Energy-saving optimization method and system for cascade refrigeration system based on compressor flow regulation

Abstract

A method and system for optimizing energy conservation in a cascade refrigeration system based on compressor flow regulation is disclosed. The optimization method includes the following steps: collecting historical system field operation data, establishing and training a data-driven model; establishing a function for calculating the system's COP based on the data-driven model; calculating the optimal intermediate temperature, taking the highest COP as the optimization objective and the upper and lower limits of the intermediate temperature operating range as constraints, given the refrigeration load required for system operation, the system condensing temperature, the system evaporating temperature, and the heat exchange temperature difference between the condenser and evaporator; predicting the high-temperature capacity adjustment slide valve / frequency setpoint and the low-temperature capacity adjustment slide valve position / frequency setpoint using the data-driven model; and controlling the high-temperature capacity adjustment slide valve / frequency based on the high-temperature capacity adjustment slide valve / frequency setpoint. At this point, the cascade refrigeration system operates under the conditions of the optimal intermediate temperature and the highest COP, thereby achieving high-temperature compressor flow control. The model of the present invention has higher accuracy and lower computational complexity, simplifying operation.

Description

Technical Field

[0001] The present invention belongs to the technical field of cascade refrigeration systems, and in particular relates to an energy-saving optimization method and system for a cascade refrigeration system based on compressor flow regulation. Background Art

[0002] Compared with single-stage compression refrigeration cycles, cascade refrigeration systems can adapt to different temperature ranges and process requirements, improve refrigeration efficiency and reduce compressor power, and are therefore widely used in the field of food freezing and refrigeration. When evaluating the coefficient of performance (COP) of a cascade refrigeration system, the system's operating state point should first be determined, including the system's cooling capacity, ambient temperature, and refrigeration temperature, that is, the fixed low-temperature stage evaporation temperature and high-temperature stage condensation temperature. It should also be assumed that the heat exchange temperature difference in the evaporator condenser connecting the high-temperature stage and the low-temperature stage is fixed. The high-temperature stage evaporation temperature and the low-temperature stage condensation temperature, that is, the intermediate temperature of the condensing evaporator, are variable operating conditions. Therefore, the main influencing parameter of COP fluctuations is the intermediate temperature. The lower the intermediate temperature, the higher the COP of the low-temperature stage, and the lower the COP of the high-temperature stage. Selecting the appropriate intermediate temperature can maximize the system's COP and achieve the goal of energy-saving operation.

[0003] At present, there are mainly two methods for calculating the optimal intermediate temperature: the empirical formula method and the thermodynamic model method. The empirical formula method uses experimental data to establish a correlation between the intermediate temperature and the system's condensing temperature, evaporating temperature, and heat exchange temperature difference, thereby directly calculating the optimal intermediate temperature. The thermodynamic model method establishes a knowledge-driven model for each device based on the system's thermodynamic process, and combines the models of each device into a system model based on the principles of conservation of mass and energy to achieve performance prediction and optimization calculations. Both calculation methods rely on experimental data or simulation data, and cannot take into account actual problems such as equipment leakage, internal scaling, and aging caused by wear during actual operation. The calculation results often have large errors compared to the actual values, the model is highly complex, and cannot be flexibly adjusted.

[0004] Based on the historical operating data of the system, combined with artificial intelligence models, data-driven modeling of the system is a system performance calculation method that has been widely studied at home and abroad. It can effectively improve the accuracy of the model and reduce the computational complexity. For example, the Chinese patent "A method for controlling the intermediate pressure of a cascade refrigeration system" (publication number: CN 112503789 A) uses a method that combines a data-driven model with a knowledge-driven model based on thermodynamic principles to optimize the intermediate pressure of the control system and improve the accuracy of the model. However, the data set for its data model training is partly derived from the calculation results of the knowledge-driven model, and the applicability of the thermodynamic model method cannot be completely avoided. The problem of high computational complexity cannot be solved and there is still a certain gap with the actual operating conditions. When the unit is actually running, after calculating the optimal intermediate temperature of the current operating conditions, how to quickly adjust the system to an energy-saving operating state is a key step from theory to practice. Summary of the Invention

[0005] The purpose of the present invention is to address the problems in the above-mentioned prior art and provide an energy-saving optimization method and system for a cascade refrigeration system based on compressor flow regulation, so as to achieve direct control of the optimal compressor flow, simplify operation and further improve accuracy.

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

[0007] A method for energy-saving optimization of a cascade refrigeration system based on compressor flow regulation comprises the following steps:

[0008] Collect historical data on the field operation of the cascade refrigeration system, and establish and train a data-driven model for the cascade refrigeration system;

[0009] Based on the data-driven model, a function for calculating the COP of the cascade refrigeration system is established;

[0010] Based on the COP calculation function of the cascade refrigeration system, with the highest COP as the optimization target and the upper and lower limits of the intermediate temperature operating range as constraints, the cooling load Q required for system operation and the system condensing temperature T are given. con , system evaporation temperature T evp and the heat exchange temperature difference ΔT of the condenser evaporator, and calculate the optimal intermediate temperature T that meets the operating conditions mid,opti ;

[0011] The optimal intermediate temperature T mid,opti As well as the cooling load Q required for system operation and the system condensing temperature T con , system evaporation temperature T evp The heat exchange temperature difference ΔT of the condenser and evaporator is used as input parameters, and the high temperature machine capacity adjustment slide valve / frequency setting value M is predicted through the established data-driven model. HT_opti And low temperature machine capacity adjustment slide valve position / frequency setting value MLT_opti ;

[0012] Adjust the slide valve / frequency setting value M according to the high temperature machine capacity HT_opti Control the high temperature machine capacity to adjust the slide valve / frequency, at this time the cascade refrigeration system meets the optimal intermediate temperature T mid,opti and COP under the conditions of the highest, to achieve high temperature compressor flow control, to achieve the goal of energy saving optimization; after the high temperature compressor flow is adjusted, according to whether the low temperature machine capacity adjustment slide valve position / frequency is adjusted to the low temperature machine capacity adjustment slide valve position / frequency setting value M LT_opti To determine whether the system has reached a stable operating state.

[0013] As a preferred solution, the historical data includes system condensing temperature, evaporating temperature, cooling capacity, intermediate temperature, condenser-evaporator heat exchange temperature difference, power consumption of low-temperature and high-temperature compressors, and positions of frequency / capacity regulating slide valves of low-temperature and high-temperature compressors;

[0014] The data-driven model includes a data-driven model for predicting the COP of the cascade refrigeration system, the energy consumption of the high-temperature and low-temperature compressors, and the frequency / capacity adjustment slide valve position of the high-temperature and low-temperature compressors;

[0015] The high-temperature and low-temperature compressors are compressors capable of achieving flow regulation.

[0016] As a preferred solution, the data-driven model is trained after the historical data is preprocessed, and the preprocessing includes noise reduction, outlier removal, data repair and data reduction processes.

[0017] As a preferred solution, the function for calculating the COP of the cascade refrigeration system is as follows:

[0018] COP=F(X)

[0019] X=(x1,x2,x3,x4,x5) T =(T con ,T evp ,T mid ,ΔT,Q) T

[0020] Where, T con is the system condensing temperature; T evp is the system evaporation temperature; T mid is the intermediate temperature, i.e. the condensing temperature of the low temperature stage; ΔT is the heat exchange temperature difference of the condenser evaporator, i.e. the difference between the condensing temperature of the low temperature stage and the evaporating temperature of the high temperature stage.

[0021] As a preferred solution, the optimal intermediate temperature T that meets the operating conditions is calculated according to the following mathematical model: mid,opti :

[0022] maxF(X)

[0023] X=(x1,x2,x3,x4,x5) T =(T con ,T evp ,T mid ,ΔT,Q) T .

[0024] T mid,down ≤T mid ≤T mid,up

[0025] As a preferred solution, the cooling load Q required for system operation and the system evaporation temperature T evp The actual intermediate temperature T in the operating condition is unchanged. mid Adjust according to the average temperature T throughout the year mid The upper and lower limits of the operating range set the constraint boundary T mid，down and T mid，up .

[0026] As a preferred solution, the data-driven model is a data model based on an artificial neural network, including an input layer, a hidden layer and an output layer:

[0027] Input layer parameters include: system condensation temperature T con ; System evaporation temperature T evp ; Intermediate temperature T mid , that is, the condensing temperature of the low-temperature stage; the heat exchange temperature difference ΔT of the condenser evaporator, that is, the difference between the condensing temperature of the low-temperature stage and the evaporating temperature of the high-temperature stage; the system refrigeration load Q;

[0028] Output layer parameters include: system COP; high temperature compressor power consumption P HT ; Low temperature compressor power consumption P LT ; High temperature compressor capacity adjustment slide valve position / frequency M HT ; Low temperature compressor capacity adjustment slide valve position / frequency M LT ;

[0029] The hidden layer uses the ReLU function as the activation function.

[0030] As a preferred solution, in the data set for training the data-driven model, the system condensing temperature T con , system evaporation temperature T evp , intermediate temperature T mid The value ranges of the heat exchange temperature difference ΔT of the condenser-evaporator and the system refrigeration load Q at least include the operating range of the current season.

[0031] As a preferred solution, the entire dataset for model training is divided into a training set and a test set using the K-Fold cross-validation method. The mean percentage error (MAPE) and root mean square error (RMSE) are used to evaluate whether the error of the test set meets the accuracy requirements. If the error is large, the model is retrained by adjusting the number of hidden layer units, the number of iterative calculations, or increasing the sample size of the training data. The accuracy requirements are as follows:

[0032] MAPE i ≤0.5%, RMSE i ≤1, i=1,2,3,4,5.

[0033] A cascade refrigeration system energy-saving optimization system based on compressor flow regulation, comprising:

[0034] Historical data collection and data-driven model training module, used to collect historical data of the cascade refrigeration system's on-site operation, and to establish and train the data-driven model of the cascade refrigeration system;

[0035] COP calculation function establishment module, used to establish the COP calculation function of the cascade refrigeration system based on the data-driven model;

[0036] The optimal intermediate temperature calculation module is used for the function of COP calculation based on the cascade refrigeration system, with the highest COP as the optimization target and the upper and lower limits of the intermediate temperature operating range as constraints. Given the cooling load Q required for system operation and the system condensing temperature T con , system evaporation temperature T evp and the heat exchange temperature difference ΔT of the condenser evaporator, and calculate the optimal intermediate temperature T that meets the operating conditions mid,opti ;

[0037] The high and low temperature machine capacity adjustment slide valve / frequency setting value prediction module is used to set the optimal intermediate temperature T mid,opti As well as the cooling load Q required for system operation and the system condensing temperature T con , system evaporation temperature T evp The heat exchange temperature difference ΔT of the condenser and evaporator is used as input parameters, and the high temperature machine capacity adjustment slide valve / frequency setting value M is predicted through the established data-driven model. HT_opti And low temperature machine capacity adjustment slide valve position / frequency setting value M LT_opti ;

[0038] High temperature compressor flow control module, used to adjust the slide valve / frequency setting value M according to the high temperature machine capacity HT_opti Control the high temperature machine capacity to adjust the slide valve / frequency, at this time the cascade refrigeration system meets the optimal intermediate temperature T mid,optiand COP under the conditions of the highest, to achieve high temperature compressor flow control, to achieve the goal of energy saving optimization; after the high temperature compressor flow is adjusted, according to whether the low temperature machine capacity adjustment slide valve position / frequency is adjusted to the low temperature machine capacity adjustment slide valve position / frequency setting value M LT_opti To determine whether the system has reached a stable operating state.

[0039] Compared with the prior art, the present invention has at least the following beneficial effects:

[0040] A data-driven model for a cascade refrigeration system was established, and the data-driven model was trained based on the historical data of the on-site operation of the cascade refrigeration system. Compared with the traditional knowledge-driven model, it can more accurately describe the operating status of the system, and the model has higher accuracy and lower computational complexity. Based on the data-driven model calculated by the system performance based on the optimal intermediate temperature, an accurate high-temperature compressor capacity adjustment slide valve position setting value is obtained, and the high-temperature stage flow is directly adjusted. The operating mode of the energy-saving operation of the cascade refrigeration system is simplified, and the system fluctuation caused by the indirect control of the high-temperature stage flow based on the optimal intermediate temperature is avoided, solving the problem from theoretical calculation to actual control. The model and energy-saving control method of the method of the present invention can be updated in time. As the system operation time passes, the model can be retrained according to the aging of the equipment, and the calculation accuracy of the model is continuously improved to ensure that the cascade refrigeration system is always in an efficient operation in the optimal energy-saving state, minimizing the system energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 Flowchart of a method for energy-saving optimization of a cascade refrigeration system based on compressor flow regulation according to an embodiment of the present invention;

[0042] Figure 2 Schematic diagram of the data-driven model structure of the cascade refrigeration system according to an embodiment of the present invention;

[0043] Figure 3 Schematic diagram of the typical NH3 / CO2 cascade refrigeration system structure. DETAILED DESCRIPTION

[0044] The present invention will be described in further detail below with reference to the accompanying drawings.

[0045] During actual chiller operation, after calculating the optimal intermediate temperature for the current operating conditions, quickly adjusting the system to an energy-efficient state is a critical step in transitioning from theory to practice. Since the evaporating temperature, condensing temperature, and cooling capacity are fixed, intermediate temperature adjustment is typically achieved by varying the refrigerant flow rate. Lowering the intermediate temperature reduces the low-temperature refrigerant flow rate and increases the high-temperature refrigerant flow rate. This can be achieved by adjusting the expansion valve opening, using a compressor with a capacity-adjusting slide valve, or using a variable-frequency compressor. Research has shown that the high-temperature flow rate has a greater impact on the system COP than the low-temperature flow rate, and adjustment of the high-temperature flow rate should be prioritized. In actual system energy-saving optimization, controlling the high-temperature compressor flow rate based on the intermediate temperature often results in "jump" errors. These initial errors are large, making overshoot more likely. Inadequate adjustment can also lead to significant operating fluctuations, compromising stable and safe system operation. Therefore, directly controlling the optimal compressor flow rate can completely avoid these issues.

[0046] In summary, developing a high-precision, low-computational-complexity prediction model for the optimal intermediate temperature of a cascade refrigeration system that accurately describes the system's actual operating conditions is crucial for energy-saving optimization of cascade refrigeration systems. Once the optimal intermediate temperature is accurately determined, directly controlling the refrigerant flow rate based on the predicted value, thereby avoiding the adverse fluctuations in system stability caused by indirect flow control, has become a pressing technical challenge. This present invention addresses this technical challenge.

[0047] See also Figure 1 The energy-saving optimization method for a cascade refrigeration system based on compressor flow regulation according to an embodiment of the present invention includes:

[0048] Step 1: Collect historical data from field equipment sensors, recording the power consumption of the low- and high-temperature compressors and the historical frequency / capacity control slide valve positions for the low- and high-temperature compressors. Based on the pressure and compressor power consumption data, calculate the system's cooling load (Q) and COP. Based on this historical operating data, develop a data-driven model to predict the COP of the cascade refrigeration system, the energy consumption of the high- and low-temperature compressors, and the frequency / capacity control slide valve positions for the high- and low-temperature compressors.

[0049] Step 2: Based on the data-driven model established in step 1, a function for calculating the system COP is formed. The calculation formula is as follows:

[0050] COP=F(X)

[0051] X=(x1,x2,x3,x4,x5) T =(T con ,T evp ,T mid ,ΔT,Q) T

[0052] Where, T conis the system condensing temperature; T evp is the system evaporation temperature; T mid is the intermediate temperature, i.e. the condensing temperature of the low temperature stage, and ΔT is the heat exchange temperature difference of the condenser evaporator, i.e. the difference between the condensing temperature of the low temperature stage and the evaporating temperature of the high temperature stage.

[0053] Step 3: Based on the system COP calculation function formed in step 2, combined with the global optimization algorithm, the highest COP is set as the optimization goal, the upper and lower limits of the intermediate temperature operating range are used as constraints, and the cooling load Q and T required for system operation are given. con 、T evp and ΔT, calculate the optimal intermediate temperature that meets the operating conditions. The mathematical model of optimization calculation is briefly described as:

[0054] maxF(X)

[0055] X=(x1,x2,x3,x4,x5) T =(T con ,T evp ,T mid ,ΔT,Q) T

[0056] T mid,down ≤T mid ≤T mid,up

[0057] Step 4: Calculate the optimal intermediate temperature T in step 3 mid,opti , and the cooling load Q and T required for system operation con 、T evp and ΔT as input parameters, and the data-driven model trained in step 1 is used to predict the high-temperature machine capacity adjustment slide valve / frequency setting value M HT_opti And low temperature machine capacity adjustment slide valve position / frequency setting value M LT_opti According to M HT_opti Control the high temperature machine capacity adjustment slide valve / frequency, at this time the system meets the T mid,opti and COP max After the high-temperature flow rate is adjusted, the position / frequency of the sliding valve is automatically adjusted to the predicted value M according to the low-temperature capacity. LT_opti To determine whether the system has reached a stable operating state.

[0058] In a possible embodiment, in the cascade refrigeration system, the high-temperature and low-temperature compressors are compressors capable of flow regulation, such as fixed-frequency compressors with capacity regulating slide valves or variable-frequency compressors with adjustable speed.

[0059] In step 3, when calculating the system energy saving optimization, the cooling capacity Q and the system evaporation temperature T should be guaranteed first. evpUnchanged. The ambient temperature limits the system condensing temperature T con , cannot be adjusted. The heat exchange temperature difference ΔT cannot be actively adjusted and is assumed to be fixed during optimization. Therefore, the actual adjustable temperature in the operating condition is the intermediate temperature T mid , according to the annual average temperature T mid The upper and lower limits of the operating range set the constraint boundaries during optimization calculation T mid，down and T mid，up .

[0060] Step 1: Before using historical data to train a data-driven model, preprocess the historical data to improve data quality and ensure model training accuracy. Data preprocessing includes noise reduction, outlier removal, data repair, and data reduction.

[0061] In one possible implementation, the data-driven model for predicting the operating conditions and energy efficiency of the cascade refrigeration system in step 1 is a data model based on an artificial neural network. The model should include an input layer, a hidden layer, and an output layer:

[0062] (1) Input layer parameters include the following five: System condensation temperature T con ; System evaporation temperature T evp ; Intermediate temperature T mid , that is, the condensing temperature of the low-temperature stage; the heat exchange temperature difference ΔT of the condenser evaporator, that is, the difference between the condensing temperature of the low-temperature stage and the evaporating temperature of the high-temperature stage; the system refrigeration load Q.

[0063] (2) Output layer parameters include the following five: system COP; high temperature compressor power consumption P HT ; Low temperature compressor power consumption P LT ; High temperature compressor capacity adjustment slide valve position / frequency M HT ; Low temperature compressor capacity adjustment slide valve position / frequency M LT .

[0064] (3) The hidden layer uses the ReLU function as the activation function to avoid gradient explosion and gradient disappearance. The ReLU function is as follows:

[0065] f(x)=max(0,x)

[0066] (4) The neural network can choose to change the gradient descent (BP) algorithm to the Levenberg-Marquardt (LM) algorithm to improve the model calculation accuracy and training speed.

[0067] The system condensation temperature T in the dataset used for model training con , system evaporation temperature T evp , intermediate temperature T midThe value ranges of the heat exchange temperature difference ΔT of the condenser-evaporator and the system refrigeration load Q should at least include the operating range of the current season. The optimal value range is the operating range of the system throughout the year to ensure that the model can accurately reflect the operating performance of the current system.

[0068] In one possible implementation, the entire data set for model training is divided into a training set and a test set using the K-Fold cross-validation method. The mean percentage error (MAPE) and root mean square error (RMSE) are used to evaluate whether the test set error meets the accuracy requirements. When the error is large, the model is retrained by adjusting the number of hidden layer units, the number of iterative calculations, or increasing the sample size of the training data. The accuracy requirements are as follows: MAPE i ≤0.5%, RMSE i ≤1, i=1,2,3,4,5.

[0069] Taking a typical NH3 / CO2 cascade refrigeration system as an example, the energy-saving optimization method of an embodiment of the present invention is described in detail.

[0070] Figure 3 This is a schematic diagram of a typical NH3 / CO2 cascade refrigeration system, with the actual measurement points marked. The high-temperature stage uses NH3 refrigerant, while the low-temperature stage uses CO2 refrigerant. The high-temperature and low-temperature stages are connected by an intermediate condenser-evaporator, which consists of the high-temperature stage evaporator and the low-temperature stage condenser. The high-temperature compressor is a fixed-frequency compressor with a capacity-adjusting slide valve. The NH3 flow rate is adjusted by varying the slide valve position. The low-temperature compressor is a variable-frequency compressor. The CO2 flow rate is adjusted by varying the compressor speed. The high-temperature stage is equipped with an NH3 liquid reservoir and NH3 gas-liquid separator, while the low-temperature stage is equipped with a CO2 liquid reservoir and a CO2 barrel pump. This eliminates the effects of condenser outlet subcooling and evaporator outlet superheat.

[0071] Condensation temperature T con is the NH3 saturated liquid temperature corresponding to the pressure at measuring point 1, and the evaporation temperature T evp is the CO2 saturated gas temperature corresponding to the pressure at measuring point 2, and the intermediate temperature T mid is the CO2 saturated liquid temperature corresponding to the pressure at measuring point 3, and the heat exchange temperature difference ΔT is T mid The difference between the NH3 saturated gas temperature and the pressure at measuring point 4. The low and high temperature compressor motor power is recorded as P CO2 and P NH3 , the high temperature compressor load setting value is recorded as Vi NH3 , the low temperature compressor frequency is recorded as Hz CO2 .

[0072] The total cooling load Q of the system is calculated as follows:

[0073] Q=m*(h2-h5)

[0074] Where h2 is the specific enthalpy of CO2 saturated gas corresponding to the pressure at measuring point 2; h2 is the specific enthalpy of CO2 saturated liquid corresponding to the pressure at measuring point 5; m is the CO2 mass flow rate, and the calculation formula is as follows:

[0075]

[0076] Where η V is the volumetric efficiency of the CO2 compressor; v2 is the specific volume of the CO2 compressor suction port, that is, the CO2 specific volume corresponding to the pressure at measuring point 2; V th The theoretical gas output of the CO2 compressor. The volumetric efficiency curve and theoretical gas output are provided by the compressor manufacturer.

[0077] The system COP is calculated as follows:

[0078]

[0079] According to step 1 of the embodiment of the present invention, collect Figure 3 Pressure sensor data and high- and low-temperature compressor power data were collected from measurement points 1 through 5 throughout the year, with a 5-minute interval. The corresponding saturation temperature and specific enthalpy were calculated using REFPROP. Due to the significant noise and outlier effects of the sensor data, wavelet thresholding, Mahalanobis distance, and linear interpolation were first used for noise reduction, outlier detection, and data repair. The Z-Score method was then used to normalize and reduce the data. A data-driven model for predicting the operating conditions and energy efficiency of the cascade refrigeration system was trained based on preprocessed, high-quality historical data. The value ranges of all parameters are shown in Table 1.

[0080] Table 1 Data model parameter selection range

[0081]

[0082] The structure of the data-driven model is as follows Figure 2 As shown, the input parameter is T con 、T evp 、T mid , ΔT, Q, the output parameters are COP, P CO2 、P NH3 、Vi NH3 , Hz CO2 A single hidden layer neural network based on the LM algorithm is used. The hidden layer contains 10 to 30 units. The training termination condition is that the number of iterations is greater than 600 and the gradient is less than 1*10 -7 , the mean square error is less than 1*10 -6A 10-fold cross-validation approach was used to divide the training set into a training set and a test set. When the MAPE of the test set was < 0.5%, the model accuracy was considered sufficient and the training was completed. Otherwise, the model accuracy was improved by adjusting the number of hidden layer units or increasing the size of the training sample.

[0083] According to step 2, the trained high-precision system performance prediction model is converted into a COP calculation function.

[0084] According to step 3, the system measuring point pressure is collected in real time to obtain T con 、T evp 、T mid , ΔT, Q, and use the fminbnd optimization algorithm to calculate the COP under the current working conditions max , and obtain the current optimal T mid,opti , T mid The optimization constraints are as follows:

[0085] -29≤T mid,opti ≤-4

[0086] According to step 4, the current T con 、T evp 、T mid,opti , ΔT, Q are input into the system performance prediction data drive model to obtain the set value Vi of the high temperature machine capacity adjustment slide valve opti and low temperature machine frequency Hz opti , adjust the system high temperature airborne position directly to Vi opti The frequency of the cryogenic machine is automatically adjusted. By observing whether the frequency of the cryogenic machine changes to Hz opti Determine whether the system has reached a stable energy-saving operation state.

[0087] When the system cooling load remains constant, the COP typically increases and the intermediate temperature decreases, resulting in a corresponding decrease in the low-temperature refrigerant flow rate and an increase in the high-temperature refrigerant flow rate. Therefore, to achieve the optimal intermediate temperature, the high-temperature refrigerant flow rate should be controlled first, specifically by controlling the position of the high-temperature compressor's capacity adjustment slide valve. The low-temperature flow rate is a secondary control parameter that automatically adjusts with the high-temperature flow rate, meaning that the low-temperature compressor frequency is automatically adjusted.

[0088] Another embodiment of the present invention further provides an energy-saving optimization system for a cascade refrigeration system based on compressor flow regulation, comprising:

[0089] Historical data collection and data-driven model training module, used to collect historical data of the cascade refrigeration system's on-site operation, and to establish and train the data-driven model of the cascade refrigeration system;

[0090] COP calculation function establishment module, used to establish the COP calculation function of the cascade refrigeration system based on the data-driven model;

[0091] The optimal intermediate temperature calculation module is used for the function of COP calculation based on the cascade refrigeration system, with the highest COP as the optimization target and the upper and lower limits of the intermediate temperature operating range as constraints. Given the cooling load Q required for system operation and the system condensing temperature T con , system evaporation temperature T evp and the heat exchange temperature difference ΔT of the condenser evaporator, and calculate the optimal intermediate temperature T that meets the operating conditions mid,opti ;

[0092] The high and low temperature machine capacity adjustment slide valve / frequency setting value prediction module is used to set the optimal intermediate temperature T mid,opti As well as the cooling load Q required for system operation and the system condensing temperature T con , system evaporation temperature T evp The heat exchange temperature difference ΔT of the condenser and evaporator is used as input parameters, and the high temperature machine capacity adjustment slide valve / frequency setting value M is predicted through the established data-driven model. HT_opti And low temperature machine capacity adjustment slide valve position / frequency setting value M LT_opti ;

[0093] High temperature compressor flow control module, used to adjust the slide valve / frequency setting value M according to the high temperature machine capacity HT_opti Control the high temperature machine capacity to adjust the slide valve / frequency, at this time the cascade refrigeration system meets the optimal intermediate temperature T mid,opti and COP under the conditions of the highest, to achieve high temperature compressor flow control, to achieve the goal of energy saving optimization; after the high temperature compressor flow is adjusted, according to whether the low temperature machine capacity adjustment slide valve position / frequency is adjusted to the low temperature machine capacity adjustment slide valve position / frequency setting value M LT_opti To determine whether the system has reached a stable operating state.

[0094] An embodiment of the present invention further provides an electronic device, comprising: a memory storing at least one instruction; and a processor executing the instruction stored in the memory to implement the energy-saving optimization method for the cascade refrigeration system based on compressor flow regulation.

[0095] An embodiment of the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the energy-saving optimization method for a cascade refrigeration system based on compressor flow regulation.

[0096] For example, the instructions stored in the memory may be divided into one or more modules / units, which are stored in a computer-readable storage medium and executed by the processor to implement the energy-saving optimization method for a cascade refrigeration system based on compressor flow regulation according to the present invention. The one or more modules / units may be a series of computer-readable instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the server.

[0097] The electronic device may be a computing device such as a smartphone, laptop, PDA, or cloud server. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will appreciate that the electronic device may include more or fewer components, or a combination of certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, and the like.

[0098] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0099] The memory may be an internal storage unit of the server, such as a hard disk or memory of the server. The memory may also be an external storage device of the server, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. equipped on the server.

[0100] Furthermore, the memory may include both an internal storage unit of the server and an external storage device. The memory is used to store the computer-readable instructions and other programs and data required by the server. The memory may also be used to temporarily store data that has been output or is about to be output.

[0101] It should be noted that the information interaction, execution process, etc. between the above-mentioned module units are based on the same concept as the method embodiment. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0102] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0103] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above-mentioned various method embodiments. Among them, the computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunications signal and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk.

[0104] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0105] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. 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 application, and should all be included in the scope of protection of the present application.

Claims

1. A method for energy saving optimization of a cascade refrigeration system based on compressor flow regulation, characterized in that: The following steps are involved: Collect historical field operation data of the cascade refrigeration system, and establish and train a data-driven model for the cascade refrigeration system; Based on the data-driven model, a function for calculating the COP of the cascade refrigeration system is established; Based on the COP calculation function of the cascade refrigeration system, with the highest COP as the optimization target and the upper and lower limits of the intermediate temperature operating range as constraints, the cooling load Q required for system operation and the system condensing temperature T are given. con , system evaporation temperature T evp and the heat exchange temperature difference ΔT of the condenser evaporator, and calculate the optimal intermediate temperature T that meets the operating conditions mid,opti ; The optimal intermediate temperature T mid,opti As well as the cooling load Q required for system operation and the system condensing temperature T con , system evaporation temperature T evp The heat exchange temperature difference ΔT of the condenser and evaporator is used as input parameters, and the high temperature machine capacity adjustment slide valve / frequency setting value M is predicted through the established data-driven model. HT_opti And low temperature machine capacity adjustment slide valve position / frequency setting value M LT_opti ; Adjust the slide valve / frequency setting value M according to the high temperature machine capacity HT_opti Control the high temperature machine capacity to adjust the slide valve / frequency, at this time the cascade refrigeration system meets the optimal intermediate temperature T mid,opti and COP under the conditions of the highest, to achieve high temperature compressor flow control, to achieve the goal of energy saving optimization; after the high temperature compressor flow is adjusted, according to whether the low temperature machine capacity adjustment slide valve position / frequency is adjusted to the low temperature machine capacity adjustment slide valve position / frequency setting value M LT_opti To determine whether the system has reached a stable operating state.

2. The energy-saving optimization method for a cascade refrigeration system based on compressor flow regulation according to claim 1, characterized in that: The historical data includes system condensing temperature, evaporating temperature, cooling capacity, intermediate temperature, condenser-evaporator heat exchange temperature difference, power consumption of low-temperature and high-temperature compressors, and positions of frequency / capacity regulating slide valves of low-temperature and high-temperature compressors; The data-driven model includes a data-driven model for predicting the COP of the cascade refrigeration system, the energy consumption of the high-temperature and low-temperature compressors, and the frequency / capacity adjustment slide valve position of the high-temperature and low-temperature compressors; The high-temperature and low-temperature compressors are compressors capable of achieving flow regulation.

3. The energy-saving optimization method for a cascade refrigeration system based on compressor flow regulation according to claim 2, characterized in that: The data-driven model is trained after the historical data is preprocessed, and the preprocessing includes noise reduction, outlier removal, data repair and data reduction processes.

4. The energy-saving optimization method for a cascade refrigeration system based on compressor flow regulation according to claim 2, characterized in that: The function for calculating the COP of the cascade refrigeration system is as follows: COP=F(X) X=(x1,x2,x3,x4,x5) T =(T con ,T evp ,T mid ,ΔT,Q) T Where, T con is the system condensing temperature; T evp is the system evaporation temperature; T mid is the intermediate temperature, i.e. the condensing temperature of the low temperature stage; ΔT is the heat exchange temperature difference of the condenser evaporator, i.e. the difference between the condensing temperature of the low temperature stage and the evaporating temperature of the high temperature stage.

5. The energy-saving optimization method for a cascade refrigeration system based on compressor flow regulation according to claim 4, characterized in that: The optimal intermediate temperature T that meets the operating conditions is calculated according to the following mathematical model mid,opti : maxF(X) X=(x1,x2,x3,x4,x5) T =(T con ,T evp ,T mid ,ΔT,Q) T 。 T mid,down ≤T mid ≤T mid,up 6. The energy-saving optimization method for a cascade refrigeration system based on compressor flow regulation according to claim 5, characterized in that: Refrigeration load Q required for system operation, system evaporation temperature T evp The actual intermediate temperature T in the operating condition is unchanged. mid Adjust according to the average temperature T throughout the year mid The upper and lower limits of the operating range set the constraint boundary T mid，down and T mid，up .

7. The energy-saving optimization method for a cascade refrigeration system based on compressor flow regulation according to claim 2, characterized in that: The data-driven model is a data model based on an artificial neural network, including an input layer, a hidden layer, and an output layer: Input layer parameters include: system condensation temperature T con ; System evaporation temperature T evp ; Intermediate temperature T mid , that is, the condensing temperature of the low-temperature stage; the heat exchange temperature difference ΔT of the condenser evaporator, that is, the difference between the condensing temperature of the low-temperature stage and the evaporating temperature of the high-temperature stage; the system refrigeration load Q; Output layer parameters include: system COP; high temperature compressor power consumption P HT ; Low temperature compressor power consumption P LT ; High temperature compressor capacity adjustment slide valve position / frequency M HT ; Low temperature compressor capacity adjustment slide valve position / frequency M LT ; The hidden layer uses the ReLU function as the activation function.

8. The energy-saving optimization method for a cascade refrigeration system based on compressor flow regulation according to claim 7, characterized in that: In the data set used to train the data-driven model, the system condensation temperature T con , system evaporation temperature T evp , intermediate temperature T mid The value ranges of the heat exchange temperature difference ΔT of the condenser-evaporator and the system refrigeration load Q at least include the operating range of the current season.

9. The energy-saving optimization method for a cascade refrigeration system based on compressor flow regulation according to claim 7, characterized in that: The entire dataset for model training is divided into a training set and a test set using the K-Fold cross-validation method. The mean percentage error (MAPE) and root mean square error (RMSE) are used to evaluate whether the test set error meets the accuracy requirements. If the error is large, the model is retrained by adjusting the number of hidden layer units, the number of iterative calculations, or increasing the sample size of the training data. The accuracy requirements are as follows: MAPE i ≤0.5%,RMSE i ≤1,i=1,2,3,4,5。 10. A cascade refrigeration system energy-saving optimization system based on compressor flow regulation, characterized in that: include: Historical data collection and data-driven model training module, used to collect historical data of the cascade refrigeration system's on-site operation, and to establish and train the data-driven model of the cascade refrigeration system; COP calculation function establishment module, used to establish the COP calculation function of the cascade refrigeration system based on the data-driven model; The optimal intermediate temperature calculation module is used for the function of COP calculation based on the cascade refrigeration system, with the highest COP as the optimization target and the upper and lower limits of the intermediate temperature operating range as constraints. Given the cooling load Q required for system operation and the system condensing temperature T con , system evaporation temperature T evp and the heat exchange temperature difference ΔT of the condenser evaporator, and calculate the optimal intermediate temperature T that meets the operating conditions mid,opti ; The high and low temperature machine capacity adjustment slide valve / frequency setting value prediction module is used to set the optimal intermediate temperature T mid,opti As well as the cooling load Q required for system operation and the system condensing temperature T con , system evaporation temperature T evp The heat exchange temperature difference ΔT of the condenser and evaporator is used as input parameters, and the high temperature machine capacity adjustment slide valve / frequency setting value M is predicted through the established data-driven model. HT_opti And low temperature machine capacity adjustment slide valve position / frequency setting value M LT_opti ; High temperature compressor flow control module, used to adjust the slide valve / frequency setting value M according to the high temperature machine capacity HT_opti Control the high temperature machine capacity to adjust the slide valve / frequency, at this time the cascade refrigeration system meets the optimal intermediate temperature T mid,opti and COP under the conditions of the highest, to achieve high temperature compressor flow control, to achieve the goal of energy saving optimization; after the high temperature compressor flow is adjusted, according to whether the low temperature machine capacity adjustment slide valve position / frequency is adjusted to the low temperature machine capacity adjustment slide valve position / frequency setting value M LT_opti To determine whether the system has reached a stable operating state.

Images