Refrigerator and defrosting control method thereof
By calculating the temperature difference and parameter prediction models of refrigeration and freezing, and dynamically adjusting the defrost strategy, the problem of inaccurate defrost control in refrigerators is solved, and the refrigerator's refrigeration efficiency and intelligence are improved.
Patent Information
- Application Number
- CN202510331280.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-19
- Publication Date
- 2025-07-04
AI Technical Summary
The existing refrigerator defrost control methods cannot accurately determine the defrost timing, resulting in unnecessary defrost operations increasing energy consumption and affecting refrigeration efficiency.
By calculating the temperature difference between refrigeration and freezing and combining the parameter prediction model, the defrost strategy is dynamically adjusted according to the real-time temperature and compressor status, and the timing of defrost is accurately judged.
It realizes the accuracy and intelligence of defrost control, reduces unnecessary defrost operations, and improves the refrigeration efficiency and intelligence of the refrigerator.
Smart Images
Figure CN120252260A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of refrigerators, and in particular to a refrigerator and a defrosting control method thereof. Background Art
[0002] With the progress of technology, the functions and performance of refrigerators have been continuously improved, especially in terms of energy conservation, intelligent control, and temperature management. However, during long-term operation of the refrigerator, the surface of the evaporator is prone to frosting, resulting in a decrease in refrigeration efficiency, an increase in energy consumption, and even affecting the freshness preservation effect of food. Therefore, how to effectively control defrosting has become an important issue in refrigerator design. Traditional refrigerator defrosting control methods are usually based on timed defrosting or defrosting according to the evaporator temperature. The disadvantage of timed defrosting is that regardless of the actual usage of the refrigerator, defrosting will be carried out at fixed time intervals, which may lead to unnecessary defrosting operations and increase energy consumption. Although the defrosting method based on the evaporator temperature improves the accuracy of defrosting to a certain extent, it still cannot fully consider the real-time temperature changes in the refrigerating chamber and the freezing chamber, resulting in inaccurate judgment of the defrosting timing. Summary of the Invention
[0003] The purpose of the embodiments of the present invention is to provide a refrigerator and a defrosting control method thereof. By calculating the refrigerating temperature difference and the freezing temperature difference, and combining with the reference temperature difference threshold output by a preset parameter prediction model, the defrosting timing is intelligently judged, realizing more accurate and efficient defrosting control, which not only improves the refrigeration efficiency of the refrigerator but also reduces energy consumption.
[0004] To achieve the above purpose, the embodiments of the present invention provide a refrigerator, including:
[0005] A cabinet in which at least one storage chamber is formed, and the storage chamber includes at least a refrigerating chamber and a freezing chamber;
[0006] A refrigeration system for providing cooling capacity for the refrigerator, and the refrigeration system includes a compressor, a condenser, and an evaporator connected by pipelines;
[0007] Temperature sensors, including a refrigerating chamber temperature sensor for obtaining the real-time refrigerating temperature, a freezing temperature sensor for obtaining the real-time freezing temperature, and an evaporator temperature sensor for obtaining the real-time evaporation temperature;
[0008] A controller configured to:
[0009] Obtain the real-time refrigerating temperature, the real-time freezing temperature, and the real-time evaporation temperature of the refrigerator in the refrigeration mode;
[0010] Calculate the refrigerating temperature difference between the real-time refrigerating temperature and the real-time evaporation temperature, and calculate the freezing temperature difference between the real-time freezing temperature and the real-time evaporation temperature;
[0011] Compare the refrigerating temperature difference and the freezing temperature difference with a reference temperature difference threshold output by a preset parameter prediction model, and when the comparison result meets the preset defrosting condition, control the refrigerator to enter the defrosting mode.
[0012] The above technical solution has the following advantages or beneficial effects: It can accurately calculate the temperature difference based on the actual real-time refrigerating temperature, real-time freezing temperature and real-time evaporation temperature of the refrigerator, and compare it with the reference temperature difference threshold to judge the defrosting timing. The defrosting is started only when the actual defrosting condition is reached, avoiding unnecessary defrosting operations and reducing the cold loss caused by the stop of refrigeration during the defrosting process, thereby effectively improving the overall refrigeration efficiency of the refrigerator. In addition, by introducing a parameter prediction model, the refrigerator has a certain intelligent judgment ability and can dynamically adjust the defrosting strategy according to the actual operation data, rather than simply operating according to the preset time. This improves the intelligent level of the refrigerator.
[0013] In some embodiments of the present application, the input data of the parameter prediction model during application includes the real-time refrigerating temperature, real-time freezing temperature, real-time evaporation temperature, real-time operating state and real-time operating time of the compressor.
[0014] The above technical solution has the following advantages or beneficial effects: By comprehensively considering the real-time refrigerating temperature, real-time freezing temperature and real-time evaporation temperature, the refrigerating temperature difference and the freezing temperature difference can be accurately calculated, and the actual frosting condition inside the refrigerator can be more accurately reflected. Combining the real-time operating state (running or stopped) and real-time operating time of the compressor, the refrigeration working condition of the refrigerator can be further understood, because the operating state and duration of the compressor are closely related to the frosting speed and degree. The input of these multi-dimensional real-time data enables the parameter prediction model to more accurately judge whether the defrosting condition is met, avoiding misjudgment or missed judgment that may occur in the traditional simple judgment method, and realizing accurate defrosting.
[0015] In some embodiments of the present application, the reference temperature difference threshold includes a refrigerating temperature difference threshold and a freezing temperature difference threshold, and the defrosting condition includes:
[0016] The refrigerating temperature difference is greater than the refrigerating temperature difference threshold and lasts for a first duration; or, the freezing temperature difference is greater than the freezing temperature difference threshold and lasts for a second duration.
[0017] The above technical solution has the following advantages or beneficial effects: By clearly distinguishing between the refrigerating temperature difference threshold and the freezing temperature difference threshold, it is possible to accurately control according to the different temperature characteristics and frosting conditions of the refrigerator's refrigerating and freezing compartments. Since the normal operating temperature ranges of the refrigerating and freezing compartments are different, and the speed and degree of frosting also vary, setting the thresholds separately makes the defrost judgment more in line with the actual needs of each compartment. At the same time, by combining the condition that the temperature difference is greater than the threshold and lasts for a certain period of time, false defrost judgments caused by short-term temperature fluctuations are avoided, ensuring that defrosting is only initiated when the frosting reaches a certain level and continuously affects the refrigeration effect of the refrigerator, thus achieving the accuracy of defrost control.
[0018] In some embodiments of the present application, the defrosting condition further includes:
[0019] The refrigerating startup temperature is greater than a preset refrigerating startup temperature threshold and lasts for a third period of time; or, the freezing startup temperature is greater than a preset freezing startup temperature threshold and lasts for a fourth period of time.
[0020] The above technical solution has the following advantages or beneficial effects: In addition to judging the defrosting condition based on the temperature difference, adding conditions related to the startup temperature makes the defrosting judgment more comprehensive. The startup temperature reflects the actual temperature situation inside the refrigerator when the compressor starts. When the refrigerating or freezing startup temperature continuously exceeds the preset threshold, it indicates that the temperature inside the refrigerator is relatively high, which may be due to severe frosting affecting the refrigeration effect. Combining this condition can more accurately capture the situation where defrosting is required, avoiding missed judgments that may occur by simply relying on the temperature difference judgment, and further improving the accuracy of defrost control.
[0021] In some embodiments of the present application, when the comparison result meets the preset defrosting condition, the controller is further configured to:
[0022] After exiting the defrosting mode, obtain the reference evaporation temperature;
[0023] When the reference evaporation temperature is less than the target evaporation temperature, update the target evaporation temperature with the reference evaporation temperature;
[0024] Input the updated target evaporation temperature into the parameter prediction model to update and iterate the parameter prediction model.
[0025] The above technical solution has the following advantages or beneficial effects: Inputting the updated target evaporation temperature into the parameter prediction model enables the model to continuously incorporate new data that is more in line with the actual operating conditions. As time goes by and operating data accumulates, the parameter prediction model can dynamically adjust its own parameters according to the changes in the evaporation temperature during the actual operation of the refrigerator, so as to better adapt to different operating environments and conditions, continuously optimize the prediction ability of the defrosting condition, further improve the accuracy and reliability of the prediction, and reduce the occurrence of false judgments and missed judgments.
[0026] In some embodiments of the present application, the initial construction process of the target evaporation temperature includes:
[0027] Obtain the initial evaporation temperature detected by the refrigerator within m minutes after exiting the defrost mode n times; where n is greater than or equal to 2, and m is less than or equal to a preset duration threshold;
[0028] Select the minimum value from the n initial evaporation temperatures as the initial target evaporation temperature.
[0029] The above technical solution has the following advantages or beneficial effects: Since the evaporation temperature within a short time after defrosting can reflect the refrigeration capacity of the refrigerator under good operating conditions to a certain extent, selecting the minimum value as the initial target evaporation temperature helps to more strictly control the refrigeration effect of the refrigerator and lay a foundation for subsequent precise control. Selecting the minimum value as the initial target evaporation temperature can obtain a relatively low and representative value, which provides a reasonable initial reference standard for subsequent defrost control and parameter prediction models. Based on this reasonable initial value, the model can better fit the operating rules of the refrigerator during subsequent learning and iteration, improving the prediction accuracy and reliability of the model.
[0030] In some embodiments of the present application, the input data during the training of the parameter prediction model includes several groups of corresponding refrigeration temperatures, freezing temperatures, evaporation temperatures, operating states, and operating times of the compressor of the refrigerator when the defrost mode is satisfied.
[0031] The above technical solution has the following advantages or beneficial effects: Rich and relevant input data enables the model to learn more features and rules related to defrosting. By analyzing the relationships between different refrigeration temperatures, freezing temperatures, and evaporation temperatures, as well as their associations with the operating state and time of the compressor, the model can discover when what temperature combinations and compressor working states occur, the refrigerator is more likely to reach the defrost condition. In this way, when facing new operating data, the model can more accurately judge whether defrosting is required based on the knowledge learned, reducing misjudgments and missed judgments, and improving the prediction accuracy. By integrating these data, the parameter prediction model can comprehensively and accurately understand the actual operating state of the refrigerator when the defrost mode is satisfied, providing a solid data foundation for accurately predicting the defrost condition.
[0032] To achieve the above object, an embodiment of the present invention provides a defrost control method for a refrigerator, including:
[0033] Obtain the real-time refrigeration temperature, real-time freezing temperature, and real-time evaporation temperature of the refrigerator in the refrigeration mode;
[0034] Calculate the refrigeration temperature difference between the real-time refrigeration temperature and the real-time evaporation temperature, and calculate the freezing temperature difference between the real-time freezing temperature and the real-time evaporation temperature;
[0035] Compare the refrigeration temperature difference and the freezing temperature difference with the reference temperature difference threshold output by a preset parameter prediction model, and when the comparison result meets the preset defrosting condition, control the refrigerator to enter the defrosting mode.
[0036] The above technical solution has the following advantages or beneficial effects: It can accurately calculate the temperature difference based on the actual real-time refrigeration temperature, real-time freezing temperature and real-time evaporation temperature of the refrigerator, and compare it with the reference temperature difference threshold to judge the defrosting timing. The defrosting is only started when the real defrosting condition is reached, avoiding unnecessary defrosting operations and reducing the cold loss caused by the refrigeration stop during the defrosting process, thus effectively improving the overall refrigeration efficiency of the refrigerator. In addition, by introducing a parameter prediction model, the refrigerator is equipped with a certain intelligent judgment ability and can dynamically adjust the defrosting strategy according to the actual operation data, rather than simply operating according to the preset time. This improves the intelligent level of the refrigerator.
[0037] In some embodiments of the present application, when the comparison result meets the preset defrosting condition, the method further includes:
[0038] After exiting the defrosting mode, obtain the reference evaporation temperature;
[0039] When the reference evaporation temperature is less than the target evaporation temperature, update the target evaporation temperature with the reference evaporation temperature;
[0040] Input the updated target evaporation temperature into the parameter prediction model to update and iterate the parameter prediction model.
[0041] The above technical solution has the following advantages or beneficial effects: Inputting the updated target evaporation temperature into the parameter prediction model enables the model to continuously incorporate new data that is more in line with the actual operating conditions. As time goes by and the operating data accumulates, the parameter prediction model can dynamically adjust its own parameters according to the change of the evaporation temperature in the actual operation of the refrigerator, so as to better adapt to different operating environments and conditions, continuously optimize the prediction ability of the defrosting conditions, further improve the accuracy and reliability of the prediction, and reduce the occurrence of misjudgment and missed judgment.
[0042] In some embodiments of the present application, the initial construction process of the target evaporation temperature includes:
[0043] Obtain the initial evaporation temperature detected by the refrigerator within m minutes after n times of exiting the defrosting mode; where n is greater than or equal to 2 and m is less than or equal to the preset duration threshold;
[0044] Select the minimum value from the n initial evaporation temperatures as the initial target evaporation temperature.
[0045] The above technical solution has the following advantages or beneficial effects: Since the evaporation temperature within a short time after defrosting can to a certain extent reflect the refrigeration capacity of the refrigerator under good operating conditions, selecting the minimum value as the initial target evaporation temperature helps to more strictly control the refrigeration effect of the refrigerator and lay a foundation for subsequent precise control. Selecting the minimum value as the initial target evaporation temperature can obtain a relatively low and representative value, which provides a reasonable initial reference standard for subsequent defrost control and parameter prediction models. Based on this reasonable initial value, the model can better fit the operating law of the refrigerator in subsequent learning and iteration, improving the prediction accuracy and reliability of the model. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] Figure 1 is a schematic diagram of the external structure of a refrigerator provided by an embodiment of the present invention;
[0047] Figure 2 is a schematic diagram of the internal structure of a refrigerator provided by an embodiment of the present invention;
[0048] Figure 3 is a schematic diagram of the structure of a refrigeration system in a refrigerator provided by an embodiment of the present invention;
[0049] Figure 4 is a schematic diagram of the connection of a controller and its control components provided by an embodiment of the present invention;
[0050] Figure 5 is the first working flowchart of the controller provided by an embodiment of the present invention;
[0051] Figure 6 is the training flowchart of the parameter prediction model provided by an embodiment of the present invention;
[0052] Figure 7 is the second working flowchart of the controller provided by an embodiment of the present invention;
[0053] Figure 8 is the third working flowchart of the controller provided by an embodiment of the present invention;
[0054] Figure 9 is the fourth working flowchart of the controller provided by an embodiment of the present invention;
[0055] Figure 10 is the flowchart of a defrost control method for a refrigerator provided by an embodiment of the present invention.
[0056] Among them, 100 is a refrigerator; 10 is a touch screen; 20 is a controller; 30 is a memory; 40 is a temperature sensor; 401 is a refrigerating temperature sensor; 402 is a freezing temperature sensor; 403 is an evaporation temperature sensor; 50 is a damper; 60 is a damper heater; 70 is a fan; 111 is a refrigerating chamber; 112 is a freezing chamber; 101 is a compressor; 102 is an evaporator; 103 is a capillary tube; 104 is a condenser; 105 is an ambient humidity sensor; 106 is an ambient temperature sensor. Detailed implementation manners
[0057] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0058] In the description of the present application, it should be understood that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present application.
[0059] The terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.
[0060] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected, or indirectly connected through an intermediate medium, and it may be the internal communication of two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific situations.
[0061] See Figure 1 , Figure 1FIG. 0 is a schematic external structure diagram of a refrigerator 100 provided by an embodiment of the present invention. The refrigerator 100 in this embodiment has an approximate cuboid shape. The refrigerator includes a box body defining a storage space and one or more door bodies provided at an opening of the box body. Among them, the door body includes a door body outer shell located outside the box body, a door body inner liner located inside the box body, an upper end cover, a lower end cover, and a heat insulation layer located between the door body outer shell, the door body inner liner, the upper end cover, and the lower end cover; generally, the heat insulation layer is filled with foaming material. The box body is provided with a chamber, and the chamber includes a component storage chamber for placing components in the refrigerator, such as a compressor compartment, etc., and also includes a storage space for storing foods, etc.
[0062] See Figure 2 , Figure 2 FIG. 7 is a schematic internal structure diagram of a refrigerator provided by an embodiment of the present invention. The storage space can be partitioned into multiple storage compartments. According to different uses, the storage compartments can be configured as a refrigerating compartment 111 and a freezing compartment 112, and can also include a variable temperature compartment, a vacuum drawer, a humidity-preserving drawer, etc. Each storage compartment corresponds to one or more door bodies. For example, in Figure 2 , the upper storage compartment is provided with double door bodies. Among them, the door body can be pivotally arranged at the opening of the box body, or can be a drawer-type opening to achieve drawer-type storage.
[0063] See Figure 3 , Figure 3Schematic diagram of the structure of the refrigeration system in the refrigerator 100 provided by the embodiment of the present invention. The refrigeration system includes a compressor 101, an evaporator 102, a drying filter (not shown in the figure), a capillary tube 103, a condenser 104, and a gas-liquid separator (not shown in the figure). The working process of the refrigeration system includes a compression process, a condensation process, a throttling process, and an evaporation process. Among them, the compression process is as follows: Plug in the power cord of the refrigerator. When the contacts of the thermostat are closed, the compressor 101 starts to work. The low-temperature and low-pressure refrigerant is sucked into the compressor 101 and compressed into a high-temperature and high-pressure superheated gas in the cylinder of the compressor 101, and then discharged into the condenser 104; the condensation process is as follows: The high-temperature and high-pressure refrigerant gas dissipates heat through the condenser 104, and the temperature continuously drops, gradually being cooled into a normal-temperature and high-pressure saturated vapor, and further cooled into a saturated liquid, and the temperature no longer drops. At this time, the temperature is called the condensation temperature, and the pressure of the refrigerant is almost unchanged during the entire condensation process; the throttling process is as follows: The condensed refrigerant saturated liquid flows into the capillary tube 103 after being filtered by the drying filter to remove moisture and impurities, and throttles and depressurizes through it, and the refrigerant becomes a normal-temperature and low-pressure wet vapor; the evaporation process is as follows: The normal-temperature and low-pressure wet vapor starts to absorb heat and vaporize in the evaporator 102, not only reducing the temperature of the evaporator 102 and its surroundings, but also turning the refrigerant into a low-temperature and low-pressure gas. The refrigerant coming out of the evaporator 102 returns to the compressor 101 again after passing through the gas-liquid separator. Repeating the above process, the heat in the refrigerator is transferred to the air outside the box, achieving the purpose of refrigeration.
[0064] See Figure 4 , Figure 4 is a schematic diagram of the connection of the controller and its control components provided by the embodiment of the present invention. The refrigerator 100 includes:
[0065] A touch screen 10 is provided on one of the cabinet doors. The touch screen 10 is used to display prompt information and receive the touch operations of the user;
[0066] A controller 20 is provided in the cabinet, and is used to receive the detection data of a temperature sensor 40, an ambient humidity sensor 105, and an ambient temperature sensor 106, and control the opening and closing of a damper 50, a damper heater 60, a blower 70, and a compressor 101;
[0067] A memory 30 is used to store the operating parameters of the refrigerator, such as the operating parameters including: the defrosting temperature of the evaporator detected by the defrosting sensor, the temperature of the storage compartment detected by the temperature sensor, the blower speed, the compressor speed, the defrosting time, etc.;
[0068] The temperature sensor 40 includes a refrigerating temperature sensor 401, a freezing temperature sensor 402, and an evaporation temperature sensor 403. The refrigerating temperature sensor 401 is disposed in the refrigerating chamber for obtaining the temperature of the refrigerating chamber. The freezing temperature sensor 402 is disposed in the freezing chamber for obtaining the temperature of the freezing chamber. The evaporation temperature sensor 403 is disposed on one side of the evaporator for obtaining the evaporation temperature of the evaporator.
[0069] The air damper 50 includes a refrigerating air damper and a freezing air damper. The refrigerating air damper is disposed in the air duct communicating with the refrigerating chamber. When the refrigerating air damper is opened, the cold air in the air duct can smoothly enter the refrigerating chamber. When the refrigerating air damper is closed, the cold air in the air duct cannot enter the refrigerating chamber. The freezing air damper is disposed in the air duct communicating with the freezing chamber. When the freezing air damper is opened, the cold air in the air duct can smoothly enter the freezing chamber. When the freezing air damper is closed, the cold air in the air duct cannot enter the freezing chamber.
[0070] The air damper heater 60 is disposed on one side of the air damper 50 (each of the refrigerating air damper and the freezing air damper corresponds to an air damper heater). After the compressor works for a period of time (about 8 - 10 hours), the air damper 50 may also frost. If defrosting is not performed, the frost will become thicker and thicker, causing the air damper 50 to not rotate (unable to close or open), affecting the air supply to the refrigerating chamber / freezing chamber. After the air damper heater 60 is turned on, the frost layer can be melted in time.
[0071] The blower 70 is disposed in the air duct of the refrigerator for enabling air to enter the evaporator for heat exchange and sending the air after heat release to the storage chamber of the refrigerator.
[0072] The ambient humidity sensor 105 is disposed outside the refrigerator body for detecting the ambient humidity of the environment where the refrigerator is located. After sending this ambient humidity to the controller, the controller can adjust its operating parameters according to the ambient humidity.
[0073] The ambient temperature sensor 106 is disposed outside the refrigerator body for detecting the ambient temperature of the environment where the refrigerator is located. After sending this ambient temperature to the controller, the controller can adjust its operating parameters according to the ambient temperature.
[0074] Specifically, the controller in the refrigerator is configured to: obtain the real-time refrigerating temperature, real-time freezing temperature, and real-time evaporation temperature in the refrigeration mode of the refrigerator; calculate the refrigerating temperature difference between the real-time refrigerating temperature and the real-time evaporation temperature, and calculate the freezing temperature difference between the real-time freezing temperature and the real-time evaporation temperature; compare the refrigerating temperature difference and the freezing temperature difference with the reference temperature difference threshold output by the preset parameter prediction model, and when the comparison result meets the preset defrosting condition, control the refrigerator to enter the defrosting mode.
[0075] Exemplarily, refer to Figure 5 ,Figure 5 This is the first working flowchart of the controller provided by an embodiment of the present invention. The controller is configured to execute steps S11 to S16. The reference temperature difference thresholds include a refrigerating temperature difference threshold and a freezing temperature difference threshold. Assume that after comparing the refrigerating temperature difference and the freezing temperature difference with their respective reference temperature difference thresholds, it is determined that the defrosting condition is met. Since the defrosting condition related to the refrigerating temperature difference is met, after receiving the signal, the control system of the refrigerator controls the refrigerator to enter the defrosting mode. In the defrosting mode, the refrigerator stops refrigerating and starts the heating device to melt the frost layer on the evaporator. When the defrosting is completed, the refrigerator exits the defrosting mode and re-enters the refrigerating mode, and starts to obtain the real-time refrigerating temperature, real-time freezing temperature, and real-time evaporation temperature again, repeating the processes of calculating the temperature difference, comparing the temperature difference, and judging the defrosting condition to achieve dynamic and intelligent control of the refrigerator defrosting. In practical applications, the parameter prediction model will continuously update and optimize parameters such as the reference temperature difference threshold according to the operation data of the refrigerator, making the defrosting control more accurate and reasonable to adapt to different usage scenarios and individual differences of the refrigerator.
[0076] In the embodiment of the present invention, it is possible to accurately calculate the temperature difference based on the actual real-time refrigerating temperature, real-time freezing temperature, and real-time evaporation temperature of the refrigerator, and compare it with the reference temperature difference threshold to judge the defrosting timing. The defrosting is started only when the defrosting condition is truly met, avoiding unnecessary defrosting operations and reducing the cold loss caused by the stop of refrigeration during the defrosting process, thereby effectively improving the overall refrigeration efficiency of the refrigerator. In addition, by introducing the parameter prediction model, the refrigerator is equipped with a certain intelligent judgment ability, and can dynamically adjust the defrosting strategy according to the actual operation data, rather than simply operating according to the preset time. This improves the intelligent level of the refrigerator.
[0077] Specifically, the input data of the parameter prediction model during application includes the real-time refrigerating temperature, real-time freezing temperature, real-time evaporation temperature, real-time operating state, and real-time operating time of the compressor.
[0078] Exemplarily, the real-time operating state refers to the current working state of the compressor, usually including states such as running, stopping, and starting. For example, "running" means that the compressor is working normally, compressing the refrigerant, so that the refrigeration system can circulate to achieve the refrigeration effect; "stopping" means that the compressor stops working and no longer compresses the refrigerant; "starting" means that the compressor starts from the stopped state and enters the operation preparation stage. By monitoring the real-time operating state of the compressor, the working condition of the refrigeration system can be understood, whether the compressor is operating normally can be judged, and whether corresponding maintenance or adjustment is required. The real-time operating time refers to the time that the compressor has continuously run from the current start time to the current time.
[0079] In the embodiments of the present invention, by comprehensively considering the real-time refrigeration temperature, real-time freezing temperature, and real-time evaporation temperature, the refrigeration temperature difference and freezing temperature difference can be accurately calculated, and the actual frosting condition inside the refrigerator can be more precisely reflected. Combining the real-time operating state (running or stopped) and real-time operating time of the compressor, the refrigeration working condition of the refrigerator can be further understood, because the operating state and duration of the compressor are closely related to the frosting speed and degree. The input of these multi-dimensional real-time data enables the parameter prediction model to more accurately determine whether the defrosting condition is met, avoiding misjudgment or missed judgment that may occur in the traditional simple judgment method, and achieving precise defrosting.
[0080] Specifically, the input data during the training of the parameter prediction model includes several groups of refrigeration temperatures, freezing temperatures, evaporation temperatures, operating states, and operating times of the compressor corresponding to the refrigerator when the defrosting mode is satisfied.
[0081] In the embodiments of the present invention, a training process of a parameter prediction model is provided. Refer to Figure 6 , Figure 6 which is the training flow chart of the parameter prediction model provided by the embodiments of the present invention, including the following steps:
[0082] S101. Data collection:
[0083] During the normal operation of the refrigerator, collect a large amount of data on the refrigeration temperature, freezing temperature, evaporation temperature, operating state of the compressor (such as running or stopped state information, which can be represented in forms such as 0 and 1), and operating time corresponding to the refrigerator when the defrosting mode is satisfied. Ensure the accuracy and integrity of the data, and record information such as the time stamp corresponding to each data point for subsequent processing. To improve the diversity and generalization ability of the data, data collection can be carried out under different ambient temperatures, different refrigerator loads (such as storing different quantities and types of items), etc.
[0084] S102. Data preprocessing:
[0085] Clean the collected data to remove outliers and noisy data. For example, check whether the refrigeration temperature, freezing temperature, and evaporation temperature are within a reasonable range, and eliminate or correct the obviously unreasonable data (such as temperature values outside the normal operating temperature range of the refrigerator). Format the operating status and operating time data of the compressor to ensure that it can be correctly understood and processed by the model. For example, convert the operating status into a numerical variable (such as 0 for shutdown and 1 for running, and the "start" mentioned above can be counted as part of the running process), and normalize the operating time (such as dividing the operating time by a fixed maximum value to make its value range between 0 and 1). Calculate the refrigeration temperature difference (the difference between the real-time refrigeration temperature and the real-time evaporation temperature) and the freezing temperature difference (the difference between the real-time freezing temperature and the real-time evaporation temperature) corresponding to each data point, and use these temperature difference values as part of the input data.
[0086] S103. Feature extraction:
[0087] Extract valuable features from the original data. In addition to the refrigeration temperature, freezing temperature, evaporation temperature, compressor operating status, operating time, and the calculated temperature difference values, other derived features can also be considered. For example, calculate the change rates of the refrigeration temperature, freezing temperature, and evaporation temperature over a period of time, or calculate the average operating time of the compressor in different time periods, etc. Screen and select features to remove features with low correlation or little impact on the model performance. Methods such as correlation coefficient analysis and feature importance evaluation can be used to determine which features are the most critical.
[0088] S104. Model training:
[0089] Divide the preprocessed and feature-extracted data into a training set and a test set. The training set is used to train the model, and the test set is used to evaluate the performance of the model. The division can be made according to a certain ratio (such as 70% for the training set and 30% for the test set). Use the training set data to train the model. In the embodiments of the present invention, the model used for training is a neural network model. During the training process, adjust the parameters of the model to make the prediction result of the model as close as possible to the actual defrosting condition (that is, the label of whether the defrosting condition is satisfied). In addition, for the neural network model, appropriate hyperparameters such as the learning rate and the number of iterations need to be set, and the method of cross-validation can be used to further optimize the hyperparameters of the model. It should be noted that cross-validation divides the training set into multiple subsets, uses one subset as the validation set each time, and the remaining subsets as the training set, trains and validates the model multiple times, and then takes the average performance as the final performance evaluation index of the model.
[0090] S105. Model evaluation:
[0091] Evaluate the trained model using the test set data. For example, metrics such as accuracy, recall, and F1-score can be used to evaluate the model's performance in predicting defrost conditions. Among them, accuracy represents the proportion of the number of samples correctly predicted by the model to the total number of samples; recall represents the proportion of the number of positive examples (i.e., samples that meet the defrost conditions) correctly predicted by the model to the actual number of positive examples; the F1-score is the harmonic mean of accuracy and recall, comprehensively considering the accuracy and recall of the model. Analyze the evaluation results of the model to identify the problems and deficiencies of the model. For example, if the accuracy of the model is low, it may be due to reasons such as large data noise, inappropriate feature selection, or insufficient model complexity; if the recall is low, it may be that the model has insufficient ability to identify positive examples.
[0092] S106. Model optimization and adjustment:
[0093] According to the results of model evaluation, optimize and adjust the model. If the model performance is not good, the following methods can be adopted: add more data to improve the generalization ability of the model; adjust the feature extraction method to extract more valuable features or perform further transformation on the existing features; adjust the hyperparameters of the model, try different parameter combinations to find the optimal model configuration; try using different models or model fusion methods to combine the prediction results of multiple models to improve the model performance.
[0094] S107. Model deployment:
[0095] When the performance of the model meets the requirements, deploy it to the control system of the refrigerator. During the deployment process, it is necessary to ensure that the model can be effectively integrated with the hardware and software systems of the refrigerator, and can receive and process the operation data of the refrigerator in real time, and accurately predict the defrost conditions. After the model is deployed, continuous monitoring and maintenance of the model are also required. In addition, the performance of the model can be evaluated regularly, and the model can be updated and optimized according to the actual situation to adapt to the changes in the refrigerator operating environment and the changes in user needs.
[0096] In the embodiments of the present invention, the rich and relevant input data enables the model to learn more features and rules related to defrosting. By analyzing the relationships between different refrigeration temperatures, freezing temperatures and evaporation temperatures, as well as their associations with the compressor operating state and time, the model can discover when a certain temperature combination and compressor working state occur, the refrigerator is more likely to reach the defrost conditions. In this way, when the model faces new operation data, it can more accurately judge whether defrosting is required based on the learned knowledge, reduce misjudgment and missed judgment situations, and improve the accuracy of prediction. By integrating these data, the parameter prediction model can comprehensively and accurately understand the actual operating state of the refrigerator when it meets the defrost mode, providing a solid data basis for accurately predicting the defrost conditions.
[0097] Specifically, the defrosting conditions include: the refrigerating temperature difference is greater than the refrigerating temperature difference threshold and lasts for the first duration; or, the freezing temperature difference is greater than the freezing temperature difference threshold and lasts for the second duration.
[0098] Exemplarily, refer to Figure 7 , Figure 7 which is the second working flowchart of the controller provided by the embodiment of the present invention. After the controller executes step S13, it also executes steps S131 to S137. Assume that the parameter prediction model of a refrigerator has been trained and relevant reference temperature difference thresholds are preset, including the following two examples:
[0099] 1) The refrigerating temperature difference threshold is 10°C, and the first duration is set to 10 minutes.
[0100] During the operation of the refrigerator, it is monitored in real time that the real-time refrigerating temperature is 5°C, the real-time evaporation temperature is 5°C, and the refrigerating temperature difference between the real-time refrigerating temperature and the real-time evaporation temperature is 13°C. At this time, the refrigerating temperature difference is greater than the refrigerating temperature difference threshold. The system starts timing. In the next 10 minutes, the refrigerating temperature and the evaporation temperature are continuously monitored, and the refrigerating temperature difference is continuously calculated. Assume that within these 10 minutes, due to reasons such as putting more warm food in the refrigerator, the refrigerating temperature always fluctuates at a relatively high level, and the evaporation temperature is relatively stable, so that the refrigerating temperature difference always remains between 10.5 - 13°C, which satisfies the condition of "the refrigerating temperature difference is greater than the refrigerating temperature difference threshold and lasts for the first duration (10 minutes)".
[0101] 2) The freezing temperature difference threshold is 15°C, and the second duration is set to 5 minutes.
[0102] During the operation of the refrigerator, it is monitored in real time that the real-time freezing temperature is -15°C, the real-time evaporation temperature is 5°C, and the refrigerating temperature difference between the real-time freezing temperature and the real-time evaporation temperature is 20°C. At this time, the freezing temperature difference is greater than the freezing temperature difference threshold. The system starts timing. In the next 5 minutes, the freezing temperature and the evaporation temperature are continuously monitored, and the freezing temperature difference is continuously calculated. Assume that within these 10 minutes, the freezing temperature difference always remains between 18 - 22°C, which satisfies the condition of "the freezing temperature difference is greater than the freezing temperature difference threshold and lasts for the second duration (5 minutes)".
[0103] In the embodiments of the present invention, the refrigerating temperature difference threshold and the freezing temperature difference threshold are clearly distinguished, enabling precise control for the different temperature characteristics and frosting conditions of the refrigerator's refrigerating and freezing compartments. Since the normal operating temperature ranges of the refrigerating and freezing compartments are different, and the frosting speed and degree also vary, setting the thresholds separately makes the defrosting judgment more in line with the actual requirements of each compartment. At the same time, by combining the condition that the temperature difference is greater than the threshold and lasts for a certain period, false defrosting caused by short-term temperature fluctuations is avoided, ensuring that defrosting is only initiated when the frosting reaches a certain level and continuously affects the refrigeration effect of the refrigerator, thus achieving the precision of defrosting control.
[0104] Specifically, the defrosting condition further includes: the refrigerating startup temperature is greater than a preset refrigerating startup temperature threshold and lasts for a third duration; or, the freezing startup temperature is greater than a preset freezing startup temperature threshold and lasts for a fourth duration.
[0105] Exemplarily, refer to Figure 8 , Figure 8 FIG. is the third working flowchart of the controller provided by the embodiments of the present invention. After the controller executes step S13, it also executes steps S141 - S151. In addition to judging the defrosting condition based on the temperature difference, adding conditions related to the startup temperature makes the defrosting judgment more comprehensive. The startup temperature reflects the actual temperature inside the refrigerator when the compressor starts. When the refrigerating or freezing startup temperature continuously exceeds the preset threshold, it indicates that the temperature inside the refrigerator is relatively high, which may be due to serious frosting affecting the refrigeration effect. Combining the above 1) and 2), the defrosting conditions also include the following 3) and 4):
[0106] 3) It is necessary to further determine while meeting the above condition 1). Assume that the preset refrigerating startup temperature threshold of the refrigerator is 5°C and the third duration is set to 10 minutes. After the refrigerator compressor stops working for a period of time and then starts again (i.e., enters the startup state), at this time, the monitored refrigerating startup temperature is 7°C, which is greater than the preset refrigerating startup temperature threshold of 5°C. The system then starts timing. Within the next 10 minutes, the refrigerating startup temperature always remains between 6 - 8°C. In this case, the defrosting condition of "the refrigerating startup temperature is greater than the preset refrigerating startup temperature threshold and lasts for the third duration" is met.
[0107] 4) It is necessary to further determine while meeting the above condition 2). Assume that the preset freezing startup temperature threshold of the refrigerator is -12°C and the fourth duration is set to 5 minutes. When the compressor starts (enters the startup state), the detected freezing startup temperature is -10°C, which is higher than the preset freezing startup temperature threshold of -12°C. Starting from this time, timing is carried out. Within the subsequent 5 minutes, the freezing startup temperature still remains between -10°C and -11°C. This meets the defrosting condition of "the freezing startup temperature is greater than the preset freezing startup temperature threshold and lasts for the fourth duration".
[0108] In the embodiment of the present invention, in combination with the above determination conditions, it is possible to more accurately capture the situation that defrosting is required, avoid misjudgment that may occur by simply relying on temperature difference judgment, and further improve the accuracy of defrosting control.
[0109] Specifically, when the comparison result meets the preset defrosting condition, the controller is further configured to: after exiting the defrosting mode, obtain a reference evaporation temperature; when the reference evaporation temperature is less than the target evaporation temperature, update the target evaporation temperature with the reference evaporation temperature; input the updated target evaporation temperature into the parameter prediction model to update and iterate the parameter prediction model.
[0110] Exemplarily, referring to Figure 9 , Figure 9 FIG. 11 is the fourth working flowchart of the controller provided by the embodiment of the present invention. After the controller executes step S15, it is further configured to execute steps S17 to S20. Within a period of time after the refrigerator exits the defrosting mode, the evaporation temperature is continuously and real-time monitored. Through comparison, it is found that, assuming that the reference evaporation temperature of -3°C is less than the target evaporation temperature of -1.8°C. When the system determines that the reference evaporation temperature is less than the target evaporation temperature, an update operation is performed. The reference evaporation temperature of -3°C is used as the new target evaporation temperature. This update process is implemented through the control system of the refrigerator. The control system will modify the variable value storing the target evaporation temperature and replace the original -1.8°C with -3°C. The model adjusts and optimizes the internal parameters based on this new data (the updated target evaporation temperature). The parameter prediction model usually receives input data in a specific data format. Before inputting the updated target evaporation temperature of -3°C into the model, it is necessary to ensure that the data format meets the requirements of the model. This may involve converting the temperature data into the numerical type required by the model (such as a floating-point number), and the model input may also include other relevant information (such as a timestamp, a refrigerator operation mode identifier, etc.).
[0111] Exemplarily, after receiving the updated target evaporation temperature data, the parameter prediction model starts to perform update iterations. Since the parameter prediction model is a neural network-based model, it has an input layer, a hidden layer, and an output layer. The model makes predictions by learning the complex relationship between the input data (such as refrigeration temperature, freezing temperature, evaporation temperature, compressor operating status, and time, etc.) and the defrosting conditions. During the previous training process, the model has determined the connection weights and bias values between the neurons of each layer. The updated target evaporation temperature data first enters the input layer, and the input layer passes the data to the hidden layer. The neurons in the hidden layer perform weighted summation based on the received data and the weights and bias values obtained from the previous training, and are processed through an activation function (such as the ReLU function), and the processed result is passed to the next layer. This process is repeated in the hidden layer until the data reaches the output layer. After the update iteration, the parameter prediction model will use the new parameter settings to predict the reference temperature difference threshold during the subsequent operation of the refrigerator. When various temperature data, compressor operating status, and time and other input data are obtained again, the model will calculate based on the updated weights and bias values and output a more accurate prediction result of the reference temperature difference threshold, thereby providing a more reliable basis for the defrost control of the refrigerator.
[0112] In the embodiment of the present invention, the updated target evaporation temperature is input into the parameter prediction model, which enables the model to continuously incorporate new data that is more in line with the actual operating conditions. As time goes by and the operating data accumulates, the parameter prediction model can dynamically adjust its own parameters according to the change of the evaporation temperature in the actual operation of the refrigerator, so as to better adapt to different operating environments and conditions, continuously optimize the prediction ability of the defrosting conditions, further improve the accuracy and reliability of the prediction, and reduce the occurrence of misjudgment and missed judgment.
[0113] Specifically, the initial construction process of the target evaporation temperature includes: obtaining the initial evaporation temperature detected within m minutes after the refrigerator exits the defrosting mode n times; where n is greater than or equal to 2, and m is less than or equal to a preset duration threshold; selecting the minimum value from the n initial evaporation temperatures as the initial target evaporation temperature.
[0114] Exemplarily, learn the evaporator temperature value in the normal operating state of the refrigerator. During the m minutes of the whole machine operation after the refrigerator defrosts, record the evaporation sensor temperature value in real time and find the minimum temperature value of the evaporation sensor. In the initial stage after the refrigerator defrosting ends, when the amount of frost on the evaporator is small and the minimum evaporation temperature occurs before the compartment temperature reaches the shutdown temperature, it is within the normal operating range. Therefore, this minimum evaporation temperature can be used as the evaporator parameter of the model.
[0115] In the embodiment of the present invention, since the evaporation temperature within a short period after defrosting can, to a certain extent, reflect the refrigeration capacity of the refrigerator under good operating conditions, selecting the minimum value as the initial target evaporation temperature helps to more strictly control the refrigeration effect of the refrigerator and lay a foundation for subsequent precise control. Selecting the minimum value as the initial target evaporation temperature can obtain a relatively low and representative value, which provides a reasonable initial reference standard for subsequent defrost control and parameter prediction models. Based on this reasonable initial value, the model can better fit the operating rules of the refrigerator during subsequent learning and iteration, improving the prediction accuracy and reliability of the model.
[0116] See Figure 10 , Figure 10 is a flowchart of a defrost control method for a refrigerator provided by an embodiment of the present invention. The defrost control method of the refrigerator is implemented by a controller, and the defrost control method of the refrigerator includes:
[0117] S1. Obtain the real-time refrigerating temperature, real-time freezing temperature, and real-time evaporation temperature of the refrigerator in the refrigeration mode;
[0118] S2. Calculate the refrigerating temperature difference between the real-time refrigerating temperature and the real-time evaporation temperature, and calculate the freezing temperature difference between the real-time freezing temperature and the real-time evaporation temperature;
[0119] S3. Compare the refrigerating temperature difference and the freezing temperature difference with a reference temperature difference threshold output by a preset parameter prediction model, and when the comparison result meets the preset defrost condition, control the refrigerator to enter the defrost mode.
[0120] Specifically, when the comparison result meets the preset defrost condition, the method further includes: after exiting the defrost mode, obtain the reference evaporation temperature; when the reference evaporation temperature is less than the target evaporation temperature, update the target evaporation temperature with the reference evaporation temperature; input the updated target evaporation temperature into the parameter prediction model to update and iterate the parameter prediction model.
[0121] Specifically, the initial construction process of the target evaporation temperature includes: obtaining the initial evaporation temperature detected within m minutes after the refrigerator exits the defrost mode n times; where n is greater than or equal to 2, and m is less than or equal to a preset duration threshold; select the minimum value from the n initial evaporation temperatures as the initial target evaporation temperature.
[0122] Specifically, the input data of the parameter prediction model during application includes the real-time refrigerating temperature, real-time freezing temperature, real-time evaporation temperature, real-time operating state, and real-time operating time of the compressor.
[0123] Specifically, the reference temperature difference threshold includes a refrigerating temperature difference threshold and a freezing temperature difference threshold, and the defrosting condition includes: the refrigerating temperature difference is greater than the refrigerating temperature difference threshold and lasts for a first duration; or, the freezing temperature difference is greater than the freezing temperature difference threshold and lasts for a second duration.
[0124] Specifically, the defrosting condition further includes: the refrigerating startup temperature is greater than a preset refrigerating startup temperature threshold and lasts for a third duration; or, the freezing startup temperature is greater than a preset freezing startup temperature threshold and lasts for a fourth duration.
[0125] Specifically, the input data during the training of the parameter prediction model includes several groups of refrigerating temperatures, freezing temperatures, evaporation temperatures, operating states and operating times of the compressor corresponding to the refrigerator when the defrosting mode is satisfied.
[0126] It should be noted that the working process of the defrosting control method of the refrigerator described in the embodiments of the present invention can refer to the working flowchart of the controller described in the above embodiments, which will not be elaborated here.
[0127] The above is the preferred embodiment of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and modifications can be made, and these improvements and modifications are also regarded as the protection scope of the present invention.
Claims
1. A refrigerator, characterized in that, Comprising: A box body, in which at least one storage chamber is formed, and the storage chamber at least includes a refrigerating chamber and a freezing chamber; A refrigeration system for providing cooling capacity for the refrigerator, and the refrigeration system includes a compressor, a condenser and an evaporator connected by pipelines; Temperature sensors, including a refrigerating chamber temperature sensor for obtaining the real-time refrigerating temperature, a freezing temperature sensor for obtaining the real-time freezing temperature, and an evaporator temperature sensor for obtaining the real-time evaporation temperature; A controller, which is configured as follows: Obtain the real-time refrigerating temperature, the real-time freezing temperature and the real-time evaporation temperature of the refrigerator in the refrigeration mode; Calculate the refrigerating temperature difference between the real-time refrigerating temperature and the real-time evaporation temperature, and calculate the freezing temperature difference between the real-time freezing temperature and the real-time evaporation temperature; Compare the refrigerating temperature difference and the freezing temperature difference with the reference temperature difference threshold output by a preset parameter prediction model, and when the comparison result meets the preset defrosting condition, control the refrigerator to enter the defrosting mode.
2. The refrigerator according to claim 1, characterized in that, The input data of the parameter prediction model during application includes the real-time refrigerating temperature, the real-time freezing temperature, the real-time evaporation temperature, the real-time operating state and the real-time operating time of the compressor.
3. The refrigerator according to claim 1, characterized in that, The reference temperature difference threshold includes a refrigerating temperature difference threshold and a freezing temperature difference threshold, and the defrosting condition includes: The refrigerating temperature difference is greater than the refrigerating temperature difference threshold and lasts for a first duration; or, the freezing temperature difference is greater than the freezing temperature difference threshold and lasts for a second duration.
4. The refrigerator according to claim 3, wherein, The defrosting condition further includes: The refrigerating start-up temperature is greater than a preset refrigerating start-up temperature threshold and lasts for a third duration; or, the freezing start-up temperature is greater than a preset freezing start-up temperature threshold and lasts for a fourth duration.
5. The refrigerator according to claim 1, characterized in that, When the comparison result meets the preset defrosting condition, the controller is further configured as follows: After exiting the defrosting mode, obtain the reference evaporation temperature; When the reference evaporation temperature is less than the target evaporation temperature, update the target evaporation temperature with the reference evaporation temperature; Input the updated target evaporation temperature into the parameter prediction model to update and iterate the parameter prediction model.
6. The refrigerator according to claim 5, wherein, The initial construction process of the target evaporation temperature includes: Obtain the initial evaporation temperature detected within m minutes after the refrigerator exits the defrosting mode n times; where n is greater than or equal to 2 and m is less than or equal to a preset duration threshold; Select the minimum value from the n initial evaporation temperatures as the initial target evaporation temperature.
7. The refrigerator according to claim 1, characterized in that, The input data of the parameter prediction model during training includes several groups of the refrigerating temperature, the freezing temperature, the evaporation temperature, the operating state and the operating time of the compressor corresponding to the refrigerator when the defrosting mode is satisfied.
8. A defrost control method for a refrigerator, characterized in that, Comprising: Obtain the real-time refrigerating temperature, the real-time freezing temperature and the real-time evaporation temperature of the refrigerator in the refrigeration mode; Calculate the refrigerating temperature difference between the real-time refrigerating temperature and the real-time evaporation temperature, and calculate the freezing temperature difference between the real-time freezing temperature and the real-time evaporation temperature; Compare the refrigerating temperature difference and the freezing temperature difference with the reference temperature difference threshold output by a preset parameter prediction model, and when the comparison result meets the preset defrosting condition, control the refrigerator to enter the defrosting mode.
9. The defrost control method of the refrigerator according to claim 8, characterized in that, When the comparison result meets the preset defrosting condition, the method further includes: After exiting the defrosting mode, obtaining the reference evaporation temperature; When the reference evaporation temperature is less than the target evaporation temperature, updating the target evaporation temperature with the reference evaporation temperature; Inputting the updated target evaporation temperature into the parameter prediction model to update and iterate the parameter prediction model.
10. The defrost control method of the refrigerator according to claim 9, characterized in that, The initial construction process of the target evaporation temperature includes: Obtaining the initial evaporation temperature detected within m minutes after the refrigerator exits the defrosting mode n times; where n is greater than or equal to 2, and m is less than or equal to a preset duration threshold; Selecting the minimum value from the n initial evaporation temperatures as the initial target evaporation temperature.