Refrigerator temperature control method and device, computer readable storage medium and refrigerator

Abstract

The invention provides a temperature control method and device of a refrigerator, a computer readable storage medium and the refrigerator. The method comprises the steps that a predicted environment temperature sequence of a future preset time period, historical operation data of the refrigerator and refrigerator body parameters are obtained; a long short-term memory network model is constructed, the predicted environment temperature sequence, the historical operation data and the refrigerator body parameters are input into the long short-term memory network model for prediction processing, and an internal temperature prediction sequence of the refrigerator in a future preset time period is obtained; and a temperature set value and current operation data of the refrigerator are obtained, a temperature control strategy of the refrigerator in the future preset time period is determined at least according to the temperature set value of the refrigerator, the current operation data, the refrigerator body parameters and the internal temperature prediction sequence, and the temperature of the refrigerator is controlled through the temperature control strategy. The problem that an existing refrigerator temperature control system depends on feedback control of an internal sensor, and the performance of the refrigerator is affected under the condition that the external environment changes suddenly is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the temperature control technology field of a refrigerator, in particular to a refrigerator temperature control method and device, a computer readable storage medium and a refrigerator. BACKGROUND

[0002] Under the background of rapid development of current smart home technology, as one of the most commonly used home appliances in the family, the intelligent level of the refrigerator directly affects the user's experience and energy efficiency. The traditional refrigerator temperature control system mainly relies on feedback control of internal sensors, that is, the running state of the compressor is adjusted according to the change of the internal temperature of the refrigerator. Although this control method can guarantee the basic function of the refrigerator, it shows limitations in dealing with external environmental changes. Specifically, the existing refrigerator temperature control system faces the following main problems:

[0003] 1. Lack of prediction ability for external environmental changes: Since the increase or decrease of external temperature cannot be predicted in advance, the system can only respond passively after the heat load of the cabinet changes significantly, which not only affects the stability of the internal temperature of the refrigerator, but also reduces the user experience and food preservation quality.

[0004] 2. Energy waste caused by frequent start-stop of the compressor: In order to respond to sudden changes in heat load, the compressor may be frequently started and stopped. This non-continuous working mode not only increases energy consumption, but also may cause the overall operating efficiency of the refrigerator to decrease, and in the long run, it will also affect the service life of the compressor.

[0005] 3. Defrost operation is out of touch with external humidity: The defrosting of the refrigerator usually relies on a timing strategy, without considering the influence of external humidity. In a high humidity environment, improper defrosting operation may cause excessive defrosting, resulting in unnecessary energy consumption; while in a dry environment, insufficient defrosting may cause the evaporator to freeze, reducing the refrigeration efficiency. SUMMARY

[0006] The main purpose of the present application is to provide a refrigerator temperature control method and device, a computer readable storage medium and a refrigerator, to at least solve the problem that the existing refrigerator temperature control system relies on feedback control of internal sensors, which affects the performance of the refrigerator in the case of external environmental mutation.

[0007] In order to achieve the above object, according to one aspect of the present application, a temperature control method of a refrigerator is provided, comprising: obtaining a predicted ambient temperature sequence of a future preset time period, historical running data and cabinet parameters of the refrigerator; constructing a long short-term memory network model, inputting the predicted ambient temperature sequence, the historical running data and the cabinet parameters into the long short-term memory network model for prediction processing to obtain an internal temperature prediction sequence of the refrigerator in the future preset time period; obtaining a temperature setting value and current running data of the refrigerator, and determining a temperature control strategy of the refrigerator in the future preset time period according to at least the temperature setting value, the current running data, the cabinet parameters and the internal temperature prediction sequence of the refrigerator, and controlling the temperature of the refrigerator by using the temperature control strategy.

[0008] Optionally, determining the temperature control strategy of the refrigerator in the future preset time period according to the temperature setting value, the current running data, the cabinet parameters and the internal temperature prediction sequence of the refrigerator comprises: determining a compressor frequency value in the temperature control strategy according to the temperature setting value, the internal temperature prediction sequence and the current running data of the refrigerator, wherein the current running data comprises a current temperature value of the refrigerator.

[0009] Optionally, determining the temperature control strategy of the refrigerator in the future preset time period according to at least the temperature setting value, the current running data, the cabinet parameters and the internal temperature prediction sequence of the refrigerator comprises: determining a cold storage board power value in the temperature control strategy according to the temperature setting value, the internal temperature prediction sequence, an effective heat exchange area of a heat conduction medium and a phase change material in a cold storage board of the refrigerator, a thickness of the phase change material and an equivalent thermal conductivity.

[0010] Optionally, determining the temperature control strategy of the refrigerator in the future preset time period according to at least the temperature setting value, the current running data, the cabinet parameters and the internal temperature prediction sequence of the refrigerator comprises: determining a refrigerator damper opening value in the temperature control strategy according to the current running data, the internal temperature prediction sequence, a heat resistance coefficient of a predetermined position of a refrigerator air duct, a damper response sensitivity and a refrigerator system safety threshold of the refrigerator, wherein the current running data comprises a compartment average temperature and a real-time temperature of a predetermined position of the refrigerator air duct.

[0011] Optionally, the determining the temperature control strategy of the refrigerator for the future preset time period according to at least the temperature set value of the refrigerator, the current running data, the cabinet parameters and the internal temperature prediction sequence comprises: acquiring an ambient relative humidity and an ambient temperature, determining a condenser and ambient temperature difference according to the ambient temperature and a condenser temperature, and determining a condenser fan speed in the temperature control strategy according to a current rotation speed of a condenser fan of the refrigerator, the condenser and ambient temperature difference, a condenser temperature rise rate and the ambient relative humidity, wherein the current running data comprises the current rotation speed of the condenser fan, the condenser temperature and the condenser temperature rise rate.

[0012] Optionally, in the process of controlling the temperature of the refrigerator by using the temperature control strategy, the method further comprises: in the case that it is detected that the condenser temperature of the refrigerator is greater than a preset temperature, determining that the condenser temperature is too high, controlling the refrigerator to open a standby air duct, controlling the rotation speed of the condenser fan of the refrigerator to reach a preset rotation speed, and forcibly closing a damper of the refrigerator.

[0013] Optionally, after the temperature of the refrigerator is controlled by using the temperature control strategy, the method further comprises: after a preset time period, acquiring a temperature over-standard cumulative amount, a total power consumption and a number of compressor start-stop cycles of the refrigerator, wherein the temperature over-standard cumulative amount is a square deviation integral value of a measured temperature in the refrigerator and a set temperature; and evaluating the comprehensive performance of the refrigerator under the control of the temperature control strategy according to the temperature over-standard cumulative amount, the total power consumption and the number of compressor start-stop cycles.

[0014] According to another aspect of the present application, a temperature control device of a refrigerator is provided, comprising: a first acquisition unit configured to acquire a prediction ambient temperature sequence for a future preset time period, historical running data and cabinet parameters of a refrigerator; a prediction unit configured to construct a long short-term memory network model, input the prediction ambient temperature sequence, the historical running data and the cabinet parameters into the long short-term memory network model for prediction processing, and obtain an internal temperature prediction sequence of the refrigerator for the future preset time period; and a determination unit configured to acquire a temperature set value and current running data of the refrigerator, determine a temperature control strategy of the refrigerator for the future preset time period according to at least the temperature set value of the refrigerator, the current running data, the cabinet parameters and the internal temperature prediction sequence, and control the temperature of the refrigerator by using the temperature control strategy.

[0015] According to still another aspect of the present application, a computer readable storage medium is provided, which comprises a stored program, wherein the program controls a device where the computer readable storage medium is located to perform any of the temperature control methods of the refrigerator when the program is running.

[0016] According to another aspect of the present application, a refrigerator is provided, comprising a controller configured to perform any of the temperature control methods of the refrigerator.

[0017] By applying the technical solution of the present application, the predicted ambient temperature sequence of a future preset time period, the historical operation data and the cabinet parameters of the refrigerator are obtained; a long short-term memory network model is constructed, the predicted ambient temperature sequence, the historical operation data and the cabinet parameters are input into the long short-term memory network model for prediction processing, and the internal temperature prediction sequence of the refrigerator in the future preset time period is obtained; the temperature setting value and the current operation data of the refrigerator are obtained, and at least according to the temperature setting value, the current operation data, the cabinet parameters and the internal temperature prediction sequence of the refrigerator, the temperature control strategy of the refrigerator in the future preset time period is determined, and the temperature control strategy is used to control the temperature of the refrigerator. According to the change trend of the future ambient temperature, the refrigerator can make an early response, adjust the internal temperature to cope with the upcoming temperature fluctuation, and the long short-term memory network model can process time series data and capture long-term dependencies, which is used to predict the internal temperature prediction value of the refrigerator under the influence of the ambient temperature. According to the internal temperature prediction value of the refrigerator, the corresponding internal temperature prediction value of the refrigerator is determined, which can significantly improve the temperature control precision and stability of the refrigerator, reduce the temperature fluctuation caused by the sudden change of the ambient temperature, and reduce the energy consumption. The problem that the existing refrigerator temperature control system relies on the feedback control of the internal sensor and affects the performance of the refrigerator in the case of sudden change of the external environment is solved. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings, which form a part of the present application, are intended to provide further understanding of the present application, and the illustrative embodiments of the present application and their description serve the purpose of explaining the present application. The accompanying drawings should not be construed as an inappropriate limitation on the present application. In the drawings:

[0019] Figure 1 A hardware structure block diagram of a mobile terminal for performing a temperature control method of a refrigerator according to an embodiment of the present application is shown;

[0020] Figure 2 A flowchart of a temperature control method of a refrigerator according to an embodiment of the present application is shown;

[0021] Figure 3 A structure diagram of a temperature control system of a refrigerator according to an embodiment of the present application is shown;

[0022] Figure 4 A structure block diagram of a temperature control device of a refrigerator according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0023] It should be noted that the embodiments and features of the present application can be combined with each other in the case of no conflict. The technical solutions in the embodiments of the present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0024] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0025] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily have to include those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to the process, method, product or device.

[0026] As introduced in the background, the existing refrigerator temperature control system relies on feedback control of internal sensors, which affects the performance of the refrigerator in the case of external environment mutation. To solve the problem that the existing refrigerator temperature control system relies on feedback control of internal sensors, which affects the performance of the refrigerator in the case of external environment mutation, the embodiments of the present application provide a refrigerator temperature control method, device, computer readable storage medium and refrigerator.

[0027] The technical solutions in the embodiments of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application.

[0028] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking the case of running on a mobile terminal, Figure 1 is a hardware structure block diagram of a mobile terminal of a refrigerator temperature control method of the embodiments of the present application. As Figure 1 shown, the mobile terminal can include one or more Figure 1The mobile terminal can further include a transmission device 106 for communication function and an input / output device 108. Those skilled in the art can understand that, Figure 1 The structure shown is only schematic and does not limit the structure of the mobile terminal. For example, the mobile terminal can include more or less components than those shown, or have a different configuration or arrangement of the components. Figure 1 The mobile terminal can include more or less components than those shown, or have a different configuration or arrangement of the components. Figure 1 The mobile terminal can include more or less components than those shown, or have a different configuration or arrangement of the components.

[0029] The memory 104 can be used to store computer programs, such as software programs and modules of application software, and a computer program corresponding to the temperature control method of the refrigerator according to the embodiments of the present application. The processor 102 can execute various function applications and data processing by running the computer program stored in the memory 104, i.e., implement the method described above. The memory 104 can include a high-speed random access memory, and can further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include a memory remotely disposed relative to the processor 102, which can be connected to the mobile terminal through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The specific examples of the network can include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet in a wireless manner.

[0030] In the embodiments, a temperature control method of a refrigerator running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] Figure 2 is a flowchart of the temperature control method of the refrigerator according to the embodiments of the present application. As Figure 2 shown, the method includes the following steps:

[0032] Step S201, obtaining a predicted ambient temperature sequence of a future preset time period, historical running data of the refrigerator and cabinet parameters;

[0033] Among them, the air temperature within 72 hours in the future can be obtained through a meteorological satellite as the predicted ambient temperature sequence; the historical running data of the refrigerator includes the cumulative working time of the compressor of the refrigerator, the time sequence data of the refrigerator door opening times; the cabinet parameters include the thickness of the cabinet foaming layer, the thermal conductivity coefficient of the cabinet, the capacity of the refrigerator, the thermal resistance coefficient of the refrigerator air duct, the effective heat exchange area of the heat conducting medium and the phase change material in the refrigerator cold storage plate, and the thickness of the phase change material.

[0034] Step S202, constructing a long short-term memory network model, inputting the predicted ambient temperature sequence, the historical running data and the cabinet parameters into the long short-term memory network model for prediction processing to obtain the internal temperature prediction sequence of the refrigerator in the future preset time period;

[0035] Specifically, a long short-term memory network (LSTM) is used to construct a long short-term memory network model, and the network structure includes:

[0036] 1, input layer (3 time sequence channels);

[0037] 2, hidden layer (64 units, tanh activation function);

[0038] 3, output layer (generate the internal temperature of the refrigerator and the temperature change rate in the cabinet).

[0039] Among them, the training data set for training the long short-term memory network model covers-30℃ to 45℃ external environment working conditions, including quick freezing, holiday mode and other special scenes.

[0040] The long short-term memory network model can be set to update the temperature prediction of the future 3 hours every 15 minutes.

[0041] Step S203, obtaining the temperature setting value and the current running data of the refrigerator, determining the temperature control strategy of the refrigerator in the future preset time period according to at least the temperature setting value, the current running data, the cabinet parameters and the internal temperature prediction sequence of the refrigerator, and controlling the temperature of the refrigerator by using the temperature control strategy.

[0042] Among them, the temperature setting value of the refrigerator includes the refrigerator refrigeration temperature setting value and the refrigerator freezing temperature setting value; the current running data includes the current refrigeration temperature value, the current refrigerator freezing temperature value, the current speed of the condenser fan, the condenser temperature, the condenser temperature rise rate, the average temperature of the interchamber, and the real-time temperature of the refrigerator air duct.

[0043] Specifically, the temperature control strategy includes adjusting the refrigerator compressor frequency value, the cold storage plate power value, the refrigerator damper opening value and the condenser fan speed. By assigning corresponding action weights, the refrigerator compressor frequency value, the cold storage plate power value, the refrigerator damper opening value and the condenser fan speed control the temperature of the above-mentioned refrigerator.

[0044] Through the above steps S201, S202 and S203, the refrigerator can make an early response according to the trend of future environmental temperature, adjust the internal temperature to cope with the upcoming temperature fluctuation, and use the long short-term memory network model to process time series data and capture long-term dependencies for predicting the refrigerator internal temperature prediction value under the influence of environmental temperature. According to the refrigerator internal temperature prediction value, the corresponding refrigerator internal temperature prediction value is determined, which can significantly improve the temperature control accuracy and stability of the refrigerator, reduce the temperature fluctuation caused by sudden changes in environmental temperature, and reduce energy consumption. The problem of the existing refrigerator temperature control system relying on feedback control of internal sensors and affecting the performance of the refrigerator in the case of external environmental mutation is solved.

[0045] In the specific implementation process, the temperature control strategy of the future preset time period of the refrigerator is determined according to the temperature set value of the refrigerator, the current running data, the cabinet parameters and the internal temperature prediction sequence, including: determining the compressor frequency value in the temperature control strategy according to the temperature set value of the refrigerator, the internal temperature prediction sequence and the current running data, wherein the current running data includes the current temperature value of the refrigerator.

[0046] The calculation formula for specifically calculating the compressor frequency value is as follows:

[0047]

[0048] Wherein, f base is the compressor frequency value, K p is the proportional gain coefficient, which represents the instantaneous response strength of the system to the temperature deviation (the frequency adjustment ability of the compressor per unit temperature difference), T set is the temperature set value of the refrigerator refrigerating chamber and / or freezing chamber, T pred is the internal temperature prediction sequence, K i is the integral gain coefficient, which is used to eliminate the historical cumulative temperature deviation (the compensation strength of the system time lag), T actual is the current temperature value of the refrigerator refrigerating chamber and / or freezing chamber, which is the real-time detection value of the high-precision sensor, is the time integral operation. Wherein, K p = 0.8 Hz / ℃, K i = 0.15 Hz / (℃·min) (the coefficient is dynamically adjusted according to the cabinet thermal inertia τ).

[0049] This method employs compressor frequency modulation technology to precisely control the refrigerator's cooling capacity by adjusting the compressor's operating frequency, ensuring the internal temperature meets the set value. The compressor frequency adjustment is based on the predicted rate of change of the internal temperature and the deviation between the current internal temperature and the set temperature, dynamically calculated using a proportional-integral-derivative (PID) control algorithm to achieve rapid response and fine-tuning of the temperature. This method effectively avoids frequent compressor start-stop cycles, reduces energy consumption, extends compressor lifespan, and maintains a constant internal temperature. Furthermore, by introducing fuzzy logic control or adaptive control, it can handle more complex and uncertain environmental conditions, addressing the problem of compressor control instability under extreme temperature environments.

[0050] Specifically, the temperature control strategy for the refrigerator for the future preset time period is determined based at least on the refrigerator's temperature setpoint, current operating data, cabinet parameters, and internal temperature prediction sequence. This includes determining the cold storage plate power value in the temperature control strategy based on the refrigerator's temperature setpoint, internal temperature prediction sequence, effective heat exchange area of ​​the heat transfer medium and phase change material in the refrigerator's cold storage plate, the thickness of the phase change material, and the equivalent thermal conductivity.

[0051] The specific formula for calculating the power value of the cold storage plate is as follows:

[0052]

[0053] Among them, Q release The power value of the cold storage plate, ΔT, represents the amount of cold released by the cold storage plate per unit time, which determines the cold storage plate's ability to absorb environmental heat load. amb A represents the temperature rise, specifically the temperature difference between the external environment and the set temperature inside the refrigerator. pcm The contact area between the phase change material and the heat transfer medium in the cold storage plate is k. eff is the equivalent thermal conductivity, the dynamic thermal conductivity of the phase change material during the solid / liquid transition process, and d is the phase change layer thickness, the physical thickness of the phase change material perpendicular to the thermal conduction direction.

[0054] The method utilizes the phase change energy storage characteristics of the cold storage plate and achieves passive regulation of the temperature in the box by controlling the power of the cold storage plate. The power control of the cold storage plate is based on the phase change temperature, effective heat exchange area and equivalent thermal conductivity of the phase change material, and the cooling release rate of the phase change material is calculated to ensure that additional heat can be absorbed during the high temperature period and the burden on the compressor is reduced. In terms of effect, this method improves the energy efficiency of the refrigerator and reduces the dependence on the compressor. Especially when the external temperature rises sharply, the cold storage plate can respond quickly to maintain the stability of the temperature in the box. In addition, the cold storage capacity can be improved by changing the type of cold storage material or increasing the number of cold storage plates, which is suitable for larger capacity refrigerators or higher temperature difference environments, and solves the problem of poor cold storage effect in extreme conditions.

[0055] More specifically, the temperature control strategy of the future preset time period of the refrigerator is determined according to the temperature set value of the refrigerator, the current running data, the box parameter and the internal temperature prediction sequence, including: determining the opening value of the refrigerator damper in the temperature control strategy according to the current running data of the refrigerator, the internal temperature prediction sequence, the damper response sensitivity and the safety threshold of the refrigerator system, wherein the current running data includes the average temperature of the compartment of the refrigerator and the real-time temperature of the damper preset position of the refrigerator air duct.

[0056] Specifically, the calculation formula of the opening value of the refrigerator damper is as follows:

[0057]

[0058] Wherein, α ij is the opening value of the refrigerator damper, controlling the opening and closing ratio of the i-th row j-th damper, T local is the local real-time temperature, the measured temperature at position (i, j), T avg is the average temperature of the compartment, the weighted average temperature of the refrigerator compartment / freezer compartment space, R thermal is the position thermal resistance coefficient, the resistance of heat transfer from outside the box to position (i, j), β is the damper response sensitivity, the gain coefficient of temperature deviation converted into opening command, 85% is the system safety threshold, the upper limit of total opening (to prevent motor overload / airflow noise).

[0059] The method adopts a damper opening dynamic adjustment technology, optimizes the cold air flow path by precisely controlling the damper opening, and improves the refrigeration efficiency. The adjustment of the damper opening is based on the box thermal resistance coefficient, the damper response sensitivity and the system safety threshold, and the damper opening is intelligently adjusted by analyzing the temperature distribution in different regions to ensure uniform distribution of cold air and avoid local overcooling or overheating. This method can significantly improve the temperature uniformity and stability of the refrigerator, reduce cold air waste, and improve user satisfaction. In other embodiments, the number of dampers can be increased or more advanced air flow guiding technologies such as micro-channel heat exchangers can be used to further optimize the cold air distribution, which is suitable for high-end refrigerators that require more precise temperature control and solves the problem of uneven temperature distribution under high load conditions.

[0060] Further, the temperature control strategy of the refrigerator in the future preset time period is determined according to at least the temperature setting value of the refrigerator, the current running data, the box parameters and the internal temperature prediction sequence, comprising: obtaining the environmental relative humidity and the environmental temperature, determining the condenser and environmental temperature difference according to the environmental temperature and the condenser temperature; determining the condenser fan speed in the temperature control strategy according to the current speed of the condenser fan of the refrigerator, the condenser and environmental temperature difference, the condenser temperature rise rate, the environmental relative humidity, wherein the current running data includes the current speed of the condenser fan, the condenser temperature, and the condenser temperature rise rate.

[0061] Specifically, the calculation formula of the condenser fan speed is as follows:

[0062]

[0063] Wherein, N fan is the condenser fan speed, N0 is the basic speed of the condenser fan, γ is the temperature difference response index, ΔT is the condenser and environmental temperature difference, B is the temperature change rate response coefficient, dT cond is the condenser temperature rise rate, K hum is the humidity compensation gain, RH is the environmental relative humidity, which is obtained in real time by the weather API.

[0064] The method adopts a condenser fan intelligent speed regulation technology, which dynamically adjusts the fan speed by monitoring the environmental temperature and humidity and the working state of the condenser to improve the heat dissipation efficiency. In principle, the adjustment of the fan speed takes into account the temperature difference between the condenser and the environment, the temperature rise rate of the condenser and the environmental relative humidity, and the optimal fan speed is calculated by establishing a condenser heat dissipation model to ensure efficient operation of the condenser. This method not only improves the heat dissipation performance of the condenser, but also reduces noise and energy consumption, and improves the overall energy efficiency of the refrigerator.

[0065] Further, in the process of controlling the temperature of the refrigerator by using the temperature control strategy, the method further comprises: in the case that the condenser temperature of the refrigerator is detected to be greater than the preset temperature, determining that the condenser temperature is too high, controlling the refrigerator to open the standby air duct, controlling the condenser fan of the refrigerator to reach a preset rotating speed, and forcibly closing the damper of the refrigerator.

[0066] The preset temperature can be set to 55℃, the preset rotating speed can be set to 3050rpm, 3100rpm, or other rotating speeds greater than 3000rpm. In the case that the condenser temperature of the refrigerator is greater than 55℃, the standby air duct is opened, the condenser fan is switched to the turbine mode (rotating speed > 3000rpm), and the damper of the refrigeration chamber is forcibly closed to reduce the consumption of 30% of the cooling capacity.

[0067] The method adopts an emergency heat dissipation protocol. When the condenser temperature is detected to be abnormal, measures are immediately taken to reduce the temperature of the condenser to prevent the system from overheating. In principle, by opening the standby air duct and increasing the rotating speed of the condenser fan, the air flow is increased, the heat dissipation effect of the condenser is strengthened, and the damper is closed to reduce the loss of cooling capacity, ensuring the stable operation of the system. This method can quickly respond in extreme conditions and avoid system failures caused by overheating of the condenser, improving the reliability and safety of the refrigerator. In addition, the heat dissipation effect can be further enhanced by increasing the surface area of the heat dissipation fins or using a water-cooled heat dissipation system, which is suitable for commercial refrigerators that need to operate for a long time in high-temperature environments, solving the problem of low condenser heat dissipation efficiency in extreme conditions.

[0068] Specifically, after the temperature of the refrigerator is controlled by using the temperature control strategy, the method further comprises: after a preset time period, obtaining a temperature exceeding standard cumulative amount, total power consumption, and compressor start-stop cycle number of the refrigerator, wherein the temperature exceeding standard cumulative amount is a square deviation integral value of the measured temperature in the refrigerator and the set temperature; and evaluating the comprehensive performance of the refrigerator under the temperature control strategy according to the temperature exceeding standard cumulative amount, the total power consumption, and the compressor start-stop cycle number.

[0069] The method adopts a performance evaluation technology to evaluate the actual effect of the temperature control strategy by collecting and analyzing the operation data of the refrigerator. By calculating the temperature exceeding standard cumulative amount, the total power consumption, and the compressor start-stop number, the energy efficiency and stability of the refrigerator under different environmental conditions are quantified, providing data support for subsequent strategy optimization. This method can objectively evaluate the pros and cons of the temperature control strategy, guide the intelligent upgrading of the refrigerator, and improve the overall operation efficiency and user experience.

[0070] In addition, the embodiment also includes an intelligent prediction algorithm for multi-source data fusion. To further improve the prediction accuracy and reliability of the refrigerator intelligent temperature control system, the embodiment proposes an intelligent prediction algorithm for multi-source data fusion, which not only relies on the temperature data provided by meteorological satellites, but also considers the influence of factors such as user habits, refrigerator door opening frequency, and food storage type. For example, by integrating a user behavior recognition module, the system can learn and predict the refrigerator door opening frequency in a specific time period (such as before and after dinner), thereby better estimating the heat load changes inside the refrigerator. In addition, by analyzing the heat dissipation characteristics of different food types, the system can make corresponding temperature adjustment plans for the storage of a large amount of fresh vegetables and fruits (high moisture, high heat dissipation).

[0071] This multi-source data fusion method makes the prediction model more close to the actual use scenario, significantly improving the accuracy of temperature control.

[0072] In order to enable those skilled in the art to more clearly understand the technical solutions of the present application, the implementation process of the temperature control method of the refrigerator of the present application will be described in detail below in conjunction with specific embodiments.

[0073] The embodiment relates to a specific refrigerator temperature control method and system. As shown in Figure 3 , the temperature of the refrigerator is obtained by a meteorological satellite within 72 hours, the temperature of the refrigerator is obtained by a temperature sensor of the refrigerator, the data is uploaded to a cloud server of a control layer, the cloud server calculates the most appropriate control scheme within 72 hours by an algorithm, and the refrigerator controller is notified to control the components of the refrigerator.

[0074] The specific refrigerator temperature control method includes the following contents:

[0075] I. System hardware architecture:

[0076] The present scheme adopts an edge computing architecture, and the hardware system includes:

[0077] 1. Environment perception module:

[0078] (1) The built-in temperature and humidity sensor (DS18B20 + SHT30) of the refrigerator monitors the temperature distribution of each compartment of the refrigerator in real time;

[0079] (2) The embedded strain gauge array (16-point layout) of the refrigerator body shell measures the thermal deformation to calculate the heat conduction coefficient;

[0080] (3) The NB-IoT module is connected to the meteorological API to obtain the hourly temperature and humidity, precipitation probability, and wind speed data within 72 hours.

[0081] 2. Intelligent control unit:

[0082] (1) The main control chip can be STM32H743IIK6, and a real-time operating system (FreeRTOS can be selected) can be used.

[0083] (2) Configure an independent AI accelerator (Kendryte K210 can be selected) for deep learning inference;

[0084] (3) Storage unit partitioning:

[0085] ①The Flash memory stores a database of thermal parameters (including the heat transfer coefficient of the enclosure under different environmental conditions);

[0086] ② SRAM caches dynamically generated control instruction queues.

[0087] 3. Execution agency cluster:

[0088] (1) Variable frequency compressor, supporting frequency adjustment with an accuracy of 0.1Hz;

[0089] (2) The three-way solenoid valve group realizes the switching of refrigerant flow direction between the two evaporators;

[0090] (3) A graphene phase change cold storage plate (15mm thick) is integrated into the rear wall of the freezer compartment and has a semiconductor cooling unit with PID temperature control.

[0091] (4) The door seal heating device uses a carbon fiber heating wire with 32-level PWM control.

[0092] II. Software Control Algorithm:

[0093] 1. Temperature Impact Prediction Model:

[0094] (1) Input data:

[0095] The temperature sequence for the next N hours {T_out(t)}, with an accuracy of ±0.5℃;

[0096] Historical operating data: Compressor cumulative operating time, door opening count time sequence data;

[0097] Box parameters: foam layer thickness (δ=75mm), dynamic correction value for thermal conductivity λ.

[0098] (2) Modeling process:

[0099] The prediction model is constructed using a Long Short-Term Memory (LSTM) network. The network structure includes:

[0100] Input layer (3 time series channels);

[0101] Hidden layer (64 units, tanh activation function);

[0102] Output layer (generates the rate of temperature change inside the chamber);

[0103] The training dataset covers environmental conditions ranging from -30℃ to 45℃, including special scenarios such as quick-freezing and holiday mode.

[0104] 3. Multi-objective optimization control strategy:

[0105] (1) Decision variables:

[0106] X = [compressor frequency f, damper opening α, cold storage plate temperature T_pcm, door seal heating power P_h, condenser fan speed].

[0107] (2) Constraints:

[0108] Refrigerator compartment temperature: 2℃≤T_fresh≤6℃(±0.3℃);

[0109] Freezer temperature: -24℃≤T_frozen≤-18℃;

[0110] Instantaneous power ≤ 110% of the nameplate nominal value;

[0111] Objective function:

[0112] min{ω1·energy consumption integral + ω2·temperature exceedance time + ω3·compressor start-stop count};

[0113] The weight coefficients ω1, ω2, and ω3 are dynamically adjusted using the Analytic Hierarchy Process (AHP).

[0114] III. Typical Workflow (Taking a High-Temperature Summer Scenarios as an Example):

[0115] Scenario description: The weather forecast shows that the temperature will reach 35℃ from 14:00 to 17:00 today (8℃ higher than the current temperature), and the humidity will reach 70%.

[0116] Control phase:

[0117] 1. Preparatory Phase (Starts at 12:00):

[0118] (1) Call historical data to confirm the current thermal inertia parameter τ = 42 min;

[0119] (2) The LSTM model predicts that the external temperature rise at 14:00 will cause the temperature in the cold storage room to rise by 0.8℃ per hour;

[0120] (3) Decision algorithm generation instructions:

[0121] The compressor enters "Boost mode": the frequency increases from 45Hz to 68Hz for 30 minutes;

[0122] Cold accumulation plate start pre-cooling: semiconductor unit power on to reduce temperature from -15℃ to -23℃;

[0123] Damper control: close the damper of the refrigeration chamber (0% opening), concentrate the cold supply to the freezer.

[0124] 2. High temperature maintenance phase (14:00-17:00):

[0125] (1) Execute energy-saving strategies:

[0126] Compressor switches to intermittent operation mode (work cycle 15min on / 25min off);

[0127] Cold accumulation plate starts phase change cooling, absorbing 35% of the heat load shock;

[0128] Door seal heating opens 3-level protection (PWM duty cycle 18%), preventing dewing.

[0129] (2) Dynamic adjustment:

[0130] When the actual outside temperature reaches 36℃ (1℃ higher than the predicted value), the following operations are added:

[0131] Condenser fan speed increases from 1800rpm to 2400rpm;

[0132] Dual evaporator switches to parallel operation, refrigerant flow increases by 40%.

[0133] 3. Recovery phase (after 17:30):

[0134] (1) Use the natural cooling source of external temperature drop:

[0135] Completely close the compressor and open the fresh air ventilation valve for 10 minutes;

[0136] Cold accumulation plate switches to charging state;

[0137] Damper returns to the standard configuration of refrigeration chamber opening 60% and freezer opening 40%.

[0138] Three, dynamic adjustment architecture:

[0139] 1. Double closed-loop control system:

[0140] Outer ring (prediction ring): based on LSTM model, update temperature prediction every 15 minutes for the next 3 hours, generate baseline control parameters;

[0141] Inner ring (feedback ring): real-time monitoring of temperature distribution inside the box through high-precision thermoelectric array (0.05℃ resolution), triggering compensation instructions.

[0142] 2. The execution priority is set as shown in Table 1:

[0143] Table 1

[0144] Module Response delay Adjustment accuracy Action weight Compressor frequency <5s ±0.1 Hz 0.45 Cold storage plate power <30s ±5W 0.30 Damper opening <10s ±1° 0.15 Condenser fan speed <3s ±50 rpm 0.10

[0145] Four, core adjustment strategy:

[0146] 1. Compressor dynamic frequency modulation:

[0147] Formula to calculate the compressor frequency: Wherein, formula parameters as shown in Table 2.

[0148] Table 2

[0149]

[0150]

[0151] Wherein, K p = 0.8 Hz / ℃, K i = 0.15 Hz / (℃·min) (coefficient with box thermal inertia τ dynamic adjustment). Anti-saturation algorithm: when the actual temperature and set value deviation exceeds 1.5℃, start frequency pulse sequence:

[0152] First 5 minutes: f = 1.2f base (overload mode);

[0153] Next 10 minutes: f = 0.7f base (compensation cooling);

[0154] Avoiding the compressor continuous high load operation resulting in COP decline.

[0155] 2. Accumulator phase change cooling control:

[0156] Cooling rate equation: Wherein, formula parameters as shown in Table 3;

[0157] Table 3

[0158]

[0159]

[0160] k eff : the equivalent thermal conductivity calculated according to the state of phase change material (such as lauric acid-stearic acid complex).

[0161] Control logic: when the outside temperature > 32℃, start gradient cooling mode (3 power adjustable);

[0162] Cooling power P pcm and compressor frequency f inverse relationship (Ppcm α1 / f 0.6 ), where 0.6 is the result of the cross-optimization of thermodynamics, fluid mechanics and system control theory. The system-level coupling of the three results in the maximum utilization of the thermal inertia buffering capacity of the cold storage device under the premise of ensuring control stability.

[0163] The phase change triggering condition is shown in Table 4:

[0164] Table 4

[0165] External temperature rise rate Cold storage plate start threshold Cold release duration ≥2℃ / h T_pcm≤-20℃ 90-180 minutes 1-2℃ / h T_pcm≤-18℃ 60-120 minutes <1℃ / h Standby mode -

[0166] 3. Damper and air flow optimization:

[0167] Air duct matrix control: a 6x6 damper array is used to realize three-dimensional air flow guidance, and the control equation is as follows:

[0168] Wherein, the meaning of the formula parameters is shown in Table 5:

[0169] Table 5

[0170]

[0171]

[0172] Wherein, the damper response sensitivity coefficient β = 0.35, R thermal The thermal resistance correction value based on the thickness of the foaming layer.

[0173] In the intelligent air duct system of the refrigerator, the position identifier (i, j) is a spatial coordinate code used to accurately locate the temperature monitoring point, and the definition rule and physical position are shown in Table 6:

[0174] Table 6

[0175]

[0176] 4. Calculate the condenser fan speed:

[0177] In the intelligent control system of the refrigerator, the adjustment formula of the condenser fan speed is as follows:

[0178] The formula integrates multiple objectives such as thermal load, energy efficiency optimization and system protection, wherein the meaning of the formula parameters is shown in Table 7:

[0179] Table 7

[0180]

[0181] Wherein, the temperature difference correction term N0·e γΔT :

[0182] Physical basis: heat flow equation Q∝ΔT 1.25 → Speed needs nonlinear growth to cope with high temperature;

[0183] Exponential form advantage:

[0184] Low temperature section (ΔT <10℃): gentle adjustment energy saving;

[0185] High temperature section (ΔT>30℃): rapid speed to prevent overheating.

[0186] Example: ΔT=35℃, e 0.018×35 ≈1.87→Speed≈1000×1.87=1870rpm;

[0187] Dynamic response term

[0188] Square term design purpose: amplify sudden heat shock signal (such as switch door heat invasion); suppress slow temperature rise interference (avoid frequent speed fluctuations).

[0189] Hierarchical response mechanism as shown in Table 8:

[0190] Table 8

[0191] Temperature rise rate Influence fan speed Application scenario 0.1℃ / s +8×0.01=0.08rpm Negligible 0.5℃ / s +8×0.25=200rpm Normal adjustment 1.0℃ / s +8×1.0=800rpm Heat wave emergency response

[0192] Humidity compensation term K hum ·(RH-55%), where 55% reference humidity: dew point critical point experimental value (RH>55% when condensate film thickening leads to heat transfer deterioration); RH three-stage compensation strategy as shown in Table 9:

[0193] Table 9

[0194] RH range Loss of heat dissipation efficiency Compensation speed 55％-65％ 8％-15％ +3.5×10%≈35rpm 65％-75％ 15％-30％ +3.5×20%≈70rpm >75％ >30％ +3.5×30%≈105rpm

[0195] Dynamic adjustment example as follows:

[0196] Scenario: typhoon high temperature and high humidity (environment 35℃, RH=85%, open and close door leads to ΔT from 20℃→35℃);

[0197] 1. Temperature difference correction: 1000×e0.018×35≈1870rpm;

[0198] 2. Dynamic response: temperature rise rate 1.2℃ / s→B=15(high temperature section)→15×(1.2) 2 =216rpm;

[0199] 3. Humidity compensation: RH85%>55%→Khum=3.5→3.5×(85-55)=105rpm;

[0200] 4. Final speed: 1870 + 216 + 105 = 2191 rpm;

[0201] Emergency heat dissipation protocol:

[0202] When the condenser temperature > 55℃:

[0203] 1) Turn on the standby air duct (increase 15% ventilation area);

[0204] 2) Condenser fan switches to turbine mode (speed > 3000 rpm);

[0205] 3) Forcedly close the refrigerator air door (reduce 30% cooling consumption).

[0206] Five, real-time optimization algorithm:

[0207] Particle dimension: 4 dimensions (compressor frequency + regenerative power + damper opening + condenser fan speed);

[0208] Fitness function: Wherein, the formula parameter meaning is shown in Table 10 and Table 11:

[0209] Table 10

[0210]

[0211] Table 11

[0212]

[0213] Iteration period: global optimization is performed every 5 minutes.

[0214] The role of fitness function: the fitness function plays the role of multi-objective optimization decision core in the refrigerator intelligent control system, and quantitatively evaluates the comprehensive performance of the control strategy, guiding the algorithm to find the optimal balance point of temperature stability, energy consumption economy and equipment life.

[0215] The essence of fitness function is to convert refrigerator control into a multi-objective optimization problem:

[0216] Mathematically describe the physical world constraints (first law of thermodynamics + equipment mechanical limit);

[0217] Break through the limitations of artificial experience with optimization algorithm (traditional control rule library contains only <100 working conditions);

[0218] Finally realize: three-dimensional breakthrough of temperature stability, energy consumption economy and equipment reliability, and promote the refrigeration industry into a new era of intelligent control.

[0219] Fault self-healing mechanism: when the sensor data is abnormal, start the digital twin simulation:

[0220] 1. Generating a virtual temperature field (0.1 mm grid accuracy) based on a box CFD model, wherein the CFD model (Computational Fluid Dynamics model) refers to a virtual simulation system that accurately reconstructs the three-dimensional temperature field and airflow field inside the refrigerator through numerical simulation technology;

[0221] 2. Reconstructing missing parameters (error < 3%) through a genetic algorithm.

[0222] Six, performance verification data:

[0223] Test a 500L variable frequency refrigerator in a 40℃ constant temperature box for 72 hours, and the test data is shown in Table 12:

[0224] Table 12

[0225] Parameter Traditional control This embodiment Lift range Temperature compliance rate 82.7％ 98.3％ +15.6％ Compressor duty cycle 67％ 49％ -26.9％ Cold storage device utilization rate 18％ 74％ +311％ Maximum temperature difference between inside and outside of the box 58℃→34℃ 58℃→29℃ +5℃ gradient System COP value 2.1 3.4 +61.9％

[0226] In this embodiment, through the prediction-feedback double-loop control and multi-physical field coupling optimization, the following technical effects are achieved in the high temperature maintenance stage:

[0227] 1. Cold supply and demand balance: the cold storage device bears 35-40% of the heat load impact;

[0228] 2. Nonlinear compensation: the heat transfer deviation caused by the deformation of the box is controlled within ±2%;

[0229] 3. Cross-time scale optimization: both second-level response (fan speed regulation) and hour-level strategy (cold storage scheduling) are considered;

[0230] 4. Safety redundancy design: it can still maintain more than 80% temperature control capability when the core component fails.

[0231] The application also provides a refrigerator temperature control device. It should be noted that the refrigerator temperature control device of the application can be used to execute the refrigerator temperature control method provided by the application. The device is used to realize the above embodiments and preferred embodiments, and will not be described again. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware or a combination of software and hardware is also possible and is contemplated.

[0232] The refrigerator temperature control device provided by the application is described below.

[0233] Figure 4 is a schematic diagram of a refrigerator temperature control device according to the application. As shown in Figure 4 , the device includes:

[0234] The first acquisition unit 41 is configured to acquire a predicted ambient temperature sequence of a future preset time period, historical running data of the refrigerator, and a cabinet parameter;

[0235] The prediction unit 42 is configured to construct a long short-term memory network model, input the predicted ambient temperature sequence, the historical running data, and the cabinet parameter into the long short-term memory network model for prediction processing, and obtain an internal temperature prediction sequence of the refrigerator in the future preset time period.

[0236] The determination unit 43 is configured to acquire a temperature setting value and current running data of the refrigerator, determine a temperature control strategy of the refrigerator in the future preset time period according to at least the temperature setting value, the current running data, the cabinet parameter, and the internal temperature prediction sequence of the refrigerator, and control the temperature of the refrigerator by using the temperature control strategy.

[0237] In the embodiment, the first acquisition unit is configured to acquire a predicted ambient temperature sequence of a future preset time period, historical running data of the refrigerator, and a cabinet parameter; the prediction unit is configured to construct a long short-term memory network model, input the predicted ambient temperature sequence, the historical running data, and the cabinet parameter into the long short-term memory network model for prediction processing, and obtain an internal temperature prediction sequence of the refrigerator in the future preset time period; and the determination unit is configured to acquire a temperature setting value and current running data of the refrigerator, determine a temperature control strategy of the refrigerator in the future preset time period according to at least the temperature setting value, the current running data, the cabinet parameter, and the internal temperature prediction sequence of the refrigerator, and control the temperature of the refrigerator by using the temperature control strategy. By means of the above-mentioned method, the refrigerator can make a response in advance according to the change trend of the future ambient temperature, adjust the internal temperature to cope with the upcoming temperature fluctuation, and use the long short-term memory network model to process time sequence data, capture long-term dependencies, and predict the internal temperature prediction value of the refrigerator under the influence of the ambient temperature. According to the internal temperature prediction value of the refrigerator, the corresponding internal temperature prediction value of the refrigerator can be determined, the temperature control precision and stability of the refrigerator can be significantly improved, the temperature fluctuation caused by the sudden change of the ambient temperature can be reduced, and the energy consumption can be reduced. The problem that the existing refrigerator temperature control system relies on the feedback control of the internal sensor and affects the performance of the refrigerator in the case of sudden change of the external environment is solved.

[0238] As an optional solution, the determination unit includes a first determination module configured to determine a compressor frequency value in the temperature control strategy according to the temperature setting value, the internal temperature prediction sequence, and the current running data of the refrigerator, wherein the current running data includes a current temperature value of the refrigerator.

[0239] In an alternative, the determining unit further comprises a second determining module configured to determine the power value of the cold storage plate in the temperature control strategy according to the temperature setting value of the refrigerator, the internal temperature prediction sequence, the effective heat exchange area of the heat conduction medium and the phase change material in the cold storage plate of the refrigerator, the thickness of the phase change material, and the equivalent thermal conductivity.

[0240] In an alternative, the determining unit further comprises a third determining module configured to determine the opening value of the air door of the refrigerator in the temperature control strategy according to the current operation data of the refrigerator, the internal temperature prediction sequence, the preset position thermal resistance coefficient of the air duct of the refrigerator, the air door response sensitivity, and the safety threshold of the refrigerator system, wherein the current operation data comprises the average temperature of the compartment of the refrigerator and the real-time temperature of the preset position of the air duct of the refrigerator.

[0241] In an alternative, the determining unit further comprises a fourth determining module and a fifth determining module, the fourth determining module is configured to obtain the relative humidity and the temperature of the environment, and determine the temperature difference between the condenser and the environment according to the temperature of the environment and the condenser temperature; the fifth determining module is configured to determine the current rotating speed of the condenser fan of the refrigerator in the temperature control strategy according to the current rotating speed of the condenser fan of the refrigerator, the temperature difference between the condenser and the environment, the condenser temperature rise rate, and the relative humidity of the environment, wherein the current operation data comprises the current rotating speed of the condenser fan, the condenser temperature, and the condenser temperature rise rate.

[0242] In an alternative, the device further comprises a control unit configured to, in the process of controlling the temperature of the refrigerator by using the temperature control strategy, determine that the condenser temperature of the refrigerator is too high when detecting that the condenser temperature of the refrigerator is greater than a preset temperature, control the refrigerator to open a standby air duct, control the rotating speed of the condenser fan of the refrigerator to reach a preset rotating speed, and forcibly close the air door of the refrigerator.

[0243] In an alternative, the device further comprises a second obtaining unit and an evaluation unit; the second obtaining unit is configured to, after controlling the temperature of the refrigerator by using the temperature control strategy, obtain the temperature exceeding cumulative amount, the total power consumption, and the number of compressor start-stop cycles of the refrigerator after a preset time period, wherein the temperature exceeding cumulative amount is the square deviation integral value of the measured temperature in the refrigerator and the set temperature; the evaluation unit is configured to evaluate the comprehensive performance of the refrigerator under the control of the temperature control strategy according to the temperature exceeding cumulative amount, the total power consumption, and the number of compressor start-stop cycles.

[0244] The temperature control device of the refrigerator comprises a processor and a memory, the first acquisition unit, the prediction unit, the determination unit and the like are stored in the memory as program units, and the corresponding functions are realized by executing the program units stored in the memory by the processor.

[0245] The processor comprises a core, and the core retrieves the corresponding program units from the memory.

[0246] The memory can comprise a non-permanent memory in a computer readable medium, a random access memory (RAM) and / or a non-volatile memory such as a read-only memory (ROM) or a flash memory (flash RAM), and the memory comprises at least one memory chip.

[0247] The embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium comprises a stored program.

[0248] The embodiment of the present application provides a refrigerator, which comprises a controller.

[0249] The embodiment of the present application provides a processor, and the processor is used for running a program.

[0250] The embodiment of the present application provides an electronic device, and the device comprises a processor, a memory and a program stored in the memory and capable of running on the processor.

[0251] The device in the present application can be a server, a PC, a PAD, a mobile phone or the like.

[0252] The present application further provides a computer program product, which is adapted to execute the program initialized with at least the refrigerator temperature control method steps when executed on a data processing device.

[0253] It should be apparent to those skilled in the art that the modules or steps of the application described above can be implemented with a general purpose computer, and can be centralized in a single computer or distributed among a network of computers, and can be implemented with program code executable by a computer, and thus can be stored in a storage device and executed by a computer, and in some cases, the steps shown or described can be executed in a different order than shown or described, or can be implemented as separate integrated circuit modules or as a single integrated circuit module, and thus the application is not limited to any particular combination of hardware and software.

[0254] Those skilled in the art will appreciate that embodiments of the application can be devised for a method, a system, or a computer program product. Accordingly, the application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the application can be in the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk memory, CD-ROMs, optical storage media, etc.) embodying computer readable program code.

[0255] The present application is described in reference to the flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 The flowchart illustrations and / or block diagrams Figure 1 Means for performing the function specified by the

[0256] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flowchart illustrations and / or block diagrams. Figure 1 The flowchart illustrations and / or block diagrams Figure 1 Means for performing the function specified by the

[0257] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flowchart illustrations and / or block diagrams.Figure 1 one or more processes and / or functions specified in one or more blocks Figure 1 one or more processes and / or functions specified in one or more blocks

[0258] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0259] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory, non-volatile memory, such as read-only memory (ROM), EPROM, and / or flash memory, etc. The memory is an example of computer readable media.

[0260] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0261] The technical features of the above-described embodiments can be combined in any manner. In order to make the description concise, not all possible combinations of the technical features in the above-described embodiments are described, however, as long as the combination of the technical features does not contradict, it should be considered within the scope of the present specification.

[0262] It should also be noted that the terms "comprising", "including", or any other variant are intended to cover non-exclusive inclusions, so that processes, methods, articles or devices that include a series of elements not only include those elements, but also include other elements not explicitly listed, or inherent to such processes, methods, articles or devices. Without more limitations, the element defined by the statement "including a" does not exclude the presence of additional identical elements in the process, method, article or device including the element.

[0263] The above descriptions are only the preferred embodiments of the present application, and are not intended to limit the present application. The present application can have various modifications and changes for those skilled in the art. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A temperature control method of a refrigerator, characterized by, The method comprises the following steps: obtaining a predicted ambient temperature sequence of a future preset time period, historical running data and cabinet parameters of a refrigerator; constructing a long short-term memory network model, inputting the predicted ambient temperature sequence, the historical running data and the cabinet parameters into the long short-term memory network model for prediction processing to obtain an internal temperature prediction sequence of the refrigerator in the future preset time period; obtaining a temperature setting value and current running data of the refrigerator, and determining a temperature control strategy of the refrigerator in the future preset time period according to at least the temperature setting value, the current running data, the cabinet parameters and the internal temperature prediction sequence of the refrigerator, and controlling the temperature of the refrigerator by using the temperature control strategy.

2. The method of claim 1, wherein, The method for determining the temperature control strategy of the refrigerator in the future preset time period according to the temperature setting value, the current running data, the cabinet parameters and the internal temperature prediction sequence of the refrigerator comprises the following steps: determining a compressor frequency value in the temperature control strategy according to the temperature setting value, the internal temperature prediction sequence and the current running data of the refrigerator, wherein the current running data comprises a current temperature value of the refrigerator.

3. The method of claim 1, wherein, The method for determining the temperature control strategy of the refrigerator in the future preset time period according to at least the temperature setting value, the current running data, the cabinet parameters and the internal temperature prediction sequence of the refrigerator comprises the following steps: determining a cold storage board power value in the temperature control strategy according to the temperature setting value, the internal temperature prediction sequence, the effective heat exchange area of the heat conducting medium and the phase change material in the cold storage board of the refrigerator, the thickness and the equivalent thermal conductivity of the phase change material.

4. The method of claim 1, wherein, The method for determining the temperature control strategy of the refrigerator in the future preset time period according to at least the temperature setting value, the current running data, the cabinet parameters and the internal temperature prediction sequence of the refrigerator comprises the following steps: determining a refrigerator damper opening value in the temperature control strategy according to the current running data, the internal temperature prediction sequence, the refrigerator air duct preset position thermal resistance coefficient, the damper response sensitivity and the refrigerator system safety threshold of the refrigerator, wherein the current running data comprises a compartment average temperature and a refrigerator air duct preset position real-time temperature of the refrigerator.

5. The method of claim 1, wherein, The method for determining the temperature control strategy of the refrigerator in the future preset time period according to at least the temperature setting value, the current running data, the cabinet parameters and the internal temperature prediction sequence of the refrigerator comprises the following steps: obtaining an ambient relative humidity and an ambient temperature, and determining a condenser and ambient temperature difference according to the ambient temperature and the condenser temperature; determining a condenser fan speed in the temperature control strategy according to the current speed of the condenser fan of the refrigerator, the condenser and ambient temperature difference, the condenser temperature rise rate and the ambient relative humidity, wherein the current running data comprises the current speed of the condenser fan, the condenser temperature and the condenser temperature rise rate.

6. The method of claim 1, wherein, In the process of controlling the temperature of the refrigerator by using the temperature control strategy, the method further comprises the following steps: In a case where it is detected that the condenser temperature of the refrigerator is greater than a preset temperature, it is determined that the condenser temperature is too high, the refrigerator is controlled to open a standby air duct, the condenser fan of the refrigerator is controlled to reach a preset rotating speed, and a damper of the refrigerator is forcibly closed.

7. The method according to any one of claims 1 to 6, characterized in that, After the temperature of the refrigerator is controlled by using the temperature control strategy, the method further includes: After a preset time period, a temperature over-standard cumulative amount, total power consumption, and compressor start-stop cycle number of the refrigerator are obtained, wherein the temperature over-standard cumulative amount is a square deviation integral value of a measured temperature in the refrigerator and a set temperature; According to the temperature over-standard cumulative amount, the total power consumption, and the compressor start-stop cycle number, a comprehensive performance of the refrigerator under the control of the temperature control strategy is evaluated.

8. A temperature control device for a refrigerator, characterized by comprising: Comprise: A first obtaining unit is configured to obtain a predicted ambient temperature sequence of a future preset time period, historical running data of a refrigerator, and a cabinet parameter; A prediction unit is configured to construct a long short-term memory network model, input the predicted ambient temperature sequence, the historical running data, and the cabinet parameter into the long short-term memory network model for prediction processing, and obtain an internal temperature prediction sequence of the refrigerator in the future preset time period; A determination unit is configured to obtain a temperature set value and current running data of the refrigerator, determine a temperature control strategy of the refrigerator in the future preset time period according to at least the temperature set value, the current running data, the cabinet parameter, and the internal temperature prediction sequence of the refrigerator, and control the temperature of the refrigerator by using the temperature control strategy.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium comprises a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the temperature control method of the refrigerator in any one of claims 1 to 7.

10. A refrigerator characterized by comprising: Comprise: A controller is configured to execute the temperature control method of the refrigerator in any one of claims 1 to 7.

Images