Cooling tower and refrigerator collaborative optimization method and control system based on whale algorithm

Abstract

The present invention proposes a collaborative optimization method and control system for cooling towers and refrigerators based on a whale algorithm, the method comprising: collecting the operating data of cooling towers and refrigerators to form an initial state set; initializing the optimization parameter space, and designing the objective function of the cooling tower based on a thermophysical constraint model; designing the energy efficiency optimization objective function of the refrigerator based on the thermophysical constraint model, and screening out the refrigerant flow and compressor power combination of refrigerators that meet the conditions; real-time monitoring data, and designing the collaborative dynamic optimization objective function of the cooling tower and refrigerator based on the real-time data, wherein the goal of the collaborative dynamic optimization objective function is to maximize the comprehensive energy efficiency ratio of the system. The present invention constructs a two-level collaborative optimization framework based on thermophysical constraints to solve the problems of target conflict, physical constraint adaptability, and insufficient dynamic adjustment capabilities in the collaborative optimization problem of cooling towers and refrigerators.

Description

Technical Field

[0001] The present invention belongs to the field of collaborative optimization of cooling towers and refrigerators, and in particular to a collaborative optimization method and control system of cooling towers and refrigerators based on a whale algorithm. Background Art

[0002] Industrial refrigeration systems are widely used in data centers, chemical plants, large commercial buildings and other fields. The coordinated operation performance of their core equipment - cooling towers and refrigerators - directly affects the energy consumption and efficiency of the system. The cooling tower discharges heat into the environment through evaporation, while the refrigerator is responsible for compressing and expanding the refrigerant to complete the heat transfer. There is a close thermodynamic coupling relationship between the two: the cooling tower outlet water temperature is an important input parameter of the refrigerator refrigeration cycle, and the heat load change of the refrigerator in turn affects the working requirements of the cooling tower. However, due to the potential conflict between the operating goals of the two, coupled with the dynamic operating conditions of the industrial refrigeration system, how to achieve efficient coordinated optimization of cooling towers and refrigerators has always been an important research topic in industry and academia.

[0003] The current technology can be divided into two main categories: control strategies based on empirical rules and joint control methods based on optimization algorithms. Control strategies based on empirical rules are often simple and reliable, but their adjustment range is limited, such as adjusting the cooling tower fan speed or the chiller refrigerant flow rate through fixed rules. However, due to the lack of in-depth modeling of the mutual coupling relationship between the cooling tower and the chiller, these strategies are usually unable to adapt to complex or changing operating conditions, which can easily lead to problems such as local optimization, energy waste, or reduced refrigeration efficiency. In contrast, the joint control method based on the optimization algorithm can significantly improve the overall performance of the system by establishing a global optimization model while considering the adjustment of the operating parameters of the cooling tower and the chiller. These methods usually use artificial intelligence or numerical optimization algorithms, such as genetic algorithms (GA), particle swarm optimization (PSO), or whale optimization algorithm (WOA). However, these methods still face the following key problems in practical applications:

[0004] Conflicts of objectives are difficult to resolve effectively: Cooling towers mainly seek to achieve precise temperature control by adjusting the fan and cooling water flow, while chillers focus on improving the energy efficiency ratio (COP). There is often a clear conflict between the optimization objectives of the two. For example, the pursuit of a lower outlet water temperature for cooling towers may lead to a significant increase in fan energy consumption, while chillers may have specific requirements for cooling tower water temperature in pursuit of high efficiency. This conflict between objectives increases the difficulty of optimization and makes it difficult for existing optimization methods to take into account the performance requirements of both.

[0005] Thermal physical constraints are often overlooked: Physical limitations in cooling towers and chiller refrigeration cycles are important conditions for ensuring stable system operation. For example, the outlet water temperature of a cooling tower cannot be lower than the minimum temperature requirement of the chiller evaporator. Existing optimization algorithms usually simplify the problem into a mathematical model and fail to explicitly incorporate these thermal physical constraints into the optimization process, resulting in optimization results that may be physically infeasible or lack engineering practice value.

[0006] Lack of adaptability to dynamic environments: The operating environment of industrial refrigeration systems is complex and changeable, and parameters such as external temperature and humidity, and cooling load demand often fluctuate dynamically. However, existing methods usually perform offline optimization based on static scenarios, ignoring the impact of dynamic environmental changes on system performance. When environmental conditions change, these static optimization results may quickly become invalid and it is difficult to continue to perform effectively in actual operation.

[0007] The optimization efficiency is limited and it is difficult to handle high-dimensional problems: The coordinated optimization of cooling towers and refrigerators involves multiple strongly coupled variables and a huge search space. Traditional optimization algorithms (such as GA and PSO) have slow convergence speed and are prone to falling into local optimality when solving high-dimensional complex problems. In practical applications, the lack of optimization efficiency may lead to untimely system response and affect the overall operation effect.

[0008] The existing technology has not yet provided a systematic and reliable solution to the above problems, especially in the multi-objective optimization, physical constraint adaptability and dynamic optimization performance between the formation of a unified optimization framework. Therefore, there is an urgent need for a collaborative optimization method that can effectively coordinate the operation objectives of the cooling tower and the refrigerator, fully consider the physical constraints and have dynamic adaptability, so as to improve the comprehensive performance of the industrial refrigeration system. Summary of the invention

[0009] The purpose of the present invention is to propose a cooling tower and refrigerator collaborative optimization method and control system based on the whale algorithm, through a two-level collaborative optimization framework based on thermal physical constraints, to solve the problems of target conflict, physical constraint adaptability and insufficient dynamic adjustment ability in the collaborative optimization problem of cooling tower and refrigerator.

[0010] In order to achieve the above object, a first aspect of the present invention provides a cooling tower and refrigerator collaborative optimization method based on a whale algorithm, the method comprising the following steps:

[0011] The operating data of the cooling tower and the refrigerator are collected to form an initial state set, a thermal physical constraint model of the cooling tower and the refrigerator is constructed according to the initial state set, and an initial operation state prediction model is constructed based on the initial state set; wherein, the initial state set includes the cooling tower inlet water temperature, the cooling tower outlet water temperature, the cooling water flow rate, the refrigerant flow rate, the refrigerator compressor power, the real-time cooling load demand and the ambient temperature; the thermal physical constraint model Including cooling tower outlet water temperature constraints and refrigeration capacity constraints of refrigeration machinery;

[0012] Wherein, the cooling tower outlet water temperature constraint is:

[0013] ;

[0014] in, is the cooling tower outlet water temperature, is the refrigerator evaporator temperature, is the minimum temperature difference allowed by the design;

[0015] The cooling capacity constraint of the refrigeration mechanism is:

[0016] ;

[0017] in, is the specific heat capacity of water; The cooling capacity provided by the cooling tower, is the cooling water flow rate, is the cooling tower inlet water temperature, is the real-time cooling load demand;

[0018] Initialize the optimization parameter space, design the objective function of the cooling tower based on the thermal physical constraint model, screen out the first candidate set that meets the conditions, then evaluate the objective function of the candidate set, select the first parameter combination with the best fitness, and if the difference between the predicted outlet water temperature and the target outlet water temperature does not reach the optimization accuracy, it is necessary to dynamically adjust the difference range and re-screen the candidate set that meets the conditions; wherein the optimization parameters include the cooling tower fan speed, cooling water flow rate and outlet water temperature;

[0019] When the cooling tower calculates the parameter combination with the best fitness, it then designs the energy efficiency optimization objective function of the refrigerator based on the thermophysical constraint model in combination with energy efficiency, cost and stability, selects the refrigerant flow and compressor power combination of the refrigerator that meets the conditions, generates the second candidate parameter set, calculates the fitness value of the selected second candidate parameter set in combination with the objective function, and dynamically predicts the future operating status of the refrigerator;

[0020] Real-time monitoring data is used to design the collaborative dynamic optimization objective function of the cooling tower and the refrigerator based on the real-time data. The goal of the collaborative dynamic optimization objective function is to maximize the overall energy efficiency ratio of the system, and then use the real-time feedback optimization enhancement algorithm to coordinately adjust the cooling tower and refrigerator parameters. At the same time, in the dynamic optimization process, real-time feedback of system performance indicators ensures that the optimization objectives are iteratively optimized. If the performance indicator change of the system is less than the set value for multiple consecutive cycles, it means that the optimization has entered a stable state, and the calculation frequency is reduced to save resources.

[0021] Furthermore, the initialization running state prediction model is constructed based on the initial state set, which is expressed as:

[0022] ;

[0023] in, is the predicted cooling tower outlet water temperature, is the current cooling tower outlet water temperature, is the rate of change of ambient temperature, and , is the cooling load demand change rate, and , and is the empirical coefficient.

[0024] Furthermore, the objective function of designing a cooling tower based on a thermophysical constraint model screens out a first candidate set that meets the conditions, and the objective function is expressed as:

[0025] ;

[0026] in, Cooling tower outlet water temperature With target temperature The absolute deviation of , the main driver of optimization; , Fan energy consumption, including is the fan power, is the fan running time; , The regularization term for operational stability limits the fluctuation range of the outlet water temperature. is the time step of the optimization cycle, t is the current time, is the cooling tower outlet water temperature at time t-1; are the weights of temperature deviation, fan energy consumption and stability constraints respectively;

[0027] Select the first candidate set that meets the conditions, including the cooling tower fan speed and cooling water flow, expressed as:

[0028] ;

[0029] in, is the first candidate set, is the cooling tower fan speed, is the cooling water flow rate, It is a thermophysical constraint model;

[0030] Among them, if the cooling tower outlet water temperature exceeds the limit value or the cooling capacity provided by the cooling tower is less than the real-time cooling load demand, the current parameter combination will be eliminated.

[0031] Furthermore, the initial screening of the thermophysical constraint model is done by global search, where the step size is set to RPM, kg / s.

[0032] Furthermore, the energy efficiency optimization objective function of the refrigerator is expressed as:

[0033] ;

[0034] in, is the comprehensive energy efficiency ratio COP; , Indicates the cooling capacity provided by the cooling tower. Optimized cooling water temperature for cooling towers; , Indicates the total power consumption of the refrigeration system, is the compressor power, is the refrigerant power; , Compressor energy consumption, is the compressor running time, and the optimization goal is to minimize, They represent the weights of energy efficiency, energy consumption and stability constraints respectively, and their specific values ​​are set according to the actual working conditions; is the refrigerator regularization term, which is used to constrain the fluctuation of compressor power:

[0035] ;

[0036] Among them, the regularization term reduces equipment wear and improves operational stability by limiting the power variation range;

[0037] Using Thermophysical Constraint Models , filter the refrigerant flow that meets the conditions and compressor power Combine to generate the second candidate parameter set , expressed as:

[0038] ;

[0039] The fitness value of the selected second candidate parameter set is calculated in combination with the objective function, and the future operating state of the refrigerator is dynamically predicted, which is expressed as:

[0040] ;

[0041] in, is the load demand change rate; is the fitting coefficient.

[0042] Furthermore, the second candidate parameter set The constraints are:

[0043] ;

[0044] ;

[0045] in, is the evaporator temperature, Optimized cooling water temperature for cooling towers, is the minimum allowable temperature difference;

[0046] The grid search method is used for parameter screening, and the step size is set to kg / s, kW.

[0047] Furthermore, the collaborative dynamic optimization objective function , expressed as:

[0048] ;

[0049] in, is the system comprehensive energy efficiency ratio, and the optimization goal is to maximize it; The cooling capacity provided to the cooling tower; is the total power consumption of the system; It is the cost item of dynamic power adjustment, which constrains the adjustment range of compressor power and avoids frequent fluctuations; , The coupling term of temperature control deviation and load fluctuation is used to quantify the joint impact of cooling tower temperature control accuracy and load demand fluctuation on the system;

[0050] The real-time feedback optimization enhancement algorithm specifically includes:

[0051] Re-update cooling tower fan speed and cooling water flow , by predicting the outlet water temperature , ensuring that it is close to the target value , expressed as:

[0052] ;

[0053] in, is the rate of change of ambient temperature; is the cooling load change rate; is the fitting coefficient, obtained by regression of historical data;

[0054] After the cooling tower adjustment is completed, the refrigerant flow of the chiller is dynamically adjusted according to the updated cooling water temperature and flow and compressor power , expressed as:

[0055] ;

[0056] in, It is a dynamic adjustment coefficient used to limit the speed of change of compressor power; It is the cost item for power adjustment to avoid instability caused by rapid power changes.

[0057] Furthermore, the iterative optimization rule is:

[0058] If the cooperative dynamic optimization objective function drops significantly, that is, below the threshold , then expand the parameter search range and call the thermal physical constraint model again for global screening;

[0059] If the coupling term of temperature control deviation and load fluctuation is closest to 0, that is, the temperature control and load fluctuation of the cooling tower are the most stable, then the weight of the coupling term of temperature control deviation and load fluctuation is reduced to optimize the comprehensive energy efficiency ratio and operation cost of the system.

[0060] In a second aspect of the present invention, a cooling tower and refrigeration machine collaborative control system based on a whale algorithm is provided, the system comprising:

[0061] The cooling tower and refrigerator operation data acquisition module is used to collect the operation data of the cooling tower and the refrigerator to form an initial state set, build a thermal physical constraint model in the operation of the cooling tower and the refrigerator according to the initial state set, and build an initial operation state prediction model based on the initial state set; wherein, the initial state set includes the cooling tower inlet water temperature, the cooling tower outlet water temperature, the cooling water flow rate, the refrigerant flow rate, the refrigerator compressor power, the real-time cooling load demand and the ambient temperature; the thermal physical constraint model Including cooling tower outlet water temperature constraints and refrigeration capacity constraints of refrigeration machinery;

[0062] Wherein, the cooling tower outlet water temperature constraint is:

[0063] ;

[0064] in, is the cooling tower outlet water temperature, is the refrigerator evaporator temperature, is the minimum temperature difference allowed by the design;

[0065] The cooling capacity constraint of the refrigeration mechanism is:

[0066] ;

[0067] in, is the specific heat capacity of water; The cooling capacity provided by the cooling tower, is the cooling water flow rate, is the cooling tower inlet water temperature, is the real-time cooling load demand;

[0068] The cooling tower optimization module is used to initialize the optimization parameter space, design the objective function of the cooling tower based on the thermal physical constraint model, screen out the first candidate set that meets the conditions, then evaluate the objective function of the candidate set, and select the first parameter combination with the best fitness. If the difference between the predicted outlet water temperature and the target outlet water temperature does not reach the optimization accuracy, it is necessary to dynamically adjust the difference range and re-screen the candidate set that meets the conditions; wherein the optimization parameters include the cooling tower fan speed, cooling water flow rate and outlet water temperature;

[0069] The refrigerator optimization module is used to calculate the parameter combination with the best fitness when the cooling tower calculates it, and then designs the energy efficiency optimization objective function of the refrigerator based on the thermophysical constraint model in combination with energy efficiency, cost and stability, screens out the refrigerant flow and compressor power combination of the refrigerator that meets the conditions, generates the second candidate parameter set, calculates the fitness value of the screened second candidate parameter set in combination with the objective function, and dynamically predicts the future operation status of the refrigerator;

[0070] The cooling tower and refrigerator operation collaborative optimization module is used to monitor data in real time and design the collaborative dynamic optimization objective function of the cooling tower and the refrigerator based on the real-time data. The goal of the collaborative dynamic optimization objective function is to maximize the system's comprehensive energy efficiency ratio, and then use the real-time feedback optimization enhancement algorithm to adjust the cooling tower and refrigerator parameters in a coordinated manner. At the same time, during the dynamic optimization process, real-time feedback of system performance indicators ensures that the optimization objectives are iteratively optimized. If the performance indicator change of the system is less than the set value for multiple consecutive cycles, it means that the optimization has entered a stable state, and the calculation frequency is reduced to save resources.

[0071] The third aspect of the present invention discloses another cooling tower and refrigerator collaborative control system based on the whale algorithm, the system comprising:

[0072] A memory storing executable program code;

[0073] a processor coupled to the memory;

[0074] The processor calls the executable program code stored in the memory to execute part or all of the steps in the cooling tower and refrigerator collaborative optimization method based on the whale algorithm disclosed in the first aspect of the present invention.

[0075] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute part or all of the steps in the cooling tower and refrigeration machine collaborative optimization method based on the whale algorithm disclosed in the first aspect of the present invention.

[0076] The beneficial technical effects of the present invention are at least as follows:

[0077] The present invention explicitly introduces the thermophysical constraints in the cooling tower and the refrigeration cycle of the refrigerator into the optimization model, such as the outlet water temperature of the cooling tower cannot be lower than the minimum operating temperature difference of the refrigerator evaporator. By optimizing the fitness function in combination with physical constraints, it is ensured that the optimization result is not only optimal in the mathematical sense, but also has engineering feasibility and physical rationality. The model realizes the organic combination of temperature control objectives and energy efficiency objectives, and solves the problem of unreliable results caused by ignoring physical constraints in the prior art.

[0078] The present invention adopts a two-stage optimization strategy, giving priority to solving the cooling tower temperature control problem, and then optimizing the overall energy efficiency of the system on the basis of meeting the temperature control requirements. In the first stage, the fan speed and cooling water flow are optimized with the cooling tower outlet water temperature as the target; in the second stage, based on the optimization results of the first stage, the refrigerant flow and power consumption of the refrigerator are further optimized to maximize the comprehensive energy efficiency. The two-stage optimization significantly improves the optimization efficiency by narrowing the search space in stages, and effectively solves the problem of target conflict.

[0079] This paper proposes an improved whale-ant colony hybrid algorithm (WOA-ACO), which combines the global search capability of the whale algorithm with the path optimization capability of the ant colony algorithm. By introducing a dynamic step size adjustment mechanism and a path constraint update method, the hybrid algorithm can converge to the global optimal solution more quickly while avoiding falling into the local optimum. Compared with traditional algorithms, the optimization efficiency and performance are significantly improved.

[0080] The present invention combines a real-time monitoring module to dynamically adjust the optimization target weights and constraints by sensing changes in external temperature and humidity and cooling load demand, thereby achieving adaptive adjustment of online optimization and control strategies. This dynamic optimization mechanism significantly improves the system's operating performance under complex dynamic conditions, solving the problem of insufficient adaptability to dynamic environments in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0082] Figure 1 A flow chart of a cooling tower and refrigerator collaborative optimization method based on a whale algorithm disclosed in an embodiment of the present invention;

[0083] Figure 2 A framework diagram of a cooling tower and refrigerator collaborative control system based on a whale algorithm disclosed in an embodiment of the present invention;

[0084] Figure 3A schematic diagram of the structure of another cooling tower and refrigerator collaborative control system based on the whale algorithm disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0085] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0086] Embodiment 1

[0087] like Figure 1 As shown, the cooling tower and refrigerator collaborative optimization method based on the whale algorithm provided by the embodiment of the present invention includes:

[0088] 101. Collect the operating data of the cooling tower and the refrigerator to form an initial state set, construct a thermal physical constraint model of the cooling tower and the refrigerator in operation according to the initial state set, and construct an initial operation state prediction model based on the initial state set; wherein the initial state set includes the cooling tower inlet water temperature, the cooling tower outlet water temperature, the cooling water flow rate, the refrigerant flow rate, the refrigerator compressor power, the real-time cooling load demand and the ambient temperature; the thermal physical constraint model Including cooling tower outlet water temperature constraints and refrigeration machine cooling capacity constraints.

[0089] Specifically, use sensors to collect the following parameters in real time and define the initial state set: , and ensure that the physical meaning of these parameters is consistent with the subsequent steps:

[0090] : Cooling tower inlet water temperature (unit: ℃).

[0091] : Cooling tower outlet water temperature (unit: ℃).

[0092] : Cooling water flow rate (unit: kg / s).

[0093] : Refrigerant flow rate (unit: kg / s).

[0094] : Refrigeration machine compressor power (unit: kW).

[0095] : Real-time cooling load demand (unit: kW).

[0096] : Ambient temperature (unit: °C).

[0097] The initial state set is defined as:

[0098] ;

[0099] All data are acquired through standard sampling methods, with a sampling period of Set according to system dynamics (such as once every 5 seconds or 10 seconds).

[0100] Furthermore, a thermal physical constraint model is constructed, and the operating characteristics of the cooling tower and the refrigerator are combined to clarify the physical constraints that need to be met in the system optimization process to ensure the practical feasibility of the optimization results:

[0101] Cooling tower outlet water temperature constraints:

[0102] ;

[0103] in, is the chiller evaporator temperature (determined by design parameters or measured by real-time feedback); is the minimum temperature difference allowed by the design;

[0104] Refrigeration capacity constraints of refrigeration machine:

[0105] ;

[0106] in, is the specific heat capacity of water (constant, unit: kJ / (kg·K)); The cooling capacity provided by the cooling tower (in kW).

[0107] if If the above conditions are violated, a constraint violation signal is generated for subsequent optimization steps to handle.

[0108] In one example, in order to serve the subsequent optimization, the initial state of the collection , build an operation status prediction model The model predicts the status change trend of cooling towers and chillers based on real-time data:

[0109] enter: , combined with the cooling load demand change rate and ambient temperature change rate .

[0110] Output: Future time Status .

[0111] The core calculation is as follows:

[0112] ;

[0113] in, and is the empirical coefficient (determined by regression based on historical data).

[0114] The output of this step It will be directly used for optimization and dynamic adjustment of subsequent steps.

[0115] Optionally, perform a sanity check on the acquired data and the generated thermo-physical constraint model:

[0116] If certain key parameters (such as or ) is missing, the missing data is filled in or estimated based on physical laws.

[0117] For the prediction model The initial output is checked against the actual collected value to ensure that the prediction accuracy meets the subsequent optimization requirements (such as error < 2%).

[0118] Final output: Thermophysical constraint model ,include and The initial state of the system ; State prediction model , predict the future state changes of cooling towers and chillers.

[0119] 102. Initialize the optimization parameter space, design the objective function of the cooling tower based on the thermal physical constraint model, screen out the first candidate set that meets the conditions, then evaluate the objective function of the candidate set, and select the first parameter combination with the best fitness. If the difference between the predicted outlet water temperature and the target outlet water temperature does not reach the optimization accuracy, it is necessary to dynamically adjust the difference range and re-screen the candidate set that meets the conditions; wherein the optimization parameters include the cooling tower fan speed, cooling water flow rate and outlet water temperature.

[0120] Specifically, initialize the optimization parameter space: cooling tower fan speed (Unit: RPM) and cooling water flow (Unit: kg / s). The initial values ​​and ranges of these two parameters are set through historical operation records, for example:

[0121] ;

[0122] .

[0123] In an example, define the objective function:

[0124] To optimize the cooling tower outlet water temperature to make it close to the target value , taking into account energy consumption and operation stability, the objective function is designed:

[0125] ;

[0126] in, : The absolute deviation of the cooling tower outlet water temperature from the target temperature, the main driving force for optimization.

[0127] : Fan energy consumption, including is the fan power, The fan running time.

[0128] : Operation stability regularization term, limiting the fluctuation range of outlet water temperature, is the time step of the optimization cycle.

[0129] : They are the weights of temperature deviation, fan energy consumption and stability constraints, which can be set through experience or system priority.

[0130] In one example, using a thermophysical constraint model , the cooling tower operating parameter combination Screening to generate candidate sets :

[0131] ;

[0132] like Exceed the limit value or Less than , then this parameter combination is eliminated.

[0133] The initial screening is done via a global search with a step size set to: RPM, kg / s.

[0134] In one example, the filtered Evaluate the objective function and select the parameter combination with the best fitness. Combined with the state prediction model Dynamically adjust optimization strategies:

[0135] ;

[0136] By predicting the outlet water temperature , evaluate the temperature control performance of the parameter combination in the future in advance. The prediction model input is (Rate of change of ambient temperature) and (load demand change rate), and output predicted values ​​for optimization iterations.

[0137] Optional, if If the optimization accuracy is not met (e.g. within 2%), dynamically adjust the parameter range and re-screen .

[0138] Combined with the objective function evaluation, the final optimization result is output: fan speed ; Cooling water flow ; Optimized water outlet temperature .

[0139] The above optimization results provide accurate cooling tower water outlet conditions for the optimization of chiller operating parameters, ensuring that the input of the next step is efficient and reliable.

[0140] 103. When the cooling tower calculates the parameter combination with the best fitness, it then designs the energy efficiency optimization objective function of the refrigerator based on the thermal physical constraint model in combination with energy efficiency, cost and stability, screens out the refrigerant flow rate (unit: kg / s) and compressor power (unit: kW) combinations of refrigerators that meet the conditions, generates the second candidate parameter set, calculates the fitness value of the screened second candidate parameter set in combination with the objective function, and dynamically predicts the future operating status of the refrigerator.

[0141] Specifically, variable initialization:

[0142] Refrigerant flow ;

[0143] Compressor power ;

[0144] The optimization goal is to improve the comprehensive energy efficiency ratio (COP) of the refrigerator, which is achieved by dynamically balancing energy consumption and operating stability.

[0145] In one example, the energy efficiency optimization objective function is defined, and an innovative objective function is designed based on the characteristics of industrial refrigeration, taking energy efficiency, cost and stability into consideration:

[0146] ;

[0147] in, : Comprehensive energy efficiency ratio COP (optimization goal is maximization).

[0148] , represents the cooling capacity provided by the cooling tower;

[0149] , represents the total power consumption of the refrigeration system.

[0150] : Compressor energy consumption, is the compressor running time, and the optimization goal is to minimize it.

[0151] : An innovative regularization term used to constrain the fluctuation of compressor power:

[0152] ;

[0153] The regularization term reduces equipment wear and improves operational stability by limiting the power variation range. : Respectively represent the weights of energy efficiency, energy consumption and stability constraints, and the specific values ​​are set according to the actual working conditions (such as w1=0.5, w2=0.3, λ=0.2).

[0154] Furthermore, using the thermophysical constraint model , filter the refrigerant flow that meets the conditions and compressor power Combination, generate a set of candidate parameters :

[0155] ;

[0156] Constraints:

[0157] Evaporator temperature constraint: ,in is the minimum allowable temperature difference.

[0158] Cooling capacity requirement constraints: , to meet the actual load requirements.

[0159] The grid search method is used for parameter screening, and the step size is set to kg / s, kW.

[0160] In one example, the selected candidate set , combined with the objective function Calculate the fitness value and dynamically predict the future running status:

[0161] ;

[0162] is the load demand change rate; is the fitting coefficient, obtained based on historical data regression (such as k3=0.8).

[0163] In one example, the weights in the objective function are adjusted dynamically:

[0164] like Close to target value , improve energy consumption The weight of to control the operating cost;

[0165] If the compressor power fluctuates significantly, increase the regularization term weights and strengthen stability constraints.

[0166] In one example, a distributed multi-objective optimization algorithm is used to optimize the objective function Perform iterative solution and output the optimal parameter: refrigerant flow rate ;Compressor power ; Optimized comprehensive energy efficiency ratio COP These optimization results are directly used for dynamic control to ensure that the system has optimal energy efficiency, stable operation and meets the needs of dynamic working conditions.

[0167] 104. Monitor data in real time and design a collaborative dynamic optimization objective function of the cooling tower and the refrigerator based on the real-time data. The goal of the collaborative dynamic optimization objective function is to maximize the overall energy efficiency ratio of the system. Then, a real-time feedback optimization enhancement algorithm is used to adjust the parameters of the cooling tower and the refrigerator in a coordinated manner. At the same time, during the dynamic optimization process, real-time feedback of system performance indicators is used to ensure iterative optimization of the optimization objectives. If the performance indicator change of the system is less than the set value for multiple consecutive cycles, it means that the optimization has entered a stable state, and the calculation frequency is reduced to save resources.

[0168] Specific, dynamic environment input (real-time monitoring data):

[0169] Ambient temperature , cooling load demand (Unit: kW);

[0170] Cooling tower temperature control deviation , used to quantify the control accuracy of cooling tower outlet water temperature;

[0171] Load change rate , indicating the dynamic change of cooling load demand.

[0172] The above inputs provide the environment basis for dynamic optimization and are (e.g. 10 seconds) to ensure real-time performance.

[0173] In one example, in a complex dynamic environment, the goal of dynamic optimization is to ensure that the cooling tower and the chiller have optimal synergistic energy efficiency and stable operation while adapting to fluctuations in cooling load and outside temperature. The objective function is defined as follows:

[0174] ;

[0175] in:

[0176] : System comprehensive energy efficiency ratio (COP), the optimization goal is to maximize;

[0177] The cooling capacity provided to the cooling tower;

[0178] is the total system power consumption.

[0179] : Dynamic power adjustment cost item, constraining the adjustment range of compressor power to avoid frequent fluctuations;

[0180] :Innovative temperature control deviation and load fluctuation coupling term quantifies the joint impact of cooling tower temperature control accuracy and load demand fluctuation on the system.

[0181] In one example, when the cooling load changes drastically ( big), Ability to amplify cooling tower temperature control deviation Ensure that the optimization process prioritizes temperature control issues;

[0182] When the environment changes steadily, reduce The weight of the coupling term is reduced to reduce the influence of the coupling term and optimize the COP and operating cost.

[0183] In one example, the real-time feedback enhanced optimization algorithm (RT-FEO) is used to adjust the parameters of the cooling tower and chiller in a coordinated manner:

[0184] Cooling tower adjustment:

[0185] Update cooling tower fan speed and cooling water flow , by predicting the outlet water temperature , ensuring that it is close to the target value :

[0186] ;

[0187] in:

[0188] is the rate of change of ambient temperature;

[0189] is the cooling load change rate;

[0190] is the fitting coefficient obtained by regression of historical data (such as k1=0.05, k2=0.1).

[0191] Refrigerator adjustment:

[0192] After the cooling tower adjustment is completed, the refrigerant flow of the chiller is dynamically adjusted according to the updated cooling water temperature and flow and compressor power :

[0193] ;

[0194] in:

[0195] is a dynamic adjustment coefficient used to limit the speed of change of compressor power (e.g. k3=0.2);

[0196] It is the cost item for power adjustment to avoid instability caused by rapid power changes.

[0197] Optional, during dynamic optimization, real-time feedback of system performance indicators to ensure optimization goals Continuous Improvement:

[0198] In one example, the iterative optimization rule:

[0199] like Significant decrease (e.g. below threshold ), expand the parameter search range, and recall the thermal physical constraint model Perform global screening;

[0200] like Close to 0 (cooling tower temperature control and load fluctuations are stable), gradually decrease weights and instead optimize COP and operating costs.

[0201] In one example, if the system performance indicator changes less than a set value (such as 1%) for multiple consecutive cycles, it enters a steady-state mode and reduces the calculation frequency to save resources.

[0202] In one example, the final output is the dynamically optimized parameter combination: cooling tower fan speed and cooling water flow ;Refrigeration machine refrigerant flow and compressor power ; System comprehensive energy efficiency ratio COP , for reference by the control system. The dynamic optimization results are transmitted to the execution module in real time, and closed-loop control is used to ensure that the cooling tower and chiller operate efficiently and stably under complex dynamic conditions.

[0203] Embodiment 2

[0204] like Figure 2 As shown, the embodiment of the present invention also provides a cooling tower and refrigerator collaborative control system based on the whale algorithm, the system comprising:

[0205] The cooling tower and refrigerator operation data acquisition module 201 is used to collect the operation data of the cooling tower and the refrigerator to form an initial state set, build a thermal physical constraint model of the cooling tower and the refrigerator in operation according to the initial state set, and build an initial operation state prediction model based on the initial state set; wherein, the initial state set includes the cooling tower inlet water temperature, the cooling tower outlet water temperature, the cooling water flow rate, the refrigerant flow rate, the refrigerator compressor power, the real-time cooling load demand and the ambient temperature; the thermal physical constraint model Including cooling tower outlet water temperature constraints and refrigeration capacity constraints of refrigeration machinery;

[0206] Wherein, the cooling tower outlet water temperature constraint is:

[0207] ;

[0208] in, is the cooling tower outlet water temperature, is the refrigerator evaporator temperature, is the minimum temperature difference allowed by the design;

[0209] The cooling capacity constraint of the refrigeration mechanism is:

[0210] ;

[0211] in, is the specific heat capacity of water; The cooling capacity provided by the cooling tower, is the cooling water flow rate, is the cooling tower inlet water temperature, is the real-time cooling load demand;

[0212] The cooling tower optimization module 202 is used to initialize the optimization parameter space, design the objective function of the cooling tower based on the thermal physical constraint model, screen out the first candidate set that meets the conditions, and then evaluate the objective function of the candidate set to select the first parameter combination with the best fitness. If the difference between the predicted outlet water temperature and the target outlet water temperature does not reach the optimization accuracy, it is necessary to dynamically adjust the difference range and re-screen the candidate set that meets the conditions; wherein the optimization parameters include the cooling tower fan speed, cooling water flow rate and outlet water temperature;

[0213] The refrigerator optimization module 203 is used to calculate the parameter combination with the best fitness when the cooling tower calculates it, and then design the energy efficiency optimization objective function of the refrigerator based on the thermophysical constraint model in combination with energy efficiency, cost and stability, screen out the refrigerant flow and compressor power combination of the refrigerator that meets the conditions, generate a second candidate parameter set, calculate the fitness value of the screened second candidate parameter set in combination with the objective function, and dynamically predict the future operation status of the refrigerator;

[0214] The cooling tower and refrigerator operation collaborative optimization module 204 is used to monitor data in real time and design the collaborative dynamic optimization objective function of the cooling tower and the refrigerator based on the real-time data. The goal of the collaborative dynamic optimization objective function is to maximize the system's comprehensive energy efficiency ratio, and then use the real-time feedback optimization enhancement algorithm to coordinately adjust the cooling tower and refrigerator parameters. At the same time, during the dynamic optimization process, real-time feedback of system performance indicators ensures that the optimization target is iteratively optimized. If the performance indicator change of the system is less than the set value for multiple consecutive cycles, it means that the optimization has entered a stable state, and the calculation frequency is reduced to save resources.

[0215] Embodiment 3

[0216] See also Figure 3 , Figure 3 The invention discloses a cooling tower and refrigerator collaborative control system based on a whale algorithm. Figure 3 The cooling tower and refrigerator coordinated control system based on the whale algorithm is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the cooling tower and refrigerator collaborative control system based on the whale algorithm may include:

[0217] A memory 301 storing executable program codes;

[0218] a processor 302 coupled to the memory 301;

[0219] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the cooling tower and refrigerator collaborative optimization method based on the whale algorithm described in the first embodiment.

[0220] Embodiment 4

[0221] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the cooling tower and refrigeration machine collaborative optimization method based on the whale algorithm described in the first embodiment.

[0222] Embodiment 5

[0223] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the cooling tower and refrigeration machine collaborative optimization method based on the whale algorithm described in Example 1.

[0224] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0225] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0226] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0227] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0228] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0229] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0230] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0231] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0232] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0233] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0234] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0235] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media including storage devices.

[0236] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0237] Finally, it should be noted that the cooling tower and refrigeration machine collaborative optimization method and control system based on the whale algorithm disclosed in the embodiment of the present invention only discloses the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A collaborative optimization method for cooling towers and refrigerators based on the whale algorithm, characterized in that: The method comprises the following steps: The operating data of the cooling tower and the refrigerator are collected to form an initial state set, a thermal physical constraint model of the cooling tower and the refrigerator is constructed according to the initial state set, and an initial operation state prediction model is constructed based on the initial state set; wherein, the initial state set includes the cooling tower inlet water temperature, the cooling tower outlet water temperature, the cooling water flow rate, the refrigerant flow rate, the refrigerator compressor power, the real-time cooling load demand and the ambient temperature; the thermal physical constraint model Including cooling tower outlet water temperature constraints and refrigeration capacity constraints of refrigeration machinery; Wherein, the cooling tower outlet water temperature constraint is: ； in, is the cooling tower outlet water temperature, is the refrigerator evaporator temperature, is the minimum temperature difference allowed by the design; The cooling capacity constraint of the refrigeration mechanism is: ； in, is the specific heat capacity of water; The cooling capacity provided by the cooling tower, is the cooling water flow rate, is the cooling tower inlet water temperature, is the real-time cooling load demand; Initialize the optimization parameter space, design the objective function of the cooling tower based on the thermal physical constraint model, screen out the first candidate set that meets the conditions, then evaluate the objective function of the candidate set, select the first parameter combination with the best fitness, and if the difference between the predicted outlet water temperature and the target outlet water temperature does not reach the optimization accuracy, it is necessary to dynamically adjust the difference range and re-screen the candidate set that meets the conditions; wherein the optimization parameters include the cooling tower fan speed, cooling water flow rate and outlet water temperature; When the cooling tower calculates the parameter combination with the best fitness, it then designs the energy efficiency optimization objective function of the refrigerator based on the thermophysical constraint model in combination with energy efficiency, cost and stability, selects the refrigerant flow and compressor power combination of the refrigerator that meets the conditions, generates the second candidate parameter set, calculates the fitness value of the selected second candidate parameter set in combination with the objective function, and dynamically predicts the future operating status of the refrigerator; Real-time monitoring data, design the collaborative dynamic optimization objective function of the cooling tower and the refrigerator according to the real-time data, the goal of the collaborative dynamic optimization objective function is to maximize the system comprehensive energy efficiency ratio, and then use the real-time feedback optimization enhancement algorithm to adjust the cooling tower and refrigerator parameters in a linked manner. At the same time, during the dynamic optimization process, real-time feedback of system performance indicators ensures that the optimization target is iteratively optimized. If the performance indicator change of the system is less than the set value for multiple consecutive cycles, it means that the optimization has entered a stable state, and the calculation frequency is reduced to save resources; The initialization running state prediction model is constructed based on the initial state set, which is expressed as: ； in, is the predicted cooling tower outlet water temperature, is the current cooling tower outlet water temperature, is the rate of change of ambient temperature, and , is the cooling load demand change rate, and , and is the empirical coefficient; The objective function of designing a cooling tower based on a thermophysical constraint model is to screen out a first candidate set that meets the conditions. The objective function is expressed as: ； in, Cooling tower outlet water temperature With target temperature The absolute deviation of , the main driver of optimization; , Fan energy consumption, including is the fan power, is the fan running time; , The regularization term for operational stability limits the fluctuation range of the outlet water temperature. is the time step of the optimization cycle, t is the current time, is the cooling tower outlet water temperature at time t-1; are the weights of temperature deviation, fan energy consumption and stability constraints respectively; Select the first candidate set that meets the conditions, including the cooling tower fan speed and cooling water flow, expressed as: ； in, is the first candidate set, is the cooling tower fan speed, is the cooling water flow rate, It is a thermophysical constraint model; Among them, if the cooling tower outlet water temperature exceeds the limit value or the cooling capacity provided by the cooling tower is less than the real-time cooling load demand, the current parameter combination will be eliminated; The energy efficiency optimization objective function of the refrigerator is expressed as: ； in, is the comprehensive energy efficiency ratio COP; , Indicates the cooling capacity provided by the cooling tower. Optimized cooling water temperature for cooling towers; , Indicates the total power consumption of the refrigeration system, is the compressor power, is the refrigerant power; , Compressor energy consumption, is the compressor running time, and the optimization goal is to minimize, They represent the weights of energy efficiency, energy consumption and stability constraints respectively, and their specific values ​​are set according to actual working conditions; is the refrigerator regularization term, which is used to constrain the fluctuation of compressor power: ； Among them, the regularization term reduces equipment wear and improves operational stability by limiting the power variation range; Using Thermophysical Constraint Models , filter the refrigerant flow that meets the conditions and compressor power Combine to generate the second candidate parameter set , expressed as: ； The fitness value of the selected second candidate parameter set is calculated in combination with the objective function, and the future operating state of the refrigerator is dynamically predicted, which is expressed as: ； in, is the load demand change rate; is the fitting coefficient; The collaborative dynamic optimization objective function , expressed as: ； in, is the system comprehensive energy efficiency ratio, and the optimization goal is to maximize it; The cooling capacity provided to the cooling tower; is the total power consumption of the system; It is the cost item of dynamic power adjustment, which constrains the adjustment range of compressor power and avoids frequent fluctuations; , The coupling term of temperature control deviation and load fluctuation is used to quantify the joint impact of cooling tower temperature control accuracy and load demand fluctuation on the system; The real-time feedback optimization enhancement algorithm specifically includes: Re-update cooling tower fan speed and cooling water flow , by predicting the outlet water temperature , ensuring that it is close to the target value , expressed as: ； in, is the rate of change of ambient temperature; is the cooling load change rate; is the fitting coefficient, obtained by regression of historical data; After the cooling tower adjustment is completed, the refrigerant flow of the chiller is dynamically adjusted according to the updated cooling water temperature and flow and compressor power , expressed as: ； in, It is a dynamic adjustment coefficient used to limit the speed of change of compressor power; It is the cost item for power adjustment to avoid instability caused by rapid power changes.

2. The cooling tower and refrigerator collaborative optimization method based on the whale algorithm according to claim 1 is characterized in that: The initial screening of the thermophysical constraint model is done by a global search, where the step size is set to RPM, kg / s.

3. The cooling tower and refrigerator collaborative optimization method based on the whale algorithm according to claim 1 is characterized in that: The second candidate parameter set The constraints are: ； ； in, is the evaporator temperature, Optimized cooling water temperature for cooling towers, is the minimum allowable temperature difference; The grid search method is used for parameter screening, and the step size is set to kg / s, kW.

4. The cooling tower and refrigerator collaborative optimization method based on the whale algorithm according to claim 1 is characterized in that: The iterative optimization rule is: If the cooperative dynamic optimization objective function drops significantly, that is, below the threshold , then expand the parameter search range and call the thermal physical constraint model again for global screening; If the coupling term of temperature control deviation and load fluctuation is closest to 0, that is, the temperature control and load fluctuation of the cooling tower are the most stable, then the weight of the coupling term of temperature control deviation and load fluctuation is reduced to optimize the comprehensive energy efficiency ratio and operation cost of the system.

5. A cooling tower and refrigerator collaborative control system based on a whale algorithm that implements the cooling tower and refrigerator collaborative optimization method based on a whale algorithm as described in any one of claims 1 to 4, characterized in that: The system comprises: The cooling tower and refrigerator operation data acquisition module is used to collect the operation data of the cooling tower and the refrigerator to form an initial state set, build a thermal physical constraint model in the operation of the cooling tower and the refrigerator according to the initial state set, and build an initial operation state prediction model based on the initial state set; wherein, the initial state set includes the cooling tower inlet water temperature, the cooling tower outlet water temperature, the cooling water flow rate, the refrigerant flow rate, the refrigerator compressor power, the real-time cooling load demand and the ambient temperature; the thermal physical constraint model Including cooling tower outlet water temperature constraints and refrigeration capacity constraints of refrigeration machinery; Wherein, the cooling tower outlet water temperature constraint is: ； in, is the cooling tower outlet water temperature, is the refrigerator evaporator temperature, is the minimum temperature difference allowed by the design; The cooling capacity constraint of the refrigeration mechanism is: ； in, is the specific heat capacity of water; The cooling capacity provided by the cooling tower, is the cooling water flow rate, is the cooling tower inlet water temperature, is the real-time cooling load demand; The cooling tower optimization module is used to initialize the optimization parameter space, design the objective function of the cooling tower based on the thermal physical constraint model, screen out the first candidate set that meets the conditions, then evaluate the objective function of the candidate set, and select the first parameter combination with the best fitness. If the difference between the predicted outlet water temperature and the target outlet water temperature does not reach the optimization accuracy, it is necessary to dynamically adjust the difference range and re-screen the candidate set that meets the conditions; wherein the optimization parameters include the cooling tower fan speed, cooling water flow rate and outlet water temperature; The refrigerator optimization module is used to calculate the parameter combination with the best fitness when the cooling tower calculates it, and then designs the energy efficiency optimization objective function of the refrigerator based on the thermophysical constraint model in combination with energy efficiency, cost and stability, screens out the refrigerant flow and compressor power combination of the refrigerator that meets the conditions, generates the second candidate parameter set, calculates the fitness value of the screened second candidate parameter set in combination with the objective function, and dynamically predicts the future operation status of the refrigerator; The cooling tower and refrigerator operation collaborative optimization module is used to monitor data in real time and design the collaborative dynamic optimization objective function of the cooling tower and the refrigerator based on the real-time data. The goal of the collaborative dynamic optimization objective function is to maximize the system's comprehensive energy efficiency ratio, and then use the real-time feedback optimization enhancement algorithm to adjust the cooling tower and refrigerator parameters in a coordinated manner. At the same time, during the dynamic optimization process, real-time feedback of system performance indicators ensures that the optimization objectives are iteratively optimized. If the performance indicator change of the system is less than the set value for multiple consecutive cycles, it means that the optimization has entered a stable state, and the calculation frequency is reduced to save resources.

6. The cooling tower and refrigerator collaborative control system based on the whale algorithm is characterized by: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the cooling tower and refrigerator collaborative optimization method based on the whale algorithm as described in any one of claims 1 to 4.

Images