Energy-saving refrigeration house refrigerating system

Abstract

The invention relates to the technical field of cold chain energy-saving management, in particular to an energy-saving refrigeration house refrigerating system, intelligent regulation and control are achieved through cooperation of a phase change cold storage unit and a compressor refrigerating unit, and the environment temperature and the surface temperature of a cold storage tank are obtained in real time through a data acquisition module; a double-branch TCN prediction model is adopted to generate predicted values of the surface temperature of a cold storage tank and the center temperature of a phase change material in the next one hour, a cold storage time window is generated based on a temperature prediction result, the phase change material is driven to store cold energy in a night off-peak electricity price period, and a multi-target optimization model is adopted to solve an optimal combination of compressor frequency and cold release rate in a non-cold storage period, so that the cold storage efficiency is improved. According to the system, the high latent heat characteristic of the phase change material is utilized, the temperature prediction and dynamic optimization algorithm is combined, the operation duration of the compressor is remarkably shortened, and the energy efficiency of the refrigeration house is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cold chain energy-saving management, and particularly to an energy-saving cold storage refrigeration system. Background Art

[0002] Fresh products, as essential consumer goods for people's livelihood, have a market volume in the trillions, but they consume a large amount of energy and emit a large amount of carbon during the circulation process. In China, the energy consumption of cold storages generally accounts for more than 70% of the energy consumption of the entire cold chain logistics enterprises. Compared with the same type of cold storages in relatively developed cold chain countries such as Japan, Europe and the United States, the power consumption of cold storages in China is about 3 times higher. The energy consumption of the refrigeration system in the cold storage accounts for more than 60% of the cold storage energy consumption. With the increasingly serious problem of high energy consumption in cold chain logistics, energy conservation and emission reduction of the cold storage system for fresh products, especially the refrigeration system of the cold storage, are imminent;

[0003] Traditional cold storage refrigeration systems generally use compressor refrigeration units as the single cold source, which have problems such as high energy consumption and large fluctuations in the power grid load. The compressor needs to run continuously at a high frequency to maintain a low-temperature environment, resulting in a sharp increase in operating costs. The energy-saving control method for the cold storage refrigeration system proposed in Chinese invention patent CN118274580A monitors the operating parameters in the compression, condensation, and evaporation stages and compares them with preset thresholds, and issues a warning to adjust the equipment parameters when the parameters do not meet the standards. Although this method can optimize each stage locally and reduce the operating cost to a certain extent, the compressor needs to run continuously at a high frequency, and its energy-saving and emission reduction effects are not ideal.

[0004] The introduction of the phase change energy storage technology provides a new idea for solving the above problems. The core of the phase change energy storage technology is to use the latent heat characteristics of phase change materials to achieve efficient storage and release of cold energy, which can significantly reduce the running time and frequency of the compressor. However, the existing technology adopts a fixed threshold control strategy and cannot intelligently optimize the collaborative ratio of the compressor operation and the phase change energy storage technology. It may still operate in a high-energy consumption mode during peak electricity price periods and cannot achieve "peak shaving and valley filling" in the true sense. Secondly, the existing technology lacks accurate prediction of the environmental temperature and the thermal state of the phase change material, and it is difficult to dynamically capture the best cold storage timing, resulting in low cold energy storage efficiency of the phase change energy storage technology and making it difficult to balance energy consumption and temperature stability.

[0005] The above problems make it difficult for the existing system to meet the energy-saving requirements under the large-scale development of cold chain logistics. There is an urgent need for a solution that integrates dynamic prediction, intelligent optimization, and high-density energy storage technology to break through the energy efficiency bottleneck and achieve energy conservation throughout the life cycle of cold storage operation. Summary of the Invention

[0006] In view of the above-mentioned prior art, the present invention aims to provide an energy-saving cold storage refrigeration system, mainly to solve the technical problems existing in the above background art.

[0007] To achieve the above object, the technical solution of the embodiment of the present invention is implemented as follows:

[0008] An energy-saving cold storage refrigeration system includes a compressor refrigeration unit. The system includes a phase change cold storage unit provided with a phase change material, and further includes:

[0009] A data acquisition module for obtaining the surface temperature of the cold storage tank and the ambient temperature outside the cold storage.

[0010] A temperature prediction module for obtaining the predicted value of the surface temperature of the cold storage tank for each hour in the future based on the surface temperature of the cold storage tank and the ambient temperature outside the cold storage, and obtaining the predicted value of the central temperature of the phase change material through the predicted value of the surface temperature of the cold storage tank;

[0011] A cold storage window generation module for determining whether the cold storage condition is satisfied according to the predicted value of the surface temperature of the cold storage tank and the predicted value of the central temperature of the phase change material, and generating a cold storage time window when the condition is satisfied.

[0012] A multi-objective optimization module for dynamically solving the optimal parameter combination between the compressor operating frequency and the cold release rate of the cold storage unit through a multi-objective optimization model during the non-cold storage time window.

[0013] A driving module for driving the phase change cold storage unit to store cold during the cold storage time window, and controlling the compressor refrigeration module and the phase change cold storage unit to achieve coordinated cooling according to the optimal parameter combination during the non-cold storage time window.

[0014] Optionally, the phase change cold storage unit includes a heat preservation tank storing a heat transfer medium and a cold storage tank filled with a phase change material. The cold storage tank is arranged outside the cold storage. The cold storage tank is connected to the heat preservation tank through a conveying pipeline. A first driving pump is arranged on the conveying pipeline, and the first driving pump drives the heat transfer medium to flow between the heat preservation tank and the cold storage tank.

[0015] Optionally, the outlet of the heat preservation tank is connected to the inlet of the evaporator in the main cold supply circuit of the cold storage through a bypass cold supply circuit. A second driving pump, a solenoid valve V1 and an electronic expansion valve EV2 are sequentially connected in series on the bypass cold supply circuit. The outlet of the evaporator is connected to the heat preservation tank through a return pipeline, and a check valve V2 is configured on the return pipeline.

[0016] Optionally, obtaining the predicted value of the surface temperature of the cold storage tank for each hour in the future based on the surface temperature of the cold storage tank and the ambient temperature outside the cold storage specifically includes: establishing a double-branch TCN prediction model, using the surface temperature of the cold storage tank as the input of the first branch and the ambient temperature outside the cold storage as the input of the second branch, and finally outputting the predicted value of the surface temperature of the cold storage tank for each hour in the future.

[0017] Optionally, each branch of the dual-branch TCN prediction model includes: a multi-scale Inception module, a TCN module, an Attention attention module, and a regression output layer. The surface temperature of the cold storage tank and the cold storage environment temperature extract features through their respective multi-scale Inception modules and TCN modules. The features extracted by each branch pass through the Attention attention module to generate a weighted feature map. The weighted feature maps of the two branches are spliced across channels to form comprehensive spatio-temporal features. The regression output layer outputs the predicted value of the surface temperature of the cold storage tank for each future hour based on the comprehensive spatio-temporal features.

[0018] Optionally, the predicted value of the central temperature of the phase change material is obtained through the predicted value of the surface temperature of the cold storage tank, which specifically includes: establishing a heat conduction equation, substituting the predicted value of the surface temperature of the cold storage tank for each future hour into the heat conduction equation, and obtaining the predicted value of the central temperature of the phase change material for each future hour.

[0019] Optionally, the cold storage condition specifically includes: setting the length of each time window to 1 hour. If, in any time window, the predicted value of the outer shell temperature of the cold storage tank is less than or equal to the lower limit of the phase change temperature of the phase change material itself, and the predicted value of the central temperature of the phase change material is greater than or equal to the upper limit of the phase change temperature of the phase change material itself, then the cold storage condition is established, and this time window is the cold storage time window.

[0020] Optionally, the optimal parameter combination between the compressor operating frequency and the cold release rate of the cold storage unit is dynamically solved through a multi-objective optimization model, which specifically includes:

[0021] Establish a multi-objective optimization function regarding energy consumption cost, temperature stability, and the remaining cold quantity of the cold storage unit:

[0022] Randomly generate parameter combinations of the compressor frequency and the cold release rate of the cold storage unit, and set a fitness function;

[0023] Perform selection, crossover, and mutation operations on the parameter combinations in the genetic algorithm until the change rate of the optimal solution for three consecutive generations < 1%, or when the maximum number of iterations is reached, output the compressor frequency and the cold release rate of the cold storage unit at this time as the optimal parameter combination.

[0024] Optionally, during the cold storage time window, drive the phase change cold storage unit to store cold, which specifically includes: if the cold storage condition is met, drive the refrigerant to flow from the insulation tank into the cold storage tank within the time window, and realize heat exchange through the radiator in the cold storage tank to reduce the temperature of the refrigerant and achieve cold storage.

[0025] Optionally, during other window periods, control the cooperative cooling behavior of the compression refrigeration module and the phase change cold storage unit, which specifically includes:

[0026] When the temperature deviation of the cold storage |Δt| ≤ 1°C, the cold is supplied only by the phase change cold storage unit, and the compression refrigeration unit is in a shutdown state;

[0027] When the temperature deviation of the cold storage |Δt| > 1°C, the phase change cold storage unit and the compression refrigeration unit are driven to cooperate in refrigeration based on the optimal parameter combination.

[0028] The beneficial effects of the present invention are as follows: The surface temperature of the cold storage tank and the ambient temperature outside the cold storage are obtained through the data acquisition module. The temperature prediction module performs feature extraction and fusion on the two types of temperature data based on the dual-branch TCN model to generate the predicted value of the surface temperature of the cold storage tank per hour in the future; Subsequently, the predicted value of the temperature at the center of the phase change material is derived through the heat conduction equation. When the external temperature is low, the phase change material filled in the cold storage tank always exchanges heat with the external environment. After the phase change material absorbs cold, a phase change occurs, storing the cold in the phase change material. The cold storage window generation module determines whether the cold storage condition is met according to the predicted value of the surface temperature of the cold storage tank and the predicted value of the temperature at the center of the phase change material. When the ambient temperature is low and the temperatures of the cold storage tank and the phase change material are appropriate, it is considered that the condition is met, and a cold storage time window is generated. During the cold storage time window, the heat transfer medium in the heat preservation tank is transported to the cold storage tank to exchange heat with the phase change material filled in the cold storage tank, reducing the temperature of the heat transfer medium in the heat preservation tank. In the non-cold storage window, when the temperature deviation of the cold storage is small, the driving module only drives the phase change cold storage unit to supply cold, and the compression refrigeration unit is in a shutdown state, reducing unnecessary energy consumption. When the temperature deviation of the cold storage is large, the driving module drives the phase change cold storage unit and the compression refrigeration unit to cooperate in refrigeration based on the optimal parameter combination to ensure the rapid recovery and stability of the cold storage temperature, significantly reducing the operating cost and improving the cold supply stability. Description of the Drawings

[0029] Figure 1 It is a schematic structural diagram of an energy-saving cold storage refrigeration system in an embodiment of the present application;

[0030] Figure 2 It is a schematic connection diagram of the heat preservation tank and the cold storage tank in an embodiment of the present application.

[0031] Explanation of the reference numerals in the drawings:

[0032] 1. Data acquisition module; 2. Temperature prediction module; 3. Cold storage window generation module; 4. Multi-objective optimization module; 5. Driving module; 6. Compression refrigeration unit; 7. Phase change cold storage unit, 8. Heat preservation tank; 9. Cold storage tank; 10. Delivery pipeline; 11. First driving pump; 12. Second driving pump. Detailed Embodiment

[0033] The technical solution of the present invention will be further elaborated in detail below in conjunction with the accompanying drawings of the specification and specific embodiments. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention. In the following description, the expression "some embodiments" is described, which describes a subset of all possible embodiments. However, it should be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with each other without conflict.

[0034] In the following description, a large number of specific details are given to provide a more thorough understanding of the present invention. However, it is obvious to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features well known in the art are not described.

[0035] It should be understood that the present invention can be implemented in different forms and should not be construed as limited to the embodiments presented herein. On the contrary, providing these embodiments will make the disclosure thorough and complete and will fully convey the scope of the present invention to those skilled in the art. And the purpose of the terms used herein is only to describe specific embodiments and not to limit the present invention. When used herein, the singular forms "a", "an" and "the" are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms "comprising" and / or "including", when used in this specification, determine the presence of the described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups. When used herein, the term "and / or" includes any and all combinations of the related listed items.

[0036] It should be noted that when an element is referred to as being "fixed to" another element, it can be directly on the other element or there can also be an intermediate element. When an element is considered to be "connected" to another element, it can be directly connected to the other element or there may be an intermediate element at the same time. The terms "vertical", "horizontal", "inner", "outer", "left", "right" and similar expressions used herein are only for the purpose of illustration and do not represent the only implementation.

[0037] In order to thoroughly understand the present invention, detailed structures will be presented in the following description to explain the technical solution proposed by the present invention. The optional embodiments of the present invention are described in detail as follows. However, in addition to these detailed descriptions, the present invention can also have other implementations.

[0038] In some technologies in this field, the working principle of the compression refrigeration unit 6 is based on the vapor compression refrigeration cycle. Through the coordinated action of the compressor, condenser, expansion valve, and evaporator, heat transfer is achieved. The compressor compresses the gaseous refrigerant, increasing its temperature and pressure so that it can release heat and liquefy in the condenser. The condenser, as a heat dissipation component, dissipates the heat carried by the refrigerant into the surrounding environment. The expansion valve reduces the pressure and temperature of the refrigerant through throttling, enabling it to absorb heat in the evaporator. The evaporator is the place where the refrigerant absorbs the heat inside the cold storage and evaporates, directly achieving the refrigeration effect inside the cold storage. The entire cycle process is continuous, ensuring the stability and continuous refrigeration of the temperature inside the cold storage.

[0039] Please refer to the attached Figures 1 to 2 Some embodiments of the present application provide an energy-saving cold storage refrigeration system, including a compression refrigeration unit 6 and a phase change cold storage unit 7 provided with a phase change material. The system further includes:

[0040] A data acquisition module 1 for obtaining the surface temperature of the cold storage tank 9 and the ambient temperature outside the cold storage.

[0041] A temperature prediction module 2 for obtaining the predicted value of the surface temperature of the cold storage tank 9 for each hour in the future based on the surface temperature of the cold storage tank 9 and the ambient temperature outside the cold storage, and obtaining the predicted value of the central temperature of the phase change material through the predicted value of the surface temperature of the cold storage tank 9;

[0042] A cold storage window generation module 3 for determining whether the cold storage condition is met based on the predicted value of the surface temperature of the cold storage tank 9 and the predicted value of the central temperature of the phase change material, and generating a cold storage time window when the condition is met;

[0043] A multi-objective optimization module 4 for dynamically solving the optimal parameter combination between the compressor operating frequency and the cold release rate of the cold storage unit through a multi-objective optimization model during the non-cold storage time window;

[0044] A driving module 5 for driving the phase change cold storage unit 7 to store cold during the cold storage time window, and controlling the compression refrigeration module and the phase change cold storage unit 7 to achieve coordinated cooling according to the optimal parameter combination during the non-cold storage time window.

[0045] In the energy-saving cold storage refrigeration system shown in the embodiments of the present application, first, the data acquisition module 1 obtains the surface temperature of the cold storage tank 9 and the ambient temperature outside the cold storage. The temperature prediction module 2 performs feature extraction and fusion on the two types of temperature data based on the dual-branch TCN model to generate the predicted value of the surface temperature of the cold storage tank 9 for each hour in the future; subsequently, the predicted value of the temperature at the center of the phase change material is derived through the heat conduction equation. When the external temperature is low, the phase change material filled in the cold storage tank 9 always exchanges heat with the external environment. After the phase change material absorbs cold energy, a phase change occurs, so that the cold energy is stored in the phase change material. The cold storage window generation module 3 determines whether the cold storage condition is met according to the predicted value of the surface temperature of the cold storage tank 9 and the predicted value of the temperature at the center of the phase change material. When the ambient temperature is low and the temperatures of the cold storage tank 9 and the phase change material are appropriate, it is considered that the condition is met, and a cold storage time window is generated. During the cold storage time window, the heat transfer medium in the heat preservation tank 8 is transported to the cold storage tank 9 to exchange heat with the phase change material filled in the cold storage tank 9, reducing the temperature of the heat transfer medium in the heat preservation tank 8. In the non-cold storage window, when the temperature deviation of the cold storage is small, the driving module 5 only drives the phase change cold storage unit 7 to supply cold, and the compression refrigeration unit 6 is in a shutdown state, reducing unnecessary energy consumption. When the temperature deviation of the cold storage is large, the driving module 5 drives the phase change cold storage unit 7 and the compression refrigeration unit 6 to cooperate in refrigeration based on the optimal parameter combination to ensure the rapid recovery and stability of the cold storage temperature.

[0046] Specifically, the data acquisition module 1 includes sensors arranged on the surface of the cold storage tank 9 and ambient temperature sensors arranged around the cold storage. For example, a plurality of high-precision contact temperature sensors are evenly arranged on the outer wall of the cold storage tank 9 and are closely attached to the surface by mechanical fixation or thermal conductive glue to ensure the heat conduction efficiency between the sensor and the tank body. The sensor array covers different heights and circumferential positions of the tank body to capture the surface temperature distribution difference;

[0047] The ambient temperature sensors are installed on the outer wall of the cold storage or in a well-ventilated external area to avoid direct sunlight or local heat source interference. The sensors adopt a multi-point distributed layout, covering different orientations of the cold storage, and comprehensively calculating the average value to reflect the real ambient temperature.

[0048] In some embodiments, the phase change cold storage unit 7 includes a heat preservation tank 8 storing a heat transfer medium and a cold storage tank 9 filled with a phase change material. The cold storage tank 9 is arranged outside the cold storage. The cold storage tank 9 is connected to the heat preservation tank 8 through a conveying pipeline 10. A first driving pump 11 is arranged on the conveying pipeline 10. The first driving pump 11 drives the heat transfer medium to flow between the heat preservation tank 8 and the cold storage tank 9. The outlet of the heat preservation tank 8 is connected to the inlet of the evaporator in the main cold supply circuit of the cold storage through a bypass cold supply circuit. A second driving pump 12, a solenoid valve V1 and an electronic expansion valve EV2 are arranged in series on the bypass cold supply circuit in sequence. The outlet of the evaporator is connected to the heat preservation tank 8 through a return pipeline, and a check valve V2 is configured on the return pipeline.

[0049] Specifically, when the heat transfer medium flows through the cold storage tank 9, it contacts the phase change material through the conveying pipeline 10, accelerating heat transfer. When the temperature of the medium is higher than the lower limit of the phase change temperature, the phase change material absorbs heat and undergoes a phase change, and the temperature of the heat transfer medium decreases accordingly; when the temperature of the heat transfer medium approaches or is lower than the upper limit of the phase change temperature, the phase change material completes solidification, and the cold quantity is locked in the solid structure. The cooled heat transfer medium returns to the heat preservation tank 8 through the return pipeline, forming a reserve of low-temperature medium to provide a cold source for subsequent cold supply.

[0050] When the cold storage needs cold quantity, the solenoid valve V1 and the electronic expansion valve EV2 are opened. The low-temperature medium in the heat preservation tank 8 enters the evaporator in the main cold supply circuit of the cold storage through the bypass cold supply circuit. The medium absorbs the heat inside the cold storage in the evaporator and returns to the heat preservation tank 8 through the return pipeline after the temperature rises. The electronic expansion valve EV2 controls the cold supply rate by adjusting the medium flow rate and pressure to match the real-time demand of the cold storage; the check valve V2 prevents the medium from flowing backward and maintains the one-way flow of the circuit. This process enables the phase change cold storage unit 7 to supply cold to the cold storage independently and reduces the operation time of the compressor.

[0051] In some embodiments, the predicted value of the surface temperature of the cold storage tank 9 for each hour in the future is obtained based on the surface temperature of the cold storage tank 9 and the ambient temperature outside the cold storage, specifically including: establishing a dual-branch TCN prediction model, using the surface temperature of the cold storage tank 9 as the input of the first branch and the ambient temperature outside the cold storage as the input of the second branch, and finally outputting the predicted value of the surface temperature of the cold storage tank 9 for each hour in the future.

[0052] Specifically, each branch of the dual-branch TCN prediction model includes: a multi-scale Inception module, a TCN module, an Attention attention module, and a regression output layer. The surface temperature of the cold storage tank 9 and the cold storage environment temperature respectively extract features through their respective multi-scale Inception modules and TCN modules. The features extracted by each branch pass through the Attention attention module to generate a weighted feature map. The weighted feature maps of the two branches are spliced across channels to form comprehensive spatio-temporal features. The regression output layer outputs the predicted value of the surface temperature of the cold storage tank 9 for each hour in the future based on the comprehensive spatio-temporal features.

[0053] Exemplarily, the multi-scale Inception module divides the input data into three paths for calculation after convolutional feature mapping:

[0054] The first path: extracts high-level feature relationships through a convolutional layer with a kernel size of 1×3, and then adjusts the channel dimension through a convolutional layer with a kernel size of 1×1 to obtain temporal feature dependencies;

[0055] The second path: passes through a convolutional layer with a kernel size of 1×3 followed by a convolutional layer with a kernel size of 1×5 to capture time dependencies;

[0056] The third path: expands the feature expression range through a convolutional layer with a kernel size of 1×7, and then reduces the number of channels through a convolutional layer with a kernel size of 1×1;

[0057] The outputs of each path are normalized by the BN layer and then spliced across channels to form multi-scale fusion features;

[0058] The TCN module performs dilated causal convolution on the multi-scale fusion features and stacks residual connections;

[0059] The Attention attention module includes:

[0060] The first unit: compresses the signal features of each input channel into a single value using global pooling operation, and learns the low-frequency trend features of temporal features through a convolutional layer with a kernel size of 1×1 and a batch normalization layer;

[0061] The second unit: uses a convolutional layer with a kernel of 1×3 for the input features, combines batch normalization and non-linear function combinations to enhance the non-linear mapping of input and output;

[0062] The outputs of the two units are linearly added and fused to generate a weighted feature map, and the more valuable features are highlighted through the Sigmoid function. The weighted feature maps of the two branches are spliced across channels to form comprehensive spatio-temporal features.

[0063] The regression output layer outputs the predicted surface temperature of the cold storage tank 9 for each hour in the future based on the comprehensive spatio-temporal features.

[0064] In some embodiments, the predicted central temperature value of the phase change material is obtained through the predicted surface temperature value of the cold storage tank 9, which specifically includes: establishing a heat conduction equation, substituting the predicted surface temperature value of the cold storage tank 9 for each hour in the future into the heat conduction equation, and obtaining the predicted central temperature value of the phase change material for each hour in the future.

[0065] Furthermore, the time is divided into time windows with a length of 1 hour. Within each time window, the predicted outer shell temperature value of the cold storage tank 9 and the predicted central temperature value of the phase change material are obtained through the temperature prediction module 2.

[0066] Specifically, the heat conduction equation includes the Fourier heat conduction equation. A three-dimensional heat diffusion model established through the Fourier heat conduction equation uses the predicted surface temperature of the cold storage tank 9 as the boundary condition to calculate the predicted central temperature value of the phase change material.

[0067] The Fourier heat conduction equation describes the variation law of the temperature inside an object with time and space. For an isotropic and homogeneous material, the three-dimensional heat conduction equation is a partial differential equation, which can be expressed as:

[0068]

[0069] where T = T(x, y, z, t) is the temperature of the phase change material at position (x, y, z) and time t, and α is the diffusivity. When calculating, the phase change cold storage tank 9 and the internal phase change material are regarded as a three-dimensional object, and a rectangular coordinate system (x, y, z) is established. The origin can be set at a certain characteristic point of the cold storage tank 9 according to the actual situation, such as the center or a certain corner. Assume that at the initial moment t = 0, the temperature distribution inside the phase change material is a known function T0(x, y, z), that is, T = T(x, y, z, 0) = T0(x, y, z), and this is used as the initial condition of the geometric model corresponding to the partial differential equation. Using the predicted surface temperature of the cold storage tank 9 as the boundary condition, the time and space of the foregoing partial differential equation are discretized by using the finite difference method or the finite element method. The three-dimensional space of the phase change material is divided into multiple small units. Starting from the initial condition, and updating the temperature values of the boundary points according to the boundary condition within each time step, and then obtaining the temperature values of each unit. Through iterative calculation, the temperature prediction result inside the phase change material, especially the temperature prediction result in the central region, is gradually solved.

[0070] In some embodiments, the cold storage conditions specifically include: setting the length of each time window to 1 hour. If, in any time window, the predicted value of the outer shell temperature of the cold storage tank 9 is less than or equal to the lower limit of the phase change temperature of the phase change material itself, and the predicted value of the central temperature of the phase change material is greater than or equal to the upper limit of the phase change temperature of the phase change material itself, then the cold storage conditions are met, and this time window is the cold storage time window.

[0071] Specifically, the cold storage conditions require that the predicted outer shell temperature of the cold storage tank 9 ≤ the lower limit of the phase change temperature of the phase change material, and at the same time, the predicted central temperature of the phase change material ≥ the upper limit of the phase change temperature. Essentially, it uses the temperature gradient to drive heat transfer. The low outer shell temperature ensures that the external environment can effectively dissipate heat, while the high central temperature indicates that there is still a liquid region (not completely solidified) inside the phase change material, and heat can continue to be absorbed through phase change. This dual constraint avoids two inefficient scenarios: too high outer shell temperature: the external environment cannot provide enough cooling capacity, resulting in low cold storage efficiency; too low central temperature: the phase change material has completely solidified and the latent heat has been released, and further cold storage is not possible. Therefore, when the above cold storage conditions are met, a cold storage time window is generated, and the cold storage operation is started within this time window. The first driving pump 11 transports the heat transfer medium in the heat preservation tank 8 to the cold storage tank 9. At this time, the phase change material in the cold storage tank 9 under the external low-temperature environment changes from solid to liquid, and when the heat transfer medium flows through the cold storage tank 9, the heat it carries is absorbed by the phase change material, resulting in a significant decrease in the temperature of the heat transfer medium. The cooled medium returns to the heat preservation tank 8 for storage, completing the cold quantity transfer.

[0072] In some embodiments, the optimal parameter combination between the compressor operating frequency and the cold release rate of the cold storage unit is dynamically solved through a multi-objective optimization model, specifically including:

[0073] Establish a multi-objective optimization function regarding energy consumption cost, temperature stability, and the remaining cold quantity of the cold storage unit:

[0074] Randomly generate parameter combinations of the compressor frequency and the cold release rate of the cold storage unit, and set a fitness function;

[0075] Perform selection, crossover, and mutation operations on the parameter combinations in the genetic algorithm until the change rate of the optimal solution for 3 consecutive generations < 1%, or when the maximum number of iterations is reached, output the compressor frequency and the cold release rate of the cold storage unit at this time as the optimal parameter combination.

[0076] Specifically, the expression of the multi-objective optimization function established regarding energy consumption cost, temperature stability, and the remaining cold quantity of the cold storage unit is:

[0077]

[0078] where C(t) is the real-time electricity price, P comp (t) is the compressor power, ΔT is the cold storage temperature deviation, Qpcm (t) is the current cooling storage amount of the cooling storage tank 9, Q max is the maximum cooling storage amount of the cooling storage tank 9, and λ1, λ2, and λ3 are weighting coefficients.

[0079] Among them, the calculation of the current cooling storage amount is based on the temperature state and thermodynamic parameters of the phase change material, and the calculation formula is as follows:

[0080]

[0081] Among them, m is the total mass of the phase change material, c s is the specific heat capacity of the solid phase change material, c l is the specific heat capacity of the liquid phase change material, ΔH is the phase change enthalpy of the phase change material, T lower is the lower limit of the phase change temperature, T upper is the upper limit of the phase change temperature, and T is the central temperature of the phase change material.

[0082] Solve the above optimal function through the genetic algorithm. During the solution process, randomly generate N groups (f comp , r dis ), among which, f comp represents the compressor frequency, r dis represents the cooling release rate of the cooling storage tank 9. Its fitness function converts multiple objectives into a single-objective optimization problem through linear weighting. In the selection operation, high-fitness individuals are retained through tournament selection, parameter combinations are formed through crossover operations, and population diversity is maintained through mutation operations. The termination condition is based on the change rate of the optimal solution in three consecutive generations <1% or reaching the maximum number of iterations, and finally the optimal parameter combination that meets the constraint conditions is output.

[0083] Furthermore, the output optimal compressor frequency can be directly used, and the output cooling release rate of the cooling storage tank 9 is related to the outflow rate of the heat transfer medium. The outflow rate of the heat transfer medium is related to the motor speed of the second driving pump 12 and the opening degree of the solenoid valve V1. Therefore, after obtaining the cooling release rate of the cooling storage tank 9, the motor speed of the second driving pump 12 and the opening degree of the solenoid valve V1 corresponding to the cooling release rate of the cooling storage tank 9 are obtained, and finally, the optimal compressor frequency, the motor speed of the second driving pump 12, and the opening degree of the solenoid valve V1 are used as adjustment parameters for control

[0084] In some embodiments, during the cooling storage time window, the phase change cooling storage unit 7 is driven to achieve cold storage, specifically including: if the cooling storage condition is met, the refrigerant is driven to flow from the heat preservation tank 8 into the cooling storage tank 9 within the time window, and heat exchange is realized through the radiator in the cooling storage tank 9 to reduce the temperature of the refrigerant and achieve cooling storage.

[0085] Specifically, within the cold storage time window, the phase change cold storage unit 7 transports the refrigerant in the heat preservation tank 8 to the cold storage tank 9 through a driving pump. The radiator in the cold storage tank 9 plays a key role in this process. By exchanging heat with the refrigerant, it transfers the heat of the refrigerant to the phase change material in the cold storage tank 9. After absorbing heat, the phase change material undergoes a phase change, usually from solid to liquid, and this process can efficiently store cold energy. In this way, the temperature of the refrigerant is significantly reduced, thus achieving cold storage.

[0086] In some embodiments, during other window periods, the cooperative cooling behavior of the compression refrigeration module and the phase change cold storage unit 7 is controlled, which specifically includes:

[0087] When the temperature deviation of the cold storage |Δt| ≤ 1°C, only the phase change cold storage unit 7 provides cooling, and the compression refrigeration unit 6 is in a shutdown state;

[0088] When the temperature deviation of the cold storage |Δt| > 1°C, the phase change cold storage unit 7 and the compression refrigeration unit 6 are driven to cooperate in refrigeration based on the optimal parameter combination.

[0089] During the non-cold storage period, the cooling mode is dynamically switched according to the temperature deviation of the cold storage to achieve energy-saving operation. When the absolute value of the temperature deviation ≤ 1°C, it indicates that the current cold energy demand is low, and only the phase change cold storage unit 7 is started for cooling: the low-temperature heat transfer medium in the heat preservation tank 8 directly enters the evaporator of the cold storage through the bypass circuit to absorb heat, and the compressor remains in a shutdown state. In this mode, the phase change material releases latent heat through the solidification or crystallization process to maintain cooling, avoiding energy consumption losses caused by frequent start-stop of the compressor. When the temperature deviation exceeds 1°C, the system determines that the cold energy demand exceeds the bearing capacity of the cold storage unit, triggering the compressor and the phase change unit to cooperate in cooling: the multi-objective optimization model dynamically calculates the optimal combination of the compressor operation frequency and the cold release rate of the phase change unit according to the real-time temperature deviation, electricity price period, and remaining cold energy. The compressor supplements cold energy through the reverse Carnot cycle, and the phase change unit synchronously releases the stored cold energy, reducing the comprehensive energy consumption while ensuring temperature stability. The measured data shows that the cooperative mode is 18 - 25% more energy-saving than single compression refrigeration, and can shorten the temperature recovery time by more than 30%.

[0090] The above is only the specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should be covered within the protection scope of the present invention. The protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. An energy-saving cold storage refrigeration system, including a compressor refrigeration unit, characterized in that: The system includes a phase change cold storage unit provided with a phase change material, and further includes: A data acquisition module for obtaining the surface temperature of the cold storage tank and the ambient temperature outside the cold storage. A temperature prediction module for obtaining the predicted value of the surface temperature of the cold storage tank for each hour in the future based on the surface temperature of the cold storage tank and the ambient temperature outside the cold storage, and obtaining the predicted value of the central temperature of the phase change material through the predicted value of the surface temperature of the cold storage tank; A cold storage window generation module for determining whether the cold storage condition is satisfied according to the predicted value of the surface temperature of the cold storage tank and the predicted value of the central temperature of the phase change material, and generating a cold storage time window when the condition is satisfied; A multi-objective optimization module for dynamically solving the optimal parameter combination between the operating frequency of the compressor and the cold release rate of the cold storage unit through a multi-objective optimization model during the non-cold storage time window; A driving module for driving the phase change cold storage unit to store cold during the cold storage time window, and controlling the compression refrigeration module and the phase change cold storage unit to achieve collaborative cooling according to the optimal parameter combination during the non-cold storage time window.

2. The energy-saving cold storage refrigeration system according to claim 1, wherein The phase change cold storage unit includes a heat preservation tank storing a heat transfer medium and a cold storage tank filled with a phase change material. The cold storage tank is arranged outside the cold storage. The cold storage tank is connected to the heat preservation tank through a conveying pipeline. A first driving pump is arranged on the conveying pipeline, and the first driving pump drives the heat transfer medium to flow between the heat preservation tank and the cold storage tank.

3. The energy-saving cold storage refrigeration system according to claim 2, characterized in that, The outlet of the heat preservation tank is connected to the inlet of the evaporator in the main cold supply circuit of the cold storage through a bypass cold supply circuit. A second driving pump, a solenoid valve V1 and an electronic expansion valve EV2 are arranged in series on the bypass cold supply circuit. The outlet of the evaporator is connected to the heat preservation tank through a return pipeline, and a check valve V2 is arranged on the return pipeline.

4. An energy-saving cold storage refrigeration system according to claim 1, characterized in that, Obtaining the predicted value of the surface temperature of the cold storage tank for each hour in the future according to the surface temperature of the cold storage tank and the ambient temperature outside the cold storage specifically includes: establishing a dual-branch TCN prediction model, using the surface temperature of the cold storage tank as the input of the first branch and the ambient temperature outside the cold storage as the input of the second branch, and finally outputting the predicted value of the surface temperature of the cold storage tank for each hour in the future.

5. An energy-saving cold storage refrigeration system according to claim 4, characterized in that Each branch of the dual-branch TCN prediction model includes: a multi-scale Inception module, a TCN module, an Attention attention module and a regression output layer. The surface temperature of the cold storage tank and the cold storage environment temperature extract features through their respective multi-scale Inception modules and TCN modules. The features extracted by each branch pass through the Attention attention module to generate a weighted feature map. The weighted feature maps of the two branches are spliced across channels to form comprehensive spatio-temporal features. The regression output layer outputs the predicted value of the surface temperature of the cold storage tank for each hour in the future based on the comprehensive spatio-temporal features.

6. The energy-saving cold storage refrigeration system according to claim 5, characterized in that, Obtaining the predicted value of the central temperature of the phase change material through the predicted value of the surface temperature of the cold storage tank specifically includes: establishing a heat conduction equation, substituting the predicted value of the surface temperature of the cold storage tank for each hour in the future into the heat conduction equation, and obtaining the predicted value of the central temperature of the phase change material for each hour in the future.

7. An energy-saving cold storage refrigeration system according to claim 6, characterized in that, The cold storage conditions specifically include: setting the length of each time window to 1 hour. If, in any time window, the predicted value of the outer shell temperature of the cold storage tank is less than or equal to the lower limit of the phase change temperature of the phase change material itself, and the predicted value of the central temperature of the phase change material is greater than or equal to the upper limit of the phase change temperature of the phase change material itself, then the cold storage condition is satisfied, and this time window is the cold storage time window.

8. An energy-saving cold storage refrigeration system according to claim 7, characterized in that, Dynamically solve the optimal parameter combination between the compressor operating frequency and the cold release rate of the cold storage unit through a multi-objective optimization model, specifically including: Establish a multi-objective optimization function regarding energy consumption cost, temperature stability, and the remaining cold quantity of the cold storage unit: Randomly generate parameter combinations of the compressor frequency and the cold release rate of the cold storage unit, and set the fitness function; Perform selection, crossover, and mutation operations in the genetic algorithm on the parameter combinations until the change rate of the optimal solution for three consecutive generations < 1%, or when the maximum number of iterations is reached, output the compressor frequency and the cold release rate of the cold storage unit at this time as the optimal parameter combination.

9. An energy-saving cold storage refrigeration system according to claim 8, characterized in that, During the cold storage time window, drive the phase change cold storage unit to achieve cold storage, specifically including: if the cold storage condition is satisfied, drive the refrigerant to flow from the insulation tank into the cold storage tank within the time window, and achieve heat exchange through the radiator in the cold storage tank to reduce the temperature of the refrigerant and achieve cold storage.

10. An energy-saving cold storage refrigeration system according to claim 9, characterized in that, Control the coordinated cooling behavior of the compression refrigeration module and the phase change cold storage unit during other window periods, specifically including: When the cold storage temperature deviation |Δt| ≤ 1°C, only the phase change cold storage unit supplies cooling, and the compression refrigeration unit is in a shutdown state; When the cold storage temperature deviation |Δt| > 1°C, drive the phase change cold storage unit and the compression refrigeration unit to cool in coordination based on the optimal parameter combination.

Images