Optimization method for improving operation efficiency of refrigerating system based on digital twin technology

Abstract

The invention discloses an optimization method for improving the operation efficiency of a refrigeration system based on a digital twin technology. Relates to the technical field of air conditioning. According to the method, the cold machine combination is primarily screened, only key parameters are selected as input, interference factors are eliminated, the model prediction precision is remarkably improved, the energy efficiency ratio and the current ratio of the primarily screened cold machine combination are predicted through the model, and a scientific basis is provided for follow-up multi-round optimization. And through two times of iterative optimization, the efficiency potential of the cold machine is fully excavated, and a cold machine combination with higher energy efficiency is found. And through double stability judgment rules, the optimal refrigerator combination is further screened out, it is guaranteed that the refrigerating system is kept stable in the start-stop process, and stability and energy efficiency are both considered. By dynamically calculating the current ratio limit value, the current ratio limit value can be forcibly set under the unique working condition of the station opening stage of the refrigeration system, and the energy-saving effect is remarkably improved. The technical problems that in the prior art, an optimization method of a refrigerating system regulation and control mode is single and extensive, and energy efficiency and stability cannot be considered at the same time are solved.

Description

Technical Field

[0001] This application relates to the technical field of air conditioning, and particularly to an optimization method for improving the operating efficiency of a refrigeration system based on digital twin technology. Background Art

[0002] Common refrigeration systems usually consist of a refrigeration host (hereinafter referred to as "chiller"), a chilled water pump, a cooling water pump, and a cooling tower, etc. As the core equipment of the refrigeration system, the operating efficiency of the chiller directly affects the energy efficiency performance of the entire system. The operating efficiency of the chiller is usually measured by the coefficient of performance (COP), that is, the ratio of the cooling capacity output by the chiller to the power consumption. Since the power consumption of the chiller accounts for 60% - 90% of the total power consumption of the entire refrigeration system, optimizing the operating efficiency of the chiller is the key to improving the overall energy efficiency of the refrigeration system.

[0003] The operating efficiency of the chiller is affected by various working parameters, mainly including the load rate, supply water temperature, and cooling water temperature, etc. Under a given refrigeration demand, the load rate and supply water temperature of the chiller are key adjustable parameters. By reasonably adjusting these parameters, the operating efficiency of the chiller can be effectively improved, thereby enhancing the energy efficiency of the entire refrigeration system. However, the existing technologies have the following defects in optimizing the operating efficiency of the chiller: (1) The optimization method is single and extensive: The existing technologies usually adopt a feedback control strategy based on the current ratio to adjust the operating state of the chiller. Specifically, when the current ratio of the operating chiller is higher than a certain set value (such as 95%), the system will start a new chiller; conversely, when the current ratio is lower than a certain set value (such as 60%), the system will reduce the operation of one chiller. Although this control method can adjust the load rate of the chiller to a certain extent, its control range is relatively extensive, and it can only avoid the chiller operating under the most unfavorable working conditions, rather than achieving refined energy efficiency optimization.

[0004] (2) It is difficult to balance stability and energy efficiency: In the existing technologies, when controlling the number of chillers starting and stopping, the air conditioning equipment of the air conditioning system is usually directly controlled only according to the coefficient of performance predicted by the model. This control strategy is likely to cause stability problems in the refrigeration system during the starting and stopping processes, and it is difficult to maximize the energy efficiency while ensuring stability.

[0005] In view of the technical problems of the single and extensive optimization method of the refrigeration system control method and the inability to balance energy efficiency and stability existing in the above-mentioned existing technologies, no effective solution has been proposed yet. Summary of the Invention

[0006] Embodiments of the present disclosure provide an optimization method for improving the operating efficiency of a refrigeration system based on digital twin technology, which at least solves the technical problems of the single and extensive optimization methods of the refrigeration system control mode in the prior art and the inability to take into account both energy efficiency and stability.

[0007] According to one aspect of the embodiments of the present disclosure, there is provided an optimization method for improving the operating efficiency of a refrigeration system based on digital twin technology, including determining the current cooling load demand, screening m primary cold machine combinations that meet the current cooling load demand from all cold machine combinations in the refrigeration system according to the maximum cooling capacity and minimum cooling capacity of each chiller in the refrigeration system, and initially decomposing the current cooling load demand to determine the initial cooling load of each chiller in each primary cold machine combination; wherein the principle of the initial decomposition is that the load rate of each chiller is the same; for each chiller in each primary cold machine combination, inputting the supply water temperature, cooling water temperature and initial cooling load under the current operating condition into a pre-trained digital twin model, and outputting the energy efficiency ratio and current ratio of the corresponding chiller under the current operating condition; determining the overall energy efficiency ratio of each primary cold machine combination according to the current cooling load demand and the energy efficiency ratio of each chiller in each primary cold machine combination; screening k candidate cold machine combinations from the m primary cold machine combinations according to the overall energy efficiency ratio of each primary cold machine combination; using a preset input parameter adjustment rule, respectively performing two iterative evaluations on each candidate cold machine combination by using the digital twin model to determine the optimal overall energy efficiency ratio of each candidate cold machine combination; wherein the input parameter adjustment rule is used to adjust the cooling load, supply water temperature and cooling water temperature of each chiller in each candidate cold machine combination; screening d optional cold machine combinations from the k candidate cold machine combinations according to the optimal overall energy efficiency ratio of each candidate cold machine combination; judging the stability of each optional cold machine combination based on a preset first stability judgment rule and second stability judgment rule according to the number of started and stopped chillers in each optional cold machine combination to obtain a first stability judgment result and a second stability judgment result; determining b cold machine combinations that meet the stability requirements from the d optional cold machine combinations according to the first stability judgment result and the second stability judgment result, and taking the cold machine combination with the highest overall energy efficiency ratio among the b cold machine combinations as the optimal cold machine combination; and controlling the start and stop of each chiller in the refrigeration system and limiting the current ratio parameter of the started chiller according to the optimal cold machine combination and the corresponding current ratio output by the digital twin model.

[0008] According to another aspect of the embodiments of the present disclosure, there is also provided a storage medium, which includes a stored program, wherein the above-mentioned method is executed by a processor when the program runs.

[0009] According to another aspect of the embodiments of the present disclosure, an optimization device for improving the operating efficiency of a refrigeration system based on digital twin technology is further provided, including: a first screening module, configured to determine the current cooling load demand, and screen m initial cold machine combinations that meet the current cooling load demand from all cold machine combinations in the refrigeration system according to the maximum cooling capacity and minimum cooling capacity of each chiller in the refrigeration system, and perform an initial decomposition on the current cooling load demand to determine the initial cooling load of each chiller in each initial cold machine combination; wherein the principle of the initial decomposition is that the load rate of each chiller is the same; an energy efficiency ratio determination module, configured to input the water supply temperature, cooling water temperature, and initial cooling load under the current operating condition of each chiller in each initial cold machine combination into a pre-trained digital twin model, and output the energy efficiency ratio and current ratio of the corresponding chiller under the current operating condition; determine the overall energy efficiency ratio of each initial cold machine combination according to the current cooling load demand and the energy efficiency ratio of each chiller in each initial cold machine combination; a second screening module, configured to screen k candidate cold machine combinations from the m initial cold machine combinations according to the overall energy efficiency ratio of each initial cold machine combination; use a preset input parameter adjustment rule to perform two iterative evaluations on each candidate cold machine combination by using the digital twin model respectively to determine the optimal overall energy efficiency ratio of each candidate cold machine combination; wherein the input parameter adjustment rule is used to adjust the cooling load, water supply temperature, and cooling water temperature of each chiller in each candidate cold machine group; a third screening module, configured to screen d optional cold machine combinations from the k candidate cold machine combinations according to the optimal overall energy efficiency ratio of each candidate cold machine combination; perform a stability judgment on each optional cold machine combination based on a preset first stability judgment rule and a second stability judgment rule according to the number of started and stopped chillers in each optional cold machine combination to obtain a first stability judgment result and a second stability judgment result; determine b cold machine combinations that meet the stability requirements from the d optional cold machine combinations according to the first stability judgment result and the second stability judgment result, and use the cold machine combination with the highest overall energy efficiency ratio among the b cold machine combinations as the optimal cold machine combination; and an adjustment control module, configured to control the start and stop of each chiller in the refrigeration system and limit the current ratio parameter of the started chiller according to the optimal cold machine combination and the corresponding current ratio output by the digital twin model.

[0010] According to another aspect of the embodiments of the present disclosure, an optimization device for improving the operating efficiency of a refrigeration system based on digital twin technology is further provided, including: a processor; and a memory connected to the processor for providing instructions for the processor to process the following steps: determining the current cooling load demand, screening m primary cold machine combinations that meet the current cooling load demand from all cold machine combinations in the refrigeration system according to the maximum cooling capacity and minimum cooling capacity of each chiller in the refrigeration system, and initially decomposing the current cooling load demand to determine the initial cooling load of each chiller in each primary cold machine combination; wherein the principle of the initial decomposition is that the load rate of each chiller is the same; for each chiller in each primary cold machine combination, inputting the supply water temperature, cooling water temperature, and initial cooling load under the current operating condition into a pre-trained digital twin model, and outputting the energy efficiency ratio and current ratio of the corresponding chiller under the current operating condition; determining the overall energy efficiency ratio of each primary cold machine combination according to the current cooling load demand and the energy efficiency ratio of each chiller in each primary cold machine combination; screening k candidate cold machine combinations from the m primary cold machine combinations according to the overall energy efficiency ratio of each primary cold machine combination; using a preset input parameter adjustment rule to perform two iterative evaluations on each candidate cold machine combination by using the digital twin model to determine the optimal overall energy efficiency ratio of each candidate cold machine combination; wherein the input parameter adjustment rule is used to adjust the cooling load, supply water temperature, and cooling water temperature of each chiller in each candidate cold machine combination; screening d optional cold machine combinations from the k candidate cold machine combinations according to the optimal overall energy efficiency ratio of each candidate cold machine combination; judging the stability of each optional cold machine combination based on a preset first stability judgment rule and second stability judgment rule according to the start-stop number of chillers in each optional cold machine combination to obtain a first stability judgment result and a second stability judgment result; determining b cold machine combinations that meet the stability requirements from the d optional cold machine combinations according to the first stability judgment result and the second stability judgment result, and taking the cold machine combination with the highest overall energy efficiency ratio among the b cold machine combinations as the optimal cold machine combination; and controlling the start-stop of each chiller in the refrigeration system and limiting the current ratio parameter of the started chiller according to the optimal cold machine combination and the corresponding current ratio output by the digital twin model.

[0011] The technical solution of this application first determines the current cooling load demand, combines the cooling capacity range of each chiller in the refrigeration system, screens out the primary cold machine combinations (m kinds) that meet the demand, and initially decomposes the total load to each chiller according to the equal load rate distribution principle to realize the coarse-grained optimization of the cold machine combination, laying a foundation for subsequent refined adjustment.

[0012] Next, input the supply water temperature, cooling water temperature, and initial cooling load into the pre-trained digital twin model, output the coefficient of performance (COP) and current ratio of each chiller, and calculate the overall energy efficiency ratio of each initially selected chiller combination. By only selecting key parameters (supply water temperature, cooling water temperature, load) as inputs and excluding interference factors, the model prediction accuracy is significantly improved. At the same time, the energy efficiency of the chiller is predicted based on the real-time working conditions, replacing the static threshold judgment that only relies on the current ratio in the prior art, providing a scientific basis for subsequent multi-round optimization.

[0013] Furthermore, screen out k high-energy-efficiency candidate combinations from the initially selected chiller combinations, and perform two iterative evaluations using the input parameter adjustment rules (adjust the load, supply water temperature, and cooling water temperature) to obtain the optimal overall energy efficiency ratio. Through the coordinated adjustment of multiple parameters and two-round iterative optimization, the limitation of only regulating the load rate in the prior art is broken through, the efficiency potential of the chiller is fully explored, and through two-round iterative optimization, chiller combinations with higher energy efficiency are found, solving the problem that the single regulation in the prior art cannot cover the optimal solution.

[0014] Subsequently, screen out d optional combinations from the candidate combinations, and in combination with the change in the number of started and stopped units, judge the stability through the first stability judgment rule (current working condition stability) and the second stability judgment rule (future load prediction stability), select b chiller combinations that meet the stability requirements, and use the chiller combination with the highest overall energy efficiency ratio among the b chiller combinations as the optimal chiller combination. Through the dual stability judgment rules, the refrigeration system remains stable during the start-stop process, taking into account both stability and energy efficiency, and avoiding the oscillation problem caused by frequent switching.

[0015] Finally, according to the optimal chiller combination and the corresponding current ratio output by the digital twin model, control the start and stop of each chiller in the refrigeration system and limit the current ratio parameter of the started chiller. By dynamically calculating the current ratio limit value, in the unique working conditions during the start-up stage of the refrigeration system, the current ratio limit value can be forcibly set, significantly improving the energy-saving effect. Thus, the technical problems of the single and extensive optimization method of the refrigeration system control method in the prior art and the inability to take into account both energy efficiency and stability are solved. Description of the Drawings

[0016] The drawings described herein are used to provide a further understanding of the present disclosure, form a part of this application, and the schematic embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation to the present disclosure. In the drawings: Figure 1 is a schematic flowchart of an optimization method for improving the operating efficiency of a refrigeration system based on digital twin technology according to Embodiment 1 of the present disclosure; Figure 2 is a schematic diagram of an optimization device for improving the operating efficiency of a refrigeration system based on digital twin technology according to Embodiment 2 of the present disclosure; and Figure 3 It is a schematic diagram of an optimization device for improving the operating efficiency of a refrigeration system based on digital twin technology according to Embodiment 3 of the present disclosure. Detailed implementation manners

[0017] In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present disclosure without creative efforts shall fall within the protection scope of the present disclosure.

[0018] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present disclosure described herein can be implemented in an order different from those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these process, method, product or device.

[0019] Embodiment 1: According to this embodiment, a method embodiment of an optimization method for improving the operating efficiency of a refrigeration system based on digital twin technology is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0020] As Figure 1 shown, according to this embodiment, an optimization method for improving the operating efficiency of a refrigeration system based on digital twin technology is provided, including: S102: Determine the current cooling load demand. According to the maximum cooling capacity and minimum cooling capacity of each chiller in the refrigeration system, screen m primary chiller combinations that meet the current cooling load demand from all chiller combinations in the refrigeration system, and perform an initial decomposition of the current cooling load demand to determine the initial cooling load of each chiller in each primary chiller combination; wherein, the principle of the initial decomposition is that the load rate of each chiller is the same; Specifically, the current cooling load demand Q can be obtained through manual input, sensor collection, or prediction based on historical data. Assume that there are N chillers in the refrigeration system, then the number of all chiller combinations in this refrigeration system is 2 N . According to the maximum cooling capacity and minimum cooling capacity of each chiller, conduct a preliminary screening, and extract m primary chiller combinations that can meet the current cooling load demand Q from 2 N types of chiller combinations; perform an initial load decomposition for each primary chiller combination. The principle of the initial decomposition is that the load rates of each chiller are the same, so as to determine the initial cooling load of each chiller in each primary chiller combination. Specifically, for each primary chiller combination, according to the maximum cooling capacity and minimum cooling capacity of each chiller, calculate the total cooling capacity range of this combination:

[0021] where, Q min,j and Q max,j are respectively the minimum cooling capacity and maximum cooling capacity of the j-th chiller in each chiller combination, and n is the number of chillers in this primary chiller combination.

[0022] Retain the chiller combinations with Q min ≤Q≤Q max , and a total of m primary chiller combinations are obtained.

[0023] After that, adopt the equal load rate distribution principle to initially decompose the total load to each chiller. That is, for the chillers in each primary chiller combination, set the same load rate LR:

[0024] Then determine the initial cooling load Q j of a single chiller through the following calculation formula:

[0025] In this way, coarse-grained optimization of chiller combinations can be achieved, laying a foundation for subsequent refined regulation.

[0026] S104: For each chiller in each primary chiller combination, input the supply water temperature, cooling water temperature, and initial cooling load under the current operating condition into the pre-trained digital twin model, and output the energy efficiency ratio and current ratio of the corresponding chiller under the current operating condition; according to the current cooling load demand and the energy efficiency ratio of each chiller in each primary chiller combination, determine the overall energy efficiency ratio of each primary chiller combination; Optionally, the digital twin model of the refrigeration system is trained through the following steps: setting the optimized operating boundary conditions of the refrigeration system; wherein, the optimized operating boundary conditions are used to define the fixed number of chillers, decision-making period, and locked operating parameters during the modeling of the refrigeration system; determining the key parameters of each chiller under corresponding operating conditions based on the operating characteristic data of each chiller in the refrigeration system under different operating conditions; wherein, the key parameters include chilled water supply temperature, cooling water outlet temperature, load rate, and energy efficiency ratio; and constructing and training the digital twin model of the refrigeration system based on the optimized operating boundary conditions and the key parameters; wherein, the task of the digital twin model is to predict the energy efficiency ratio and current ratio of a chiller under a certain operating condition according to the supply temperature, cooling water temperature, and cooling load of the chiller under a certain operating condition.

[0027] Optionally, the operation of determining the overall energy efficiency ratio of each initial chiller combination according to the current cooling load demand and the energy efficiency ratio of each chiller in each initial chiller combination includes: calculating the power consumption of each chiller in each initial chiller combination according to the current cooling load demand and the energy efficiency ratio of each chiller in each initial chiller combination; and determining the overall energy efficiency ratio of each initial chiller combination according to the current cooling load demand and the power consumption of each chiller in each initial chiller combination.

[0028] Specifically, for a specified refrigeration system, the number of chillers is determined. The decision-making period of this refrigeration system is about 15 minutes to 60 minutes. During this period, the required cooling load and cooling temperature at the end are determined, and the cooling water temperature transported from the cooling tower to the chiller is determined. Therefore, the number of chillers, cooling load, cooling temperature, and cooling water temperature are set as boundary conditions.

[0029] Then, collect the operation characteristic data of each chiller under different working parameters, including chilled water supply temperature, chilled water return temperature, chilled water flow rate, cooling water outlet temperature, cooling water return temperature, cooling load, load rate, electric power, energy efficiency ratio, current ratio, and the rated parameters of the chiller, etc. Substitute them into the thermodynamic formula to calculate the chilled water supply temperature, cooling water outlet temperature, load rate, and energy efficiency ratio as key parameters to participate in the subsequent model training. Conduct data governance on the historical data, including standard conversion of measurement units, cleaning of mutation data, interpolation of missing data, alignment of timestamps of each parameter, etc. Randomly group the processed data, where 70% of the data is used as training data and 30% as test data. For the training data, use the MLP (Multi-Layer Perceptron Regression Model) algorithm for modeling, and use the test data to verify the model. After multiple rounds of parameter tuning, when the model prediction accuracy reaches the preset accuracy of 97% (this value can be adjusted), complete the digital twin modeling to obtain the digital twin model of the refrigeration system. This model can predict the energy efficiency ratio and current ratio according to the input operating condition parameters. During the subsequent continuous operation of the system, the input data of actual operation and the accurately calculated output data will be regularly compared with the model prediction results. When the deviation is higher than the preset value, enter the next round of modeling iteration optimization.

[0030] Next, after completing the coarse-grained optimization of the chiller combination through the above step S102, for each chiller in the i-th initially selected chiller combination, with the supply temperature and cooling water temperature under the current operating condition, and the decomposed cooling load Q j Substitute it into the digital twin model to obtain the energy efficiency ratio COP of the j-th chiller under this operating condition j , current ratio and other parameters. Among them, i = 1~m. Then, according to the formula , calculate the electric power P of the j-th chiller j . Conduct an overall energy efficiency analysis of the energy efficiency ratios of each chiller in the i-th initially selected chiller combination. Through the formula , obtain the overall energy efficiency ratio COP of the i-th initially selected chiller combination i .

[0031] Thus, by only selecting key parameters (supply temperature, cooling water temperature, load) as inputs and excluding interference factors, the model prediction accuracy is significantly improved. At the same time, predicting the chiller energy efficiency based on real-time operating conditions replaces the static threshold judgment that only relies on the current ratio in the existing technology, providing a scientific basis for subsequent multiple rounds of optimization.

[0032] S106: Screen k candidate chiller combinations from m initially selected chiller combinations according to the overall energy efficiency ratio of each initially selected chiller combination; use a preset input parameter adjustment rule and utilize the digital twin model to perform two iterative evaluations on each candidate chiller combination respectively to determine the optimal overall energy efficiency ratio of each candidate chiller combination; wherein, the input parameter adjustment rule is used to adjust the cooling load, supply water temperature and cooling water temperature of each chiller in each candidate chiller combination. Optionally, the operation of using a preset input parameter adjustment rule and utilizing the digital twin model to perform two iterative evaluations on each candidate chiller combination respectively to determine the optimal overall energy efficiency ratio of each candidate chiller combination includes: Under a preset first constraint condition, redistribute the cooling load of each chiller in each candidate chiller combination by adjusting the chilled water flow rate, input the supply water temperature, cooling water temperature and the redistributed cooling load under the current operating condition into the digital twin model, output the energy efficiency ratio and current ratio of the corresponding chiller under the current operating condition, and determine the first overall energy efficiency ratio of each candidate chiller combination according to the current cooling load demand and the energy efficiency ratio of each chiller in each candidate chiller combination; wherein, the first constraint condition is that the total cooling load of all chillers in the candidate chiller combination is equal to the current cooling load demand; Under the first constraint condition and a preset second constraint condition, while redistributing the cooling load of each chiller in each candidate chiller combination by adjusting the supply water temperature and chilled water flow rate of each chiller, change the supply water temperature of each chiller, input the changed supply water temperature, the cooling water temperature under the current operating condition and the adjusted cooling load into the digital twin model, output the energy efficiency ratio and current ratio of the corresponding chiller under the current operating condition, and determine the second overall energy efficiency ratio of each candidate chiller combination according to the current cooling load demand and the energy efficiency ratio of each chiller in each candidate chiller combination; wherein, the second constraint condition is: ; T 总供水温度 is the total supply water temperature of the refrigeration system, T 总管回水温度 is the total return water temperature of the refrigeration system, Q is the current cooling load demand, Flow j is the chilled water flow rate of the j-th chiller in each candidate chiller combination; and based on the first overall energy efficiency ratio and the second overall energy efficiency ratio, determine the optimal overall energy efficiency ratio of each candidate chiller combination.

[0033] Specifically, first, according to the overall energy efficiency ratio of each initially selected chiller combination, k candidate chiller combinations are screened out from m initially selected combinations. The screening rule is, for example, to sort all the initially selected chiller combinations according to the overall energy efficiency ratio and retain the top k initially selected chiller combinations, thereby obtaining k candidate chiller combinations. Then, for each of the screened candidate chiller combinations, two iterative evaluations are performed using a preset input parameter adjustment rule to further determine the optimal overall energy efficiency ratio of these candidate chiller combinations. Among them, the input parameter adjustment rule is mainly used to adjust the cooling load, supply water temperature, and cooling water temperature of each chiller. The following are the detailed steps of the two iterative evaluations: (1) The first iterative evaluation to determine the first overall energy efficiency ratio of each candidate chiller combination: 1) Under the preset first constraint condition (i.e., the total cooling load of all chillers in the candidate chiller combination is equal to the current cooling load demand), the cooling load of each chiller is redistributed by adjusting the chilled water flow rate. Among them, the adjustment strategy is, for example, to preferentially increase the flow rate of high-efficiency chillers and reduce the flow rate of low-efficiency chillers, and ensure that the load of each chiller is within the allowable range, i.e., Q min,j ≤Q j ≤Q max,j ; 2) Input the supply water temperature, cooling water temperature, and redistributed cooling load under the current operating condition into the digital twin model; 3) The model outputs the energy efficiency ratio and current ratio of the corresponding chiller under the current operating condition; 4) According to the current cooling load demand and the energy efficiency ratio of each chiller in each candidate chiller combination, the overall energy efficiency ratio of each candidate chiller combination (corresponding to the first overall energy efficiency ratio) is re-determined according to the corresponding process in step S104 above.

[0034] (2) The second iterative evaluation to determine the second overall energy efficiency ratio of each candidate chiller combination: 1) Under the first constraint condition and the preset second constraint condition, the cooling load is redistributed by adjusting the supply water temperature and chilled water flow rate of each chiller, and at the same time, the supply water temperature is changed. Among them, the second constraint condition is: ; T 总供水温度 is the total supply water temperature of the refrigeration system, T 总管回水温度 is the total return water temperature of the main pipe of the refrigeration system, Q is the current cooling load demand, Flow j is the chilled water flow rate of the j-th chiller in each candidate chiller combination.

[0035] Among them, the adjustment strategy is: according to the target total supply water temperature back-calculate the required total chilled water flow rate : Among them, ρ is the density of water, and c is the specific heat capacity of water. Then, according to the total flow rate obtained by back-calculation, the chilled water flow rates of each chiller are allocated, and the corresponding supply water temperature is calculated through the following formula :

[0036] 2) Input the changed supply water temperature, the cooling water temperature under the current operating condition, and the adjusted cooling load into the digital twin model; 3) The model also outputs the energy efficiency ratio and current ratio of the corresponding chiller under the current operating condition; 4) According to the current cooling load demand and the energy efficiency ratio of each chiller in each candidate chiller combination, re-determine the overall energy efficiency ratio of each candidate chiller combination (corresponding to the second overall energy efficiency ratio) according to the corresponding process in step S104 above.

[0037] (3) Based on the first overall energy efficiency ratio and the second overall energy efficiency ratio, determine the optimal overall energy efficiency ratio of each candidate chiller combination. Among them, for each candidate chiller combination, take the maximum value from the first overall energy efficiency ratio and the second overall energy efficiency ratio as the optimal overall energy efficiency ratio of the candidate chiller combination.

[0038] Thus, through multi-parameter collaborative regulation and two iterative optimizations, break through the limitation of only regulating the load rate in the existing technology, fully tap the potential of chiller efficiency, and through two iterative optimizations, discover a chiller combination with higher energy efficiency, and solve the problem that the single regulation in the existing technology cannot cover the optimal solution.

[0039] S108: According to the optimal overall energy efficiency ratio of each candidate chiller combination, screen out d optional chiller combinations from the k candidate chiller combinations; according to the number of started and stopped chillers in each optional chiller combination, based on the preset first stability judgment rule and the second stability judgment rule, perform stability judgment on each optional chiller combination to obtain the first stability judgment result and the second stability judgment result; according to the first stability judgment result and the second stability judgment result, determine b chiller combinations that meet the stability requirements from the d optional chiller combinations, and take the chiller combination with the highest overall energy efficiency ratio among the b chiller combinations as the optimal chiller combination.

[0040] Optionally, the first stability judgment rule is: compare each optional chiller combination with the currently operating chiller combination, and select the chiller combination whose difference in the number of started and stopped chillers from the currently operating chiller combination is less than the first preset threshold from the d optional chiller combinations.

[0041] Optionally, the second stability judgment rule is as follows: Determine the future cooling load demand of the refrigeration system within a preset future time period. Based on the future cooling load demand and the digital twin model, select multiple target chiller combinations that meet the future cooling load demand from all chiller combinations of the refrigeration system. Compare each of the d optional chiller combinations with the multiple target chiller combinations pairwise, and select the chiller combinations from the d optional chiller combinations where the difference in the number of chiller starts and stops between them and the multiple target chiller combinations is less than a second preset threshold.

[0042] Specifically, the principle for screening d optional chiller combinations from k candidate chiller combinations is as follows: Taking the candidate chiller combination with the highest energy efficiency as the benchmark, all combinations not lower than 98% (this value can be adjusted) of the energy efficiency of this group. Considering that chillers should not be frequently started and stopped and switched, the formulated chiller combinations should pursue high energy efficiency ratios while taking into account the operating stability and reducing the number of chiller starts and stops. Therefore, it is necessary to perform two types of stability judgment and screening on the d optional chiller combinations screened in step S106. The detailed process is as follows: (1) The first type of stability judgment: 1) Taking the currently operating chiller combination as the comparison target, the stability judgment condition is that the change in the number of starts and stops of the candidate chiller combination does not exceed a first preset threshold (for example, 1, this value can be adjusted) to avoid equipment wear and system oscillation caused by frequent starts and stops; 2) Obtain the currently operating chiller combination, and calculate the difference in the number of chillers between each optional chiller combination and the currently operating chiller combination; 3) Determine whether the difference is less than the first preset threshold. If it is less, it passes the first stability judgment; otherwise, it does not.

[0043] (2) The second type of stability judgment: 1) Taking the cooling load demand in a future preset time period (such as the next cycle or the next 1 hour) as the prediction target, use a time series model (ARIMA / LSTM) to predict the future cooling load demand, and then use the same method as steps S102 - S106 above to generate multiple target chiller combinations that meet the future cooling load demand; 2) For each optional chiller combination, calculate the difference in the number of chiller starts and stops between it and the multiple target chiller combinations; 3) Determine whether the difference is less than the second preset threshold. If it is less, it passes the second stability judgment; otherwise, it does not.

[0044] (3) Further screen the two stability judgment results. Taking the principle of the best satisfaction of the two stability judgment conditions and preferentially satisfying the first stability judgment condition, determine b chiller combinations that meet the stability requirements from the d optional chiller combinations while taking into account the operating stability.

[0045] Thus, through the first stability judgment rule, the change in the number of start-stop units can be restricted, equipment impact can be avoided, and the short-term stability of the refrigeration system is ensured. Through the second stability judgment rule, it can be ensured that the combination can still make a smooth transition under future loads, and the long-term adaptability of the refrigeration system is guaranteed. Thus, the optimal combination that takes into account both efficiency and stability is finally selected, providing a reliable input for the control instruction issuance (step S110), enabling the refrigeration system to remain stable during the start-stop process, taking into account both stability and energy efficiency, and avoiding the oscillation problem caused by frequent switching.

[0046] S110: According to the optimal chiller combination and the corresponding current ratio output by the digital twin model, control the start and stop of each chiller in the refrigeration system and limit the current ratio parameters of the started chillers.

[0047] Specifically, usually the refrigeration system needs to be started in advance before going to work to remove the high-temperature load accumulated at night in the building. At this time, the circulating water temperature (25°C - 35°C) is much higher than the water temperature during normal operation (about 12°C). Therefore, the chiller will directly operate under extremely high load rates, and all conventional strategies for adding or subtracting chillers will fail. This working condition generally needs to run for 30 minutes to 120 minutes before it can enter the normal working mode, consuming a large amount of energy. Through the above steps S102 - S108, the optimal chiller combination and the corresponding working current ratio parameters can be evaluated, and the current ratio parameters of these chillers can be limited according to the optimization results, so as to ensure that the refrigeration system can still operate under high energy efficiency conditions in this specific scenario.

[0048] Thus, by dynamically calculating the current ratio limit value, in the unique working condition during the startup stage of the refrigeration system, the current ratio limit value can be forcibly set, significantly improving the energy-saving effect.

[0049] As described in the background technology, the prior art has the following defects in the optimization of chiller operation efficiency: (1) The optimization method is single and extensive: The prior art usually adopts a feedback control strategy based on the current ratio to adjust the operation state of the chiller. Specifically, when the current ratio of the operating chiller is higher than a certain set value (such as 95%), the system will start a new chiller; conversely, when the current ratio is lower than a certain set value (such as 60%), the system will reduce the operation of a chiller. Although this control method can adjust the load rate of the chiller to a certain extent, its control range is relatively extensive, and it can only avoid the chiller operating under the most unfavorable working conditions, rather than achieving refined energy efficiency optimization. (2) It is difficult to balance stability and energy efficiency: In the control of the number of start-stop units of the chiller in the prior art, usually only the energy efficiency ratio obtained by model prediction is directly used to control the air-conditioning equipment of the air-conditioning system. This control strategy is likely to cause stability problems in the refrigeration system during the start-stop process, and it is difficult to maximize energy efficiency while ensuring stability.

[0050] In view of this, the technical solution of the present application first determines the current cooling load demand, combines the cooling capacity ranges of each chiller in the refrigeration system, screens out the initial selected chiller combinations (m types) that meet the demand, and initially decomposes the total load to each chiller according to the equal load rate distribution principle to achieve the coarse-grained optimization of the chiller combination and lay a foundation for subsequent refined adjustment.

[0051] Then, the supply water temperature, the cooling water temperature, and the initial cooling load are input into the pre-trained digital twin model to output the coefficient of performance (COP) and the current ratio of each chiller, and calculate the overall coefficient of performance of each initial selected chiller combination. By only selecting the key parameters (supply water temperature, cooling water temperature, load) as the input and excluding interference factors, the model prediction accuracy is significantly improved. At the same time, the chiller energy efficiency is predicted based on the real-time working conditions, replacing the static threshold judgment that only relies on the current ratio in the prior art, providing a scientific basis for subsequent multi-round optimization.

[0052] Furthermore, k high-energy-efficiency candidate combinations are screened out from the initial selected chiller combinations, and two iterative evaluations are carried out using the input parameter adjustment rules (adjusting the load, supply water temperature, and cooling water temperature) to obtain the optimal overall coefficient of performance. Through the multi-parameter collaborative adjustment and two-round iterative optimization, the limitation of only regulating the load rate in the prior art is broken through, the potential of chiller efficiency is fully explored, and through two-round iterative optimization, chiller combinations with higher energy efficiency are found, solving the problem that the single regulation in the prior art cannot cover the optimal solution.

[0053] Subsequently, d optional combinations are screened out from the candidate combinations. Combining the change in the number of started and stopped units, the stability is judged through the first stability judgment rule (the stability of the current working condition) and the second stability judgment rule (the stability of the future load prediction), and b chiller combinations that meet the stability requirements are selected, and the chiller combination with the highest overall coefficient of performance among the b chiller combinations is used as the optimal chiller combination. Through the dual stability judgment rules, the refrigeration system remains stable during the start-stop process, taking into account both stability and energy efficiency, and avoiding the oscillation problem caused by frequent switching.

[0054] Finally, according to the optimal chiller combination and the corresponding current ratio output by the digital twin model, the start-stop of each chiller in the refrigeration system is controlled, and the current ratio parameter of the started chiller is limited. By dynamically calculating the current ratio limit value, in the unique working condition at the start-up stage of the refrigeration system, the current ratio limit value can be forcibly set, significantly improving the energy-saving effect. Thus, the technical problems in the prior art, such as the single and extensive optimization method of the refrigeration system control method and the inability to take into account both energy efficiency and stability, are solved.

[0055] The following takes the refrigeration system of a large industrial project as an example to give a specific application scenario of this embodiment: The refrigeration system of a large industrial project consists of 10 refrigeration units, specifically 2 fixed-frequency units (rated cooling capacity 6822 kW, rated COP 5.67, hereinafter referred to as Class A units), 3 variable-frequency units (rated cooling capacity 8051 kW, rated COP 5.0, hereinafter referred to as Class B units), 4 variable-frequency units (rated cooling capacity 10021 kW, rated COP 5.13, hereinafter referred to as Class C units), and 1 variable-frequency unit (rated cooling capacity 8051 kW, rated COP 6.58, hereinafter referred to as Class D units). The current operating conditions are: the current cooling demand is 15000 kW, the chilled water supply temperature is 7 degrees Celsius, and the cooling water outlet temperature is 33 degrees Celsius.

[0056] Under the current operating conditions, the optimization process of the refrigeration system is as follows: (1) Primary selection of chiller combinations screening: According to the maximum and minimum cooling capacities of each chiller in the refrigeration system, m primary chiller combinations that meet the current cooling load demand are screened from all chiller combinations in the refrigeration system. The number of operating units for each primary chiller combination is 2, 3, or 4. Subsequently, each chiller in each primary chiller combination is initially decomposed to determine the initial cooling load of each chiller. (2) Initial evaluation of energy efficiency ratio: According to the pre-established digital twin model of the refrigeration system, the operating energy efficiency (i.e., the overall energy efficiency ratio) of each primary chiller combination is obtained. The parameters of some primary chiller combinations are as follows: 1) 2 Class B units, with a single-unit cooling capacity allocation of 7500 kW and a load factor of 93.2%, and an overall energy efficiency of 5.96; 2) 1 Class A unit + 3 Class B units, with a single-unit cooling capacity of 3304 kW for the Class A unit and 3899 kW for each Class B unit, and a load factor of 48.4% for both, and an overall energy efficiency of 5.96; 3) 3 Class C units, with a single-unit cooling capacity allocation of 5000 kW and a load factor of 49.9%, and an overall energy efficiency of 6.29; 4) 2 Class A units + 1 Class D unit, with a single-unit cooling capacity of 4717 kW for each Class A unit and 5566 kW for the Class D unit, and a load factor of 69.1% for both, and an overall energy efficiency of 6.30; 5) 3 Class B units, with a single-unit cooling capacity allocation of 5000 kW and a load factor of 62.1%, and an overall energy efficiency of 6.31; and so on; (3) Iterative evaluation of candidate chiller combinations: Based on the overall energy efficiency ratio of each preliminary selected chiller combination, k candidate chiller combinations are screened out from the m preliminary selected chiller combinations. Then, each candidate chiller combination is subjected to two iterative evaluations. After adjusting the iterative parameters, new operating conditions of each combination can be obtained, and energy efficiency evaluation is carried out according to the pre-established digital twin model to screen out high-energy efficiency combinations, and the optimal overall energy efficiency ratio of each candidate chiller combination is obtained. The parameters of the k candidate chiller combinations are as follows: 1) 1 unit of Class B chiller, single-unit cooling capacity of 4834 kW, load rate of 60.0%; 2 units of Class C chillers, single-unit cooling capacity of 5083 kW, load rate of 50.7%, overall energy efficiency of 6.27; 2) 2 units of Class B chillers, single-unit cooling capacity of 4350 kW, load rate of 54.0%; 1 unit of Class D chiller, single-unit cooling capacity of 6301 kW, load rate of 78.2%, overall energy efficiency of 6.40; 3) 1 unit of Class D chiller, single-unit cooling capacity of 5589 kW, load rate of 69.4%, chilled water supply temperature of 5.5 °C; 2 units of Class C chillers, single-unit cooling capacity of 4706 kW, load rate of 47.0%, chilled water supply temperature of 7.7 °C, overall energy efficiency of 6.48; (4) Screening of optional chiller combinations and stability judgment: Based on the optimal overall energy efficiency ratio of each candidate chiller combination, d optional chiller combinations are screened out from the k candidate chiller combinations. Then, stability judgment is carried out for each optional chiller combination: compare with the currently actually operating chiller combination, compare with the chiller combination to be operated in a future period of time, and make a better choice or gradual switch according to the set stability boundary conditions; (5) Optimization adjustment of the start-up scenario: The refrigeration system needs to be started in advance before work to remove the high-temperature load accumulated at night in the building. At this time, the circulating water temperature (25 °C - 35 °C) is much higher than the water temperature during normal work (about 12 °C). Therefore, the chiller will directly operate under extremely high load rate conditions, and the current ratio is near 100%. Through this method, the optimal chiller combination and the corresponding working current ratio parameters (such as 50% - 60%) can be evaluated, and the current ratio parameters of the chiller are limited to ensure that the refrigeration system can still operate under high-energy efficiency conditions in this specific scenario; and during the process of the circulating water temperature transitioning to the normal water temperature, multiple rounds of optimization and reset of the current ratio parameters are carried out.

[0057] Through the above optimization process, the refrigeration system can achieve efficient and stable operation while meeting the current cooling demand, and bring significant energy-saving benefits (energy saving of 5% - 15%).

[0058] In addition, according to this embodiment, a storage medium is also provided. The storage medium includes a stored program, wherein the method described in any one of the above is executed by a processor when the program runs.

[0059] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0060] Embodiment 2: Figure 2The structural schematic diagram of an optimization device 200 for improving the operation efficiency of a refrigeration system based on digital twin technology according to this embodiment is shown. The optimization device 200 includes: a first screening module 210, configured to determine the current cooling load demand, and screen m primary chiller combinations that meet the current cooling load demand from all chiller combinations in the refrigeration system according to the maximum cooling capacity and minimum cooling capacity of each chiller in the refrigeration system, and perform an initial decomposition on the current cooling load demand to determine the initial cooling load of each chiller in each primary chiller combination; wherein the principle of the initial decomposition is that the load rates of each chiller are the same; an energy efficiency ratio determination module 220, configured to input the water supply temperature, cooling water temperature, and initial cooling load under the current operating condition into a pre-trained digital twin model for each chiller in each primary chiller combination, and output the energy efficiency ratio and current ratio of the corresponding chiller under the current operating condition; determine the overall energy efficiency ratio of each primary chiller combination according to the current cooling load demand and the energy efficiency ratio of each chiller in each primary chiller combination; a second screening module 230, configured to screen k candidate chiller combinations from the m primary chiller combinations according to the overall energy efficiency ratio of each primary chiller combination; use a preset input parameter adjustment rule to perform two iterative evaluations on each candidate chiller combination by using the digital twin model respectively to determine the optimal overall energy efficiency ratio of each candidate chiller combination; wherein the input parameter adjustment rule is used to adjust the cooling load, water supply temperature, and cooling water temperature of each chiller in each candidate chiller combination; a third screening module 240, configured to screen d optional chiller combinations from the k candidate chiller combinations according to the optimal overall energy efficiency ratio of each candidate chiller combination; perform stability judgments on each optional chiller combination based on a preset first stability judgment rule and a second stability judgment rule according to the start-stop number of chillers in each optional chiller combination to obtain a first stability judgment result and a second stability judgment result; determine b chiller combinations that meet the stability requirements from the d optional chiller combinations according to the first stability judgment result and the second stability judgment result, and use the chiller combination with the highest overall energy efficiency ratio among the b chiller combinations as the optimal chiller combination; and an adjustment and control module 250, configured to control the start-stop of each chiller in the refrigeration system and limit the current ratio parameter of the started chillers according to the optimal chiller combination and the corresponding current ratio output by the digital twin model.

[0061] Optionally, the optimization device 200 further includes a model construction and training module for training the digital twin model of the refrigeration system through the following steps: setting the optimized operating boundary conditions of the refrigeration system; wherein the optimized operating boundary conditions are used to define the fixed number of chillers, decision-making period, and locked operating parameters when modeling the refrigeration system; determining the key parameters of each chiller under the corresponding operating conditions based on the operating characteristic data of each chiller in the refrigeration system under different operating conditions; wherein the key parameters include the chilled water supply temperature, the cooling water outlet temperature, the load rate, and the energy efficiency ratio; and constructing and training the digital twin model of the refrigeration system based on the optimized operating boundary conditions and the key parameters; wherein the task of the digital twin model is to predict the energy efficiency ratio and current ratio of a certain chiller under a certain operating condition according to the supply temperature, cooling water temperature, and cooling load of the chiller under a certain operating condition.

[0062] Therefore, according to this embodiment, by only selecting the key parameters (supply temperature, cooling water temperature, load) as inputs and excluding interference factors, the model prediction accuracy is significantly improved. At the same time, predicting the chiller energy efficiency based on real-time operating conditions replaces the static threshold judgment relying only on the current ratio in the prior art, providing a scientific basis for subsequent multi-round optimization. Through multi-parameter collaborative regulation and two rounds of iterative optimization, the limitation of only regulating the load rate in the prior art is broken through, the potential of chiller efficiency is fully explored, and through two rounds of iterative optimization, a chiller combination with higher energy efficiency is found, solving the problem that the single regulation in the prior art cannot cover the optimal solution. Through the dual stability judgment rules, the refrigeration system remains stable during the start-stop process, taking into account both stability and energy efficiency, and avoiding the oscillation problem caused by frequent switching. By dynamically calculating the current ratio limit value, in the unique operating conditions during the start-up stage of the refrigeration system, the current ratio limit value can be forcibly set, significantly improving the energy-saving effect. Thus, the technical problems existing in the prior art, such as the single and extensive optimization method of the refrigeration system regulation method and the inability to balance energy efficiency and stability, are solved.

[0063] Embodiment 3: This embodiment provides an optimization device for improving the operating efficiency of a refrigeration system based on digital twin technology, including: a processor 310; and a memory 320, connected to the processor 310 and used to provide instructions for the processor 310 to process the following steps: determining the current cooling load demand, screening m primary cold machine combinations that meet the current cooling load demand from all cold machine combinations in the refrigeration system according to the maximum cooling capacity and minimum cooling capacity of each chiller in the refrigeration system, and initially decomposing the current cooling load demand to determine the initial cooling load of each chiller in each primary cold machine combination; wherein the principle of the initial decomposition is that the load rate of each chiller is the same; for each chiller in each primary cold machine combination, inputting the water supply temperature, cooling water temperature, and initial cooling load under the current operating condition into a pre-trained digital twin model, and outputting the energy efficiency ratio and current ratio of the corresponding chiller under the current operating condition; determining the overall energy efficiency ratio of each primary cold machine combination according to the current cooling load demand and the energy efficiency ratio of each chiller in each primary cold machine combination; screening k candidate cold machine combinations from the m primary cold machine combinations according to the overall energy efficiency ratio of each primary cold machine combination; using a preset input parameter adjustment rule, respectively performing two iterative evaluations on each candidate cold machine combination by using the digital twin model to determine the optimal overall energy efficiency ratio of each candidate cold machine combination; wherein the input parameter adjustment rule is used to adjust the cooling load, water supply temperature, and cooling water temperature of each chiller in each candidate cold machine combination; screening d optional cold machine combinations from the k candidate cold machine combinations according to the optimal overall energy efficiency ratio of each candidate cold machine combination; judging the stability of each optional cold machine combination based on a preset first stability judgment rule and second stability judgment rule according to the number of started and stopped chillers in each optional cold machine combination to obtain a first stability judgment result and a second stability judgment result; determining b cold machine combinations that meet the stability requirements from the d optional cold machine combinations according to the first stability judgment result and the second stability judgment result, and taking the cold machine combination with the highest overall energy efficiency ratio among the b cold machine combinations as the optimal cold machine combination; and controlling the start and stop of each chiller in the refrigeration system and limiting the current ratio parameter of the started chillers according to the optimal cold machine combination and the corresponding current ratio output by the digital twin model.

[0064] Thus, according to this embodiment, by only selecting key parameters (supply water temperature, cooling water temperature, load) as inputs and excluding interference factors, the model prediction accuracy is significantly improved. At the same time, the chiller energy efficiency is predicted based on the real-time working conditions, replacing the static threshold judgment relying only on the current ratio in the prior art, and providing a scientific basis for subsequent multi-round optimization. Through multi-parameter collaborative regulation and two rounds of iterative optimization, the limitation of only regulating the load rate in the prior art is broken through, the potential of chiller efficiency is fully explored, and through two rounds of iterative optimization, a chiller combination with higher energy efficiency is found, solving the problem that the single regulation in the prior art cannot cover the optimal solution. Through the dual stability judgment rules, the refrigeration system remains stable during the start-stop process, taking into account both stability and energy efficiency, and avoiding the oscillation problem caused by frequent switching. By dynamically calculating the current ratio limit value, in the unique working conditions at the start-up stage of the refrigeration system, the current ratio limit value can be forcibly set, significantly improving the energy-saving effect. Thus, the technical problems existing in the prior art, such as the single and rough optimization method of the refrigeration system regulation method and the inability to take into account both energy efficiency and stability, are solved.

[0065] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0066] In the above embodiments of the present invention, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0067] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and modifications can be made, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. An optimization method for improving the operating efficiency of a refrigeration system based on digital twin technology, characterized in that, Including: Determine the current cooling load demand. According to the maximum cooling capacity and minimum cooling capacity of each chiller in the refrigeration system, screen m primary chiller combinations that meet the current cooling load demand from all chiller combinations in the refrigeration system, and perform an initial decomposition of the current cooling load demand to determine the initial cooling load of each chiller in each primary chiller combination; wherein, the principle of the initial decomposition is that the load rates of all chillers are the same; For each chiller in each primary chiller combination, input the supply water temperature, cooling water temperature, and initial cooling load under the current operating condition into a pre-trained digital twin model, and output the energy efficiency ratio and current ratio of the corresponding chiller under the current operating condition; according to the current cooling load demand and the energy efficiency ratio of each chiller in each primary chiller combination, determine the overall energy efficiency ratio of each primary chiller combination; According to the overall energy efficiency ratio of each primary chiller combination, screen k candidate chiller combinations from the m primary chiller combinations; use a preset input parameter adjustment rule to perform two iterative evaluations on each candidate chiller combination using the digital twin model respectively to determine the optimal overall energy efficiency ratio of each candidate chiller combination; wherein, the input parameter adjustment rule is used to adjust the cooling load, supply water temperature, and cooling water temperature of each chiller in each candidate chiller combination; According to the optimal overall energy efficiency ratio of each candidate chiller combination, screen d optional chiller combinations from the k candidate chiller combinations; according to the start-stop number of chillers in each optional chiller combination, based on a preset first stability judgment rule and second stability judgment rule, perform a stability judgment on each optional chiller combination to obtain a first stability judgment result and a second stability judgment result; according to the first stability judgment result and the second stability judgment result, determine b chiller combinations that meet the stability requirements from the d optional chiller combinations, and take the chiller combination with the highest overall energy efficiency ratio among the b chiller combinations as the optimal chiller combination; and According to the optimal chiller combination and the corresponding current ratio output by the digital twin model, control the start-stop of each chiller in the refrigeration system and limit the current ratio parameter of the started chillers.

2. The method according to claim 1, wherein Train the digital twin model of the refrigeration system through the following steps: Set the optimal operating boundary conditions of the refrigeration system; wherein, the optimal operating boundary conditions are used to limit the fixed number of chillers, decision-making period, and locked operating parameters during the modeling of the refrigeration system; Based on the operating characteristic data of each chiller in the refrigeration system under different operating conditions, determine the key parameters of each chiller under the corresponding conditions; wherein, the key parameters include chilled water supply temperature, cooling water outlet temperature, load rate, and energy efficiency ratio; and Based on the optimal operating boundary conditions and the key parameters, construct and train the digital twin model of the refrigeration system; wherein, the task of the digital twin model is to predict the energy efficiency ratio and current ratio of a certain chiller under a certain operating condition according to the supply water temperature, cooling water temperature, and cooling load of the chiller under that operating condition.

3. The method according to claim 1, wherein The operation of determining the overall energy efficiency ratio of each initial selected chiller combination according to the current cooling load demand and the energy efficiency ratio of each chiller in each initial selected chiller combination includes: Calculating the power consumption of each chiller in each initial selected chiller combination according to the current cooling load demand and the energy efficiency ratio of each chiller in each initial selected chiller combination; and Determining the overall energy efficiency ratio of each initial selected chiller combination according to the current cooling load demand and the power consumption of each chiller in each initial selected chiller combination.

4. The method according to claim 1, characterized in that, The operation of using the preset input parameter adjustment rule to perform two iterative evaluations on each candidate chiller combination by using the digital twin model to determine the optimal overall energy efficiency ratio of each candidate chiller combination includes: Under the preset first constraint condition, reallocating the cooling load of each chiller in each candidate chiller combination by adjusting the chilled water flow rate, inputting the supply water temperature, cooling water temperature and the reallocated cooling load under the current operating condition into the digital twin model, outputting the energy efficiency ratio and current ratio of the corresponding chiller under the current operating condition, and determining the first overall energy efficiency ratio of each candidate chiller combination according to the current cooling load demand and the energy efficiency ratio of each chiller in each candidate chiller combination; wherein, the first constraint condition is that the total cooling load of all chillers in the candidate chiller combination is equal to the current cooling load demand; Under the first constraint condition and the preset second constraint condition, while redistributing the cooling load of each chiller in each candidate chiller combination by adjusting the water supply temperature and chilled water flow rate of each chiller, and changing the water supply temperature of each chiller, the changed water supply temperature, the cooling water temperature under the current operating condition, and the adjusted cooling load are input into the digital twin model to output the energy efficiency ratio and current ratio of the corresponding chiller under the current operating condition, and the second overall energy efficiency ratio of each candidate chiller combination is determined according to the current cooling load demand and the energy efficiency ratio of each chiller in each candidate chiller combination; wherein, the second constraint condition is: ; T 总供水温度 is the total water supply temperature of the refrigeration system, T 总管回水温度 is the total return water temperature of the refrigeration system, Q is the current cooling load demand, Flow j is the chilled water flow rate of the j-th chiller in each candidate chiller combination; and Determining the optimal overall energy efficiency ratio of each candidate chiller combination based on the first overall energy efficiency ratio and the second overall energy efficiency ratio.

5. The method according to claim 1, wherein The first stability judgment rule is: comparing each optional chiller combination with the currently operating chiller combination, and selecting a chiller combination from the d optional chiller combinations whose difference in the number of started and stopped chillers from that of the currently operating chiller combination is less than the first preset threshold.

6. The method according to claim 1, wherein The second stability judgment rule is: determining the future cooling load demand within a preset time period in the future for the refrigeration system, selecting multiple target chiller combinations that meet the future cooling load demand from all chiller combinations of the refrigeration system based on the future cooling load demand and the digital twin model, comparing each of the d optional chiller combinations with the multiple target chiller combinations pairwise, and selecting a chiller combination from the d optional chiller combinations whose difference in the number of started and stopped chillers from that of the multiple target chiller combinations is less than the second preset threshold.

7. A storage medium, characterized in that, The storage medium includes a stored program, wherein the method according to any one of claims 1 to 6 is executed by a processor when the program runs.

8. An optimization device for improving the operating efficiency of a refrigeration system based on digital twin technology, comprising: A first screening module, configured to determine the current cooling load demand, screen m initial selected chiller combinations that meet the current cooling load demand from all chiller combinations of the refrigeration system according to the maximum cooling capacity and minimum cooling capacity of each chiller in the refrigeration system, and perform an initial decomposition of the current cooling load demand to determine the initial cooling load of each chiller in each initial selected chiller combination; wherein, the principle of the initial decomposition is that the load rate of each chiller is the same; The energy efficiency ratio determination module is used to input the water supply temperature, cooling water temperature, and initial cooling load under the current operating conditions into the pre-trained digital twin model for each chiller in each initially selected chiller combination, and output the energy efficiency ratio and current ratio of the corresponding chiller under the current operating conditions; and determine the overall energy efficiency ratio of each initially selected chiller combination according to the current cooling load demand and the energy efficiency ratio of each chiller in each initially selected chiller combination. The second screening module is used to screen out k candidate chiller combinations from the m initially selected chiller combinations according to the overall energy efficiency ratio of each initially selected chiller combination; and use the preset input parameter adjustment rule to perform two iterative evaluations on each candidate chiller combination by using the digital twin model to determine the optimal overall energy efficiency ratio of each candidate chiller combination; wherein, the input parameter adjustment rule is used to adjust the cooling load, water supply temperature, and cooling water temperature of each chiller in each candidate chiller combination. The third screening module is used to screen out d optional chiller combinations from the k candidate chiller combinations according to the optimal overall energy efficiency ratio of each candidate chiller combination; perform stability judgment on each optional chiller combination based on the preset first stability judgment rule and second stability judgment rule according to the start-stop number of chillers in each optional chiller combination to obtain the first stability judgment result and the second stability judgment result; determine b chiller combinations that meet the stability requirements from the d optional chiller combinations according to the first stability judgment result and the second stability judgment result, and use the chiller combination with the highest overall energy efficiency ratio among the b chiller combinations as the optimal chiller combination; and The adjustment and control module is used to control the start-stop of each chiller in the refrigeration system and limit the current ratio parameter of the started chillers according to the optimal chiller combination and the corresponding current ratio output by the digital twin model.

9. The device according to claim 8, wherein It further includes a model construction and training module, which is used to train the digital twin model of the refrigeration system through the following steps: Set the optimal operating boundary conditions of the refrigeration system; wherein, the optimal operating boundary conditions are used to limit the fixed number of chillers, decision-making period, and locked operating parameters during the modeling of the refrigeration system. Based on the operating characteristic data of each chiller in the refrigeration system under different operating conditions, determine the key parameters of each chiller under the corresponding conditions; wherein, the key parameters include the chilled water supply temperature, cooling water outlet temperature, load rate, and energy efficiency ratio. Based on the optimal operating boundary conditions and the key parameters, construct and train the digital twin model of the refrigeration system; wherein, the task of the digital twin model is to predict the energy efficiency ratio and current ratio of a certain chiller under a certain operating condition according to the water supply temperature, cooling water temperature, and cooling load of the chiller under a certain operating condition.

10. An optimization device for improving the operating efficiency of a refrigeration system based on digital twin technology, characterized in that, It includes: A processor; And A memory, connected to the processor, and used to provide instructions for the processor to perform the following processing steps: Determine the current cooling load demand. According to the maximum cooling capacity and minimum cooling capacity of each chiller in the refrigeration system, screen out m primary chiller combinations that meet the current cooling load demand from all chiller combinations in the refrigeration system, and initially decompose the current cooling load demand to determine the initial cooling load of each chiller in each primary chiller combination; wherein, the principle of the initial decomposition is that the load rate of each chiller is the same. For each chiller in each primary chiller combination, input the supply water temperature, cooling water temperature, and initial cooling load under the current operating condition into the pre-trained digital twin model, and output the energy efficiency ratio and current ratio of the corresponding chiller under the current operating condition; determine the overall energy efficiency ratio of each primary chiller combination according to the current cooling load demand and the energy efficiency ratio of each chiller in each primary chiller combination. According to the overall energy efficiency ratio of each primary chiller combination, screen out k candidate chiller combinations from the m primary chiller combinations; use the preset input parameter adjustment rule to perform two iterative evaluations on each candidate chiller combination using the digital twin model respectively, and determine the optimal overall energy efficiency ratio of each candidate chiller combination; wherein, the input parameter adjustment rule is used to adjust the cooling load, supply water temperature, and cooling water temperature of each chiller in each candidate chiller combination. According to the optimal overall energy efficiency ratio of each candidate chiller combination, screen out d optional chiller combinations from the k candidate chiller combinations; based on the preset first stability judgment rule and second stability judgment rule, judge the stability of each optional chiller combination according to the number of starting and stopping chillers in each optional chiller combination, and obtain the first stability judgment result and the second stability judgment result; according to the first stability judgment result and the second stability judgment result, determine b chiller combinations that meet the stability requirements from the d optional chiller combinations, and take the chiller combination with the highest overall energy efficiency ratio among the b chiller combinations as the optimal chiller combination; and According to the optimal chiller combination and the corresponding current ratio output by the digital twin model, control the starting and stopping of each chiller in the refrigeration system and limit the current ratio parameter of the started chiller.

Images