CN-121115957-B - Fishery pond water temperature control optimization method based on group intelligent algorithm

CN121115957BCN 121115957 BCN121115957 BCN 121115957BCN-121115957-B

Abstract

The invention discloses a fishery pond water temperature control optimization method based on a group intelligent algorithm, which belongs to the technical field of control optimization and comprises the following steps of S1, constructing a fishery pond water temperature PID control system with an improved single-angle whale optimization algorithm module, S2, introducing the improved single-angle whale optimization algorithm, constructing the improved single-angle whale optimization algorithm module, S3, utilizing the improved single-angle whale optimization algorithm to perform setting optimization on pond water temperature PID control parameters to obtain optimal control parameters, and S4, setting the optimal control parameters obtained by utilizing the improved single-angle whale optimization algorithm as parameters of a pond water temperature PID controller, and optimizing pond water temperature adjustment control effects. The invention introduces a population intelligent optimization algorithm, namely an improved single-angle whale optimization algorithm, realizes high-performance control on the temperature of pool water, and provides reliable control technical support for guaranteeing high-efficiency, stable and safe operation of aquaculture.

Inventors

LIU XIAOCHEN
CAO LILI
DONG JUN

Assignees

山东省淡水渔业研究院（山东省淡水渔业监测中心）

Dates

Publication Date: 20260508
Application Date: 20251117

Claims (10)

1. A fishery pond water temperature control optimization method based on a group intelligent algorithm is characterized by comprising the following steps: S1, constructing a fishery pond water temperature PID control system, wherein the system comprises a pond water temperature error calculation module, a pond water temperature PID controller module, an improved single-angle whale optimization algorithm module, a pond water temperature adjustment module and a pond water temperature monitoring module; s2, introducing an improved single-angle whale optimization algorithm, wherein the specific improvement strategy comprises the following steps: s21, introducing a mirror habitat initialization strategy, and generating a random population and a corresponding reverse population and preferentially selecting the random population and the corresponding reverse population, so that the quality of an initial population is improved; s22, introducing a group collaborative hunting strategy, and selecting a random number as the strategy Less than the exploration rate When executing group collaborative hunting strategy to enhance global search capability, when the strategy selects random numbers Not less than the exploration rate Executing a long tooth stunning and predation strategy; s23, introducing a reverse protrusion strategy under the ice layer, and when the best prey is located Continuous and continuous When the generation is not improved, triggering a reverse surrounding strategy under the ice layer to generate Is a reverse solution of (2) And performs preferential replacement for jumping out of local optimum, wherein Is a stall threshold; S24, introducing a chaotic long tooth fine thorn strategy, and when the iteration times are equal to each other Greater than the number of initial iterations in the later stage When using Tent chaotic mapping pair Disturbance is carried out to generate And performing preferential replacement for improving the later convergence precision; s3, setting the pond water temperature PID control parameters in the fishery pond water temperature PID control system by utilizing an improved single-angle whale optimization algorithm, and obtaining the optimal control parameters through optimizing; S4, setting the optimal control parameters obtained by optimizing an improved single-angle whale optimization algorithm as parameters of a pool water temperature PID controller in the fishery pool water temperature PID control system, and optimizing the pool water temperature regulation control effect.
2. The fishery pond water temperature control optimization method based on the population intelligent algorithm according to claim 1, wherein in the fishery pond water temperature PID control system constructed in the step S1, the pond water temperature monitoring module is used for collecting the actual temperature of pond water and transmitting the actual temperature to the pond water temperature error calculation module, the pond water temperature error calculation module is used for receiving the set pond water target temperature, carrying out error calculation on the target temperature and the actual temperature, and outputting a real-time error to the pond water temperature PID controller module, and the improved single-corner whale optimization algorithm module is used for carrying out error calculation on the internal parameters of the PID controller module And (3) performing continuous optimization, calculating a control quantity according to the error by an optimized PID controller, and outputting the control quantity to a pool water temperature adjusting module to realize the adjustment of the pool water temperature.
3. The optimization method for controlling water temperature in a fishery pond based on a population intelligent algorithm according to claim 1, wherein the mirrored habitat initialization strategy of step S21 comprises the steps of: s211, in the search space And Internal random generation Initial one-corner whales ; S212, pass through Calculation of Inverse solution of And is opposite to Performing boundary restoration, wherein In order to solve the problem in the reverse direction, In order to search the lower bound of the space, For the upper bound of the search space, Is an initial unicorn whale; s213, combining And Form and include A population of candidate solutions; s214, evaluation The fitness of each candidate solution is selected, and the optimal fitness is selected Individual solutions as initial one-corner whale populations 。
4. The method for optimizing water temperature control in a fishery pond based on a group intelligent algorithm according to claim 1, wherein the group collaborative hunting strategy of step S22 comprises the following steps: S221, randomly selecting two indexes different from the current index Index of (2) And ; S222, calculating DE variation vector , , Wherein the method comprises the steps of In order to obtain the DE variation vector, For the current location of the individual, In order for the scaling factor to be a factor, In order to be the best place of the prey, And A location of the individual selected at random; s223, generating DE test vector For a pair of Is of the order of each dimension of (1) When (when) Or (b) Equal to random dimension index In the time-course of which the first and second contact surfaces, Otherwise Wherein Is a random number between 0 and 1, Is the crossover probability; S224, new position is to be set Is set as 。
5. The method for optimizing water temperature control in a fishery pond based on a population intelligent algorithm according to claim 1, wherein the long-tooth stun and predation strategy of step S22 comprises the following steps: s225, selecting random numbers based on the policies for policy selection And generating a utilization coefficient random number ; S226, calculating the utilization coefficient , , Wherein the method comprises the steps of In order to explore the decay factor, Selecting a random number for a policy for policy selection; S227, calculating the utilization coefficient , , Wherein the method comprises the steps of A random number generated for step S225; S228, calculating the suction strength , , Wherein the method comprises the steps of In order to be a strength of the suction force, Exploration rate for dynamic update Is a target of the energy of the hunting species, For the current individual With the best prey location Euclidean distance therebetween, and wherein the following relationship is satisfied; , And is also provided with The energy attenuation rate is used, and t is the iteration number; S229, calculate suction force , , Wherein the method comprises the steps of In the form of a suction force, In order to be a strength of the suction force, Exploration rate for dynamic update Is the prey energy of (a); s2210, updating individual position , , Wherein the method comprises the steps of In order to update the position of the object, For the current individual to be present, In order to be the best place of the prey, For individuals Is the dimension of the solution vector, Is a random noise vector independent from dimension to dimension.
6. The method for optimizing water temperature control in a fishery pond based on a population intelligent algorithm according to claim 1, wherein the ice layer under reverse protrusion strategy of step S23 comprises the following steps: S231, pass through Calculation of Is a reverse solution of (2) And performing boundary restoration, wherein In order to solve the problem in the reverse direction, In order to search the lower bound of the space, For the upper bound of the search space, Is the best prey location; s232, evaluation Obtain the adaptability ; S233, when the inverse solution is adaptive Less than optimal fitness When updating And And reset the stall counter Is 0.
7. The method for controlling and optimizing the water temperature of the fishery pond based on the group intelligent algorithm according to claim 1, wherein the chaotic long tooth fine-puncturing strategy of the step S24 comprises the following steps: S241 updating chaotic variable through Tent chaotic mapping ; S242, calculating chaotic disturbance step length , , Wherein the method comprises the steps of For the chaotic disturbance step size, For the current number of iterations, For the number of initial iterations in the later stage, The maximum iteration number; S243, generating chaotic disturbance solution And the boundary restoration is carried out, , Wherein the method comprises the steps of For the solution of the chaotic disturbance, In order to be the best place of the prey, For the chaotic disturbance step size, For the upper bound of the search space, In order to search the lower bound of the space, Is a Tent chaotic variable; s244, evaluation Obtain the adaptability ; S245, when inverse solution is applied Less than optimal fitness When updating And And reset the stall counter Is 0.
8. The fishery pond water temperature control optimization method based on the population intelligent algorithm according to claim 1, wherein the specific steps of the step S3 include: s31, starting a slave current iteration number Up to the maximum number of iterations Is an iterative optimization loop of (a); S32, in the iteration loop, calculating all individuals Is of the acoustic wave intensity of (2) For long stun and predation strategies; S33, traversing each individual in the population According to the search rate And policy selection random numbers Selectively executing a group collaborative hunting strategy or a long-tooth stun and predation strategy to generate a new position ; S34, for all new positions Performing boundary restoration and calculating fitness thereof; S35, updating population Is that ; S36, updating the global optimal prey position according to the updated population Stall counter ; S37, judging stagnation counter Whether or not it is greater than the stall threshold If (3) Greater than Then execute the reverse burst strategy under the ice layer if Not greater than Skipping the reverse protrusion strategy under the ice layer and entering step S38; s38, judging the current iteration times Whether or not it is greater than the number of initial iterations in the later stage If (3) Greater than Then the chaotic long tooth fine thorn strategy is executed, if Not greater than Skipping the chaotic long tooth fine puncturing strategy and continuing to circulate; s39, when Reach to Ending the iterative optimization loop and outputting 。
9. The method for optimizing water temperature control in a fishing pool based on a population intelligent algorithm as set forth in claim 8, wherein step S3 further includes the step of updating hunting state when performing an iterative optimization loop: S3001, updating the exploration attenuation factor , , Wherein the method comprises the steps of In order to explore the decay factor, For the current number of iterations, The maximum iteration number; S3002, updating prey energy , , Wherein the method comprises the steps of In order to be able to play a role in the energy of the prey, In order to achieve a rate of energy decay, The current iteration number; s3003, dynamically updating the exploration rate , Calculating fitness improvement value , Wherein the method comprises the steps of In order to adapt the value of the improvement, For the best fitness of the previous generation, The current best fitness; When (when) Less than a preset improvement threshold At the time, set For the first exploration rate , When (when) Not less than And is also provided with Less than a preset energy threshold At the time, set For the second exploration rate , When (when) Not less than And is also provided with Not less than At the time, set For the first exploration rate 。
10. The optimization method for controlling water temperature in a fishery pond based on a population intelligent algorithm according to claim 1, wherein the improved one-corner whale optimization algorithm in step S3 is used for evaluating the fitness function of the PID control parameters The method comprises the following steps: , Wherein the method comprises the steps of For the settling time, the threshold is a preset value, The weight is penalized for the amount of overshoot, Is the step response overshoot percentage.

Description

Fishery pond water temperature control optimization method based on group intelligent algorithm Technical Field The invention belongs to the technical field of control optimization, and particularly relates to a fishery pond water temperature control optimization method based on a group intelligent algorithm. Background The water temperature control system of the fishery pond is at the core position in the aquaculture system, and the main responsibility of the water temperature control system is to maintain the water temperature in a proper range so as to meet the physiological demands of fishes in different growth stages. The water temperature not only affects physiological activities such as ingestion, digestion, immunity and the like of fish, but also directly determines metabolic intensity and growth rate, so that stability and accuracy of temperature control become basic conditions for guaranteeing cultivation efficiency, reducing cultivation risk and improving survival rate. In the actual running process, the temperature of the pool water can be continuously disturbed by various factors such as day and night air temperature difference, seasonal variation, wind speed variation, radiation intensity fluctuation, pool heat preservation condition variation, heat generation effect generated by the activity of fishes, and the like, so that the heat balance of the water body is frequently changed. The system needs to rely on natural heat dissipation, a heating device, cooling equipment or a circulating water system to regulate the disturbance in real time, and the regulation process has higher requirements on response speed, control precision and dynamic adaptability. At present, a common farmer generally adopts a manual regulation or simple temperature controller mode, and triggers a heating or cooling unit by setting upper and lower limit thresholds, but the coarse-grain control strategy is obviously insufficient in the scene of frequent disturbance, high change rate and limited equipment performance, for example, the accumulation of measurement deviation of a sensor leads to expansion of control errors, overshoot of temperature caused by hysteresis characteristics of a heating device or a refrigerating module, unstable regulation caused by inconsistent linkage response among different equipment, and the like, so that the system is difficult to maintain the dynamic balance of water temperature in a complex environment, and the energy consumption cost and management burden are easy to be further increased. In order to overcome the limitations of the traditional method, the current advanced method adopts a PID controller and an optimization strategy thereof to improve the stability of the system, the PID controller can adjust the output quantity in real time according to the variation trend of the error, thereby improving the problems of overshoot, hysteresis and steady-state error in the temperature adjustment process, and in order to further improve the PID control effect, the more advanced method introduces intelligent optimization methods such as a genetic algorithm, a particle swarm optimization algorithm and the like to set control parameters so as to enhance the sensitivity and adaptability of the system to external disturbance, but the conventional intelligent optimization methods generally have the defects of easy sinking into local optimum, slow convergence speed, insufficient algorithm stability and the like to improve the setting efficiency and control performance to a certain extent, and are difficult to continuously maintain the high-quality parameter optimizing capability in a high-dimensional complex search space. Under the background that the randomness of disturbance of the water body environment is enhanced, the dynamic characteristics of the system are complicated and the control precision requirements are continuously improved, the requirements of the modern fishery culture system on stability, robustness and self-adaptability can not be met only by relying on the traditional PID setting method or the early intelligent optimization algorithm, so that the advanced group intelligent optimization algorithm is introduced, the advantages of the advanced group intelligent optimization algorithm in the aspects of global searching capability, local optimum jumping-out mechanism, convergence speed acceleration and structure expandability are utilized, the deep optimization of the PID parameters of the pool water temperature control system becomes the necessary requirements of digital fishery development, and the group intelligent optimization algorithm can realize the parameter optimization with higher quality and higher adaptability in the complex environment with obvious multi-constraint, multi-disturbance and nonlinear characteristics. Disclosure of Invention In order to overcome the technical problems in the background art, the invention provides a fishery pond water temperature control optimi