A refrigerator temperature control system, method and refrigerator

Abstract

The present disclosure provides a refrigerator temperature control system, method and refrigerator, relating to the technical field of refrigerator temperature control. The refrigerator temperature control system comprises a collection terminal and a processing terminal. The collection terminal is used to collect a plurality of temperature and humidity data of a refrigeration path and an environment in which the refrigerator is located in a historical period, and label data of the environment; the processing terminal is used to analyze the change characteristics of the plurality of temperature and humidity data to obtain operation state data of the refrigerator; a preset regression model is trained and tested, so that various types of data construct a regression relationship with the historical temperature in the cabinet in the corresponding insensitive band; the current environment data of the refrigerator is input into the trained regression model, and the target cabinet temperature of the refrigerator is obtained based on the output result of the regression model; and the refrigeration temperature of the refrigerator in a future period is controlled according to the target cabinet temperature. The technical scheme formulates different temperature control strategies for different environments, so that the refrigerator realizes adaptive control of temperature in different scenes.

Description

Technical Field

[0001] This disclosure relates to the technical field of freezer temperature control, specifically to a freezer temperature control system, method, and freezer. Background Technology

[0002] In today's market, freezers are widely used in food, pharmaceutical and other fields, and their temperature control accuracy directly affects the preservation effect and energy efficiency of goods. Currently, there are two main solutions to achieve intelligent temperature control: the first is to control the temperature based on a strict rule base, controlling the start and stop of the compressor and evaporator / condenser fan by preset temperature thresholds and temperature hysteresis ranges; the second is to use a PID (Proportional-Integral-Derivative) algorithm to adjust the compressor power based on the first solution, so as to achieve dynamic temperature control.

[0003] Looking at mainstream solutions, existing technologies mostly use rule-based temperature control systems, but they are all unable to dynamically adapt to the complex temperature control scenarios of freezers, and have not fundamentally solved the problem that existing freezers cannot achieve temperature self-adaptation. Summary of the Invention

[0004] This disclosure provides a freezer temperature control system, method, and freezer; enabling the freezer to achieve adaptive temperature control in different scenarios.

[0005] The technical solution disclosed herein is implemented as follows:

[0006] In a first aspect, embodiments of the present invention provide a freezer temperature control system, the system comprising:

[0007] The data acquisition terminal is used to collect multiple temperature and humidity data of the freezer during historical periods, including the refrigeration path and the surrounding environment, as well as the label data of the surrounding environment.

[0008] The processing terminal is connected to the acquisition terminal. The processing terminal is used to analyze the changing characteristics of multiple temperature and humidity data to obtain the operating status data of the freezer.

[0009] Based on multiple temperature and humidity data, label data, and operating status data, the preset regression model is trained and tested to establish a regression relationship between various types of data and the historical temperature inside the cabinet in the corresponding insensitive zone.

[0010] Input the current environmental data of the freezer into the trained regression model, and obtain the target internal temperature of the freezer based on the output of the regression model;

[0011] The cooling temperature of the freezer is controlled based on the target internal temperature, and the regression model is retrained after the future period to implement temperature regulation.

[0012] In one optional embodiment, the data acquisition terminal includes:

[0013] A humidity sensor, connected to the first input terminal of the processing terminal, is installed on the freezer; the humidity sensor is used to collect the ambient humidity of the freezer and output it externally.

[0014] The first temperature sensor is connected to the second input terminal of the processing terminal and is installed on the freezer. The first temperature sensor is used to collect the first temperature of the environment in which the freezer is located and output it to the outside.

[0015] The second temperature sensor is connected to the third input terminal of the processing terminal. The second temperature sensor is installed inside the freezer and connected to the storage space of the freezer. The second temperature sensor is used to collect the second temperature of the storage space inside the freezer and output it to the outside.

[0016] The third temperature sensor is connected to the fourth input terminal of the processing terminal. The third temperature sensor is installed at the location of the condenser on the freezer. The third temperature sensor is used to collect the third temperature located on the side of the freezer condenser and output it to the outside.

[0017] The fourth temperature sensor is connected to the fifth input terminal of the processing terminal. The fourth temperature sensor is installed at the location of the evaporator on the freezer. The fourth temperature sensor is used to collect the fourth temperature located on the side of the freezer evaporator and output it to the outside.

[0018] In one alternative embodiment, the processing terminal includes:

[0019] The server is configured to communicate with the data acquisition terminal. The server is used to process the data output by the data acquisition terminal to obtain the target internal temperature of the freezer.

[0020] The controller is configured to communicate with the server and is installed inside the freezer. The controller is used to control the cooling temperature of the freezer in a future period based on the target temperature inside the freezer.

[0021] In a second aspect, embodiments of the present invention also provide a method for controlling the temperature of a freezer, applicable to any of the control systems in the first aspect, the method comprising:

[0022] Acquire multiple temperature and humidity data of the freezer during historical periods, including the refrigeration path and the surrounding environment, as well as the label data of the surrounding environment.

[0023] Analyze the changing characteristics of multiple temperature and humidity data to obtain the operating status data of the freezer;

[0024] Based on multiple temperature and humidity data, label data, and operating status data, the preset regression model is trained and tested to establish a regression relationship between various types of data and the historical temperature inside the cabinet in the corresponding insensitive zone.

[0025] Input the current environmental data of the freezer into the trained regression model, and obtain the target internal temperature of the freezer based on the output of the regression model;

[0026] The cooling temperature of the freezer is controlled based on the target internal temperature, and the regression model is retrained after the future period to implement temperature regulation.

[0027] In one optional embodiment, the variation characteristics of multiple temperature and humidity data are analyzed to obtain the operating status data of the freezer, including:

[0028] Based on the change of each temperature and humidity data over time, data curves for each temperature and humidity data are obtained. Among them, multiple data curves include the ambient humidity curve and the first temperature curve of the environment where the freezer is located, the second temperature curve of the storage space inside the freezer, the third temperature curve of the condenser side of the freezer, and the fourth temperature curve of the evaporator side of the freezer.

[0029] The relationship between the ambient humidity curve, the first temperature curve, the second temperature curve, the third temperature curve, and the fourth temperature curve is analyzed to obtain the opening and closing frequency and operating load rate of the freezer.

[0030] The frequency of door opening and closing and the operating load rate are determined as the operating status data of the freezer.

[0031] In an optional embodiment, before training and testing the preset regression model, the method further includes:

[0032] When the freezer reaches a target state that meets multiple preset conditions, obtain the cooling power consumption of the freezer during the preset time of operation in the target state and the temperature change of the internal storage space of the freezer.

[0033] Based on the refrigeration power consumption, temperature change, and the mass of newly added items in the storage space inside the freezer, the specific heat capacity data of the stored items inside the freezer are obtained.

[0034] Configure specific heat capacity data as the target data for training and testing the regression model.

[0035] In one optional embodiment, determining that the freezer has reached a target state that satisfies multiple preset conditions includes:

[0036] It is determined that the freezer is not running in energy-saving mode, the current door status is closed, and the door has completed the preset number of pull-down temperature cycles after the last closing.

[0037] If so, then confirm that the freezer is operating in the target state.

[0038] In an optional embodiment, before training and testing the preset regression model, the method further includes:

[0039] During the nighttime period, the current customer flow of the freezer is determined based on the second temperature change in the internal storage space of the freezer.

[0040] When the current passenger flow is lower than the preset value, the regression model is trained and tested.

[0041] In an optional embodiment, before training and testing the preset regression model, the method further includes:

[0042] Determine the working scenario characteristics of the freezer based on at least one of the following data: temperature and humidity data, label data, and operating status data.

[0043] Based on the characteristics of the work scenario, corresponding training weights are configured for various types of data to improve the prediction accuracy of the regression model for the target cabinet temperature in the corresponding scenario.

[0044] Thirdly, embodiments of the present invention also provide a freezer, which includes any of the control systems described in the first aspect.

[0045] The present invention has the following beneficial effects:

[0046] The technical solution of this invention includes a data acquisition terminal and a processing terminal. The data acquisition terminal is used to collect multiple temperature and humidity data of the freezer during historical periods, including the refrigeration path and the surrounding environment, as well as the label data of the surrounding environment, providing raw time-series data reflecting changes in the refrigeration path and environment. The processing terminal is used to analyze the changing characteristics of the multiple temperature and humidity data to obtain the freezer's operating status data. Since the multiple temperature and humidity data, label data, and operating status data characterize the freezer's usage status and disturbance operating characteristics from different dimensions, a preset regression model is trained and tested, enabling various types of data to establish regression relationships with the historical temperature inside the freezer in their corresponding insensitive zones. The regression relationships are constructed and verified using multi-source features as training basis. The current environmental data of the freezer is input into the trained regression model, and the target temperature inside the freezer is obtained based on the output of the regression model. The refrigeration temperature of the freezer is controlled according to the target temperature inside the freezer in future periods, and the regression model is retrained after the future periods to implement temperature regulation. This technical solution collects a large amount of data to determine the environment in which the freezer is located and formulates different temperature control strategies for different environments. The regression model then determines the contribution of different data features to the internal temperature of the freezer within their respective insensitive zones, thereby closing the loop to correct prediction errors and adjust model parameters, forming a continuous adaptive prediction, execution, and update cycle. This fundamentally bypasses the limitations of using a PID algorithm to control the compressor frequency alone, resulting in higher efficiency and more reasonable control logic, thus enabling the freezer to achieve adaptive temperature control in different scenarios. Attached Figure Description

[0047] Figure 1This is a schematic diagram of a refrigerator temperature control system provided in one embodiment of the present invention;

[0048] Figure 2 A flowchart illustrating a method for controlling the temperature of a freezer according to an embodiment of the present invention;

[0049] Figure 3 A first schematic diagram illustrating the training of a regression model according to an embodiment of the present invention;

[0050] Figure 4 A second schematic diagram illustrating the training of a regression model according to an embodiment of the present invention;

[0051] Figure 5 This is a schematic diagram of the temperature insensitivity zone between the cabinet interior and ambient temperature, provided in one embodiment of the present invention.

[0052] Figure 6 A schematic diagram of the insensitive zone between the cabinet temperature and the fourth temperature on the evaporator side, provided in an embodiment of the present invention;

[0053] Figure 7 This is an implementation architecture diagram of the refrigerator temperature control provided in one embodiment of the present invention. Detailed Implementation

[0054] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a freezer temperature control system, method, and freezer proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0056] Regarding temperature control strategies for freezers, the first approach employs a strict rule base to control temperature. For example, it obtains a temperature threshold based on the sum of the set temperature and the temperature hysteresis. Cooling is initiated when the internal temperature is greater than or equal to the threshold; cooling is stopped and the compressor is shut down when the internal temperature is less than or equal to 1°C below the set temperature. The second approach combines the first approach with PID control, but it can only be applied to freezers equipped with variable frequency compressors, thus limiting its application. Currently, although intelligent temperature controllers are widely used in freezers, their verification still relies on setting fixed temperature thresholds based on human experience, and suffers from the following problems:

[0057] 1. Poor environmental adaptability: When the external temperature fluctuates or the frequency of door opening and closing changes, the fixed threshold is prone to causing the internal temperature to exceed the limit, and it cannot dynamically adapt to changes in the environment.

[0058] 2. Energy waste: Excessive cooling or unreasonable temperature hysteresis settings lead to power loss.

[0059] 3. Insufficient intelligence: Lack of comprehensive analysis capabilities for multi-source data (such as load and item type).

[0060] In summary, existing technologies for temperature control of freezers cannot enable adaptive temperature control in different scenarios. The following, in conjunction with the accompanying drawings, specifically describes a freezer temperature control system, method, and specific freezer solution provided by this invention.

[0061] Please see Figure 1 , Figure 1 This is a schematic diagram of a refrigerator temperature control system according to an embodiment of the present invention. The control system includes a data acquisition terminal 1 and a processing terminal 2. The data acquisition terminal 1 is connected to the processing terminal 2 to transmit the acquired data to the processing terminal 2.

[0062] The data acquisition terminal 1 can be configured with multiple temperature and humidity sensors to collect various temperature and humidity data of the freezer during historical periods along the refrigeration path and in its surrounding environment, as well as label data of the environment. The data acquisition terminal and processing terminal can be built on an embedded system architecture. Signal conditioning circuits and data transmission circuits can be configured at the output terminals of each temperature and humidity sensor. The signal conditioning circuit filters the raw signals of each temperature and humidity data, and the data transmission circuit transmits the filtered raw signals according to a preset protocol. For example, a low-pass filter can be used to reduce high-frequency noise interference during the acquisition process, and an amplification circuit can be used to condition the signal amplitude to meet the input requirements of the analog-to-digital converter. An analog-to-digital conversion unit can be set on the data acquisition terminal to convert the filtered and amplified analog signals into digital signals, which are then transmitted to the processing terminal 2 via the data bus of the data transmission circuit or a wireless communication module (such as RS485, Bluetooth, or Wi-Fi).

[0063] Processing terminal 2 is used to analyze the variation characteristics of multiple temperature and humidity data to obtain the operating status data of the freezer. The operating status data characterizes the frequency of door opening and closing, load rate, etc., of the freezer operation. Based on multiple temperature and humidity data, label data, and operating status data, a preset regression model is trained and tested to establish a regression relationship between various data and the historical temperature inside the freezer in the corresponding insensitive zone. The regression model can be configured as an SVR (Support Vector Regression) model; of course, it can also be configured as a decision tree model or a random forest model, without specific restrictions. The current environmental data of the freezer is input into the trained regression model, and the target internal temperature of the freezer is obtained based on the output of the regression model. The cooling temperature of the freezer is controlled according to the target internal temperature in the future period, and the regression model is retrained after the future period to implement temperature control.

[0064] The processing terminal can be integrated into the main control board of the freezer temperature controller. Its hardware structure includes a microprocessor, memory, and interface circuits. The microprocessor is used to perform data parsing and regression model training calculations, while the memory is used to store various data and model parameters from historical periods. The processing terminal can be further configured with an independent power supply regulator circuit and heat sink to prevent calculation errors caused by power supply fluctuations or heat accumulation. The processing terminal can also be connected to the control circuits of the freezer's compressor, evaporator fan, and condenser fan at its output end, executing control commands for the target freezer temperature via PWM speed regulation or relay switching. Through the above hardware configuration, the acquisition terminal achieves high-precision acquisition and anti-interference processing of environmental data, and the processing terminal achieves integrated execution of data processing and temperature control, thereby ensuring that the entire temperature control system can stably and accurately implement adaptive temperature control under different operating environments.

[0065] In practical applications, collecting local temperatures at specific locations along the refrigeration path of a freezer may affect the accuracy of subsequent temperature predictions within the target freezer. Therefore, in one specific implementation, the data acquisition terminal includes a humidity sensor, a first temperature sensor, a second temperature sensor, a third temperature sensor, and a fourth temperature sensor. The models of each temperature and humidity sensor can be selected based on actual needs; for example, 18B20 sensors can be used for temperature data acquisition. By setting up each temperature and humidity sensor, data from their respective locations can be acquired and stored and updated at preset intervals. Since the heat exchange process of a freezer involves four typical thermal nodes—the external environment, the storage space, the condenser side (i.e., the condenser side), and the evaporator side (i.e., the evaporator side)—the dynamic changes in temperature at each node directly reflect the efficiency of the refrigeration cycle and the changing patterns of the heat load.

[0066] The humidity sensor is connected to the first input terminal of the processing terminal. The humidity sensor is installed on the freezer, located outside the storage space. It collects the ambient humidity of the freezer and outputs the data to the processing terminal. High humidity environments reduce the heat transfer efficiency of the freezer evaporator. Ambient humidity indicates the impact of air moisture content on the freezer's heat dissipation and frost formation; therefore, humidity data is an important parameter for assessing environmental load.

[0067] The first temperature sensor is connected to the second input terminal of the processing terminal and is installed on the freezer. The first temperature sensor is used to collect the first temperature of the environment in which the freezer is located and output it to the processing terminal. The first temperature serves as the external boundary condition for the freezer's temperature control and is the basic data for calculating the heat dissipation capacity of the refrigeration system and the amount of external heat penetration.

[0068] The second temperature sensor is connected to the third input terminal of the processing terminal. The second temperature sensor is installed inside the freezer and connected to its storage space. It collects the second temperature within the storage space inside the freezer and outputs it to the processing terminal. Changes in this second temperature can determine whether the freezer's cooling has met the set requirements and can also determine the temperature fluctuation range inside the freezer, thus providing benchmark data for the regression model's output and temperature control feedback.

[0069] The third temperature sensor is connected to the fourth input terminal of the processing terminal. The third temperature sensor is installed at the location of the condenser on the freezer. It collects the third temperature located on the condenser side of the freezer and outputs it to the processing terminal. The third temperature characterizes the thermal state of the high-temperature end of the freezer's refrigeration cycle. The difference between the third temperature and the ambient temperature characterizes the condensing efficiency and heat dissipation. When the ambient temperature is high or ventilation is poor, the condenser temperature rises, leading to increased energy consumption. Therefore, this data reflects the freezer's operating performance under high load.

[0070] The fourth temperature sensor is connected to the fifth input terminal of the processing terminal. The fourth temperature sensor is installed at the location of the evaporator on the freezer. It collects the fourth temperature located on the evaporator side of the freezer and outputs it to the processing terminal. This fourth temperature characterizes the temperature at the low-temperature end of the refrigeration cycle. Its value changes correspond to the temperature characteristics at the compressor's suction end, reflecting the evaporator's heat absorption effect and evaporation temperature fluctuations, and indirectly reflecting the refrigerant flow rate and evaporation intensity of the freezer.

[0071] Through the coordinated arrangement of the four temperature and humidity sensors, the temperature control system can establish a temperature and humidity distribution database at four key thermal nodes: the external environment, the condenser side, the evaporator side, and the storage space, obtaining temperature gradient information throughout the refrigeration path. The collected multidimensional data characterizes the thermal cycle state of the freezer and provides a sufficient data foundation for processing terminal analysis of operating status data and establishing regression relationships, thereby enabling the freezer to achieve precise temperature control and adaptive adjustment under different environmental and load conditions.

[0072] After collecting the aforementioned feature data, the data is stored in memory as a two-dimensional data set, with the collection time as the row index and the data value as the column index, awaiting retrieval by the processing terminal. It should be noted that due to space constraints on the circuit board layout of freezers, most thermostats on the market today do not even have flash memory chips. Even the flash memory in some high-end thermostats has a capacity of only around 4Mb. Therefore, the memory capacity limitation of the thermostat must be considered when designing the data storage logic. Taking 4Mb as an example, according to actual tests, if data is stored at a set point every half hour, the flash memory can support three months of data storage. After comprehensive consideration, the total data collection volume was set to 72 hours, collected every ten minutes. The advantage of this is that it provides sufficient data for machine learning in the regression model without affecting the thermostat's normal historical data storage function. After the 72-hour data storage capacity is full, newly collected data will gradually replace data with earlier timestamps according to the time index, ensuring that the data stored in memory is the latest 72-hour data, thus ensuring the data's adaptability to seasonal environments.

[0073] Training regression models requires significant computing power, but the hardware configured in freezers often uses lower-power hardware to balance energy consumption and cost. Therefore, in one specific implementation, the processing terminal includes a server and a controller. The server can be configured as a cloud server or a local server communicating via network cable.

[0074] The server is configured to communicate with the data acquisition terminal. It processes the data output by the terminal to obtain the target internal temperature of the freezer. The server possesses high computing power and can run support vector machine regression algorithms to fit and predict multi-source feature data, thereby accurately outputting the target internal temperature of the freezer.

[0075] The controller is configured to communicate with the server and is installed inside the freezer. It controls the freezer's cooling temperature for future periods based on the target internal temperature. The controller achieves accurate temperature control within the freezer by adjusting the operation of the compressor, evaporator fan, and condenser fan. The distributed design of the server and controller ensures that data computation and execution control are independent, guaranteeing both high-performance data analysis at the computational level and real-time performance and stability of the device-side control.

[0076] Based on the same technical concept as the control system, this invention also provides a method for controlling the temperature of a freezer. Please refer to [link / reference]. Figure 2 , Figure 2 This is a flowchart of a method for controlling the temperature of a freezer. This method is applied to any of the control systems mentioned above. The control method can be run based on the processing terminal of the control system. The control method includes:

[0077] S11. Obtain multiple temperature and humidity data of the freezer during historical periods in the refrigeration path and the surrounding environment, as well as the label data of the surrounding environment.

[0078] Specifically, the historical time period can be configured based on the temperature control accuracy requirements of the freezer, for example, 72 hours prior to training the regression model. Each temperature and humidity data point represents the temperature or humidity of the freezer at the corresponding node in the refrigeration path or in its environment, and can be acquired through various sensors. Tag data can represent the season and / or geographical location of the environment. When tag data represents the season, the season tag is calculated by the temperature controller's built-in clock based on the date and time; when representing the geographical location tag, the geographical coordinates are obtained by the temperature controller's built-in communication unit from the network base station. A 72-hour sliding window can be used to save the most recently acquired data to balance storage limitations with the training sample size requirements of the regression model. After acquiring various data through various sensors, clocks, and network base station coordinates, proceed to step S12.

[0079] S12. Analyze the changing characteristics of multiple temperature and humidity data to obtain the operating status data of the freezer.

[0080] Specifically, multiple temperature and humidity data can characterize changes in the freezer's operating status. For example, the openness of the freezer door can be determined based on the temperature change characteristics inside the freezer, and the frequency of door opening and closing can be determined by counting the number of times the door is opened. Alternatively, door opening and closing events can be identified based on temperature abrupt changes and recovery curves to calculate the door opening and closing frequency. Since temperature and humidity data change over time, time-domain features can be extracted and events detected based on this data. For example, the first-order difference of the internal temperature / humidity, short-term maximum and minimum values, recovery time, and energy consumption per operating cycle can be calculated. These data characterize the operating status, and the operating load rate can be estimated based on the recovery time and amplitude of the evaporator-side temperature within the compressor cycle. The extracted operating status data is added to the feature set in standardized numerical form as an indicator reflecting freezer operating disturbances and load.

[0081] For example, step S12 includes sub-steps S12-1 to S12-3, which are described in detail below:

[0082] S12-1. Based on the change of each temperature and humidity data point over time, obtain the data curves for each temperature and humidity data point. These multiple data curves include the ambient humidity curve and the first temperature curve for the environment where the freezer is located; the second temperature curve for the internal storage space of the freezer; the third temperature curve for the condenser side of the freezer; and the fourth temperature curve for the evaporator side of the freezer. Each temperature curve represents the change of the corresponding temperature data over time. By analyzing each temperature curve, the operational events that occur during the operation of the freezer can be identified.

[0083] S12-2. Analyze the relationship between the ambient humidity curve, the first temperature curve, the second temperature curve, the third temperature curve, and the fourth temperature curve to obtain the door opening / closing frequency and operating load rate of the freezer. When the freezer door is opened, the internal temperature rises instantaneously due to the entry of hot air from outside; after the door is closed, the evaporator side temperature drops rapidly to return to the set temperature. Therefore, the first derivative of the fourth temperature curve, which characterizes the change in evaporator side temperature data over a continuous period, can be calculated. When a positive temperature jump is detected within a short period, such as a temperature change greater than 2°C, and the temperature difference with the ambient temperature decreases, it is determined as a door opening event; after the door is closed, the first derivative changes from positive to negative and returns to stability, which is defined as a door closing event. Statistical analysis of the occurrence cycle of door opening / closing events yields the door opening / closing frequency per unit time. Since the temperature changes caused by door opening / closing are simultaneously characterized by the ambient humidity curve, the first temperature curve, the second temperature curve, and the third temperature curve, the change characteristics characterized by the fourth temperature curve can be verified through other curves to accurately analyze the door opening / closing frequency.

[0084] Furthermore, the operating load of the freezer is related to the thermal balance of the refrigeration system. A higher operating load results in a higher compressor start frequency and longer operating time. The load level can be analyzed using a fourth temperature curve characterizing evaporator-side temperature changes and a third temperature curve characterizing condenser-side temperature changes. For example, within each compressor operating cycle, the operating time from compressor start-up to shutdown can be measured. The compressor stops when the cabinet temperature returns to the set target value; simultaneously, the evaporator temperature drop during this cycle is calculated. The effective cooling power per unit time is defined as the ratio of the cycle operating time to the temperature drop rate, i.e. , Effective cooling power; based on historical no-load reference power. With effective cooling power The ratio is used to calculate the operating load rate for the corresponding operating cycle. ,Right now This calculation method is based on the energy balance equation of the refrigeration system, assuming that the cooling capacity of the compressor is constant under the same conditions. Therefore, the longer the temperature recovery time, the lower the cooling efficiency, which means that the operating load is greater.

[0085] It should be noted that the load rate can also be calculated using fitting models such as linear regression or recurrent neural networks. Based on the corresponding curves, the evaporator temperature drop rate, condenser temperature rise rate, and ambient temperature gradient are obtained. Using the evaporator temperature drop rate, condenser temperature rise rate, and ambient temperature gradient as input features, the functional relationship between the compressor operating cycle and the cooling rate is fitted, thereby estimating the operating load rate of the freezer per unit time.

[0086] S12-3. Door opening / closing frequency and operating load rate are defined as the operating status data of the freezer. Door opening / closing frequency represents the user's usage behavior of the freezer, and its changes directly affect the heat exchange between the freezer and the external environment. Operating load rate reflects the matching between the internal heat capacity of the freezer's contents and the output capacity of the refrigeration system, and is a parameter describing the internal heat load level of the equipment. These two types of parameters can dynamically reflect the degree of thermal disturbance and cooling intensity of the freezer under different operating conditions, and are key state quantities that directly affect the temperature change inside the freezer.

[0087] At this point, the calculation of the operating status data has been completed, and we proceed to step S13.

[0088] S13. Based on multiple temperature and humidity data, label data, and operating status data, train and test the preset regression model to establish a regression relationship between various data in the corresponding insensitive zone and the historical temperature inside the cabinet.

[0089] Specifically, this step includes distinguishing between the training and test sets, and training a regression model using the training set data. To adapt the freezer's temperature control to seasonal changes, such as increased humidity in summer, the regression model can be retrained every 24 hours using the latest 72-hour data to ensure the constructed regression relationship is adapted to the freezer's new operating environment. The input data for the regression model includes the ambient humidity of the freezer's environment, a first temperature representing the ambient temperature, a third temperature on the condenser side, a fourth temperature on the evaporator side, the freezer's door opening and closing frequency and operating load rate, as well as seasonal labels and geographic coordinates. The output of the regression model is a second temperature representing the internal temperature of the freezer.

[0090] When dividing the data into training and test sets, all collected data were divided into training and test sets in a 70% to 30% ratio. The training set comprises 70% to ensure sufficient data for model training. Since the training set includes both input and output data features, the model can find corresponding relationships based on these features to complete training. The remaining 30% serves as the test set. Because the test set has the same data structure as the training set and also includes output features, the input features in the test set can be used to test the model and obtain prediction results. The model's prediction results are then compared with the output features to calculate the prediction accuracy. When the prediction accuracy exceeds a preset accuracy threshold, it indicates that the regression model can accurately predict the temperature inside the cabinet, confirming that the regression model has completed training.

[0091] Because freezers operate in diverse environments, the impact on refrigeration performance varies depending on the environment. For example, if the geographical coordinates indicate that the freezer operates in a tropical region, where seasons are not distinct and winters are hot, similar to summer, then treating all features equally during the training phase of the regression model could lead to prediction biases in specific scenarios.

[0092] Based on this, in one specific implementation, before training and testing the preset regression model, the method further includes:

[0093] Based on at least one of the following data points—temperature and humidity, labeling data, and operational status data—the operating scenario characteristics of the freezer are determined. These characteristics identify the current environmental category and operating mode of the freezer, such as high humidity, high load, frequent door opening, or seasonal transition. Training weights are assigned to each data type based on these operating scenario characteristics to improve the regression model's accuracy in predicting the target freezer's internal temperature within the corresponding scenario. Features with significant impact require increased weighting; conversely, features with relatively minor impact require decreased weighting. For example, humidity data in high-humidity environments and load rate data under high load conditions require increased weighting; seasonal labels for tropical regions require decreased weighting.

[0094] Under normal circumstances, all data features should have the same weight, i.e., 1. However, in certain special scenarios, the weights of some data should be adjusted accordingly. For example, in tropical regions where seasons are not distinct, the actual impact of seasons on freezer temperature is very small. Therefore, in this case, the weight of the season label needs to be reduced to 0.5. By introducing scenario feature recognition and dynamic weight allocation mechanisms, the regression model can focus on the main influencing factors in different working scenarios, thereby effectively suppressing the error amplification caused by scenario differences.

[0095] In practical applications, existing temperature control methods often neglect the differences in heat capacity of the stored items inside the freezer, while the specific heat capacity of the stored items has a relevant impact on the cooling rate and energy consumption. Under the same cooling conditions, the differences in heat capacity of different types of stored items (such as beverages, fruits, and meats) will lead to different temperature response speeds inside the freezer. If this factor is not considered, the predictions of the regression model will be biased, resulting in over-cooling or under-cooling.

[0096] Based on this, in a specific embodiment, before training and testing the preset regression model, the control method further includes: determining when the freezer operates to a target state that meets multiple preset conditions, and obtaining the cooling power consumption and temperature change of the freezer's internal storage space for a preset duration in the target state. The multiple preset conditions include the freezer not operating in energy-saving mode, the current door being closed, and the door being closed for the last time and completing a preset number of temperature drop cycles. The preset number of cycles can be set to 3, i.e., dropping from the current temperature to the set target internal temperature, rising to the hysteresis, and then dropping back to the set target internal temperature, repeating this cycle 3 times. Because by default, an item to be tested will be placed inside when the door is opened, and the item's temperature should be consistent with the local ambient temperature before placement, it should drop to the freezer's set temperature at the start of the calculation. There is generally a temperature difference of about 20°C, requiring at least 3 cooling cycles to ensure that the item's temperature drops to the target temperature.

[0097] After meeting multiple preset conditions, the cooling power consumption of the freezer's refrigeration system within a preset time period is recorded. ; and by monitoring temperature changes inside the cabinet using temperature sensors, the amount of temperature change in the storage space can be determined. The formula for calculating specific heat capacity is: Where C represents specific heat capacity and m represents the mass of the item. It should be noted that the specific heat capacity of food inside the freezer is measured using the most direct calorimetric method, which calculates the specific heat capacity by measuring the temperature change and heat exchange of the item within the freezer. This method requires that the initial temperature of the item being tested be consistent with the freezer's set temperature; therefore, before applying this method, it is necessary to ensure that the temperature of the item being tested has dropped to or is close to the freezer's set temperature. Since the specific heat capacity of items stored in the freezer is related to the freezer's set temperature, the specific heat capacity data needs to be configured as the target data for training and testing the regression model.

[0098] In the daily operation of refrigerated display cases, training regression models requires computational resources. However, if training is performed during periods of high customer traffic or frequent door openings, it may cause system response delays or temperature control instability. Furthermore, the higher the customer traffic, the more frequent the temperature fluctuations in the refrigerated display case, and the greater the data noise. If this data is directly used for model training, it can easily lead to overfitting or prediction bias.

[0099] Based on this, before training and testing the pre-defined regression model, the control methods also include:

[0100] During nighttime hours, the current customer flow of the freezer is determined based on the second temperature change within the freezer's internal storage space. The nighttime period can be set to the early morning hours, and the current customer flow can be calculated using the rate of change and frequency of fluctuation of the second temperature. When the current customer flow is below a preset threshold, the freezer is considered to be in a stable operating state, and the training and testing process of the regression model is then initiated. At this point, temperature changes are stable, the representativeness and continuity of the collected data are higher, and the training process does not affect the freezer's real-time temperature control, thus improving the stability of the freezer's operation.

[0101] After clarifying the basic characteristics of the training and test sets, the training set is imported into the regression model for training. The model chosen here is the Support Vector Machine (SVM) regression model. The core of this regression model is to fit the data by minimizing the prediction error. Taking two-dimensional data as an example... Figure 3 As shown, the regression model defines a boundary consisting of a center line and two parallel boundary lines (dashed lines). The distance between these boundary lines is called the margin. The interval can be freely set; the region outside the interval is denoted as K. The goal of the regression model is to find a function that minimizes the prediction error of data points falling within the interval and the region outside the interval K. These data points falling outside the interval K are called support vectors. Data within the interval is ignored; only support vectors outside the interval affect the model's trend.

[0102] The conditions that points within the boundary in the regression model must satisfy are: x is the input feature vector, such as ambient humidity, tag data, specific heat capacity, and load rate; y is the predicted cabinet temperature. b is the regression coefficient; b is the bias term. The width parameter is the insensitive interval. The objective that the regression model needs to optimize is: That is, to construct a width of The insensitive band minimizes the distance to the data points farthest from the center line, thereby capturing the distribution trend of the data.

[0103] Please see Figure 4 The final result of the regression model processing high-dimensional data is to fit a curve L0, with the insensitive band denoted as S0, thereby achieving the model's predictive function. In the actual model fitting process, the behavior of the regression model can be understood as setting a certain error tolerance range so that most data falls within this range, and minimizing the impact of support vectors on the prediction centerline. In the embodiments of this invention, the learning process of the regression model is automatically completed by the computer; some of the logical processes are explained below.

[0104] Please see Figure 5 We selected two-dimensional data to represent the second temperature of the environment in which the freezer is located and the historical temperature inside the freezer as examples. Since the data is captured at a fixed time, the ambient temperature at a certain moment and the historical temperature inside the freezer have a one-to-one correspondence, which can be placed in a two-dimensional coordinate system.

[0105] Depend on Figure 5 The data shows that the freezer temperature fluctuates between 3℃ and 12℃, while the ambient temperature fluctuates between approximately 22℃ and 28℃ during this period. Setting the insensitivity band width to 3℃, the regression model, under these conditions, gives a prediction result of a straight line L1 with y=25. Figure 5 It can be seen that the 3℃ interval almost encompasses the vast majority of data points, and the support vectors are evenly distributed around the insensitive zone S1. Therefore, the predicted trend of the regression model is accurate and reliable. For the second temperature and the historical temperature inside the cabinet, the regression model predicts that the ambient temperature will remain at 25℃ during this data period and will not change regardless of the cabinet temperature. After obtaining the predictions for the ambient temperature and the historical temperature inside the cabinet, another set of two-dimensional data representing the evaporator-side temperature, the fourth temperature and the historical temperature inside the cabinet, will be selected for regression prediction.

[0106] like Figure 6As shown, the historical temperature data points for the evaporator side and the cabinet interior are distributed within the range of -5℃ to 5℃ on the evaporator side and 3℃ to 12℃ inside the cabinet during this period, corresponding to the normal cooling process of the evaporator. A regression model was used to perform regression analysis on these data points, with an insensitive band S2 set at 3℃ intervals. The resulting regression line is a straight line L2. Based on the data points, the equation of this line can be roughly estimated as follows: Here, x represents the historical temperature inside the cabinet. Based on the analysis, it can be seen that within the above time points, the evaporator-side temperature and the historical temperature inside the cabinet show a significant positive correlation, and the regression equation is: Here, x represents the historical temperature inside the cabinet. The historical temperature inside the cabinet can be calculated using the evaporator side temperature.

[0107] Repeating the same process, all data features are combined pairwise. The regression model will then derive the regression relationships between each set of data features, expressed as an equation. Since this scheme involves nine sets of data features, specifically including the regression relationships between environmental humidity, first temperature, third temperature, fourth temperature, door opening / closing frequency, load rate, geographical coordinates, seasonal labels, and specific heat capacity with nine corresponding historical temperatures inside the cabinet, the prediction equation output after the fitting process should be a high-order polynomial. As previously analyzed, the final regression equation for a two-dimensional array will contain two data features; therefore, the polynomial obtained based on nine sets of data features will encompass all data features, resulting in a more comprehensive and accurate prediction.

[0108] After the fitting process is complete, the final model is a support vector machine regression model. This model is trained using the latest 72 hours of data and is retrained every 24 hours based on updated data to ensure adaptability to the environment. Because the entire process is independent of the temperature control system, data collection, data updates, and model training can all be performed seamlessly. The resource-intensive training process will be scheduled during the early morning hours when passenger traffic is low, so it will not affect the overall operation of the machine.

[0109] At this point, the training and testing of the regression model have been completed, and we will proceed to step S14.

[0110] S14. Input the current environmental data of the freezer into the trained regression model, and obtain the target internal temperature of the freezer based on the output of the regression model.

[0111] Specifically, the current environmental data includes data directly collected by various sensors in the freezer, such as current ambient humidity and current initial temperature. Inputting this data into the regression model yields the target internal temperature that the freezer needs to control. This step can be implemented through interaction between the temperature controller and the regression model, involving each sensor reading environmental data. The temperature controller reads real-time environmental data through its integrated sensors. Importing the current environmental data into the regression model differs from typical rule-based temperature controller systems. Here, the temperature controller interacts with the trained regression model, providing data for prediction. Based on the imported current environmental data, the regression model outputs a prediction result—the most suitable target internal temperature as determined by the model. This temperature value is then fed back to the temperature control system, proceeding to step S15.

[0112] S15. Control the cooling temperature of the freezer in the future period based on the target temperature inside the freezer, and retrain the regression model after the future period to implement temperature regulation.

[0113] Specifically, the predicted temperature value output by the regression model, as the target cabinet temperature, will be accepted by the temperature control system and used to replace its original set temperature. Because the set temperature is specified, the temperature controller will utilize all resources, such as the compressor, evaporator fan, and condenser fan, to adjust the temperature to the target cabinet temperature. The temperature adjustment process can be set with a corresponding implementation frequency, such as adjusting the set temperature once per hour. The more frequent the adjustments, the better the temperature controller's cooling strategy adapts to the ambient temperature. It should be noted that the future time period can be set based on actual conditions, such as a fixed value of 24 hours; of course, it can also be set as a dynamic value of 24-48 hours based on seasonal changes or changes in ambient temperature, without specific limitations.

[0114] After the freezer has been running for 24 hours based on the target internal temperature, the regression model is retrained using the latest 72-hour data to predict the new target internal temperature. The temperature controllers installed inside the freezer then adjust the temperature based on the updated target internal temperature over the next 24 hours.

[0115] Please see Figure 7 , Figure 7 This is a diagram illustrating the implementation architecture of the freezer temperature control system. The server collects real-time feature data, including various data related to the freezer's internal temperature settings; stores and organizes various historical data, updating it based on preset intervals; imports the historical data into a regression model for training and validation; and obtains the trained regression model. The temperature controller imports the current environmental data collected by various sensors into the trained regression model, causing the model to output the target internal temperature of the freezer for a future time period. The temperature controller then adaptively sets the temperature based on the target internal temperature, implementing the freezer's adaptive temperature control strategy.

[0116] Based on the same technical concept as the control system, embodiments of the present invention also provide a freezer, which includes the control system described in any of the above embodiments.

[0117] This invention addresses the technical problems of existing technologies by leveraging the computational advantages of regression models. It calculates the real-time target internal temperature of the freezer based on changes in various environmental variables surrounding the freezer, using this as a temperature threshold and establishing a corresponding temperature control strategy. This transforms traditional passive temperature control into active temperature control, fundamentally solving a series of problems associated with setting fixed temperature thresholds based on human experience, such as frequent start-stop cycles or temperature overshoot. Strategies that use PID algorithms to adjust compressor frequency suffer from fixed parameters and fail to consider the impact of seasonal changes on heat dissipation efficiency, leading to problems like overcooling in winter and insufficient cooling in summer. Furthermore, these strategies only control the compressor itself, and the compressor frequency has no direct logical relationship with cooling. This invention, however, collects extensive environmental data to assess the external environment and develops different temperature control strategies for different environments. It fundamentally bypasses the limitations of solely controlling the compressor frequency with PID algorithms, directly affecting temperature settings, resulting in higher efficiency and more rational control logic.

[0118] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0119] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A temperature control system for a freezer, characterized in that, The system includes: The data acquisition terminal is used to collect multiple temperature and humidity data of the freezer during historical periods, including the refrigeration path and the surrounding environment, as well as the label data of the surrounding environment. A processing terminal is connected to the acquisition terminal. The processing terminal is used to analyze the variation characteristics of the multiple temperature and humidity data to obtain the operating status data of the freezer. Based on the multiple temperature and humidity data, the label data, and the operating status data, the preset regression model is trained and tested to establish a regression relationship between various types of data and the historical temperature inside the cabinet in the corresponding insensitive zone. The current environmental data of the freezer is input into the trained regression model, and the target internal temperature of the freezer is obtained based on the output of the regression model. The refrigeration temperature of the freezer is controlled according to the target temperature inside the freezer for a future period, and the regression model is retrained after the future period to implement temperature regulation. Before training and testing the pre-defined regression model, the following steps are also included: When the freezer is determined to operate to a target state that meets multiple preset conditions, the cooling power consumption of the freezer and the temperature change of the internal storage space of the freezer are obtained for a preset duration of operation in the target state. Based on the cooling power consumption, the temperature change, and the mass of newly added items in the storage space inside the freezer, the specific heat capacity data of the stored items in the freezer are obtained. The specific heat capacity data is configured as the target data for training and testing the regression model.

2. The freezer temperature control system according to claim 1, characterized in that, The data acquisition terminal includes: A humidity sensor is connected to the first input terminal of the processing terminal and is installed on the freezer; the humidity sensor is used to collect the ambient humidity of the freezer and output it to the outside. A first temperature sensor is connected to the second input terminal of the processing terminal and is installed on the freezer. The first temperature sensor is used to collect the first temperature of the environment in which the freezer is located and output it to the outside. The second temperature sensor is connected to the third input terminal of the processing terminal. The second temperature sensor is installed inside the freezer and connected to the storage space of the freezer. The second temperature sensor is used to collect the second temperature of the storage space inside the freezer and output it to the outside. The third temperature sensor is connected to the fourth input terminal of the processing terminal. The third temperature sensor is installed at the location of the condenser on the freezer. The third temperature sensor is used to collect the third temperature located on the side of the freezer condenser and output it to the outside. A fourth temperature sensor is connected to the fifth input terminal of the processing terminal. The fourth temperature sensor is installed at the location of the evaporator on the freezer. The fourth temperature sensor is used to collect the fourth temperature located on the evaporator side of the freezer and output it to the outside.

3. The freezer temperature control system according to claim 1, characterized in that, The processing terminal includes: A server is configured to communicate with the data acquisition terminal. The server is used to process the data output by the data acquisition terminal to obtain the target internal temperature of the freezer. A controller, configured to communicate with the server, is installed inside the freezer and is used to control the cooling temperature of the freezer in a future time period based on the target internal temperature.

4. A method for controlling the temperature of a freezer, characterized in that, Applied to the control system according to any one of claims 1-3, the method comprises: Acquire multiple temperature and humidity data of the freezer during historical periods, including the refrigeration path and the surrounding environment, as well as the label data of the surrounding environment; The changing characteristics of the multiple temperature and humidity data are analyzed to obtain the operating status data of the freezer; Based on the multiple temperature and humidity data, the label data, and the operating status data, the preset regression model is trained and tested to establish a regression relationship between various types of data and the historical temperature inside the cabinet in the corresponding insensitive zone. The current environmental data of the freezer is input into the trained regression model, and the target internal temperature of the freezer is obtained based on the output of the regression model. The refrigeration temperature of the freezer is controlled according to the target temperature inside the freezer for a future period, and the regression model is retrained after the future period to implement temperature regulation. Before training and testing the pre-defined regression model, the following steps are also included: When the freezer is determined to operate to a target state that meets multiple preset conditions, the cooling power consumption of the freezer and the temperature change of the internal storage space of the freezer are obtained for a preset duration of operation in the target state. Based on the cooling power consumption, the temperature change, and the mass of newly added items in the storage space inside the freezer, the specific heat capacity data of the stored items in the freezer are obtained. The specific heat capacity data is configured as the target data for training and testing the regression model.

5. The freezer temperature control method according to claim 4, characterized in that, The step of analyzing the variation characteristics of the multiple temperature and humidity data to obtain the operating status data of the freezer includes: Based on the change of each temperature and humidity data over time, data curves for each temperature and humidity data are obtained. Among them, multiple data curves include the ambient humidity curve and the first temperature curve of the environment where the freezer is located, the second temperature curve of the storage space inside the freezer, the third temperature curve of the freezer condenser side, and the fourth temperature curve of the freezer evaporator side. The relationship between the ambient humidity curve, the first temperature curve, the second temperature curve, the third temperature curve, and the fourth temperature curve is analyzed to obtain the opening and closing frequency and operating load rate of the freezer. The door opening and closing frequency and the operating load rate are determined as the operating status data of the freezer.

6. The freezer temperature control method according to claim 4, characterized in that, Determining the freezer to operate in a target state that meets multiple preset conditions includes: It is determined that the freezer is not running in energy-saving mode, and the current door status is closed, and the door has been closed for the last time and the temperature cycle has been pulled down a preset number of times. If so, then the freezer is determined to be operating in the target state.

7. The freezer temperature control method according to claim 4, characterized in that, Before training and testing the preset regression model, the method further includes: During the nighttime period, the current customer flow of the freezer is determined based on the second temperature change of the storage space inside the freezer. When the current passenger flow is lower than a preset value, the regression model is trained and tested.

8. The freezer temperature control method according to claim 4, characterized in that, Before training and testing the preset regression model, the method further includes: The working scenario characteristics of the freezer are determined based on at least one of the multiple temperature and humidity data, the label data, and the operating status data; Based on the characteristics of the work scenario, corresponding training weights are configured for various types of data so that the regression model can improve the prediction accuracy of the target cabinet temperature in the corresponding scenario.

9. A freezer, characterized in that, The freezer includes the control system described in any one of claims 1-3.

Images