Refrigerating system cooperative control method and system, medium and terminal

Abstract

The invention relates to the technical field of refrigeration system control, in particular to a refrigeration system cooperative control method and system, a medium and a terminal. The control method comprises the steps that running state parameters of the refrigerating system are obtained in real time; predicting the temperature and energy efficiency of the refrigeration system based on the constructed and initialized physical prediction model; performing global optimization on the operation state parameters and the predicted temperature and energy efficiency based on a constructed and initialized meta-heuristic algorithm to generate optimization control parameters; generating a real-time adjusting instruction according to the current operation state parameter by utilizing a PID controller; and the optimization control parameters and the real-time adjustment instruction are fused to generate a dynamic cooperative control signal, and the dynamic cooperative control signal serves as an output control signal of the refrigeration system. Through the arrangement, the calculation burden can be reduced, the real-time performance can be improved, the method can adapt to high-precision control of a complex multi-physics field coupling scene, and the energy efficiency, the dynamic response speed and the multi-working-condition adaptability of the refrigeration system are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of refrigeration system control, and particularly to a refrigeration system collaborative control method, system, medium, and terminal. Background Art

[0002] Refrigeration systems are widely used in industrial, commercial, and domestic fields, and their core function is to maintain a low-temperature environment. Traditional control methods mainly rely on PID (Proportional-Integral-Derivative) control, and achieve temperature stability by adjusting the state of compressors or fans. However, due to the complex multi-physical field coupling characteristics of refrigeration systems, including thermal fields, mass fields, and dynamic fields, etc., the dynamic coupling effect between physical fields increases the complexity of system operation, making it difficult for traditional PID control methods to meet the requirements of rapid response and efficient control under non-linear and dynamically changing working conditions.

[0003] In existing improvement schemes, meta-heuristic algorithms optimize parameters through global search, but they have a large amount of calculation and slow response speed, and their application in real-time control is limited. In addition, there are difficulties when such algorithms cooperate with existing control methods, lacking the ability of real-time dynamic adjustment and fine control, especially under the condition of rapid change of system operating conditions, their performance is not good.

[0004] Therefore, how to improve control technology to enhance the real-time response ability and dynamic adjustment ability of refrigeration systems has become a key issue in current refrigeration system control. Summary of the Invention

[0005] To solve at least one deficiency in the control technology of refrigeration systems in the above-mentioned existing technologies, the present invention provides a refrigeration system collaborative control method to improve the real-time response ability and dynamic adjustment ability of refrigeration systems.

[0006] In a first aspect, the refrigeration system collaborative control method provided by the present invention includes the following steps: Obtain the operating state parameters of the refrigeration system in real time; Predict the temperature and energy efficiency of the refrigeration system based on a constructed and initialized physical prediction model; Based on a constructed and initialized meta-heuristic algorithm, globally optimize the operating state parameters and the predicted temperature and energy efficiency to generate optimized control parameters; Use a PID controller to generate real-time adjustment instructions according to the current operating state parameters; Fuse the optimized control parameters and the real-time adjustment instructions to generate a dynamic collaborative control signal, and use the dynamic collaborative control signal as the output control signal of the refrigeration system.

[0007] In some embodiments, the meta-heuristic algorithm adopts one of HHO, WOA, and GWO.

[0008] In some embodiments, the formula for predicting the temperature of the refrigeration system based on the physical preset model is:

[0009] In the formula, is the predicted temperature at the next moment, is the temperature at the current moment, is the input of the system, is the environmental change parameter.

[0010] In some embodiments, when the meta-heuristic algorithm adopts the HHO algorithm, the fitness function of the HHO algorithm combining energy efficiency and temperature is:

[0011] In the formula, , , are weight coefficients respectively, is the predicted energy efficiency, response time, is the predicted temperature, is the target temperature.

[0012] In some embodiments, when the meta-heuristic algorithm adopts the HHO algorithm, the HHO algorithm updates the positions of the population by switching between the exploration phase and the exploitation phase, and the formula for position update is:

[0013] In the formula, is the new position of the current population individual, is the current position of the population individual, is the position of the local optimal solution, is the position of the global optimal solution, , are weight coefficients for controlling the exploration phase and the exploitation phase; The HHO algorithm also controls the balance between the exploration phase and the exploitation phase by dynamically adjusting the escape energy; the formula for dynamically adjusting the escape energy is:

[0014] In the formula, is the current escape energy, is the initial escape energy, is the current iteration number, is the maximum iteration number.

[0015] In some embodiments, the operating state parameters and the predicted temperature and energy efficiency are globally optimized to generate optimized control parameters The formula is:

[0016] In the formula, is the error metric based on the current state of the system, is the constraint function based on the physical prediction model, is the balance coefficient.

[0017] In some embodiments, the formula for fusing the optimized control parameter and the real-time adjustment instruction to generate a dynamic collaborative control signal is:

[0018] In the formula, is the finally output dynamic collaborative control signal, is the output signal of the PID controller, , is the predicted temperature and the target temperature in the physical prediction model, , , are the weighting coefficients.

[0019] In a second aspect, the present invention further provides a collaborative control system for a refrigeration system, including: A parameter acquisition module for real-time acquisition of the operating state parameters of the refrigeration system; A physical prediction module for predicting the temperature and energy efficiency of the refrigeration system based on the constructed and initialized physical prediction model; A metaheuristic optimization module for globally optimizing the operating state parameters and the predicted temperature and energy efficiency based on the constructed and initialized metaheuristic algorithm to generate optimized control parameters; A PID control module that uses a PID controller to generate real-time adjustment instructions according to the current operating state parameters; A dynamic collaboration module for fusing the optimized control parameter and the real-time adjustment instruction to generate a dynamic collaborative control signal, and using the dynamic collaborative control signal as the output control signal of the refrigeration system.

[0020] In a third aspect, the present invention further provides a storage medium, which is a non-volatile storage medium or a non-transitory storage medium, on which a computer program is stored, and when the computer program is run by a processor, it executes the refrigeration system collaborative control method according to any one of the embodiments in the first aspect above.

[0021] Fourthly, the present invention further provides a terminal, which is characterized in that it includes a memory and a processor, a computer program capable of running on the processor is stored on the memory, and when the processor operates the computer program, it executes the refrigeration system collaborative control method described in any embodiment of the first aspect above.

[0022] Based on the above, compared with the prior art, the refrigeration system collaborative control method provided by the present invention solves the problems of slow response, low energy efficiency, poor adaptability, etc. in the control of traditional refrigeration systems through the collaborative optimization of physical prediction models, meta-heuristic algorithms, and PID control. It can not only reduce the computational burden and improve real-time performance, but also adapt to the high-precision control of complex multi-physical field coupling scenarios, significantly improving the energy efficiency, dynamic response speed, and multi-condition adaptability of the refrigeration system.

[0023] Other features and beneficial effects of the present invention will be described in the subsequent description, and part of them will become obvious from the description, or be understood by implementing the present invention. The objectives and other beneficial effects of the present invention can be achieved and obtained through the structures specifically pointed out in the description, claims, and drawings. Description of the Drawings

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings; in the following description of the positional relationship of the drawings, unless otherwise specified, the direction shown by the components in the drawings is used as the reference.

[0025] Figure 1 It is a flowchart of the steps of the refrigeration system collaborative control method provided by an embodiment of the present invention; Figure 2 It is a flowchart of the operation of the refrigeration system collaborative control method provided by an embodiment of the present invention; Figure 3 It is a response curve diagram of the HHO algorithm to the condensing pressure; Figure 4 It is a response curve diagram of the HHO algorithm to the suction pressure; Figure 5 It is a response curve diagram of the HHO algorithm for optimizing PID parameters to the condensing pressure; Figure 6 It is a response curve diagram of the HHO algorithm for optimizing PID parameters to the suction pressure; Figure 7 It is a comparison diagram of the response curves of different algorithms to the condensing pressure; Figure 8Comparison chart of the response curves of different algorithms to the suction pressure; Figure 9 Comparison chart of the condensation pressure control performance indicators under different algorithms; Figure 10 Comparison chart of the suction pressure control performance indicators under different algorithms; Figure 11 Comparison chart of the coefficient of performance (COP) under different algorithms; Figure 12 Structural block diagram of the refrigeration system collaborative control system provided by another embodiment of the present invention. Detailed implementation manners

[0026] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention; the technical features designed in different implementation manners of the present invention described below can be combined with each other as long as they do not conflict with each other; all other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts belong to the scope of protection of the present invention.

[0027] In the description of the present invention, it should be noted that all terms used in the present invention (including technical terms and scientific terms) have the same meanings as those commonly understood by those of ordinary skill in the art to which the present invention belongs, and should not be construed as limiting the present invention; it should be further understood that the terms used in the present invention should be understood as having meanings consistent with their meanings in the context of this specification and the relevant art, and should not be understood in an idealized or overly formal sense, unless clearly defined as such in the present invention.

[0028] Currently, the most commonly used control method for refrigeration system energy efficiency control technology is PID control. The PID controller maintains the temperature stability by adjusting the operating states of the compressor and the fan in real time. Its advantages lie in simplicity and easy implementation, and it is applicable to various control scenarios. However, when facing the complex non-linear dynamic characteristics and significant time lag of the refrigeration system, the performance of PID control is often not ideal. This is because the PID controller relies on fixed parameters and is difficult to quickly adapt to changes in the system operating conditions, resulting in slow response speed and insufficient adjustment accuracy, thus restricting the further improvement of energy efficiency.

[0029] To overcome the deficiencies of PID control, researchers have attempted to introduce metaheuristic algorithms into the control of refrigeration systems, such as the Harris Hawks Optimization (HHO) algorithm. HHO simulates swarm intelligence behavior in nature, efficiently searches for optimal solutions in complex parameter spaces, and improves the optimization efficiency by balancing global exploration and local exploitation capabilities, providing the possibility for improving the performance of refrigeration systems. However, due to the large computational amount and slow response speed of metaheuristic algorithms, their application in real-time control is limited. In addition, there are difficulties in coordinating such algorithms with existing control methods, lacking the ability of real-time dynamic adjustment and fine control, especially in the case of rapid changes in system operating conditions, and the performance is not ideal.

[0030] On the other hand, some studies also adopt the method of predicting the future state of the system by constructing a dynamic model of the refrigeration system and combining operation data to adjust the control strategy in advance. However, although this method can theoretically improve the control accuracy and adaptability of the system, it has high requirements for the accuracy and integrity of data. In actual operation, parameters may fluctuate due to environmental changes or equipment aging, resulting in a decrease in prediction accuracy. The process of model establishment is complex, especially in systems involving complex thermodynamic processes and multiple control variables, with a heavy computational burden and poor real-time performance. At the same time, in order to maintain the effectiveness of the model, a large amount of real-time data is required for calibration, further increasing the computational cost and system complexity. In addition, there are also difficulties in integrating the prediction model with other control strategies, making it difficult to fully utilize its prediction ability.

[0031] In view of the significant deficiencies of the above technologies in terms of energy efficiency improvement, real-time response, and dynamic adjustment capabilities, the present invention provides a dynamic cooperative optimization method that combines the global search ability of metaheuristic algorithms, the real-time adjustment advantage of PID control, and the forward-looking prediction ability of physical prediction models to effectively solve the above problems. Through multi-physical field coupling modeling and dynamic cooperative control strategies, the present invention can significantly improve the energy efficiency, dynamic response speed, and multi-condition adaptability of refrigeration systems, providing a new solution to the problem of high energy consumption in refrigeration systems.

[0032] The technical solutions of the present invention will be described and illustrated in detail through various specific embodiments in combination with different embodiments and the accompanying drawings of the specification.

[0033] Embodiment 1 Please refer to Figure 1 , the cooperative control method of the refrigeration system provided in this embodiment includes the following steps: Step S10, obtain the operating state parameters of the refrigeration system in real time.

[0034] In specific implementation, according to the actual operating conditions of the refrigeration system, the data acquisition module can collect the operating state parameters of the refrigeration system to provide necessary information input for the subsequent optimization process. The operating state parameters include but are not limited to the temperature, pressure (such as the condensation pressure of the condenser, the suction pressure of the evaporator and the compressor, etc.), the fan speed, the compressor speed, and other key parameters involved in the refrigeration operation process.

[0035] Step S20, predict the temperature and energy efficiency of the refrigeration system based on the constructed and initialized physical prediction model. The physical prediction model is constructed according to the actual physical characteristics. Specifically, by considering factors such as the thermodynamic process, nonlinear characteristics, and environmental changes of the refrigeration system, a suitable mathematical model can be established to predict the future state of the system. The physical prediction model provides preliminary system state predictions (such as temperature changes, energy efficiency changes, etc.) for the meta-heuristic algorithm, and these predicted values can be used to guide the search process of the meta-heuristic algorithm, thus guiding the algorithm to optimize more accurately.

[0036] As an example, assume that the physical prediction model predicts the temperature based on the thermodynamic equation and nonlinear characteristics. Then the formula for predicting the temperature of the refrigeration system based on the physical preset model is:

[0037] In the formula, is the predicted temperature at the next moment, is the temperature at the current moment, is the input of the refrigeration system, is the environmental change parameter. The physical prediction model predicts the temperature at the next moment through the feedback of the input and the system state, and feeds this prediction result back to the meta-heuristic algorithm and the PID controller to guide the optimization process and the generation of control instructions. Specifically, is the input signal of the refrigeration system, such as the control signals of the compressor power and the fan speed, which are reasonably set according to the actual input requirements of the refrigeration system, and it reflects the active adjustment ability of the refrigeration system (such as the adjustment of the compressor power). is the environmental change parameter, such as including external temperature, humidity and other external interference factors, The value of can be reasonably designed according to the actual interference factors, and it represents the passive impact of the external environment on the system (such as the decrease in heat dissipation efficiency caused by a high-temperature environment). If varies dynamically with the environment (such as the decrease in heat exchange efficiency caused by the increase in humidity), and this value implies a nonlinear relationship, then the specific expression of can be determined through experiments or data calibration or combined with empirical formulas. The above formula is used to predict the temperature evolution trend of the refrigeration system in real time, providing forward-looking constraints for the meta-heuristic algorithm and the PID control, thereby improving the control accuracy and response speed.

[0038] In another example, the formula for the physical prediction model to predict the energy efficiency of the refrigeration system is:

[0039] In the formula, is the coefficient of performance (COP) at the current moment, representing the cooling capacity per unit energy consumption; is the effective cooling capacity of the refrigeration system, calculated through the heat exchange of the evaporator; is the real-time power of the compressor; is the real-time power of the fan. This formula can be used in the fitness function of the meta-heuristic algorithm to guide the algorithm to preferentially select control parameters with high energy efficiency. That is, by quantifying the coefficient of performance, it provides key inputs for the dynamic collaborative optimization of the refrigeration system, ensuring that the control strategy takes into account both the response speed and energy efficiency. Among them, the higher the coefficient of performance (COP), the greater the cooling capacity per unit energy consumption, and the better the system energy efficiency. The cooling capacity can be calculated through thermodynamic equations, such as , is the refrigerant mass flow rate, is the specific heat capacity, is the temperature difference between the inlet and outlet of the evaporator.

[0040] Step S30: Based on the constructed and initialized meta-heuristic algorithm, globally optimize the operating state parameters and the predicted temperature and energy efficiency to generate optimized control parameters; use the PID controller to generate real-time adjustment instructions according to the current operating state parameters.

[0041] Specifically, in implementation, the meta-heuristic algorithm uses its global search ability to optimize the system parameters to find the optimal solution. Its optimization process is: initialize the meta-heuristic algorithm population according to the current operating state parameters and prediction results, then calculate the fitness value of each individual, and at the same time update the population position through the corresponding algorithm mechanism, and output the optimal control parameters after the iteration reaches the maximum number of times or the fitness converges.

[0042] Among them, the meta-heuristic algorithm can be but is not limited to HHO (Harris Hawks Optimization Algorithm), WOA (Whale Optimization Algorithm), or GWO (Grey Wolf Optimization Algorithm). In this embodiment, HHO is preferably used.

[0043] In this embodiment, the fitness function is used to calculate the fitness value of each individual to evaluate the quality of the control parameters. The fitness function not only considers performance indicators such as energy efficiency and response time, but also combines the prediction output of the physical prediction model (such as temperature change), thereby guiding the optimization process. Among them, the fitness function is designed by combining energy efficiency, temperature error, and system stability indicators, and its formula is:

[0044] In the formula, , , are weight coefficients respectively, is the predicted energy efficiency, is the response time, is the predicted temperature, is the target temperature. That is, , are the energy efficiency and temperature predicted by the physical prediction model respectively. , , are weight coefficients used to balance energy efficiency, accuracy and stability, and can be reasonably set according to the actual working conditions. Among them, . For example , , . In the fitness function provided above, the predicted temperature affects the optimization process and can effectively help the meta-heuristic algorithm avoid control strategies that may lead to instability or inefficiency.

[0045] When the meta-heuristic algorithm adopts HHO, this embodiment updates the population position through an "exploration - exploitation" mechanism. That is, the HHO algorithm updates the population position by switching between the exploration stage and the exploitation stage, and the key formula for this position update is:

[0046] In the formula, is the new position of the current population individual, is the current position of the population individual, is the position of the local optimal solution, is the position of the global optimal solution, , are weight coefficients for controlling the exploration stage and the exploitation stage.

[0047] Among them, the HHO algorithm also controls the balance between the exploration stage and the exploitation stage by dynamically adjusting the escape energy. The formula for dynamically adjusting the escape energy is:

[0048] In the formula, is the current escape energy, is the initial escape energy, is the current iteration number, is the maximum iteration number.

[0049] Based on the position update steps combined with the above fitness value calculation, position update formula, and escape energy formula, the combination of the physical prediction model and the HHO algorithm can effectively achieve the global iterative optimization of the HHO algorithm. Specifically, the physical prediction model predicts the future state of the system by considering thermodynamic processes, nonlinear characteristics, and environmental changes. When the physical prediction model is combined with the HHO algorithm, the prediction results output by the physical prediction model are used as an important feedback constraint in the optimization process. Assuming that the physical model predicts the temperature T(t) and energy efficiency E(t) at the current time t, the search process of the HHO can be adjusted using the physical prediction results.

[0050] Among them, the operating state parameters and the predicted temperature and energy efficiency are globally optimized to generate optimized control parameters The formula for is:

[0051] In the formula, is the error metric based on the current state of the system, is the constraint function based on the physical prediction model, is the balance coefficient. Through this formula, the results predicted by the physical model become part of the optimization of the HHO algorithm, helping to ensure that the optimization process conforms to physical constraints and avoiding invalid or unstable control strategies.

[0052] Specifically, the error metric based on the current state of the system comprehensively considers the current operating state S(t) and control parameters P of the system, and is used to measure the deviation degree between the system and the ideal state under the current control strategy. The construction of this function can comprehensively consider performance indicators such as energy efficiency and response time. The smaller this value is, the closer the current control strategy is to the optimal, and the better the system can achieve the expected performance indicators, such as the temperature being stable near the set value and the energy efficiency reaching a high level.

[0053] is the constraint function constructed according to the output of the physical prediction model (such as the predicted temperature and energy efficiency), and is specifically designed reasonably according to actual needs. For example, if it is predicted that the temperature will be too high under certain control parameters, then can be set as a function related to the temperature deviation. The greater the temperature deviation, the greater the value of. This function can convert the prediction results into constraints on the control parameter P. Another example is that the physical prediction model may predict that under certain control parameters, the temperature of the system will exceed the safe range or the energy efficiency will drop sharply, then will reflect this adverse situation and limit these parameters in the optimization process. The balance coefficient It is determined according to the characteristics of the system and the actual application requirements. For example, for a refrigeration system that is more sensitive to temperature changes, the value can be appropriately increased to consider more the constraints of the physical prediction model.

[0054] Based on the above, when certain termination conditions are met, such as reaching the maximum number of iterations or the fitness value converges to a certain extent, the iteration is stopped. And the control parameters corresponding to the individual with the optimal fitness value are selected as the final optimized control parameters.

[0055] It should be understood that in this embodiment, the prediction of the physical prediction model only exemplifies predicting the temperature and energy efficiency at the current time. Those skilled in the art, according to the concept of the present invention, can also construct other parameter values that consider thermodynamic processes, non-linear characteristics, and environmental changes to predict the future state of the system according to actual needs, and apply the parameter values to the meta-heuristic algorithm to adjust and optimize the search process of the meta-heuristic algorithm, and all such methods fall within the protection scope of the embodiments of the present invention.

[0056] In step S30, a PID controller is also used to generate a real-time adjustment instruction according to the current operating state parameters. Specifically, the PID controller makes a preliminary adjustment to the current operating state of the system according to the preset control strategy to improve the dynamic response of the system. The specific control strategy and adjustment method can be reasonably set with reference to the existing PID control, and will not be elaborated in this embodiment.

[0057] Step S40, fusing the optimized control parameters and the real-time adjustment instruction to generate a dynamic collaborative control signal, and using the dynamic collaborative control signal as the output control signal of the refrigeration system.

[0058] Specifically in implementation, in this embodiment, the optimized control parameters optimized by the meta-heuristic algorithm are combined with the real-time adjustment instruction of the real-time feedback of the PID controller, and the final control instruction is generated by the weighted average method to optimize the response speed and stability of the system.

[0059] Preferably, the formula for fusing the optimized control parameters and the real-time adjustment instruction to generate a dynamic collaborative control signal is:

[0060] In the formula, is the finally output dynamic collaborative control signal, is the output signal of the PID controller, , is the predicted temperature in the physical prediction model and the target temperature 、 、 is the weighting coefficient. The weighting coefficient , , is used to balance the PID feedback, physical prediction error, and HHO optimization result. The specific value should be reasonably set according to the actual working condition requirements. Through this formula setting, the results of the physical prediction model, meta-heuristic algorithm optimization, and PID controller are combined to ensure that the system can quickly respond to environmental changes and adjust according to the prediction results while maintaining high efficiency performance.

[0061] In this embodiment, the innovation and optimization of the refrigeration system control strategy are realized through the above steps. Specifically, by combining the global search ability of the meta-heuristic algorithm, the immediate adjustment feedback of the PID controller, and the future state prediction of the physical prediction model, the dynamic response speed and stability of the system are significantly improved, the energy efficiency is optimized, and the environmental impact is reduced.

[0062] Based on the specific steps of the above refrigeration system collaborative control method Figure 2 shows the operation process of the above refrigeration system collaborative control method. The process starts from the "Start" node. First, the operation state parameters are read, and these parameters may include key data such as the current operation state and performance indicators of the refrigeration system. Subsequently, the physical prediction model is initialized to predict the future behavior of the system, such as temperature changes and energy efficiency trends. Then, the meta-heuristic algorithm is initialized to perform global search in the solution space to find the optimal solution. At this time, the prediction results of the physical prediction model can be input into the meta-heuristic algorithm to help the HHO algorithm optimize more precisely to better adapt to the changes of the system. After initializing the HHO, the system calculates the fitness of the current population based on the fitness function, that is, evaluates the quality of the current solution. Then, the system enters a decision node to judge whether to continue iterative optimization. If iterative optimization is required, the system will update the population position, which is achieved through the iterative process of the meta-heuristic algorithm, aiming to gradually approach the optimal solution. If iterative optimization is not required, the system will directly obtain the best position in the current iteration, that is, the optimal solution to generate the optimized control parameters. After obtaining the best position, the system enters the PID adjustment stage, and the PID controller initially adjusts the current operation state of the system according to the preset control strategy to generate real-time adjustment instructions, thereby improving the dynamic response of the system. Subsequently, the system integrates the HHO algorithm and the PID control strategy and determines the next adjustment speed. This step is to ensure that the adjustment of the system is both fast and accurate. That is, the optimized control parameters and real-time adjustment instructions are fused to generate a dynamic collaborative control signal and determine the speed.

[0063] After integrating HHO-PID and determining the speed, the system monitors its performance parameters to ensure the effectiveness of the optimization process and the stability of the system. Then, the system enters the decision node again to determine whether the preset performance goal has been achieved, that is, whether the set point has been reached. If the system has reached the set point, it will enter the stable operation state, which means that the refrigeration system has been optimized to the best performance and can operate with the highest stability and energy efficiency. If the system has not reached the set point, the process will return to the step of updating the population position and continue the iterative optimization until the performance requirements are met.

[0064] The entire flowchart embodies a closed-loop optimization mechanism. Through continuous iteration and fine adjustment, it ensures that the refrigeration system can maintain the best performance under dynamically changing operating conditions. The introduction of the physical prediction model enables the optimization process to better adapt to future system state changes and provides a more accurate decision-making basis for PID regulation and metaheuristic algorithms. Finally, when the system operates stably and reaches the expected performance goal, the process terminates at the "end" node. The control method provided by the present invention not only improves the dynamic response speed and stability of the system, but also significantly enhances the energy efficiency, reduces the environmental impact, and has broad industrial application potential.

[0065] To effectively illustrate the effect of the above-mentioned cooperative control method for the refrigeration system, this embodiment also tests the effect of using the metaheuristic algorithm alone, specifically as Figure 3 、 Figure 4 shown, which shows the response of the Harris hawk algorithm (HHO algorithm) to the condensing pressure and the suction pressure. It can be observed from the figure that when using the HHO algorithm alone, the system may experience some fluctuations before reaching the set value and cannot immediately stabilize near the target value. This indicates that although the HHO algorithm has excellent global search ability, in a dynamic environment, it may need to be combined with other control strategies to achieve a faster response speed and higher stability. Figure 5 and Figure 6 show the response of the HHO algorithm to the condensing pressure and the suction pressure by optimizing the PID parameters. It can be observed from the figure that the system cannot stabilize near the target value. This indicates that using the metaheuristic algorithm to optimize the PID parameters is not applicable to the refrigeration system.

[0066] Therefore, the present invention combines the metaheuristic algorithm with PID control and proposes a new control strategy aimed at improving the real-time stability of the refrigeration system. As Figure 7 and Figure 8As shown, the performance of a PID controller combined with three meta-heuristic algorithms (HHO, WOA, GWO) and a traditional PID control algorithm in regulating the condensing pressure and suction pressure of a refrigeration system was compared. The experimental results show that the HHO+PID control strategy is superior to other combinations in terms of response speed, system stability, and energy efficiency.

[0067] Furthermore, in the experimental test, this embodiment uses a cold storage test bench for testing. The test bench includes a cold storage tank, a refrigeration module, and a data acquisition module. Its working principle is to cool the water in the cold storage tank through a refrigeration system to achieve energy storage. During the experiment, the refrigeration module transfers cold energy to the water in the cold storage tank, causing its temperature to drop, so that the stored cold energy can be released when needed. The data acquisition module is responsible for monitoring and recording key parameters during the whole process, providing accurate data for the analysis and evaluation of experimental results.

[0068] The results obtained from the experimental test on the above test bench are as Figure 9 、 Figure 10 and Figure 11 shown. The HHO+PID algorithm (i.e., the control method provided by the present invention) is significantly superior to other algorithm combinations in terms of response time and the time required for the system to reach a steady state, and has the smallest steady-state error. Although the overshoot of the HHO+PID algorithm is slightly higher than that of other algorithms, considering the priority of fast response and steady-state accuracy in this study, the HHO+PID algorithm still shows its significant advantages in condensing pressure and suction pressure control. The experimental results also show that the HHO+PID algorithm has significant advantages in improving the energy efficiency of the refrigeration system. Specifically, compared with the traditional PID control method, the HHO+PID strategy significantly reduces the response time by 63.3% and the stabilization time by 69.2%, and the energy efficiency is increased by 19.65%. These data not only confirm the advantages of the HHO+PID algorithm in quickly adapting to dynamic environmental changes and improving system stability, but also highlight its potential in energy conservation and environmental protection.

[0069] In summary, these advantages of the HHO+PID control strategy indicate its broad application prospects in the field of industrial refrigeration system control. It can not only improve the operating efficiency of the system, but also contribute to the realization of environmental protection goals, providing strong technical support for the design and optimization of refrigeration systems. Therefore, this embodiment combines the physical prediction model under the HHO+PID control strategy to adjust and optimize HHO, which can further improve the response speed of the system, enhance its dynamic stability and multi-condition adaptability, and at the same time achieve a significant improvement in energy efficiency, having broad practical application value.

[0070] Embodiment 2 Please refer to Figure 12, an embodiment of the present invention further provides a refrigeration system collaborative control system, which at least includes: A parameter acquisition module for real-time acquisition of the operating state parameters of the refrigeration system; A physical prediction module for predicting the temperature and energy efficiency of the refrigeration system based on a constructed and initialized physical prediction model; A meta-heuristic optimization module for globally optimizing the operating state parameters and the predicted temperature and energy efficiency based on a constructed and initialized meta-heuristic algorithm to generate optimized control parameters; A PID control module that uses a PID controller to generate real-time adjustment instructions according to the current operating state parameters; A dynamic collaboration module for fusing the optimized control parameters and the real-time adjustment instructions to generate a dynamic collaboration control signal, and using the dynamic collaboration control signal as the output control signal of the refrigeration system.

[0071] This system can not only improve the operating efficiency of the system, but also promote the realization of environmental protection goals, providing strong technical support for the design and optimization of refrigeration systems, and having broad application prospects in the field of industrial refrigeration system control. The specific ways in which each module in the above-mentioned second embodiment performs operations have been described in detail in the first embodiment of the method, and will not be elaborated here.

[0072] Embodiment Three An embodiment of the present invention further provides a storage medium, which is a non-volatile storage medium or a non-transient storage medium, on which a computer program is stored, and when the computer program is run by a processor, it executes the refrigeration system collaborative control method described in any one of the above embodiments.

[0073] Specifically, the storage medium is a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD), etc.; the storage medium may also include a combination of the above types of memories.

[0074] Embodiment Four An embodiment of the present invention further provides a terminal, which includes a memory and a processor. A computer program capable of running on the processor is stored on the memory, and when the processor operates the computer program, it executes the refrigeration system collaborative control method described in any one of the above embodiments.

[0075] In specific implementation, the number of processors can be one or more. The processor can be a central processing unit (CPU). The processor can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., or a combination of the above types of chips. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0076] The memory and the processor can be communicatively connected through a bus or other means. The memory stores program instructions executable by at least one processor, and the program instructions are executed by at least one processor so that the processor executes the refrigeration system cooperative control method described in any of the above embodiments.

[0077] In summary, the refrigeration system cooperative control method, system, medium, and terminal provided by the present invention combine the global search ability of the meta-heuristic algorithm, the immediate adjustment feedback of the PID controller, and the future state prediction of the physical prediction model, significantly improving the dynamic response speed and stability of the system, optimizing the energy efficiency, and reducing the environmental impact.

[0078] In addition, those skilled in the art should understand that although there are many problems in the prior art, each embodiment or technical solution of the present invention can be improved in only one or several aspects, and it is not necessary to solve all the technical problems listed in the prior art or the background art at the same time. Those skilled in the art should understand that the content not mentioned in a claim should not be used as a limitation to that claim.

[0079] Although terms such as refrigeration system, physical prediction model, meta-heuristic algorithm, optimization control parameter, real-time adjustment instruction, dynamic cooperative control signal, etc. are used more frequently in this article, the possibility of using other terms is not excluded. These terms are used only to more conveniently describe and explain the essence of the present invention; interpreting them as any additional limitation is contrary to the spirit of the present invention; the terms "first", "second", etc. (if any) in the specification, claims, and above-mentioned drawings of the embodiments of the present invention are used to distinguish similar objects and do not have to be used to describe a specific order or sequence.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A refrigeration system coordinated control method, characterized in that: The following steps are involved: Obtain the operating status parameters of the refrigeration system in real time; Predicting the temperature and energy efficiency of the refrigeration system based on the constructed and initialized physical prediction model; Based on the constructed and initialized meta-heuristic algorithm, the operating state parameters and the predicted temperature and energy efficiency are globally optimized to generate optimized control parameters; Use PID controller to generate real-time adjustment instructions according to current operating state parameters; The optimized control parameters and the real-time adjustment instructions are integrated to generate a dynamic coordinated control signal, and the dynamic coordinated control signal is used as an output control signal of the refrigeration system.

2. The refrigeration system coordinated control method according to claim 1, characterized in that: The meta-heuristic algorithm adopts one of HHO, WOA and GWO.

3. The refrigeration system coordinated control method according to claim 1, characterized in that: The formula for predicting the temperature of the refrigeration system based on the physical preset model is: In the formula, is the predicted temperature at the next moment, is the current temperature, is the input of the refrigeration system, is the environmental variation parameter.

4. The refrigeration system coordinated control method according to claim 1, characterized in that: The fitness function of the meta-heuristic algorithm combines energy efficiency and temperature as follows: In the formula, , , are weight coefficients, To predict the energy efficiency, Response time, is the predicted temperature, is the target temperature.

5. The refrigeration system coordinated control method according to claim 1, characterized in that: When the meta-heuristic algorithm adopts the HHO algorithm, the HHO algorithm updates the position of the population by switching between the exploration phase and the development phase. The formula for the position update is: In the formula, is the new position of the current population individual, is the current position of the individual in the population, is the location of the local optimal solution, is the position of the global optimal solution, , To control the weight coefficients of the exploration and development stages; The HHO algorithm also controls the balance between the exploration phase and the development phase by dynamically adjusting the escape energy; the formula for dynamically adjusting the escape energy is: In the formula, is the current escape energy, is the initial escape energy, is the current iteration number, is the maximum number of iterations.

6. The refrigeration system coordinated control method according to claim 1, characterized in that: Perform global optimization on the operating state parameters and predicted temperature and energy efficiency to generate optimized control parameters The formula is: In the formula, is the error measure based on the current state of the system, is a constraint function based on the physical prediction model, is the balance coefficient.

7. The refrigeration system coordinated control method according to claim 6, characterized in that: The formula for integrating the optimized control parameters and real-time adjustment instructions to generate dynamic coordinated control signals is: In the formula, is the dynamic cooperative control signal outputted finally. is the output signal of the PID controller, , The temperature predicted by the physical prediction model With target temperature The error value between , , is the weighting coefficient.

8. A refrigeration system coordinated control system, characterized in that: include: A parameter acquisition module is used to obtain the operating status parameters of the refrigeration system in real time; A physical prediction module, used for predicting the temperature and energy efficiency of the refrigeration system based on a constructed and initialized physical prediction model; A meta-heuristic optimization module, for globally optimizing the operating state parameters and the predicted temperature and energy efficiency based on a constructed and initialized meta-heuristic algorithm, so as to generate an optimized control parameter; PID control module, which uses PID controller to generate real-time adjustment instructions according to current operating state parameters; The dynamic coordination module is used to fuse the optimization control parameters and the real-time adjustment instructions to generate a dynamic coordination control signal, and use the dynamic coordination control signal as the output control signal of the refrigeration system.

9. A storage medium, characterized in that: The storage medium is a non-volatile storage medium or a non-transient storage medium, on which a computer program is stored. When the computer program is executed by a processor, the refrigeration system collaborative control method according to any one of claims 1 to 7 is executed.

10. A terminal, characterized in that: It includes a memory and a processor, the memory stores a computer program that can be run on the processor, and the processor executes the refrigeration system collaborative control method according to any one of claims 1 to 7 when running the computer program.

Images