated individual, F(iter) represents the position of the current individual, represents the calculation formula of the dynamic weight factor as shown in Equation (4), represents the position of the optimal individual in the population, represents the positions of three new individuals randomly formed by splitting the positions of the individuals ranked 2-6 in fitness value in the population through different dimensions. In the optimization of the PID controller, the dimension value dim = 3, represents the weight of the i-th individual among the three new individuals. The weight values of the three new individuals are randomly allocated by (1 - );

[0022] (4);

[0023] In formula (4), iter represents the current iteration number, max_iter represents the maximum iteration number, and the value of the dynamic weight changes non-linearly from 0.25 to 0.85 as the iteration number increases.

[0024] Preferably, a dynamic multi-dimensional weight update strategy takes the optimal individual as the main guide, and as the iteration number increases, the weight changes dynamically. The weight changes non-linearly from low to high, prompting the algorithm to gradually shift from global search to local search. This strategy takes into account the positions of multiple excellent individuals and improves the exploration ability of the algorithm by selecting combined individuals in multiple dimensions, which helps the algorithm quickly jump out when falling into a local optimal solution and improves the optimization accuracy of the algorithm.

[0025] Preferably, in S2, a distance-based optimal learning strategy is used to improve the optimal learning strategy in the group training of the football team training optimization algorithm. The specific mathematical formula after improvement is shown in formula (5):

[0026] (5);

[0027] In formula (5), represents the position of the updated individual, F(iter) represents the position of the current individual, rand represents a random number between [0, 1], and the dist() function represents calculating the Euclidean distance between the positions of two individuals. represents the maximum distance of the entire search space, α represents the local search weight factor. represents the position of the optimal individual in the population, and α = log(1 + iter / max_iter).

[0028] Preferably, a distance-based optimal learning strategy is dynamically adjusted by combining the distance between the current individual and the global optimal individual. Individuals with a large distance rely on the guidance of the global optimal individual for extensive search, while individuals with a small distance rely more on local search and focus on fine search. This strategy effectively balances the global and local optimization of the algorithm, enabling the algorithm to have excellent optimization performance at all stages.

[0029] Preferably, in step three, the improved football team training optimization algorithm is used to optimize the PID control in the fishery oxygen regulation control system. The specific steps are as follows:

[0030] step1, Initialize the parameters of the improved football team training optimization algorithm, including the population size N, the problem dimension dim to be optimized by the algorithm, the maximum iteration number max_iter, the upper limit ub and the lower limit lb of the search space of the algorithm, and generate an initial population through the initial parameters of the algorithm;

[0031] Step 2: Map the improved football team training optimization algorithm to the PID controller in the fishery oxygen regulation control system, establish the connection between the individual position vector F(iter) in the algorithm population and the three parameters Kp, Ki, and Kd of the PID controller. The problem dimension dim of the algorithm is 3, so the individual position vector corresponds to three-dimensional values, which respectively correspond to Kp, Ki, and Kd. As the positions in the population are updated through the iteration of the algorithm, the three control parameters of the PID controller will be continuously adjusted, and finally a set of optimal control parameters of the PID controller will be obtained;

[0032] Step 3: Set the fitness value function of the improved football team training optimization algorithm, calculate the fitness values of the individuals in the initial population through the set fitness value function, sort them according to the magnitude of the fitness values, and select the individual with the optimal fitness value as , and the specific fitness value function is shown in Equation (6):

[0033] (6);

[0034] In Equation (6), J represents the fitness value, e(t) represents the real-time error value, L represents the running time of the system, M represents the overshoot of the system response, that is, the peak value exceeding the target value, and λ represents the weight of the overshoot, with a value of 0.1;

[0035] Step 4: Update the positions of the individuals in the population through the mathematical model of the improved football team training optimization algorithm. The improved football team training optimization algorithm is divided into three stages, specifically:

[0036] Stage 1: Collective training stage. In the collective training stage, the individuals in the population are divided into four types: followers, discoverers, thinkers, and fluctuators. When the algorithm enters the collective training stage, first classify the individuals and use the corresponding type of mathematical model for position update. The update strategy of the followers is shown in Equation (3), and the update strategies of the other three types are shown in Equation (7):

[0037] (7);

[0038] In Equation (7), represents the updated position of the individual, F(iter) represents the current position of the individual, represents the position of the optimal individual in the population, rand, rand1, and rand2 all represent random numbers between [0, 1], represents the position of the worst individual in the population, iter represents the current iteration number, and t(iter) represents a random number subject to the t-distribution;

[0039] Phase II: Group training phase. The MGEM clustering method is used to group individuals. There are three ways for members within each group to train, specifically including: optimal learning, random learning, and random communication. The update strategy for optimal learning is shown in Equation (5), and the update strategies for random learning and random communication are shown in Equation (8):

[0040] (8);

[0041] In Equation (8), represents updating the position of an individual, F_rand(iter) represents the position of an individual randomly selected in the current phase, and randn represents a number randomly generated from a normal distribution;

[0042] Phase III: Personal additional training phase. After the group training phase ends, the optimal individual in the population will be selected for training. The specific update strategy is shown in Equation (9):

[0043] (9);

[0044] In Equation (9), represents the updated optimal position, represents the position of the optimal individual in the population, iter represents the current iteration number, Gauss represents the Gaussian distribution, and Gauchy represents the Cauchy distribution;

[0045] In each iteration, the fitness value of the updated position is compared with the fitness value before the update to determine whether to retain the updated position;

[0046] step5. Determine whether the current iteration number has reached the maximum iteration number. If it has reached the maximum iteration number, the optimization is completed and the optimal solution is output. Otherwise, continue to execute step4 for optimization.

[0047] By adopting the above technical solutions, the beneficial effects of the present invention are as follows: The performance of the football team training optimization algorithm is significantly improved through two improvement strategies. The dynamic multi-dimensional weight update strategy better realizes the smooth transition of the algorithm from global search to local search. At the same time, the multi-dimensional recombination is used to enhance the ability of the algorithm to jump out of the local optimal solution and improve the optimization accuracy. The distance-based optimal learning strategy guides the direction by dynamically adjusting the distance between the individual and the global optimum, strengthening the adaptability of the algorithm at different stages. Through the synergistic effect of the two strategies, taking into account the exploration and development efficiency, the convergence and solution quality of the algorithm are significantly improved. By optimizing the PID controller in the fishery oxygen regulation control system with the improved football team training optimization algorithm, the dynamic response speed and steady-state accuracy of the entire control system can be significantly improved, effectively adapting to the fluctuations of environmental parameters, reducing overshoot and oscillation phenomena, while enhancing the anti-interference ability of the system, achieving more accurate oxygen regulation control, taking into account the breeding safety and economy, and realizing efficient and reliable adaptive control. Description of the Drawings

[0048] Figure 1 It is a flowchart of an adaptive adjustment method for a fishery oxygen regulation control system;

[0049] Figure 2 It is a model diagram of a fishery oxygen regulation control system;

[0050] Figure 3 It is a comparison diagram of the change of fitness values during the optimization process of the improved football team training optimization algorithm and the standard football team training optimization algorithm;

[0051] Figure 4 It is a comparison diagram of the effects of optimizing the PID controller by the improved football team training optimization algorithm and the standard football team training optimization algorithm. Detailed Embodiments

[0052] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments; based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0053] The present invention provides a technical solution: an adaptive adjustment method for a fishery oxygen regulation control system, which specifically includes the following steps, as Figure 1 shown.

[0054] Step 1: Construct a fishery oxygen regulation control system, convert the fishery oxygen regulation control problem into a mathematical model to be optimized. The fishery oxygen regulation control system includes: an error calculation module, a PID controller, an improved football team training optimization algorithm module, a real-time detection module, and an oxygen regulation control module, as Figure 2As shown

[0055] Furthermore, in step one, the execution process of each module in the constructed fishery oxygen regulation control system is as follows: by inputting the given target oxygen regulation concentration and the actual oxygen concentration obtained by the real-time detection module into the error calculation module, the real-time error e(t) is calculated, and then this error is input into the PID controller. The PID controller uses the improved football team training optimization algorithm module to optimize it to obtain the optimal parameters. The optimized PID controller calculates and outputs the control quantity u(t) according to these optimal parameters. This control quantity is then transmitted to the oxygen regulation control module, and then adjusts the oxygen supply quantity to achieve the required oxygen concentration. The mathematical model of the oxygen regulation control module is shown in Equation (1):

[0056] (1);

[0057] In Equation (1), O(t) represents the oxygen concentration in water, Kc represents the oxygen consumption coefficient, which is related to the biomass and temperature in water, Nc represents the biological quantity coefficient in water, O_min represents the lowest oxygen concentration in water, which is related to water quality, and u(t) represents the control quantity output by the PID controller. The specific formula is shown in Equation (2):

[0058] (2);

[0059] In Equation (2), Kp represents the proportional gain, Ki represents the integral gain, Kd represents the derivative gain, and e(t) represents the real-time error.

[0060] Step two, improve the football team training optimization algorithm. The specific improvements include:

[0061] S1. Use a dynamic multi-dimensional weight update strategy to improve the update strategy of followers in the collective training stage of the football team training optimization algorithm. A dynamic multi-dimensional weight update strategy is to select the top 6 individuals with the best fitness values in the search population. The weight of the individual ranked first increases non-linearly with the increase of the algorithm iteration times. Decompose the position vectors of the remaining 5 individuals according to different dimensions, and randomly form three new individuals according to different dimensions. The weights of these three new individuals are dynamically allocated from the remaining weights, and the sum of all weights is 1;

[0062] S2. Use a distance-based optimal learning strategy to improve the optimal learning strategy in the group training of the football team training optimization algorithm. A distance-based optimal learning strategy is to guide the current individual by means of the position of the optimal individual in the population, and adjust the position of the current individual through the distance between the optimal individual and the current individual, so as to achieve the update of the position.

[0063] Further, in S1, a dynamic multi-dimensional weight update strategy is used to improve the update strategy of followers in the collective training stage of the football team training optimization algorithm. The specific mathematical model after improvement is shown in Equation (3):

[0064] (3);

[0065] In Equation (3), represents the position of the updated individual, F(iter) represents the position of the current individual, represents that the calculation formula of the dynamic weight factor is shown in Equation (4), represents the position of the optimal individual in the population, represents three new individual positions randomly formed by splitting the positions of individuals ranked 2-6 in fitness value in the population through different dimensions. In the optimization of the PID controller, the dimension value dim = 3, represents the weight of the i-th individual among the three new individuals. The weight values of the three new individuals are randomly assigned from (1 - );

[0066] (4);

[0067] In Equation (4), iter represents the current iteration number, max_iter represents the maximum iteration number, and the value of the dynamic weight changes non-linearly from 0.25 to 0.85 as the iteration number increases.

[0068] Further, in S2, a distance-based optimal learning strategy is used to improve the optimal learning strategy in the group training of the football team training optimization algorithm. The specific mathematical formula after improvement is shown in Equation (5):

[0069] (5);

[0070] In Equation (5), represents the position of the updated individual, F(iter) represents the position of the current individual, rand represents a random number between [0, 1], and the dist() function represents calculating the Euclidean distance between the positions of two individuals, represents the maximum distance of the entire search space, α represents the local search weight factor, represents the position of the optimal individual in the population, and α = log(1 + iter / max_iter).

[0071] Step 3: Use the improved football team training optimization algorithm to optimize the PID control in the fishery oxygen control system, and obtain the optimal set of PID control parameter values of Kp, Ki, and Kd through the iterative optimization of the algorithm.

[0072] Further, in step 3, the PID control in the fishery oxygenation control system is optimized by using an improved football team training optimization algorithm. The specific steps are as follows:

[0073] step1. Initialize the parameters of the improved football team training optimization algorithm, including the population size N, the problem dimension dim to be optimized by the algorithm, the maximum number of iterations max_iter, the upper bound ub and the lower bound lb of the algorithm's search space, and generate an initial population through the initial parameters of the algorithm.

[0074] step2. Map the improved football team training optimization algorithm to the PID controller in the fishery oxygenation control system, establish a connection between the individual position vector F(iter) in the algorithm population and the three parameters Kp, Ki, and Kd of the PID controller. Since the problem dimension dim of the algorithm is 3, the values of the three dimensions corresponding to the individual position vector respectively correspond to Kp, Ki, and Kd. As the positions in the population are updated through the iteration of the algorithm, the three control parameters of the PID controller will be continuously adjusted, and finally a set of optimal control parameters for the PID controller will be obtained.

[0075] step3. Set the fitness value function of the improved football team training optimization algorithm, calculate the fitness values of the individuals in the initial population through the set fitness value function, and sort them according to the size of the fitness values, and select the individual with the optimal fitness value as , and the specific fitness value function is shown in Equation (6):

[0076] (6);

[0077] In Equation (6), J represents the fitness value, e(t) represents the real-time error value, L represents the running time of the system, M represents the overshoot of the system response, that is, the peak value exceeding the target value, and λ represents the weight of the overshoot, with a value of 0.1.

[0078] step4. Update the positions of the individuals in the population through the mathematical model of the improved football team training optimization algorithm. The improved football team training optimization algorithm is divided into three stages, specifically:

[0079] Stage 1. Collective training stage. In the collective training stage, the individuals in the population are divided into four types: followers, discoverers, thinkers, and waverers. When the algorithm enters the collective training stage, the individuals are first classified and the corresponding type of mathematical model is used for position update. The update strategy of the followers is shown in Equation (3), and the update strategies of the other three types are shown in Equation (7):

[0080] (7);

[0081] In Equation (7), It represents the position of the updated individual, and F(iter) represents the position of the current individual. It represents the position of the optimal individual in the population. rand, rand1, and rand2 all represent random numbers between [0, 1]. It represents the position of the worst individual in the population. iter represents the current iteration number, and t(iter) represents a random number following the t-distribution.

[0082] Stage 2: Group training stage. The MGEM clustering method is used to group individuals. There are three ways for the members within each group to train, specifically including: optimal learning, random learning, and random communication. The update strategy of optimal learning is shown in Equation (5), and the update strategies of random learning and random communication are shown in Equation (8):

[0083] (8);

[0084] In Equation (8), It represents the position of the updated individual, F_rand(iter) represents the position of the individual randomly selected in the current stage, and randn represents a number randomly generated from the normal distribution.

[0085] Stage 3: Individual extra training stage. After the group training stage, the optimal individual in the population will be selected for training. The specific update strategy is shown in Equation (9):

[0086] (9);

[0087] In Equation (9), It represents the updated optimal position. It represents the position of the optimal individual in the population. iter represents the current iteration number, Gauss represents the Gaussian distribution, and Gauchy represents the Cauchy distribution.

[0088] In each iteration, the fitness value of the updated position will be compared with the fitness value before the update to determine whether to retain the updated position.

[0089] Step 5: Determine whether the current iteration number has reached the maximum iteration number. If it has reached the maximum iteration number, the optimization is completed and the optimal solution is output. Otherwise, continue to execute Step 4 for optimization.

[0090] Step 4: Input the set of optimal Kp, Ki, and Kd parameters optimized in Step 3 into the PID controller in the fishery oxygen regulation control system to optimize the control effect of the entire fishery aquaculture pond oxygen regulation control system.

[0091] Furthermore, to verify the superiority of the improved football team training optimization algorithm for the optimization of the fishery oxygenation control system, MATLAB and Simulink simulation tools are used for simulation experiments. The mathematical model of the standard football team training optimization algorithm is improved by MATLAB, and the simulation model of the fishery oxygenation control system is constructed by Simulink. The initial parameters of the algorithm are initialized as follows: the maximum number of iterations is 30, the problem dimension is 3, the population size is 100, and the range of the search space is [50, 0.001]. The mathematical model of the oxygenation control module is Laplace-transformed, and specific parameter values are given. The formula is: , where s is a complex variable. Run the experimental code and model, and the experimental results are as Figures 3 - 4 shown.

[0092] Furthermore, Figure 3 Figure [0000247] is a comparison chart of the fitness value changes during the optimization process of the improved football team training optimization algorithm and the standard football team training optimization algorithm. It can be seen from the figure that after the improved algorithm quickly reaches near the optimal solution during the optimization process, it will continue to search downward instead of falling into the local optimal solution, and the fitness value of the obtained solution is lower and the optimization accuracy is better. Figure 4 Figure [0000248] is a comparison chart of the effects of the improved football team training optimization algorithm and the standard football team training optimization algorithm on optimizing the PID controller. The target value is set to 1 unit. Using the improved algorithm to optimize the PID controller, the response curve has better stability and reaches the stable state in a shorter time, indicating that the optimized system has stronger robustness.

Claims

1. An adaptive adjustment method for a fishery oxygen regulation control system, characterized in that, The specific steps are as follows: Step 1: Construct a fishery oxygen regulation control system, and convert the fishery oxygen regulation control problem into a mathematical model to be optimized. The fishery oxygen regulation control system includes: an error calculation module, a PID controller, an improved football team training optimization algorithm module, a real-time detection module, and an oxygen regulation control module; Step 2: Improve the football team training optimization algorithm. The specific improvements include: S1. Use a dynamic multi-dimensional weight update strategy to improve the update strategy of followers in the collective training stage of the football team training optimization algorithm. This strategy is to select the top 6 individuals with the best fitness values in the search population. The weight of the individual in the first position increases non-linearly as the number of algorithm iterations increases. Decompose the position vectors of the remaining 5 individuals according to different dimensions, and randomly form three new individuals according to different dimensions. The weights of these three new individuals are dynamically allocated from the remaining weights, and the sum of all weights is 1. The specific mathematical model after improvement is shown in Equation (3): (3)； In formula (3), represents the position of the updated individual, and F(iter) represents the position of the current individual, represents that the calculation formula of the dynamic weight factor is as shown in formula (4), represents the position of the optimal individual in the population, represents three new individual positions randomly formed by splitting the positions of the individuals ranked 2-6 in fitness value in the population through different dimensions. In the optimization of the PID controller, the dimension value dim = 3, represents the weight of the i-th individual among the three new individuals. The weight values of the three new individuals are randomly assigned (1 - ); (4)； In Equation (4), iter represents the current iteration number, max_iter represents the maximum iteration number, and the value of the dynamic weight changes non-linearly from 0.25 to 0.85 as the number of iterations increases; S2. Use a distance-based optimal learning strategy to improve the optimal learning strategy in the group training of the football team training optimization algorithm. This strategy is to guide the current individual by means of the position of the optimal individual in the population, and adjust the position of the current individual through the distance between the optimal individual and the current individual, so as to achieve position update. The specific mathematical formula after improvement is shown in Equation (5): (5)； In formula (5), represents the position of the updated individual, F(iter) represents the position of the current individual, rand represents a random number between [0, 1], and the dist() function represents calculating the Euclidean distance between the positions of two individuals, represents the maximum distance of the entire search space, and α represents the local search weight factor, represents the position of the optimal individual in the population, and α = log(1 + iter / max_iter); Step 3: Use the improved football team training optimization algorithm to optimize the PID control in the fishery oxygen regulation control system, and obtain the optimal set of PID control parameter values of Kp, Ki, and Kd through the iterative optimization of the algorithm; Step 4: Input the optimal set of Kp, Ki, and Kd parameters obtained in Step 3 into the PID controller in the fishery oxygen regulation control system to optimize the control effect of the entire fishery oxygen regulation control system.

2. The adaptive adjustment method of a fishery oxygen regulation control system according to claim 1, wherein In Step 1, the execution process of each module in the constructed fishery oxygen regulation control system is as follows: Input the given target oxygen concentration and the actual oxygen concentration obtained by the real-time detection module into the error calculation module to calculate the real-time error e(t), and then input this error into the PID controller. The PID controller uses the improved football team training optimization algorithm module to optimize it to obtain the optimal parameters. The optimized PID controller calculates and outputs the control quantity u(t) according to these optimal parameters. This control quantity is then transmitted to the oxygen regulation control module, and then adjusts the oxygen supply amount to achieve the required oxygen concentration.

3. The adaptive adjustment method of a fishery oxygen regulation control system according to claim 2, characterized in that, In Step 3, use the improved football team training optimization algorithm to optimize the PID control in the fishery oxygen regulation control system. The specific steps are as follows: Step 1: Initialize the parameters of the improved football team training optimization algorithm, including the population size N, the problem dimension dim to be optimized by the algorithm, the maximum number of iterations max_iter, the upper bound ub and the lower bound lb of the search space of the algorithm, and generate an initial population through the initial parameters of the algorithm; Step 2: Map the improved football team training optimization algorithm to the PID controller in the fishery oxygenation control system, establish a connection between the individual position vector F(iter) in the algorithm population and the three parameters Kp, Ki, and Kd of the PID controller. Since the problem dimension dim of the algorithm is 3, the individual position vector corresponds to three-dimensional values, which respectively correspond to Kp, Ki, and Kd. As the positions in the population are updated through the iteration of the algorithm, the three control parameters of the PID controller will be continuously adjusted, and finally a set of optimal control parameters of the PID controller will be obtained; Step 3. Set the fitness value function of the improved football team training optimization algorithm, calculate the fitness values of individuals in the initial population through the set fitness value function, sort them according to the magnitudes of the fitness values, and select the individual with the optimal fitness value as , and the specific fitness value function is shown in Equation (6): (6)； In Equation (6), J represents the fitness value, e(t) represents the real-time error value, L represents the running time of the system, M represents the overshoot of the system response, that is, the peak value exceeding the target value, and λ represents the weight of the overshoot, with a value of 0.1; Step 4: Update the positions of the individuals in the population through the mathematical model of the improved football team training optimization algorithm. The improved football team training optimization algorithm is divided into three stages, specifically: Stage 1: Collective training stage. In the collective training stage, the individuals in the population are divided into four types: followers, discoverers, thinkers, and waverers. When the algorithm enters the collective training stage, the individuals are first classified and the corresponding type of mathematical model is used for position update; Stage 2: Group training stage. The MGEM clustering method is used to group the individuals, and the members within each group are trained in three ways, specifically including: optimal learning, random learning, and random communication; Stage 3: Individual extra training stage. After the group training stage, the optimal individual in the population will be selected for training; In each iteration, the fitness value of the updated position is compared with the fitness value before the update to determine whether to retain the updated position; Step 5: Determine whether the current number of iterations has reached the maximum number of iterations. If the maximum number of iterations is reached, the optimization is completed and the optimal solution is output. Otherwise, continue to execute Step 4 for optimization.

Images