Refrigeration appliance and method of controlling the same, controller, medium and program product

Abstract

The application provides a refrigeration equipment and a control method, a controller, a medium and a program product thereof, comprising: establishing a thermodynamic dynamic model corresponding to a box according to box structure parameters, refrigeration system configuration and environmental parameters of the refrigeration equipment; estimating the temperature of a virtual measuring point of the box according to collected operation parameters of the refrigeration equipment based on the thermodynamic dynamic model to construct temperature field data corresponding to the box; inputting the temperature field data into a pre-trained prediction model to output a target temperature prediction value of the box in a first time period after a current time through the prediction model; determining a target control amount through a cost function according to the target temperature prediction value, and controlling an actuator of the refrigeration equipment according to the target control amount. The application can improve the temperature uniformity in the box, eliminate local hot spots or cold spots, and also can adjust the refrigeration capacity in advance, reduce temperature overshoot and fluctuation, and improve the control precision and stability of the refrigeration equipment.

Description

Technical Field

[0001] This application relates to the field of refrigeration equipment technology, and in particular to a refrigeration equipment and its control method, controller, medium and program product. Background Technology

[0002] In related technologies, refrigerator cabinets are widely used in food, medicine, scientific research and other fields, where high requirements are placed on the uniformity and stability of the internal temperature. In traditional temperature control, temperature acquisition often relies on sensors placed inside the cabinet. The local temperature collected by one or more sensors is used to reflect the temperature of the entire cabinet, and the start and stop of the compressor and fan are adjusted in a closed loop based on the deviation between the temperature sensor's measured value and the set temperature to regulate the temperature inside the cabinet.

[0003] However, this method has at least the following drawbacks: First, limitations in temperature sensing: Using sensors at specific locations can only measure the temperature at the installation point, resulting in a significant error compared to the actual temperature inside the cabinet. It fails to reflect the distribution of the temperature field within the cabinet, leading to poor temperature uniformity and frequent localized overheating or undercooling. The sensor installation location only reflects the local temperature, making it difficult to characterize the overall temperature of the compartment and the surface temperature of the food, easily causing localized overcooling / overheating, which is detrimental to preservation and energy consumption. Second, control lag and variability: In threshold and simple feedback control, adjustment is only made when the temperature deviates from the set value, resulting in a lag in response and a tendency to cause temperature overshoot and oscillations at local temperature thresholds. Due to the principle of thermal inertia, the sensor's response to the actual compartment temperature is significantly delayed under disturbances such as ambient temperature, door opening and closing, compressor start / stop, and defrosting, leading to control lag and oscillations. Summary of the Invention

[0004] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes a refrigeration device and its control method, controller, medium, and program products, designed to achieve precise and uniform temperature control of the refrigerator compartment.

[0005] In a first aspect, embodiments of this application provide a control method for a refrigeration device, the method comprising: Based on the cabinet structure parameters, refrigeration system configuration, and environmental parameters of the refrigeration equipment, a thermodynamic dynamic model corresponding to the cabinet of the refrigeration equipment is established. Based on the thermodynamic dynamic model, the temperature of the virtual measuring points of the box is estimated according to the collected operating parameters of the refrigeration equipment, and temperature field data corresponding to the box is constructed. The temperature field data is input into a pre-trained prediction model, and the prediction model outputs the target temperature prediction value of the box in the first time period after the current moment. The prediction model is pre-trained based on the normal operating parameters of standard refrigeration equipment under various operating conditions. Based on the predicted target temperature, a target control quantity is determined through a cost function, and the actuator of the refrigeration equipment is controlled according to the target control quantity. The step of determining the target control variable based on the predicted target temperature using a cost function includes: The constraints corresponding to the actuator, the temperature deviation between the predicted target temperature and the reference target temperature, the temperature variance of each virtual measuring point, and the system energy consumption are determined. Based on the temperature deviation, the temperature variance, and the system energy consumption, a cost function is constructed. For the first time period, the cost function is solved by minimizing the performance index to obtain the target control quantity.

[0006] According to some embodiments of this application, the method further includes: The enclosure structural parameters include at least one of the following: the enclosure volume, wall thickness, insulation material, and door seal structure; The refrigeration system configuration includes at least one of the following: compressor, evaporator, condenser, fan, and electronic expansion valve; The environmental parameters include at least one of the following: ambient temperature and ambient humidity; The thermodynamic dynamic model includes multiple virtual control bodies divided based on the internal space of the box. Each virtual control body corresponds to a heat capacity parameter, and two adjacent virtual control bodies are connected by thermal resistance.

[0007] According to some embodiments of this application, the step of estimating the temperature of virtual measuring points of the enclosure based on the thermodynamic dynamic model and the collected operating parameters of the refrigeration equipment, and constructing temperature field data corresponding to the enclosure, includes: The heat exchange efficiency parameters of the enclosure are determined based on the environmental parameters, and a virtual sensor is constructed based on the heat exchange efficiency parameters and the internal environment of the enclosure, and a data-driven model is constructed for the virtual sensor. The system receives the evaporator temperature, ambient temperature, and internal temperature of certain locations within the chamber from physical sensors. Using the data-driven model and the thermodynamic dynamic model, the temperature of the entire internal space of the chamber is estimated based on the evaporator temperature, the ambient temperature, and the chamber temperature, thereby generating temperature field data corresponding to the chamber.

[0008] According to some embodiments of this application, the step of minimizing the performance index of the cost function for the first time period to obtain the target control quantity includes: For the first time period, the cost function is solved by minimizing the performance index so that the system output in the first time period fits the preset reference value, and the optimal control sequence in the second time period is calculated, wherein the end time of the second time period is earlier than the end time of the first time period. The first control variable in the optimal control sequence is selected as the target control variable for the next time step, and the remaining control variables in the optimal control sequence are discarded.

[0009] According to some embodiments of this application, the cost function is as follows:

[0010] Among them, the The temperature deviation between the predicted target temperature and the reference target temperature is characterized by the following: The temperature variance of each virtual measuring point within the enclosure is characterized. Characterizing the system's energy consumption, the Characterize the control sequence.

[0011] According to some embodiments of this application, the target temperature prediction value includes at least one of the following: equivalent volume temperature of the box, equivalent surface temperature of the food.

[0012] According to some embodiments of this application, the prediction model is trained through the following steps: Auxiliary variables of a standard refrigerator under various operating conditions are obtained, wherein the auxiliary variables include at least one of the following: sensor data, operating status of the refrigeration equipment, and behavioral events; Obtain the dominant variable of the standard refrigerator, wherein the dominant variable includes at least one of the following: refrigerator volume temperature and food surface temperature; The auxiliary variable and the dominant variable are input into the prediction model for training to obtain the trained prediction model.

[0013] According to some embodiments of this application, the method further includes: The operating conditions include at least one of the following: no-load operating condition, half-load operating condition, and full-load operating condition; The sensor data includes at least one of the following: internal temperature, ambient temperature, and evaporator temperature; The operating status of the refrigeration equipment includes at least one of the following: compressor status, fan speed, valve opening, defrosting status, and heater power; The behavioral events include at least one of the following: door open / closed status, cumulative door open duration, and door open frequency.

[0014] According to some embodiments of this application, the method further includes: Obtain the actual measured temperature from the physical sensor; Based on the actual measured temperature, the thermodynamic dynamic model and the prediction model are corrected using the recursive least squares method.

[0015] Secondly, embodiments of this application provide a controller, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the control method for the refrigeration device described in the first aspect when running the computer program.

[0016] Thirdly, embodiments of this application provide a refrigerator that includes the controller described in the second aspect above.

[0017] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions for performing the control method of the refrigeration device as described in the first aspect above.

[0018] Fifthly, embodiments of this application provide a computer program product, including a computer program or computer instructions, the computer program or computer instructions being stored in a computer-readable storage medium, a processor of a computer device reading the computer program or computer instructions from the computer-readable storage medium, and the processor executing the computer program or computer instructions to cause the computer device to perform the control method of the refrigeration device as described in the first aspect above.

[0019] According to the technical solution of the embodiments of this application, at least the following beneficial effects are achieved: First, the embodiments of this application establish a thermodynamic dynamic model of the refrigeration equipment box structure, refrigeration system configuration, and environmental parameters. Based on this thermodynamic dynamic model and combined with the operating parameters of the refrigeration equipment, virtual measuring point temperature estimation is completed. The temperature field distribution inside the box is obtained through virtual sensors, thereby constructing complete temperature field data inside the box. This breaks through the limitation of traditional single-point or multi-point physical sensors that can only collect local temperature data, enabling the refrigeration equipment to sense the global temperature field, thereby coordinating various actuators, eliminating local hot spots or cold spots, and improving the temperature inside the box. Uniformity, adapting to preservation needs and optimizing energy consumption; secondly, the embodiments of this application input temperature field data into a pre-trained prediction model, which can predict the target temperature change trend of the cabinet in the future time period, and then determine the optimal target control quantity through cost function to regulate the refrigeration equipment actuator. It can use future prediction information to adjust the cooling capacity in advance, reduce temperature overshoot and fluctuation, and significantly reduce the temperature fluctuation amplitude inside the cabinet. It can overcome the adjustment lag defect of traditional passive feedback control, suppress temperature overshoot and temperature oscillation, maintain the stability of the temperature inside the cabinet, and thus improve the control accuracy and stability of the refrigeration equipment.

[0020] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0021] The accompanying drawings are used to provide a further understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0022] Figure 1 This is a flowchart of a control method for a refrigeration device provided in one embodiment of this application; Figure 2 yes Figure 1 A flowchart of a sub-step of one embodiment of step S120; Figure 3 yes Figure 1 A flowchart of a sub-step of one embodiment of step S140; Figure 4 yes Figure 3 A flowchart of a sub-step of one embodiment of step S330; Figure 5 This is a flowchart of the training process of a prediction model provided in one embodiment of this application; Figure 6 This is a flowchart of model calibration provided in one embodiment of this application; Figure 7This is a schematic diagram illustrating the specific implementation process of an MPC strategy provided in one embodiment of this application; Figure 8 This is a schematic diagram of the data interaction process between the MPC controller and the enclosure system according to an embodiment of this application; Figure 9 This is a schematic diagram illustrating the training and application process of a prediction model provided in one embodiment of this application; Figure 10 This is a schematic diagram of a controller for performing a control method for a refrigeration device according to an embodiment of this application. Detailed Implementation

[0023] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0024] In the description of this application, it should be understood that the orientation descriptions, such as up, down, front, back, left, right, etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0025] In the description of this application, "several" means one or more, "more than" means two or more, "greater than," "less than," and "exceeding" are understood to exclude the stated number, while "above," "below," and "within" are understood to include the stated number. The use of "first" and "second" in the description is merely for distinguishing technical features and should not be construed as indicating or implying relative importance, or implicitly indicating the number of indicated technical features, or implicitly indicating the order of the indicated technical features.

[0026] In the description of this application, unless otherwise expressly defined, terms such as "setup," "installation," and "connection" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this application in conjunction with the specific content of the technical solution.

[0027] In some applications, refrigerators are widely used in food, pharmaceutical, and scientific research fields, where high uniformity and stability of internal temperature are crucial. Traditional temperature control often relies on sensors placed inside the refrigerator. These sensors collect localized temperatures to reflect the overall temperature of the refrigerator, and the deviation between the sensor readings and the set temperature is used to regulate the compressor and fan operation in a closed-loop system to control the internal temperature. However, this approach has at least the following drawbacks: First, limitations of temperature sensing: Using sensors at specific locations can only measure the temperature at the installation point, resulting in a significant error compared to the actual temperature inside the cabinet. This fails to reflect the distribution of the temperature field within the cabinet, leading to poor temperature uniformity and frequent instances of localized overheating or overcooling. Furthermore, the sensor installation location only reflects the local temperature, making it difficult to characterize the overall temperature of the compartment and the surface temperature of the food, easily causing localized overcooling / overheating, which is detrimental to preservation and energy consumption.

[0028] Second, control lag and variability: In threshold and simple feedback control, adjustment is only made when the temperature deviates from the set value, resulting in lag and a tendency for temperature overshoot and oscillations at local temperature thresholds. Due to the principle of thermal inertia, the sensor's response to the actual room temperature is significantly delayed under disturbances such as ambient temperature, door opening and closing, compressor start and stop, and defrosting, leading to control lag and oscillations.

[0029] Third, sensor failure risk: long-term operation of sensors may cause drift or failure, affecting control reliability and making it difficult to achieve the user-set temperature.

[0030] Fourth, cost and energy waste: The placement of sensors in refrigerator cabinets of different volumes is not fixed. Determining the placement relies on extensive experimental data verification, and changes in placement increase assembly difficulty and cost. Improper placement can easily lead to frequent compressor start-stops or over-operation, increasing refrigerator energy consumption.

[0031] Fifth, fixed parameters and simple control: defrosting, defrosting, damper switching, fan speed regulation, etc. make the thermodynamic process nonlinear and time-varying, and fixed parameter control is difficult to adapt to various working conditions.

[0032] Based on the above, this application proposes a refrigeration device and its control method, controller, medium, and program product, which aims to achieve precise and uniform temperature control of the refrigerator body. It is suitable for solving the problems of limited temperature perception, control lag and variability, high cost and energy consumption caused by relying solely on the arrangement of sensors to control the whole from a local perspective.

[0033] The various embodiments of the control method for the refrigeration system of this application will be further described below with reference to the accompanying drawings.

[0034] like Figure 1 As shown, Figure 1 This is a flowchart of a control method for a refrigeration device provided in one embodiment of this application. The control method for the refrigeration device may include, but is not limited to, steps S110, S120, S130, and S140.

[0035] Step S110: Based on the cabinet structure parameters, refrigeration system configuration and environmental parameters of the refrigeration equipment, establish a thermodynamic dynamic model corresponding to the cabinet of the refrigeration equipment; Step S120: Based on the thermodynamic dynamic model, the temperature of the virtual measuring points of the box is estimated according to the collected operating parameters of the refrigeration equipment, and the temperature field data corresponding to the box is constructed. Step S130: Input the temperature field data into the pre-trained prediction model, and output the target temperature prediction value of the box in the first time period after the current moment through the prediction model. The prediction model is pre-trained based on the normal operating parameters of the standard refrigeration equipment under various working conditions. Step S140: Based on the predicted target temperature, determine the target control quantity through a cost function, and control the actuator of the refrigeration equipment according to the target control quantity.

[0036] In one embodiment, firstly, for step S110, this embodiment can combine the inherent properties of the refrigeration equipment itself with external environmental conditions, such as considering the structural parameters of the cabinet, such as the cabinet volume, wall thickness, and insulation material, as well as the hardware configuration parameters of the refrigeration system, such as the compressor, evaporator, and fan. At the same time, it can also consider real-time external environmental parameters. Based on the changing laws of heat transfer, cabinet thermal inertia, and refrigeration coupling, a thermodynamic dynamic model corresponding to the actual operating characteristics of the refrigeration equipment cabinet can be built. Therefore, this embodiment can understand the heat exchange law and temperature dynamic changes inside the cabinet through the thermodynamic dynamic model.

[0037] Then, for step S120, based on the constructed thermodynamic dynamic model corresponding to the box, various actual operating parameters of the refrigeration equipment are collected, such as evaporator temperature, ambient temperature, internal temperature of some parts of the box, or compressor speed or power. At the same time, combined with the heat transfer law and zone heat transfer characteristics inside the box, the temperature of each virtual measuring point inside the box is estimated. Therefore, the embodiments of this application do not need to rely on a large number of physical temperature sensors to obtain temperature information of different areas of the box, thereby integrating the temperature estimation results of all virtual measuring points, and then constructing temperature field data covering the entire space of the box.

[0038] Next, in step S130, the temperature field data is used as the input basis and input into the prediction model that has been trained under multiple operating conditions in advance. The prediction model is based on a large number of normal operating parameters accumulated by the standard refrigeration equipment under different environments, loads and operating conditions to complete the early learning iteration. It has the ability to analyze the temperature evolution law of the box. Therefore, in this embodiment of the application, by using the prediction model and combining it with real-time temperature field data, it is possible to predict the target temperature of the box within a certain period of time after the current moment, i.e., within the prediction interval, thereby predicting the dynamic change trend of the temperature inside the box in advance.

[0039] Finally, for step S140, based on the predicted future target temperature output by the prediction model, a cost function is constructed using at least one of temperature deviation, temperature uniformity, and operating energy consumption. One or more target optimization calculations are completed by solving the cost function, and the optimal target control quantity is selected and determined. Then, according to the target control quantity, the compressor, fan, valve and other actuators are controlled to achieve dynamic and advanced control and adjustment of the refrigeration operation status.

[0040] It should be noted that, firstly, this embodiment establishes a thermodynamic dynamic model of the refrigeration equipment box structure, refrigeration system configuration, and environmental parameters. Based on this thermodynamic dynamic model and combined with the operating parameters of the refrigeration equipment, virtual measuring point temperature estimation is completed. The temperature field distribution inside the box is obtained through virtual sensors, thereby constructing complete temperature field data inside the box. This breaks through the limitation of traditional single-point or multi-point physical sensors that can only collect local temperature data, enabling the refrigeration equipment to sense the global temperature field, thereby coordinating various actuators, eliminating local hot spots or cold spots, improving the temperature uniformity inside the box, adapting to preservation needs, and optimizing energy consumption. Secondly, this embodiment inputs the temperature field data into a pre-trained prediction model, which can predict the target temperature change trend of the box in the future time period. Then, the optimal target control quantity is determined by solving the cost function to regulate the actuators of the refrigeration equipment. It can use future prediction information to adjust the cooling capacity in advance, reduce temperature overshoot and fluctuations, and significantly reduce the temperature fluctuation amplitude inside the box. This can overcome the adjustment lag defect of traditional passive feedback control, suppress temperature overshoot and temperature oscillation, maintain the temperature stability inside the box, and thus improve the control accuracy and stability of the refrigeration equipment.

[0041] In one embodiment, the enclosure structural parameters include at least one of the following: enclosure volume, wall thickness, insulation material, and door seal structure.

[0042] Specifically, when establishing a thermodynamic dynamic model, the refrigerator's hardware structure information is taken into account, such as the internal volume, wall thickness, type of insulation material, and door sealing structure, among other factors. These structural conditions determine the refrigerator's insulation quality, heat dissipation speed, and heat leakage, thus affecting the rate and pattern of heat changes inside the refrigerator. Therefore, in establishing the thermodynamic dynamic model, this embodiment needs to consider these parameters to ensure that the constructed model more closely reflects the actual characteristics of the refrigerator.

[0043] In one embodiment, the refrigeration system configuration includes at least one of the following: a compressor, an evaporator, a condenser, a fan, and an electronic expansion valve.

[0044] Specifically, when establishing a thermodynamic dynamic model, one or more of the refrigeration components such as the compressor, evaporator, condenser, fan, and electronic expansion valve will be referenced. Since the configuration of these refrigeration systems can determine the cooling strength, heat dissipation speed, air outlet size, and refrigerant delivery efficiency, they can affect the refrigeration effect of the refrigerator. Therefore, when establishing a thermodynamic dynamic model, the embodiments of this application need to incorporate the actual configuration of the refrigeration components into the modeling, so as to realistically restore the refrigeration working state of the refrigerator and better fit the actual operating law of the whole machine.

[0045] In one embodiment, the environmental parameters include at least one of the following: ambient temperature and ambient humidity.

[0046] Specifically, when establishing the thermodynamic dynamic model, this embodiment of the application incorporates one or both of the ambient temperature and ambient humidity as reference conditions. The ambient temperature and humidity affect the refrigerator's heat dissipation rate, the amount of heat entering the refrigerator, and the speed of frost formation, thus interfering with internal temperature changes. Therefore, this embodiment of the application needs to consider these external environmental factors when establishing the thermodynamic dynamic model, enabling the model to adapt to different usage environments.

[0047] In one embodiment, the thermodynamic dynamic model includes multiple virtual control bodies divided based on the internal space of the box, wherein each virtual control body corresponds to a heat capacity parameter, and two virtual control bodies in adjacent positions are connected by thermal resistance.

[0048] Specifically, the internal space of the refrigerator can be divided into several independent virtual control areas, such as the upper, middle, lower, near-door, and inside of the refrigerator, which are virtual control volumes. Each virtual control area is matched with its corresponding heat capacity parameters to correspond to its heat storage and temperature change rate. At the same time, adjacent virtual control areas are interconnected through thermal resistance to simulate the heat conduction and diffusion process between the upper and lower layers, the door, and the depth inside the refrigerator.

[0049] The above-mentioned division into upper, middle, lower, near-door, and inner sides of the refrigerator is based on the significant differences in the actual environment and heating conditions of different areas of the refrigerator. For example, the upper and lower layers have different temperatures due to the sinking of cold air and the effects of cold air circulation; the area near the door is prone to frequent heat leakage and is more susceptible to external air interference; and the inner side of the refrigerator, which is in close contact with the refrigeration pipes and insulation layer, has a more stable heat dissipation and heat storage state. Therefore, the embodiment of this application, based on the above-mentioned division method, can distinguish the temperature differences in different areas of the refrigerator, conform to the actual characteristics such as cold air flow and heat leakage when the door is opened, restore the true temperature field inside the refrigerator, and improve the accuracy of temperature estimation; at the same time, it can also achieve zoned control and reduce the phenomenon of local overcooling or overheating.

[0050] In addition, the heat capacity parameter is used to characterize the heat that each virtual control body can store. The heat capacity parameter of the virtual control body is negatively correlated with the temperature change rate of the virtual control body. For example, if the heat capacity parameter is larger, the temperature change rate is slower; if the heat capacity parameter is smaller, the temperature change rate is faster.

[0051] In addition, thermal resistance is used to characterize the difficulty of heat transfer between virtual control bodies. The thermal resistance between two virtual control bodies is positively correlated with the difficulty of heat transfer between them. For example, the greater the thermal resistance, the greater the difficulty of heat transfer; the smaller the thermal resistance, the easier the heat transfer.

[0052] In addition, such as Figure 2 As shown, Figure 2 yes Figure 1 A flowchart of the sub-steps of one embodiment of step S120. The temperature field construction process in step S120 may include, but is not limited to, steps S210, S220, and S230.

[0053] Step S210: Determine the heat exchange efficiency parameters of the chamber based on the environmental parameters, construct a virtual sensor based on the heat exchange efficiency parameters and the internal environment of the chamber, and construct a data-driven model for the virtual sensor; Step S220: Receive the evaporator temperature, ambient temperature, and internal temperature of some locations inside the chamber collected by the physical sensors. Step S230: Using a data-driven model and a thermodynamic dynamic model, the temperature of the entire internal space of the chamber is estimated based on the evaporator temperature, ambient temperature, and chamber temperature, generating temperature field data corresponding to the chamber.

[0054] In one embodiment, the heat dissipation and heat exchange capacity parameters of the refrigerator are determined based on environmental parameters such as external temperature and humidity. Then, combined with the actual internal spatial environment of the refrigerator, virtual sensors distributed at various locations are constructed. For example, virtual sensors are constructed at different locations such as the upper and lower shelves, door edges, and inner side of the refrigerator. Simultaneously, a data-driven model is built for these virtual sensors to simulate the temperature change patterns in each area. Next, this embodiment combines the data-driven model with a thermodynamic dynamic model for collaborative calculation. Using the evaporator temperature actually collected by the refrigerator, the external ambient temperature, and the measured temperatures at a few points inside the refrigerator as input conditions, and combining the heat transfer and dissipation patterns of different areas of the refrigerator, the real-time temperatures of all areas, including the upper shelf, lower shelf, door edges, and inner side of the refrigerator, are calculated. Finally, the temperature information from all areas is integrated to generate complete internal temperature field data.

[0055] Therefore, the embodiments of this application can make up for the deficiency of insufficient physical sensor placement by combining a small number of physical temperature measurement points with dual-model fusion calculation, accurately simulate the heat exchange and temperature changes in various parts of the box, fully restore the overall temperature distribution inside the box, and solve the problems of partial single-point temperature measurement and incomplete regional temperature perception.

[0056] In addition, such as Figure 3 As shown, Figure 3 yes Figure 1 A flowchart of the sub-steps of one embodiment of step S140. The process of determining the target control quantity in step S140 may include, but is not limited to, steps S310, S320, and S330.

[0057] Step S310: Determine the constraints corresponding to the actuator, the temperature deviation between the predicted target temperature and the reference target temperature, the temperature variance of each virtual measuring point, and the system energy consumption; Step S320: Construct a cost function based on temperature deviation, temperature variance, and system energy consumption; Step S330: For the first time period, minimize the performance index of the cost function to obtain the target control quantity.

[0058] In one embodiment, firstly, the working range of each actuator of the refrigerator is defined to ensure that the compressor speed, fan speed, valve and damper opening degree are all constrained within a reasonable operating range. At the same time, the difference between the target temperature prediction value and the target temperature reference value, the temperature difference between each virtual area of ​​the refrigerator, and the overall operating energy consumption of the equipment are also considered. Then, based on the temperature deviation, temperature variance of each area, and system energy consumption obtained in the previous step, a cost function is constructed to integrate optimization objectives such as temperature stability, temperature uniformity, and machine power consumption to measure the quality of the temperature control scheme. Next, for the predicted time interval after the current moment, the cost function is minimized to calculate the comprehensive target control quantity.

[0059] Therefore, the embodiments of this application can not only ensure the safe operation of components such as compressors and fans, but also take into account the accuracy of temperature inside the chamber, the uniformity of temperature throughout the chamber and the energy consumption of the equipment, so as to achieve advance prediction and adjustment and reduce temperature fluctuations and local temperature differences.

[0060] In addition, such as Figure 4 As shown, Figure 4 yes Figure 3 A flowchart of the sub-steps of one embodiment of step S330. The process of determining the target control quantity in step S330 may include, but is not limited to, steps S410 and S420.

[0061] Step S410: For the first time period, the performance index of the cost function is minimized to make the system output in the first time period fit the preset reference value, and the optimal control sequence in the second time period is calculated, wherein the end time of the second time period is earlier than the end time of the first time period. Step S420: Select the first control quantity in the optimal control sequence as the target control quantity for the next moment, and discard the remaining control quantities in the optimal control sequence.

[0062] In one embodiment, the first time period is a prediction time period, and the second time period is a control time period. The start segment of the prediction time period is the control time period, and the end time of the control time period is earlier than the end time of the prediction time period. First, this embodiment of the application performs a cost function minimization calculation to ensure that the actual operating temperature, energy consumption, and other indicators of the refrigerator are as close as possible to the preset reference values. This allows for the calculation of a complete set of continuous optimal control schemes within the prediction time period, i.e., the optimal control sequence. Then, only the first control variable from the optimal control sequence is selected as the target control variable for the refrigerator at the next moment, and all subsequent control schemes are discarded.

[0063] Therefore, the embodiments of this application can continuously and dynamically update the control scheme by solving the optimal control sequence and executing only the first control quantity in a rolling optimization method. This allows for flexible adaptation to various real-time disturbances such as refrigerator door opening and environmental changes, continuously reducing temperature deviation, balancing temperature difference and energy consumption, and making temperature control more in line with real-time operating conditions.

[0064] In one embodiment, the system output value and the preset reference value during the first time period can be the temperature value inside the box, such as the equivalent volume temperature of the box or the equivalent surface temperature of the food.

[0065] In one embodiment, the cost function is as follows:

[0066] in, Characterizing the temperature deviation between the predicted target temperature and the reference target temperature. Characterize the temperature variance at each virtual measuring point inside the chamber. Characterizes the system's energy consumption. Characterize the control sequence.

[0067] Specifically, It is used to measure the difference between the predicted temperature and the set ideal temperature, ensuring that the overall temperature of the refrigerator does not deviate from the set value. It represents the temperature variance of all virtual temperature measurement areas inside the refrigerator, used to constrain the temperature difference between different locations such as upper and lower layers, door edges, and inner sides, so as to make the temperature inside the refrigerator more uniform. This corresponds to the overall energy consumption of the refrigerator and is used to limit the high-load operation of the refrigeration components to avoid excessive power consumption.

[0068] In one embodiment, the target temperature prediction value includes at least one of the following: the equivalent volume temperature of the box and the equivalent surface temperature of the food.

[0069] Specifically, the equivalent volume temperature of the refrigerator cabinet refers to the overall average temperature of the air in all areas of the cabinet, such as the overall average temperature calculated by combining the air temperatures of the upper, lower, door, and interior areas of the refrigerator; the equivalent surface temperature of the food refers to the actual temperature of the food's surface, such as the average of the surface temperatures of all food items.

[0070] The equivalent volume temperature of the refrigerator compartment is primarily used to control the overall cooling temperature of the refrigerator, responsible for overall temperature control. The equivalent surface temperature of the food is used to determine the actual temperature state of the food, matching preservation needs and rationally adjusting fan speed and defrosting logic. This embodiment combines these two temperature types for prediction, not only controlling the internal air temperature but also considering the food preservation experience, making the adjustments to cooling, fan speed, and defrosting more aligned with actual usage needs.

[0071] In addition, such as Figure 5 As shown, Figure 5 This is a flowchart of the training process of a prediction model provided in one embodiment of this application. The training process of the prediction model may include, but is not limited to, steps S510, S520, and S530.

[0072] Step S510: Obtain auxiliary variables of a standard refrigerator under various operating conditions, wherein the auxiliary variables include at least one of the following: sensor data, operating status of the refrigeration equipment, and behavioral events; Step S520: Obtain the dominant variables of the standard refrigerator, wherein the dominant variables include at least one of the following: refrigerator volume temperature and food surface temperature; Step S530: Input the auxiliary variables and the dominant variables into the prediction model for training to obtain the trained prediction model.

[0073] In one embodiment, firstly, this application embodiment collects various data from a standard refrigerator under various operating conditions, i.e., auxiliary variables, including temperature data detected by various sensors, the operating status of components such as the compressor and fan, and usage behavior events such as opening and closing the door, thus collecting all kinds of real operating data under different operating conditions. Secondly, this application embodiment collects important temperature data from the standard refrigerator as dominant variables, including the overall average temperature of the refrigerator and the equivalent temperature of the food surface. Next, this application embodiment inputs the previously collected auxiliary data and important temperature data into a predictive model for continuous learning and training, allowing the model to identify and obtain the changing patterns between various operating data and the internal temperature and food temperature, ultimately training a mature and usable predictive model.

[0074] In one embodiment, the operating condition includes at least one of the following: no-load operating condition, half-load operating condition, and full-load operating condition.

[0075] Specifically, when training the prediction model, this embodiment of the application collects data under different storage conditions of the refrigerator: empty, half-loaded, and fully loaded. Empty means the refrigerator contains no food, half-loaded means it contains only a portion of food, and fully loaded means it is packed with food. Since different loading levels affect the amount of heat stored inside the refrigerator, the speed of cold air circulation, and the rate of temperature change, this embodiment of the application includes all these conditions in the training scope when training the prediction model. This allows the model to learn to adapt to different storage conditions, accurately predicting temperature changes regardless of the amount of food in the refrigerator, and ensuring that temperature control is more closely aligned with actual usage.

[0076] In one embodiment, the sensor data includes at least one of the following: chamber temperature, ambient temperature, and evaporator temperature.

[0077] Specifically, when training the prediction model, this embodiment of the application collects data from one or more of the following sensors as references: the internal temperature of the refrigerator, the external ambient temperature, and the evaporator temperature. Since these temperatures affect the refrigerator's cooling effect and internal temperature changes, accurately reflecting the working status of the refrigeration components, external environmental interference, and the internal temperature conditions, this embodiment of the application incorporates this sensor data into the model during training. This allows the model to understand the relationships between different temperatures, resulting in more accurate temperature predictions and more realistic temperature control.

[0078] In one embodiment, the operating state of the refrigeration equipment includes at least one of the following: compressor status, fan speed, valve opening, defrosting status, and heater power.

[0079] Specifically, during the training of the prediction model, this embodiment of the application collects various operating status data of the refrigerator, including compressor operation status, fan speed, valve opening and closing, whether it is in defrost mode, and the power of the heating device. Since these operating parameters determine the cooling strength, cold air circulation speed, and defrosting rhythm, and significantly affect the internal temperature changes of the refrigerator, this embodiment of the application incorporates this operating data into the model training. This allows the model to understand the correlation between the device's operating status and temperature changes, thereby more accurately predicting subsequent temperature trends and making temperature control more reasonable.

[0080] In one embodiment, the behavioral event includes at least one of the following: door open / closed state, cumulative door opening duration, and door opening frequency.

[0081] Specifically, during the training of the prediction model, this embodiment of the application collects usage behavior data such as the refrigerator door opening and closing status, cumulative door opening time, and number of door openings. Since frequent door opening and prolonged door opening time allow hot air from outside to enter the refrigerator, causing the internal temperature to rise and the temperature fluctuations to increase, this embodiment of the application needs to incorporate these behavioral events into the model learning process when training the prediction model. This allows the model to learn about the temperature disturbances caused by door opening, adapt to daily usage habits in advance, more accurately predict temperature changes, and achieve more stable temperature control.

[0082] In addition, such as Figure 6 As shown, Figure 6 This is a flowchart illustrating the calibration of a model according to an embodiment of this application. The calibration process may include, but is not limited to, steps S610 and S620.

[0083] Step S610: Obtain the actual measured temperature of the physical sensor; Step S620: Based on the actual measured temperature, the thermodynamic dynamic model and the prediction model are corrected using the recursive least squares method.

[0084] In one embodiment, the present application first reads the actual measured temperature of the refrigerator's physical sensors in real time. This accurate actual measured temperature is used as a reference standard for model correction, comparing it with the predicted temperature calculated by the model. Specifically, the recursive least squares method can be used to continuously compare and correct the actual measured temperature of the sensors, fine-tuning the internal parameters of the thermodynamic dynamic model and the temperature prediction model in real time. This gradually narrows the gap between the model's calculated value and the actual temperature, ensuring that the model continuously matches the actual operating state of the refrigerator and avoiding problems such as deviation and inaccuracy that may occur during long-term model operation.

[0085] Based on the control methods of the refrigeration equipment in the above embodiments, the overall embodiments of the control methods of the refrigeration equipment of this application are presented below.

[0086] In one embodiment, the control method of the refrigeration equipment of this application includes the following steps one to four: Step 1: Construct a thermodynamic dynamic model of the box; Step 2: Reconstruct the temperature field inside the chamber using virtual sensor technology; Step 3: Using the reconstructed temperature field as the state change of the box system, design the MPC controller with the goal of ensuring temperature field uniformity and minimizing temperature deviation and system energy consumption. Step 4: Perform system integration and online calibration.

[0087] In one embodiment, the virtual sensor in step two employs a data-driven model, using evaporator temperature, ambient temperature, and a small number of in-box temperature measurements, and integrates a thermodynamic model to estimate the temperature distribution across the entire field.

[0088] In one embodiment, step two, constructing a virtual sensor, includes: determining heat transfer efficiency parameters based on test data of environmental parameters, and constructing a virtual sensor based on the heat transfer efficiency and the environment.

[0089] In one embodiment, the MPC in step three employs multi-objective optimization, where the uniformity index is defined as the sum of squares of the differences between the temperature at each virtual measuring point and the average temperature.

[0090] In one embodiment, the online calibration in step four uses the recursive least squares method to update the model parameters online, including thermal resistance and thermal capacity parameters.

[0091] In one embodiment, the system further includes a fault diagnosis module that triggers model correction when the deviation between the virtual sensor's estimated value and the physical sensor's measured value exceeds a threshold; when the physical sensor fails, the virtual sensor can replace the physical sensor to perform temperature monitoring.

[0092] In one embodiment, this application also provides a temperature control system for implementing the above method, specifically including: The data acquisition module is used to collect easily measurable process variables; The virtual sensor module is used to estimate the temperature at multiple points inside the chamber and reconstruct the temperature field distribution. The Model Predictive Control (MPC) module is used to calculate the optimal control input based on the temperature field distribution. Actuators, including compressors, fans, electronic expansion valves, and dampers; The online calibration module is used to update model parameters based on feedback from physical sensors.

[0093] In one embodiment, the precise and uniform temperature control method of this application embodiment will be further described below with reference to the accompanying drawings.

[0094] Based on the structural parameters of the refrigeration enclosure (such as volume, wall thickness, insulation material, and door seal structure), the configuration of the refrigeration system (such as compressor, evaporator, condenser, fan, and electronic expansion valve), and environmental conditions, an identification model describing the temperature field distribution and dynamics of the refrigeration system within the enclosure is established; this is known as a thermodynamic dynamic model. The model divides the internal space of the enclosure into multiple virtual control volumes, such as layered or zoned sections. Each virtual control volume has a heat capacity parameter, and adjacent virtual control volumes are connected by thermal resistance, reflecting the dynamic temperature changes at different locations.

[0095] By utilizing easily measurable process variables, including one or more of the following: evaporator inlet and outlet temperatures, compressor speed / power, ambient temperature, and local point temperatures within the chamber, a data-driven model is used to estimate the temperature at each virtual measuring point within the chamber online, reconstructing the complete temperature field distribution. The output of the virtual sensors includes estimated temperatures at multiple points within the chamber and their confidence intervals.

[0096] The MPC strategy utilizes the current state and constraints of the system to predict its state over a finite future timeframe. It then obtains an optimal control sequence by solving the cost function; this finite timeframe is the prediction interval. After obtaining the optimal control sequence, considering system uncertainties and errors, only the initial structure of the optimal control sequence is selected as the input to the system at the next time step. At the next time step, the same control method is used until the desired system state is reached, which is the state defined by the system cost function. A schematic diagram of the specific implementation process of the MPC strategy is shown below. Figure 7 As shown, Figure 7 In the context, time k represents the current time. It is a positive integer greater than or equal to 3.

[0097] Furthermore, the MPC strategy employs a rolling optimization concept. Starting from time k, it solves the optimization problem within the prediction interval (the prediction duration shown in the diagram, i.e., the first time period mentioned above), minimizing the performance index of the cost function (i.e., the output within the prediction duration shown in the diagram, infinitely close to the reference value), and calculates the optimal control sequence within the control interval (the control time domain shown in the diagram, i.e., the second time period mentioned above). Simultaneously, based on the calculated optimal control sequence and the system state model, it predicts changes in the system state. After completing the calculation of the control sequence and the system prediction, only the first term of the control sequence is applied to the system, and the remaining control variables are discarded. At the next time step, k+1, the system enters a new state, and the above operation is repeated starting from this time step.

[0098] In this embodiment, the spatial temperature distribution model constructed in step two serves as the system state; the compressor speed, fan speed, and damper opening serve as the controller's control variables, i.e., the system's input variables; the system's temperature deviation, uniformity, and energy consumption serve as the controller's cost functions, achieving forward-looking, multi-objective optimization control. A schematic diagram of the data interaction process between the MPC controller and the enclosure system is shown below. Figure 8 As shown.

[0099] The cost function of the MPC controller can be expressed as:

[0100] Among them, the first item The second item represents the deviation between the average temperature inside the chamber and the user-set temperature. The third term represents the variance of the temperature at each virtual node within the enclosure. This refers to system energy consumption. In the enclosure system, the compressor speed, fan speed, and valve and damper openings must be kept within their constraints, and the temperature of all virtual nodes must be kept within a safe range (e.g., refrigerated storage: 2~8℃). These component constraints directly affect the cost function.

[0101] The preceding steps completed the establishment of the thermodynamic model, the design of the virtual sensor, and the construction of the MPC controller. This step deploys these modules into the embedded system and ensures their long-term stable operation. Due to various uncertainties in actual operation, the enclosure exhibits changes in heat capacity and thermal resistance with frost aging, and the physical sensors experience zero-point drift after long-term use. Compressor efficiency and fan airflow also change. Periodically using actual measurements from the physical sensors to perform online calibration of the virtual sensor model and the MPC model compensates for model mismatch and parameter drift; this online calibration module enables the system to have adaptive capabilities.

[0102] Therefore, compared with the prior art, the embodiments of this application have the following technical effects: First, significantly improved temperature uniformity: By acquiring the temperature field distribution inside the chamber through virtual sensors, the controller can perceive the global temperature field, thereby coordinating various actuators and eliminating local hot / cold spots. Second, improved control accuracy and stability: The MPC uses future prediction information to adjust the cooling capacity in advance, reducing temperature overshoot and fluctuations, and significantly reducing the amplitude of temperature fluctuations inside the chamber. Third, significant energy saving effect: Precise temperature control avoids overcooling and frequent start-stop, improving compressor operating efficiency and effectively reducing overall energy consumption. Fourth, enhanced system reliability: Virtual sensors can serve as redundant backups for physical sensors; even if some physical sensors fail, the system can still maintain basic temperature control capabilities; at the same time, the online calibration mechanism ensures long-term model accuracy. Fifth, strong adaptability: Applicable to refrigeration chambers of different volumes and operating conditions; deployment can be quickly achieved simply by adjusting model parameters.

[0103] In addition, such as Figure 9 As shown, Figure 9 This is a schematic diagram illustrating the training and application process of a prediction model provided in one embodiment of this application, mainly including the following aspects: First, system composition: Dominant variable (obtained through additional point experiments): Air node (Compartment volume temperature), equivalent surface nodes of food .

[0104] Sensors: At least one compartment temperature sensor (Can be the evaporator side, return / supply air side, or near the wall), ambient temperature Humidity H, evaporator temperature .

[0105] Execution / Operation Status: Compressor Status Pc (Start / Stop / Speed / Power), Fan Speed ​​Nf, Damper Opening Vd, Defrosting Status Df, Heater Power Ph.

[0106] Events and behaviors: Door open / closed status Cumulative opening time Door opening frequency .

[0107] Control actuators: compressor (fixed / inverter), fan, damper, defrost heater, etc.

[0108] Controller and Computing: Microcontrollers / SoCs execute soft measurement algorithms and control strategies.

[0109] Second, soft measurement models, i.e., prediction models: Model training: Under typical operating conditions (such as no load, half load, and full load), collect the above variable data and train the model parameters through deep learning.

[0110] Third, data processing and event detection: Preprocessing: sensor noise reduction, outlier removal, temperature drift correction; smoothing and filtering of current / power signals.

[0111] Event detection: Door magnetic signal edge detection; compressor start / stop determination; defrost cycle identification; rapid temperature jump detection.

[0112] Fourth, real-time correction and control coupling: Output: Compartment volume temperature (For overall temperature control), equivalent surface nodes of food ingredients (Used for preservation and airflow / defrosting strategies).

[0113] Correction strategy: The controller is based on Rather than original Perform setpoint tracking; improve control response in rapidly changing operating conditions and suppress fluctuations in steady state.

[0114] Safety and Boundaries: Set upper / lower limits for the estimated confidence interval; fall back to a safety control strategy in case of abnormal sensing or model mismatch.

[0115] Fifth, calibration and training: Initial parameters can be obtained in a laboratory environment through step response, open-load test, and steady-state energy consumption test.

[0116] Online adaptive updates are performed slowly while ensuring stability; weighted estimation is performed after specific events (such as power-on, self-test, and defrosting completion).

[0117] Therefore, this application establishes a soft measurement model with the actual temperature of the compartment (including the volume temperature of the compartment and the equivalent surface temperature of the food) as the dominant variable and temperature sensor readings and refrigerator operation / environment / load status as auxiliary variables. Through online state estimation, it outputs real-time estimated compartment temperatures and dynamically corrects physical sensor measurements for control decisions, thereby improving temperature control accuracy, response speed, and spatial representativeness, reducing energy consumption, and improving food preservation. It reduces the impact of sensor hysteresis and positional deviation on control, improving set temperature tracking performance and steady-state error. It provides estimates that simultaneously approximate the overall temperature of the compartment and the equivalent surface temperature of the food, enhancing the targeting of preservation strategies. It rapidly corrects temperature estimates under transient conditions such as door opening, defrosting, and heavy loads, reducing overshoot and fluctuations. Through model switching and adaptive identification, it adapts to multiple compartments (refrigeration / freezing / variable temperature compartments), multiple structures (air-cooled / direct-cooled), and diverse user scenarios. It reduces reliance on high-precision physical sensors, decreasing hardware costs and layout complexity.

[0118] Therefore, compared with the prior art, the embodiments of this application have the following technical effects: First, fast response speed: predicting temperature change trends by load status, compensating for sensor lag, and improving control real-time performance. Second, global temperature characterization: comprehensively estimating the overall temperature of the compartment and the surface temperature of the food by integrating multiple variables, reducing local measurement errors. Third, strong adaptability: the model can be updated online to adapt to different usage habits or environmental conditions.

[0119] Based on the control methods of the refrigeration equipment in the above embodiments, the following presents various embodiments of the controller, refrigeration system, computer-readable storage medium, and computer program product of this application.

[0120] like Figure 10 As shown, Figure 10This is a schematic diagram of a controller for performing a control method for a refrigeration device according to an embodiment of this application. The controller 100 implemented in this application includes: a processor 110, a memory 120, and a computer program stored in the memory 120 and executable on the processor 110, wherein... Figure 10 The example uses a processor 110 and a memory 120.

[0121] Processor 110 and memory 120 can be connected via a bus or other means. Figure 10 Taking the example of a connection between China and Israel via a bus.

[0122] Memory 120, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory 120 may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 120 may optionally include remotely located memories 120 relative to processor 110, which can be connected to controller 100 via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0123] Those skilled in the art will understand that Figure 10 The device structure shown does not constitute a limitation on the controller 100 and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0124] exist Figure 10 In the controller 100 shown, the processor 110 can be used to call the control program stored in the memory 120, thereby implementing the control method of the refrigeration device described above. Specifically, the non-transitory software program and instructions required to implement the control method of the refrigeration device in the above embodiment are stored in the memory 120. When executed by the processor 110, the control method of the refrigeration device in the above embodiment is executed.

[0125] It is worth noting that, since the controller 100 of this application embodiment can execute the control method of the refrigeration equipment of any of the above embodiments, the specific implementation method and technical effect of the controller 100 of this application embodiment can refer to the specific implementation method and technical effect of the control method of the refrigeration equipment of any of the above embodiments.

[0126] Furthermore, one embodiment of this application also provides a refrigeration system, which includes the controller described in the above embodiment.

[0127] It is worth noting that, since the refrigeration system of this application embodiment includes the controller of the above embodiment, and the controller of the above embodiment is capable of executing the control method of the refrigeration device of any of the above embodiments, the specific implementation method and technical effect of the refrigeration system of this application embodiment can refer to the specific implementation method and technical effect of the control method of the refrigeration device of any of the above embodiments.

[0128] Furthermore, one embodiment of this application provides a computer-readable storage medium storing computer-executable instructions for performing the control method of the refrigeration device described above.

[0129] It is worth noting that, since the computer-readable storage medium of this application embodiment can execute the control method of the refrigeration device of any of the above embodiments, the specific implementation and technical effects of the computer-readable storage medium of this application embodiment can be referred to the specific implementation and technical effects of the control method of the refrigeration device of any of the above embodiments.

[0130] Furthermore, one embodiment of this application also provides a computer program product, including a computer program or computer instructions, which are stored in a computer-readable storage medium. The processor of a computer device reads the computer program or computer instructions from the computer-readable storage medium and executes the computer program or computer instructions, causing the computer device to perform the aforementioned control method for the refrigeration device.

[0131] It is worth noting that, since the computer program product of this application embodiment can execute the control method of the refrigeration equipment of any of the above embodiments, the specific implementation method and technical effect of the computer program product of this application embodiment can refer to the specific implementation method and technical effect of the control method of the refrigeration equipment of any of the above embodiments.

[0132] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically include computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0133] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0134] In the several embodiments provided in this application, it should be understood that the disclosed systems, instruments, and methods can be implemented in other ways. For example, the instrument embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between instruments or units may be electrical, mechanical, or other forms. Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, i.e., they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0135] It should also be understood that the various implementation methods provided in this application can be combined arbitrarily to achieve different technical effects.

[0136] The above provides a detailed description of the preferred embodiments of this application. However, this application is not limited to the above-described embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A control method for a refrigeration device, characterized in that, The method includes: Based on the cabinet structure parameters, refrigeration system configuration, and environmental parameters of the refrigeration equipment, a thermodynamic dynamic model corresponding to the cabinet of the refrigeration equipment is established. Based on the thermodynamic dynamic model, the temperature of the virtual measuring points of the box is estimated according to the collected operating parameters of the refrigeration equipment, and temperature field data corresponding to the box is constructed. The temperature field data is input into a pre-trained prediction model, and the prediction model outputs the target temperature prediction value of the box in the first time period after the current moment. The prediction model is pre-trained based on the normal operating parameters of standard refrigeration equipment under various operating conditions. Based on the predicted target temperature, a target control quantity is determined through a cost function, and the actuator of the refrigeration equipment is controlled according to the target control quantity. The step of determining the target control variable based on the predicted target temperature using a cost function includes: The constraints corresponding to the actuator, the temperature deviation between the predicted target temperature and the reference target temperature, the temperature variance of each virtual measuring point, and the system energy consumption are determined. Based on the temperature deviation, the temperature variance, and the system energy consumption, a cost function is constructed. For the first time period, the cost function is solved by minimizing the performance index to obtain the target control quantity.

2. The method according to claim 1, characterized in that: The enclosure structural parameters include at least one of the following: the enclosure volume, wall thickness, insulation material, and door seal structure; The refrigeration system configuration includes at least one of the following: compressor, evaporator, condenser, fan, and electronic expansion valve; The environmental parameters include at least one of the following: ambient temperature and ambient humidity; The thermodynamic dynamic model includes multiple virtual control bodies divided based on the internal space of the box. Each virtual control body corresponds to a heat capacity parameter, and two adjacent virtual control bodies are connected by thermal resistance.

3. The method according to claim 1, characterized in that, Based on the thermodynamic dynamic model, the temperature of the virtual measuring points of the enclosure is estimated according to the collected operating parameters of the refrigeration equipment, and temperature field data corresponding to the enclosure is constructed, including: The heat exchange efficiency parameters of the enclosure are determined based on the environmental parameters, and a virtual sensor is constructed based on the heat exchange efficiency parameters and the internal environment of the enclosure, and a data-driven model is constructed for the virtual sensor. The system receives the evaporator temperature, ambient temperature, and internal temperature of certain locations within the chamber from physical sensors. Using the data-driven model and the thermodynamic dynamic model, the temperature of the entire internal space of the chamber is estimated based on the evaporator temperature, the ambient temperature, and the chamber temperature, thereby generating temperature field data corresponding to the chamber.

4. The method according to claim 1, characterized in that, For the first time period, minimizing the performance index of the cost function to obtain the target control quantity includes: For the first time period, the cost function is solved by minimizing the performance index so that the system output in the first time period fits the preset reference value, and the optimal control sequence in the second time period is calculated, wherein the end time of the second time period is earlier than the end time of the first time period. The first control variable in the optimal control sequence is selected as the target control variable for the next time step, and the remaining control variables in the optimal control sequence are discarded.

5. The method according to claim 4, characterized in that, The cost function is given by the following formula: Among them, the The temperature deviation between the predicted target temperature and the reference target temperature is characterized by the following: The temperature variance of each virtual measuring point within the enclosure is characterized. Characterizing the system's energy consumption, the Characterize the control sequence.

6. The method according to claim 1, characterized in that, The target temperature prediction value includes at least one of the following: the equivalent volume temperature of the box, and the equivalent surface temperature of the food.

7. The method according to claim 1, characterized in that, The prediction model is trained through the following steps: Auxiliary variables of a standard refrigerator under various operating conditions are obtained, wherein the auxiliary variables include at least one of the following: sensor data, operating status of the refrigeration equipment, and behavioral events; Obtain the dominant variable of the standard refrigerator, wherein the dominant variable includes at least one of the following: refrigerator volume temperature and food surface temperature; The auxiliary variable and the dominant variable are input into the prediction model for training to obtain the trained prediction model.

8. The method according to claim 7, characterized in that: The operating conditions include at least one of the following: no-load operating condition, half-load operating condition, and full-load operating condition; The sensor data includes at least one of the following: internal temperature, ambient temperature, and evaporator temperature; The operating status of the refrigeration equipment includes at least one of the following: compressor status, fan speed, valve opening, defrosting status, and heater power; The behavioral events include at least one of the following: door open / closed status, cumulative door open duration, and door open frequency.

9. The method according to claim 1, characterized in that, The method further includes: Obtain the actual measured temperature from the physical sensor; Based on the actual measured temperature, the thermodynamic dynamic model and the prediction model are corrected using the recursive least squares method.

10. A controller, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, performs a control method for a refrigeration device as described in any one of claims 1 to 9.

11. A refrigeration device, characterized in that, Includes the controller as described in claim 10.

12. A computer-readable storage medium, characterized in that: The device stores computer-executable instructions for performing a control method for a refrigeration device as described in any one of claims 1 to 9.

13. A computer program product, comprising a computer program or computer instructions, characterized in that, The computer program or the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer program or the computer instructions from the computer-readable storage medium and executes the computer program or the computer instructions, causing the computer device to perform the control method of the refrigeration device as described in any one of claims 1 to 9.

Images