Refrigerator and refrigerator control method

Abstract

The invention relates to a refrigerator and a refrigerator control method. Comprising the following steps: estimating ozone concentration based on negative ion concentration in the storage room and door opening and closing information of the storage room to obtain an ozone concentration estimated value of the storage room at the current detection moment; the ozone concentration estimated value at the current detection moment is input into a trained ozone concentration prediction model for ozone concentration prediction, an ozone concentration predicted value at the current detection moment is obtained, and the ozone concentration predicted value at the current detection moment is used for controlling work of an ion generator, the ozone concentration prediction model is obtained by training a machine learning model based on a difference value between an ozone concentration measured value of the sample storage room at the first detection moment and an ozone concentration predicted value of the sample storage room at the first detection moment; the ozone concentration predicted value at the first detection moment is predicted by the machine learning model based on the ozone concentration estimated value of the sample storage room at the first detection moment. The ozone concentration can be more accurately controlled.

Description

Technical Field

[0001] This application relates to the field of refrigerator technology, and in particular to a refrigerator and a refrigerator control method. Background Technology

[0002] Because food stored in a refrigerator for a long time is prone to bacterial growth and odors, or cross-contamination of smells between foods, users will smell unpleasant odors when they open the door, affecting their user experience. To eliminate bacteria, refrigerators typically have ion generators. These generators produce negative ions through discharge. When these negative ions encounter bacteria, they alter the bacterial membrane structure, inactivating the bacteria and thus achieving a sterilization effect. Additionally, the discharge process may also produce oxygen free radicals and molecules, which can also remove odor gases.

[0003] Currently, ion generators produce ozone during the discharge process. If the ozone concentration exceeds the standard, it can easily harm the human body. If the ion generator is frequently turned off to avoid exceeding the ozone concentration standard, it can easily lead to insufficient negative ion concentration and affect the sterilization effect. However, if the operation of the ion generator is not effectively controlled, it can easily lead to excessive ozone concentration.

[0004] However, existing negative ion sterilization modes usually cannot intelligently detect ozone concentration, resulting in insufficient precision in ozone concentration control. Therefore, there is an urgent need for a method that can intelligently detect ozone concentration in order to control ozone concentration more accurately. Summary of the Invention

[0005] This application provides a refrigerator and a refrigerator control method to solve the problem of inaccurate ozone concentration control.

[0006] In a first aspect, some embodiments provide a refrigerator, including: a cabinet including a storage compartment; an ion generator disposed in the storage compartment for generating negative ions through discharge to purify gas, and generating ozone during the discharge process; a negative ion sensor disposed in the storage compartment for collecting the concentration of negative ions in the storage compartment; and a controller configured to: estimate the ozone concentration based on the concentration of negative ions in the storage compartment and the door opening / closing information of the storage compartment, to obtain an estimated value of the ozone concentration in the storage compartment at the current detection time; input the estimated value of the ozone concentration at the current detection time into a trained ozone concentration prediction model to predict the ozone concentration, to obtain a predicted value of the ozone concentration at the current detection time, wherein the predicted value of the ozone concentration at the current detection time is used to control the operation of the ion generator, wherein the ozone concentration prediction model is obtained by training a machine learning model based on the difference between the measured value of the ozone concentration in the sample storage compartment at a first detection time and the predicted value of the ozone concentration at the first detection time, and the predicted value of the ozone concentration at the first detection time is predicted by the machine learning model based on the estimated value of the ozone concentration in the sample storage compartment at the first detection time.

[0007] In this embodiment, since the negative ion concentration and door opening / closing status are related to the ozone concentration, the ozone concentration is estimated based on the negative ion concentration and door opening / closing information in the storage room. This allows for the estimation of the ozone concentration in the storage room at the current detection time. The ozone concentration prediction model is trained using the difference between the measured ozone concentration at the first detection time and the predicted ozone concentration at the first detection time. The predicted ozone concentration at the first detection time is obtained by the machine learning model based on the estimated ozone concentration at the first detection time. Therefore, the ozone concentration prediction model has learned the ability to predict ozone concentration based on the estimated ozone concentration. Thus, the estimated ozone concentration at the current detection time is input into the trained ozone concentration prediction model to predict the ozone concentration, obtaining the predicted ozone concentration at the current detection time. This allows for intelligent detection of the ozone concentration. Since the predicted ozone concentration at the current detection time is used to control the operation of the ion generator, the ion generator can be controlled more precisely, leading to more accurate control of the ozone concentration.

[0008] Secondly, some embodiments also provide a refrigerator control method applied to the refrigerator provided in the first aspect. The refrigerator includes: a storage compartment, an ion generator, a negative ion sensor, and a controller. The method includes: estimating ozone concentration based on the negative ion concentration in the storage compartment and the door opening / closing information of the storage compartment to obtain an estimated ozone concentration value of the storage compartment at the current detection time; inputting the estimated ozone concentration value at the current detection time into a trained ozone concentration prediction model to predict ozone concentration and obtain a predicted ozone concentration value at the current detection time. The predicted ozone concentration value at the current detection time is used to control the operation of the ion generator. The ozone concentration prediction model is obtained by training a machine learning model based on the difference between the measured ozone concentration value of the sample storage compartment at the first detection time and the predicted ozone concentration value at the first detection time. The predicted ozone concentration value at the first detection time is predicted by the machine learning model based on the estimated ozone concentration value of the sample storage compartment at the first detection time.

[0009] In this embodiment, since the negative ion concentration and door opening / closing status are related to the ozone concentration, the ozone concentration is estimated based on the negative ion concentration and door opening / closing information in the storage room. This allows for the estimation of the ozone concentration in the storage room at the current detection time. The ozone concentration prediction model is trained using the difference between the measured ozone concentration and the predicted ozone concentration at the first detection time. The predicted ozone concentration at the first detection time is obtained by the machine learning model based on the estimated ozone concentration at that time. Therefore, the ozone concentration prediction model has learned the ability to predict ozone concentration based on the estimated ozone concentration. Thus, the estimated ozone concentration at the current detection time is input into the trained ozone concentration prediction model to predict the ozone concentration, obtaining the predicted ozone concentration at the current detection time. This model allows for intelligent detection of ozone concentration. Since the predicted ozone concentration at the current detection time is used to control the operation of the ion generator, the ion generator can be controlled more precisely, leading to more accurate control of the ozone concentration.

[0010] Thirdly, some embodiments also provide a refrigerator control device, including: an ozone concentration estimation module, used to estimate the ozone concentration based on the negative ion concentration in the storage room and the door opening / closing information of the storage room, to obtain an estimated ozone concentration value of the storage room at the current detection time; an ozone concentration prediction module, used to input the estimated ozone concentration value at the current detection time into a trained ozone concentration prediction model to predict the ozone concentration, to obtain a predicted ozone concentration value at the current detection time, the predicted ozone concentration value at the current detection time being used to control the operation of the ion generator; wherein, the ozone concentration prediction model is obtained by training a machine learning model based on the difference between the measured ozone concentration value of the sample storage room at the first detection time and the predicted ozone concentration value at the first detection time, the predicted ozone concentration value at the first detection time being predicted by the machine learning model based on the estimated ozone concentration value of the sample storage room at the first detection time.

[0011] Fourthly, some embodiments also provide a computer-readable storage medium storing a computer program that, when executed by a processor, performs the following steps: estimating ozone concentration based on the negative ion concentration in the storage room and the door opening / closing information of the storage room, to obtain an estimated ozone concentration value of the storage room at the current detection time; inputting the estimated ozone concentration value at the current detection time into a trained ozone concentration prediction model to predict ozone concentration, to obtain a predicted ozone concentration value at the current detection time, wherein the predicted ozone concentration value at the current detection time is used to control the operation of the ion generator, wherein the ozone concentration prediction model is obtained by training a machine learning model based on the difference between the measured ozone concentration value of the sample storage room at the first detection time and the predicted ozone concentration value at the first detection time, and the predicted ozone concentration value at the first detection time is predicted by the machine learning model based on the estimated ozone concentration value of the sample storage room at the first detection time.

[0012] Fifthly, some embodiments also provide a computer program product, including a computer program that, when executed by a processor, performs the following steps: estimating ozone concentration based on the negative ion concentration in the storage room and the door opening / closing information of the storage room, to obtain an estimated ozone concentration value of the storage room at the current detection time; inputting the estimated ozone concentration value at the current detection time into a trained ozone concentration prediction model to predict ozone concentration, to obtain a predicted ozone concentration value at the current detection time, wherein the predicted ozone concentration value at the current detection time is used to control the operation of an ion generator, wherein the ozone concentration prediction model is obtained by training a machine learning model based on the difference between the measured ozone concentration value of the sample storage room at the first detection time and the predicted ozone concentration value at the first detection time, and the predicted ozone concentration value at the first detection time is predicted by the machine learning model based on the estimated ozone concentration value of the sample storage room at the first detection time.

[0013] The aforementioned refrigerator control device, computer-readable storage medium, and computer program product, because of the relationship between negative ion concentration and door opening / closing status and ozone concentration, estimate ozone concentration based on the negative ion concentration and door opening / closing information in the storage room. This allows them to obtain an estimated ozone concentration in the storage room at the current detection time. Since the ozone concentration prediction model is trained on the difference between the measured ozone concentration and the predicted ozone concentration at the first detection time, the predicted ozone concentration at the first detection time is obtained by training the machine learning model based on this difference. The ozone concentration is estimated at the detection time, thus the ozone concentration prediction model has learned the ability to predict ozone concentration based on the estimated ozone concentration. Therefore, the estimated ozone concentration at the current detection time is input into the trained ozone concentration prediction model to predict the ozone concentration at the current detection time. The ozone concentration prediction model can be used to intelligently detect the ozone concentration. Since the predicted ozone concentration at the current detection time is used to control the operation of the ion generator, the ion generator can be controlled more accurately through the predicted ozone concentration, thereby achieving more precise control of the ozone concentration. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 This application provides schematic diagrams of the external structure of a refrigerator for some embodiments.

[0016] Figure 2 A schematic diagram of the hardware configuration of a refrigerator provided in some embodiments of this application;

[0017] Figure 3 A schematic diagram of the hardware configuration of the controller and its associated devices provided in some embodiments of this application;

[0018] Figure 4 Schematic diagram of a control ion generator provided for some embodiments of this application;

[0019] Figure 5 A schematic flowchart illustrating a refrigerator control method provided in some embodiments of this application;

[0020] Figure 6 A schematic diagram illustrating the principle of training a machine learning model provided for some embodiments of this application;

[0021] Figure 7Schematic diagrams for training machine learning models provided in other embodiments of this application;

[0022] Figure 8 A schematic diagram illustrating the principle of predicting ozone concentration provided for some embodiments of this application;

[0023] Figure 9 A schematic diagram of the hardware configuration of a calibration storage room provided for some embodiments of this application;

[0024] Figure 10 A schematic diagram of the hardware configuration of a refrigerator provided for other embodiments of this application;

[0025] Figure 11 A schematic diagram of a refrigerator control method provided in some embodiments of this application;

[0026] Figure 12 A system framework diagram of a refrigerator control method provided in some embodiments of this application;

[0027] Figure 13 Timing diagrams for refrigerator control methods provided in some embodiments of this application;

[0028] Figure 14 Structural block diagrams of refrigerator control devices provided in some embodiments of this application;

[0029] Figure 15 This is an internal structural diagram of a computer device provided in some embodiments of this application. Detailed Implementation

[0030] The embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described below do not represent all embodiments consistent with this application. They are merely examples of systems and methods consistent with some aspects of this application as detailed in the claims.

[0031] It should be noted that the brief descriptions of terms in this application are only for the convenience of understanding the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise stated, these terms should be understood in their ordinary and common meaning.

[0032] The terms "first," "second," "third," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar or related objects or entities, and do not necessarily imply a specific order or sequence, unless otherwise specified. It should be understood that such terms are interchangeable where appropriate.

[0033] The terms “comprising” and “having”, and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device that includes a range of components is not necessarily limited to all of the components that are clearly listed, but may include other components that are not clearly listed or that are inherent to such product or device.

[0034] The term "module" refers to any known or subsequently developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functions associated with that element.

[0035] Figure 1 This is a schematic diagram of the external structure of a refrigerator 100 provided in an embodiment of this application. The refrigerator 100 in this embodiment has an approximately cuboid shape. The refrigerator includes a cabinet defining a storage space and one or more doors located at the opening of the cabinet. Each door includes a door shell located outside the cabinet, a door inner liner located inside the cabinet, an upper cover, a lower cover, and an insulation layer located between the door shell, the door inner liner, the upper cover, and the lower cover. Typically, the insulation layer is filled with foam material. The cabinet has chambers, including component storage chambers for placing components inside the refrigerator, such as a compressor compartment, and storage chambers for storing food, etc. Of course, the refrigerator in this application can also be of other shapes, and this application does not limit the external structure of the refrigerator.

[0036] Figure 2 This is a schematic diagram of the internal structure of a refrigerator according to an embodiment of this application. The refrigerator's storage space can be divided into multiple storage compartments. These compartments can be configured as refrigerator compartments, freezer compartments, variable temperature compartments, vacuum drawers, and humidifier drawers, depending on their purpose. Each storage compartment corresponds to one or more doors, for example, in... Figure 2 The upper storage compartment 102 is equipped with a double door. The door can be pivotally mounted at the opening of the cabinet, or it can open like a drawer for drawer-style storage. An ion generator 103 and a negative ion sensor 104 are installed in the storage compartment 102. A door status sensor 105 is installed on the door, which can be, but is not limited to, a magnetic door switch sensor. The door status sensor can be placed at any position on the door, and it can also be placed inside the storage compartment; this application does not impose many limitations on the installation location of the door status sensor. A temperature and humidity sensor may also be installed in the storage compartment 102.

[0037] The refrigerator also includes a controller, which is the intelligent core of the refrigerator and is responsible for managing its operating status. It monitors the refrigerator's sensor data and makes adjustments based on the operating environment. Especially under fault or abnormal conditions, the controller can control the compressor's operation according to set logic. Both the controller and the compressor are located inside the refrigerator.

[0038] In the embodiments of this application, the controller can be a micro controller unit (MCU) or other types of controllers. The embodiments of this application do not specifically limit the controller.

[0039] The refrigerator also includes an integrated main inverter and display board, which is located inside the refrigerator body. The controller can be housed on this integrated board. The main inverter and display board includes a controller, power filter circuit, rectifier components, voltage detection circuit, three-phase inverter circuit, drive circuit, current sampling circuit, memory, voltage analog-to-digital converter module, pulse width modulation signal output module, temperature analog-to-digital converter module, operational amplifier, key detection circuit, display drive circuit, display module, fan, drive circuit, and fan interface. The power filter circuit stabilizes the DC voltage using the energy storage and release characteristics of capacitors. The rectifier components convert AC to DC. The three-phase inverter circuit converts DC to three-phase AC, providing a suitable three-phase AC power supply for the compressor.

[0040] The voltage detection circuit primarily detects the bus voltage using voltage divider resistors and sends the detected voltage to the voltage-to-digital converter (ADC). The ADC converts the received voltage into a voltage signal, enabling the controller to acquire it. The current sampling circuit samples the DC bus current and sends the sampled current to an operational amplifier. The operational amplifier processes the sampled current and sends the processed current to the current-to-digital converter (ADC). The ADC converts the received current into a current signal, allowing the controller to acquire it.

[0041] The controller analyzes and processes the digital current signal to obtain a Pulse Width Modulation (PWM) signal for controlling the compressor's operation. This PWM signal is then sent to the drive circuit via a PWM signal output module. The drive circuit uses the PWM signal to control the output of the three-phase inverter circuit, thereby controlling the compressor's operating state. The memory stores information such as the refrigerator's settings; however, this embodiment does not specifically limit the information that the memory can store. The temperature analog-to-digital converter module converts the temperature collected by the temperature sensor into a temperature signal, enabling the controller to obtain the temperature signal from the temperature analog-to-digital converter module.

[0042] The button detection circuit monitors the button status in real time and adjusts the refrigerator's settings and control modes accordingly. The display driver circuit drives the display module to display the settings and mode information. It should be noted that the buttons are located on the refrigerator itself, allowing users to adjust settings such as temperature. The fan driver operates the refrigerator's fan via a fan interface. The controller receives information from the button detection circuit through an interface and transmits data to the display driver circuit and fan driver circuit via the same interface.

[0043] Figure 3 This is a connection diagram of the controller and its control devices provided in the embodiments of this application. The refrigerator 100 includes: a controller 200, which is disposed inside the refrigerator and is used to receive detection data from the temperature sensor 201, the negative ion sensor 202 and the door status sensor 203, and to control the opening and closing of the ion generator 204, the damper 205, the fan 206 and the compressor 207; and a memory 208, which is used to store the operating parameters of the refrigerator 100. The air ducts include a refrigerator air duct and a freezer air duct. The refrigerator air duct is located in the air duct that connects to the refrigerator compartment. When the refrigerator air duct is open, cold air in the air duct can smoothly enter the refrigerator compartment. When the refrigerator air duct is closed, cold air in the air duct cannot enter the refrigerator compartment. The freezer air duct is located in the air duct that connects to the freezer compartment. When the freezer air duct is open, cold air in the air duct can smoothly enter the freezer compartment. When the freezer air duct is closed, cold air in the air duct cannot enter the freezer compartment. The fan is located in the air duct of the refrigerator and is used to allow air to enter the evaporator for heat exchange and send the heated air to the refrigerator storage compartment.

[0044] Figure 4 This is a schematic diagram of the control of the negative ion sensor provided in the embodiment of this application. The refrigerator 100 also includes a comparator 300, which can monitor the working status of the ion generator 204. When the ion generator 204 is found to be malfunctioning, the ion generator 204 can be turned off, for example, the control circuit can switch the power supply of the ion generator 204.

[0045] Based on this, in some embodiments, this application provides a refrigerator, which includes: a cabinet including a storage compartment; an ion generator disposed in the storage compartment for generating negative ions through discharge to purify gas, and generating ozone during the discharge process; a negative ion sensor disposed in the storage compartment for collecting the concentration of negative ions in the storage compartment; and a controller configured to: estimate the ozone concentration based on the concentration of negative ions in the storage compartment and the door opening / closing information of the storage compartment, to obtain an estimated value of the ozone concentration in the storage compartment at the current detection time; input the estimated value of the ozone concentration at the current detection time into a trained ozone concentration prediction model to predict the ozone concentration, to obtain a predicted value of the ozone concentration at the current detection time, wherein the predicted value of the ozone concentration at the current detection time is used to control the operation of the ion generator, wherein the ozone concentration prediction model is obtained by training a machine learning model based on the difference between the measured value of the ozone concentration in the sample storage compartment at the first detection time and the predicted value of the ozone concentration at the first detection time, and the predicted value of the ozone concentration at the first detection time is predicted by the machine learning model based on the estimated value of the ozone concentration in the sample storage compartment at the first detection time.

[0046] In this embodiment, since the negative ion concentration and door opening / closing status are related to the ozone concentration, the ozone concentration is estimated based on the negative ion concentration and door opening / closing information in the storage room. This allows for the estimation of the ozone concentration in the storage room at the current detection time. The ozone concentration prediction model is trained using the difference between the measured ozone concentration and the predicted ozone concentration at the first detection time. The predicted ozone concentration at the first detection time is obtained by the machine learning model based on the estimated ozone concentration at that time. Therefore, the ozone concentration prediction model has learned the ability to predict ozone concentration based on the estimated ozone concentration. Thus, the estimated ozone concentration at the current detection time is input into the trained ozone concentration prediction model to predict the ozone concentration, obtaining the predicted ozone concentration at the current detection time. This model allows for intelligent detection of ozone concentration. Since the predicted ozone concentration at the current detection time is used to control the operation of the ion generator, the ion generator can be controlled more precisely, leading to more accurate control of the ozone concentration.

[0047] Based on this, in some embodiments, this application provides a refrigerator control method, applied to a refrigerator, such as... Figure 5 As shown, the method includes:

[0048] Step 502: Based on the negative ion concentration in the storage room and the opening and closing information of the storage room, the ozone concentration is estimated to obtain the estimated value of the ozone concentration in the storage room at the current detection time.

[0049] The door opening / closing information can include at least one of the following: door opening time, door closing time, or door opening duration. The controller can calculate an estimated ozone concentration at preset intervals. The preset interval can be set according to actual needs, such as 5 minutes or 2 minutes.

[0050] Step 504: Input the estimated ozone concentration at the current detection time into the trained ozone concentration prediction model to predict the ozone concentration and obtain the predicted ozone concentration at the current detection time. The predicted ozone concentration at the current detection time is used to control the operation of the ion generator. The ozone concentration prediction model is obtained by training a machine learning model based on the difference between the measured ozone concentration at the first detection time and the predicted ozone concentration at the first detection time. The predicted ozone concentration at the first detection time is predicted by the machine learning model based on the estimated ozone concentration at the first detection time.

[0051] The machine learning model can be linear regression, logistic regression, support vector machine, decision tree, or neural network model, such as a time series neural network model. A time series neural network model is a neural network model used to process time series data, capable of capturing temporal information and patterns in the data for prediction and classification. The time series neural network model can be, but is not limited to, a recurrent neural network (RNN), a long short-term memory network (LSTM), or a gated recurrent unit (GRU). The ozone concentration prediction model is a trained machine learning model. The sample storage room is the storage room in the sample refrigerator, which is of the same type as the refrigerator in this application, for example, it can be a refrigerator produced in the same batch. The measured ozone concentration is the ozone concentration collected using an ozone analyzer.

[0052] The measured and estimated ozone concentrations at the first detection time constitute a training sample, where the measured ozone concentration at the first detection time serves as the training label. Multiple training samples can be used to iteratively train the machine learning model, with different training samples corresponding to different first detection times.

[0053] In some embodiments, the controller can determine the difference between the measured ozone concentration and the predicted ozone concentration in the training samples, and obtain the loss value corresponding to the training samples, such as... Figure 6As shown, the controller inputs the estimated ozone concentration at the first detection time into the machine learning model to predict the ozone concentration at the first detection time, obtaining the predicted ozone concentration at that time. Based on the measured and predicted ozone concentrations at the first detection time, a loss value is generated. The controller can sum the loss values ​​corresponding to a batch of training samples to obtain the model loss value, which is positively correlated with the difference. The controller can adjust the parameters of the machine learning model in a direction that reduces the model loss value, for example, by using gradient descent. Iterative training of the machine learning model can be performed using different batches of training samples until the model converges. The machine learning model at convergence is then defined as the trained ozone concentration prediction model.

[0054] In this embodiment, since the negative ion concentration and door opening / closing status are related to the ozone concentration, the ozone concentration is estimated based on the negative ion concentration and door opening / closing information in the storage room. This allows for the estimation of the ozone concentration in the storage room at the current detection time. The ozone concentration prediction model is trained using the difference between the measured ozone concentration and the predicted ozone concentration at the first detection time. The predicted ozone concentration at the first detection time is obtained by the machine learning model based on the estimated ozone concentration at that time. Therefore, the ozone concentration prediction model has learned the ability to predict ozone concentration based on the estimated ozone concentration. Thus, the estimated ozone concentration at the current detection time is input into the trained ozone concentration prediction model to predict the ozone concentration, obtaining the predicted ozone concentration at the current detection time. This model allows for intelligent detection of ozone concentration. Since the predicted ozone concentration at the current detection time is used to control the operation of the ion generator, the ion generator can be controlled more precisely, leading to more accurate control of the ozone concentration.

[0055] The refrigerator control method provided in this application can alleviate the problem of incomplete sterilization caused by excessive shutdown of the ion generator in order to prevent ozone concentration from exceeding the standard by more precisely controlling the operation of the ion generator, thereby improving the purification efficiency and sterilization effect.

[0056] The ozone concentration inside a refrigerator needs to be controlled below 0.05 ppm. However, low-concentration ozone detection sensors are expensive and prone to drift. The enclosed environment inside a refrigerator is subject to severe disturbances, making direct application difficult in ordinary refrigerators. This application, in the absence of a dedicated ozone detection sensor, utilizes existing refrigerator door opening and closing data and adds a negative ion detection sensor to implement a multi-sensor fusion-based method for predicting refrigerator ozone concentration. It predicts the refrigerator ozone concentration through physical calculations (i.e., estimating ozone concentration) and an AI (Artificial Intelligence) machine learning model. Algorithm compensation achieves reliable prediction and control of ozone concentration while saving hardware costs. ppm is an abbreviation for parts per million, which translates to "parts per million concentration" or "parts per million rate".

[0057] In some embodiments, the predicted ozone concentration at the first detection time is obtained by a machine learning model based on the estimated ozone concentration at the first detection time and a sample sequence. The sample sequence includes the measured ozone concentration values ​​of the sample storage room at multiple second detection times, and the measured ozone concentration values ​​in the sample sequence are arranged in chronological order, with the second detection times preceding the first detection time. When the controller executes the process of inputting the estimated ozone concentration at the current detection time into the trained ozone concentration prediction model to predict the ozone concentration and obtain the predicted ozone concentration at the current detection time, it is configured to: acquire a historical sequence containing the predicted ozone concentration values ​​of the storage room at multiple historical detection times, with the predicted ozone concentration values ​​in the historical sequence arranged in chronological order, and the historical detection times preceding the current detection time; input the estimated ozone concentration at the current detection time and the historical sequence into the ozone concentration prediction model to predict the ozone concentration and obtain the predicted ozone concentration at the current detection time.

[0058] In this dataset, both the first and second detection times are historical moments, with the second detection time being earlier than the first. The earlier the second detection time, the higher the measured ozone concentration value at that time will rank in the sample sequence. Similarly, the earlier the historical detection time, the higher the predicted ozone concentration value at that time will rank in the historical sequence.

[0059] In some embodiments, the training samples also include historical sequences, such as Figure 7 As shown, the controller inputs the estimated ozone concentration at the first detection time and the sample sequence into the machine learning model to obtain the predicted ozone concentration at the first detection time, and then obtains the loss value. Similarly, in order to improve the accuracy of the ozone concentration prediction value output by the ozone concentration prediction model, as... Figure 8As shown, when using the ozone concentration prediction model, inputting the estimated ozone concentration at the current detection time and the historical sequence into the ozone concentration prediction model can improve the accuracy of the ozone concentration prediction value output by the ozone concentration prediction model by utilizing the historical sequence.

[0060] In this embodiment, the ozone concentration prediction at the first detection time is obtained by the machine learning model based on the ozone concentration estimate at the first detection time and the sample sequence. The sample sequence includes the measured ozone concentration values ​​of the sample storage room at multiple second detection times. The measured ozone concentration values ​​in the sample sequence are arranged in chronological order, and the second detection time is before the first detection time. Therefore, during training, the accuracy of the ozone concentration prediction value output by the machine learning model can be improved based on the measured ozone concentration values ​​in the sample sequence.

[0061] In some embodiments, when the controller performs ozone concentration estimation based on the negative ion concentration in the storage room and the door opening / closing information of the storage room to obtain an estimated ozone concentration in the storage room at the current detection time, it is configured to: estimate the ozone concentration in the storage room up to the current detection time while keeping the door closed, based on the negative ion concentration in the storage room, and obtain a cumulative ozone concentration value; determine the cumulative door opening time of the storage room up to the current detection time based on the door opening / closing information of the storage room, and determine the ozone concentration loss value based on the cumulative door opening time; and determine the difference between the cumulative ozone concentration value and the ozone concentration loss value as the estimated ozone concentration in the storage room at the current detection time.

[0062] Specifically, the controller integrates the negative ion concentration in the storage room over time to obtain the current cumulative negative ion concentration. Based on this cumulative negative ion concentration, it estimates the ozone concentration in the storage room up to the current detection time while keeping the door closed, thus obtaining the cumulative ozone concentration. The negative ion concentration at time T can be expressed as... Then the current cumulative negative ion concentration = Where t0≤T≤t1, T=t0 represents the moment the ion generator in the storage chamber was last started, and T=t1 represents the current detection moment. The cumulative ozone concentration can be understood as the ozone concentration formed from t0 to t1 due to the continuous change in ozone concentration.

[0063] Since opening the refrigerator door releases ozone from inside, thus reducing the ozone concentration, the ozone concentration loss can be determined based on the cumulative time the door is open. If the estimated ozone concentration is expressed as... ,but = Cumulative ozone concentration - Ozone concentration loss.

[0064] In this embodiment, the cumulative ozone concentration is estimated based on the negative ion concentration in the storage room, and the ozone concentration loss is determined based on the cumulative door opening time. The difference between the cumulative ozone concentration and the ozone concentration loss is then used as the estimated ozone concentration in the storage room at the current detection time, thus realizing a method for estimating ozone concentration.

[0065] In some embodiments, when the controller performs the operation of estimating the ozone concentration in the storage room up to the current detection time while keeping the door closed, based on the negative ion concentration in the storage room, and obtaining the cumulative ozone concentration value, it is configured to: calculate the cumulative value of the negative ion concentration in the storage room up to the current detection time to obtain the current cumulative negative ion concentration value; obtain the ozone conversion coefficient, which is used to reflect the conversion relationship between the cumulative value of the negative ion concentration in the storage room and the ozone concentration when the door is closed; and convert the current cumulative negative ion concentration value based on the ozone conversion coefficient to obtain the cumulative ozone concentration value.

[0066] The current cumulative negative ion concentration can be the cumulative value of negative ion concentration from the moment the ion generator in the storage room was last turned on to the current detection time.

[0067] In some embodiments, the controller can use the product of the ozone conversion coefficient and the current cumulative negative ion concentration as the cumulative ozone concentration. For example, if the ozone conversion coefficient is denoted as K, then the current cumulative negative ion concentration = .

[0068] In this embodiment, the ozone concentration accumulation value can be intelligently determined based on the current cumulative negative ion concentration value through the ozone conversion coefficient, which helps to improve the efficiency and accuracy of estimating ozone concentration.

[0069] In some embodiments, the calibration storage room is equipped with an ion generator, an ozone analyzer, and a negative ion sensor. The calibration storage room is in a sealed state. During the operation of the ion generator in the calibration storage room, the ozone analyzer in the calibration storage room collects the ozone concentration in the calibration storage room in real time, and the negative ion sensor in the calibration storage room collects the negative ion concentration in the calibration storage room in real time. The ozone conversion coefficient is calculated based on the collected ozone concentration and negative ion concentration.

[0070] Among them, such as Figure 9 The diagram shows a schematic of the hardware configuration for calibrating the storage compartment. The calibrated storage compartment can be a storage compartment in the refrigerator described in this application, or a storage compartment in a refrigerator of the same type as the refrigerator described in this application.

[0071] In some embodiments, the calibration storage room can be sealed (e.g., the door of the calibration storage room can be closed), and an ozone analyzer and a negative ion sensor can be placed inside. The ozone analyzer collects the ozone concentration in the calibration storage room in real time, and the negative ion sensor collects the negative ion concentration in real time. After the ion generator operates in the calibration storage room for a period of time, for example from t2 to t3, the negative ion concentration in the calibration storage room is integrated during the time period from t2 to t3 to obtain the cumulative value of the sample negative ion concentration. The ratio of the ozone concentration at time t3 in the calibration storage room to the cumulative value of the sample negative ion concentration is determined as the ozone conversion coefficient. For example, if the ozone concentration at time t3 is... ,but The ozone concentration at time t3 is the ozone concentration formed after the continuous change of ozone concentration from t2 to t3, and can therefore be understood as a cumulative value, and can be the ozone concentration under steady state.

[0072] In some embodiments, The unit is ppm. The unit for time is units per cubic centimeter (ions / cm³), and the unit for time is seconds (s). The unit of K is ions·s / cm³, therefore the unit of K is ppm·cm³ / ions·s. For example, the range of K values ​​is... .

[0073] In some embodiments, during the calibration of the ozone conversion coefficient, the temperature and humidity inside the calibration storage room can be controlled. For example, the temperature inside the calibration storage room can be set to 5°C and the humidity to 80%.

[0074] In this embodiment, the ozone conversion coefficient calculated by calibrating the ozone concentration and negative ion concentration collected in the storage room ensures that the ozone conversion coefficient is reliable.

[0075] In some embodiments, when the controller performs the determination of ozone concentration loss based on cumulative door opening time, it is configured to: acquire the ozone decay rate in the open state, the ozone decay rate being used to reflect the rate of ozone decomposition in the storage room in the open state; and determine the ozone concentration loss based on the ozone decay rate and the cumulative door opening time.

[0076] The ozone decay rate is an empirical value, also known as the natural ozone decay rate. The unit for ozone decay rate is ppm / min, and the value ranges from 0.01 to 0.03 ppm / min. The ozone decay rate reflects the rate of ozone decomposition inside the refrigerator (catalyzed by temperature and humidity). The cumulative door opening time is measured in minutes (min), representing the equivalent time of ozone loss due to air exchange. Ozone has a half-life of approximately 20-40 minutes; opening and closing the refrigerator door causes airflow reset, which is a transient process.

[0077] The cumulative door opening time refers to the total time the door of the storage room remains open from the moment the ion generator in the storage room was last turned on to the current detection time.

[0078] Ozone decay rate can be expressed as The cumulative door opening time can be expressed as Then the ozone concentration loss value = .thereby, .

[0079] For example, if , , , ,but A negative number indicates that ozone has been completely removed.

[0080] In this embodiment, since the ozone decay rate is used to reflect the rate of ozone decomposition in the storage room when the door is open, the ozone concentration loss value can be accurately determined based on the ozone decay rate and the cumulative door opening time.

[0081] In some embodiments, the controller is further configured to: control the ion generator to stop working when the predicted ozone concentration at the current detection time is greater than or equal to the ozone concentration threshold; control the ion generator to start working to increase the negative ion concentration when the predicted ozone concentration at the current detection time is less than the ozone concentration threshold and the ion generator is in a non-working state; and adjust the operating parameters of the ion generator to increase the negative ion concentration when the predicted ozone concentration at the current detection time is less than the ozone concentration threshold and the ion generator is in a working state.

[0082] Specifically, if the predicted ozone concentration at the current detection time is less than the ozone concentration threshold and the ion generator is not in operation, the controller can activate the ion generator according to preset operating parameters. These preset operating parameters are default parameters and can be set according to actual needs.

[0083] The standard requires that the ozone concentration inside the refrigerator be ≤0.05ppm, and the ozone concentration threshold be less than or equal to 0.05ppm, for example, the ozone concentration threshold can be 0.04ppm.

[0084] In some embodiments, if the predicted ozone concentration at the current detection time is less than the ozone concentration threshold and the ion generator is in an inactive state, the controller compares the negative ion concentration at the current detection time with the negative ion concentration threshold. If the negative ion concentration at the current detection time is greater than or equal to the negative ion concentration threshold, the ion generator remains in an inactive state; if the negative ion concentration at the current detection time is less than the negative ion concentration threshold, the ion generator is activated. When the negative ion concentration in the storage room reaches the negative ion concentration threshold, the storage room can be adequately sterilized. The negative ion concentration threshold can be experimentally determined as needed.

[0085] In some embodiments, when the predicted ozone concentration at the current detection time is less than the ozone concentration threshold and the ion generator is in operation, the controller compares the negative ion concentration at the current detection time with the negative ion concentration threshold. If the negative ion concentration at the current detection time is greater than or equal to the negative ion concentration threshold, the controller stops the ion generator from operating. If the negative ion concentration at the current detection time is less than the negative ion concentration threshold, the controller adjusts the operating parameters of the ion generator to increase the negative ion concentration. For example, the controller may increase at least one of the operating voltage or operating current of the ion generator.

[0086] In this embodiment, when the predicted ozone concentration is greater than or equal to the ozone concentration threshold, the ion generator is controlled to stop working, which can prevent the generation of more ozone in time. When the predicted ozone concentration is less than the ozone concentration threshold, the ion generator is controlled to start working or the working parameters of the ion generator are adjusted to increase the negative ion concentration, which can improve the sterilization effect.

[0087] In some embodiments, the storage chamber further includes an adsorption device for adsorbing ozone, and the controller is further configured to: control the adsorption device to operate at a first power when the predicted ozone concentration at the current detection time is greater than the ozone concentration threshold; and control the adsorption device to operate at a second power when the predicted ozone concentration at the current detection time is less than the ozone concentration threshold, wherein the first power is greater than the second power.

[0088] Among them, such as Figure 10 As shown, an adsorption device 106 is installed in the storage room. The first power is greater than the second power; for example, the second power is the normal power, and the first power is the high power. The higher the power of the adsorption device, the greater its ability to adsorb ozone; that is, the ozone adsorption capacity of the adsorption device is positively correlated with its power. The adsorption device can be, but is not limited to, an activated carbon fan.

[0089] In this embodiment, since the first power is greater than the second power, when the predicted ozone concentration is greater than the ozone concentration threshold, the adsorption device is controlled to operate at the first power. This can improve the ozone adsorption capacity of the adsorption device when the predicted ozone concentration is high. Conversely, when the predicted ozone concentration is less than the ozone concentration threshold, the adsorption device is controlled to operate at the second power. This can save energy consumed by the adsorption device when the predicted ozone concentration is low.

[0090] In some embodiments, the refrigerator further includes a comparator configured to: acquire the operating current value of the ion generator; and control the ion generator to stop operating when the operating current value reaches a current threshold.

[0091] The refrigerator's hardware shutdown circuit may include a comparator. The operating current value can be, for example, the discharge current. A current threshold is used to determine if the ion generator is malfunctioning; exceeding the current threshold indicates that the ion generator may be over-operating. Controlling the ion generator to stop operating can be achieved, for example, by cutting off its power supply.

[0092] Specifically, when the operating current of the ion generator exceeds the current threshold, the power supply to the ion generator can be directly cut off by the comparator without going through the MCU (Microcontroller Unit), to prevent the ozone concentration from exceeding the standard due to controller malfunction or ozone concentration prediction model failure.

[0093] In this embodiment, since the controller controls the operation of the ion generator based on the predicted ozone concentration at the current detection time, if the controller malfunctions or the predicted ozone concentration is abnormal, the ion generator may overwork. Therefore, a comparator independent of the controller is set in the refrigerator so that when the ion generator overworks due to abnormal conditions, the comparator can promptly control the ion generator to stop working, thereby improving the accuracy of the ion generator control.

[0094] In some embodiments, such as Figure 11 The diagram illustrates a schematic of a refrigerator control method. This method predicts the ozone concentration in the refrigerator based on multi-sensor fusion. Specifically, it detects the negative ion concentration using a negative ion sensor in the refrigerator's storage compartment, detects the door opening / closing signal using a door open / close sensor (i.e., door status sensor) to determine the door opening time and duration, calibrates the refrigerator's ozone conversion coefficient in a laboratory, and constructs a physical calculation model for the ozone concentration (i.e.,... The ozone concentration is estimated using a physical calculation model, and then fed into a machine learning model to predict the ozone concentration. The model is then trained by comparing the actual ozone concentration detected by an ozone analyzer (i.e., the measured ozone concentration) to ensure the predicted ozone concentration is close to the actual value. This trained machine learning model is then deployed in a refrigerator to predict ozone concentration. The refrigerator can then control the ion generator and adsorption device to operate based on the predicted ozone concentration and negative ion concentration, optimizing the sterilization and purification effect inside the refrigerator. The control unit running the physical calculation model and the control unit running the machine learning model communicate via an SPI (Serial Peripheral Interface) interface. The refrigerator control method uses a combination of physical calculation and machine learning to predict ozone concentration.

[0095] In some embodiments, such as Figure 12 The diagram illustrates a system framework for a refrigerator control method, comprising a sensing module, a physical calculation module, a machine learning module, and a safety execution module. The sensing model includes a negative ion sensor and a door magnetic switch sensor, used to acquire real-time information on the negative ion concentration inside the refrigerator, the door's open / closed status, and duration. The physical calculation module estimates the ozone concentration based on the physical calculation model. The machine learning module predicts the ozone concentration based on the ozone concentration prediction model. The safety execution module controls the opening and closing of the ion generator and adsorption device based on the predicted ozone concentration and the negative ion concentration. Furthermore, to ensure the ozone concentration does not exceed the standard, a hardware shutdown circuit including a comparator is included. The safety execution module also allows for direct power cut-off without the MCU when the ion generator current exceeds a certain threshold, preventing ozone exceedances due to ozone model malfunction.

[0096] In some embodiments, such as Figure 13 As shown, a timing diagram corresponding to a refrigerator control method is provided, specifically including:

[0097] 1. The controller acquires the negative ion concentration collected by the negative ion sensor and receives the door opening time and duration collected by the door switch sensor.

[0098] 2. The controller uses a physical calculation model to estimate the ozone concentration in the storage room based on the acquired data, and obtains an estimated ozone concentration value.

[0099] From a physics perspective, ozone formation inside a refrigerator follows electrochemical reaction patterns. Therefore, a quantitative model is constructed based on the electrochemical principles of ion generation, resulting in an estimated ozone accumulation value based on physical equations:

[0100] .

[0101] in, The time integral of the negative ion concentration reflects the total charge released by the ion generator and is directly related to the ozone generation potential.

[0102] K is the inherent conversion coefficient of the ion generator to ozone (i.e., the ozone conversion coefficient), which reflects the amount of ozone that can be generated per unit of negative ions. It is a device-specific parameter obtained from the calibration of the refrigerator system (when negative ions are generated by discharge, ozone is produced, and the conversion efficiency of a specific ion generator to ozone has an inherent efficiency, similar to the fuel consumption coefficient of a car, which is determined by the electrode material and voltage characteristics).

[0103] The ozone conversion coefficient K value was calibrated in advance in the laboratory. The calibration process involved setting the environment in a sealed chamber at 5°C and 80% humidity. The controller activated the ion generator, and a negative ion sensor was used to measure the negative ion concentration. Simultaneously, an ozone detector was used to measure the ozone concentration inside the chamber, obtaining the cumulative ozone concentration under stable conditions. ,calculate .

[0104] 3. The controller inputs the estimated ozone concentration into the ozone concentration prediction model to obtain the predicted ozone concentration.

[0105] 4. The controller controls the operation of the ion generator and adsorption device based on the predicted ozone concentration.

[0106] 5. The comparator obtains the operating parameters of the ion generator. If an abnormality is determined based on the operating parameters, the ion generator is shut down.

[0107] The ion generator and adsorption device can be controlled in parallel, and there is no need for a specific order. The comparator can acquire the operating parameters of the ion generator in real time and determine whether it is malfunctioning. It does not only acquire the operating parameters of the ion generator and determine whether it is malfunctioning after obtaining the ozone concentration prediction value, so as to shut down the ion generator in time when there is an abnormality.

[0108] In this embodiment, since the negative ion concentration and door opening / closing status are related to the ozone concentration, the ozone concentration is estimated based on the negative ion concentration and door opening / closing information in the storage room. This allows for the estimation of the ozone concentration in the storage room at the current detection time. The ozone concentration prediction model is trained using the difference between the measured ozone concentration and the predicted ozone concentration at the first detection time. The predicted ozone concentration at the first detection time is obtained by the machine learning model based on the estimated ozone concentration at that time. Therefore, the ozone concentration prediction model has learned the ability to predict ozone concentration based on the estimated ozone concentration. Thus, the estimated ozone concentration at the current detection time is input into the trained ozone concentration prediction model to predict the ozone concentration, obtaining the predicted ozone concentration at the current detection time. This model allows for intelligent detection of ozone concentration. Since the predicted ozone concentration at the current detection time is used to control the operation of the ion generator, the ion generator can be controlled more precisely, leading to more accurate control of the ozone concentration.

[0109] The refrigerator control method provided in this application can control the ozone peak below the safety line and avoid incomplete sterilization due to excessive shutdown, thereby improving purification efficiency and effect.

[0110] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0111] Based on the same inventive concept, this application also provides a refrigerator control device for implementing the refrigerator control method described above. The solution provided by this device is similar to the solution described in the above method, and specific limitations can be found in the limitations of the refrigerator control method above, which will not be repeated here.

[0112] In some embodiments, a refrigerator control device is provided, including: an ozone concentration estimation module 1402 and an ozone concentration prediction module 1404, wherein:

[0113] The ozone concentration estimation module 1402 is used to estimate the ozone concentration based on the negative ion concentration in the storage room and the opening and closing information of the storage room, so as to obtain the estimated ozone concentration value of the storage room at the current detection time.

[0114] The ozone concentration prediction module 1404 is used to input the estimated ozone concentration at the current detection time into a trained ozone concentration prediction model to predict the ozone concentration, thereby obtaining the predicted ozone concentration at the current detection time. The predicted ozone concentration at the current detection time is used to control the operation of the ion generator. The ozone concentration prediction model is obtained by training a machine learning model based on the difference between the measured ozone concentration at the first detection time and the predicted ozone concentration at the first detection time. The predicted ozone concentration at the first detection time is predicted by the machine learning model based on the estimated ozone concentration at the first detection time.

[0115] In some embodiments, the predicted ozone concentration at the first detection time is obtained by a machine learning model based on the estimated ozone concentration at the first detection time and a sample sequence. The sample sequence includes the measured ozone concentration values ​​of the sample storage room at multiple second detection times, and the measured ozone concentration values ​​in the sample sequence are arranged in chronological order, with the second detection times preceding the first detection time. The ozone concentration prediction module 1404 is further configured to acquire a historical sequence, which includes the predicted ozone concentration values ​​of the storage room at multiple historical detection times, and the predicted ozone concentration values ​​in the historical sequence are arranged in chronological order, with the historical detection times preceding the current detection time. The estimated ozone concentration at the current detection time and the historical sequence are input into the ozone concentration prediction model to predict the ozone concentration, thereby obtaining the predicted ozone concentration at the current detection time.

[0116] In some embodiments, the ozone concentration estimation module 1402 is further configured to estimate the ozone concentration in the storage room up to the current detection time while keeping the door closed, based on the negative ion concentration in the storage room, and obtain a cumulative ozone concentration value; determine the cumulative door opening time of the storage room up to the current detection time based on the door opening and closing information of the storage room, and determine the ozone concentration loss value based on the cumulative door opening time; and determine the difference between the cumulative ozone concentration value and the ozone concentration loss value as the estimated ozone concentration of the storage room at the current detection time.

[0117] In some embodiments, the ozone concentration estimation module 1402 is further configured to: calculate the cumulative value of negative ion concentration in the storage room up to the current detection time to obtain the current cumulative value of negative ion concentration; obtain the ozone conversion coefficient, which reflects the conversion relationship between the cumulative value of negative ion concentration in the storage room and the ozone concentration when the door is closed; and convert the current cumulative value of negative ion concentration based on the ozone conversion coefficient to obtain the cumulative value of ozone concentration.

[0118] In some embodiments, the calibration storage room is equipped with an ion generator, an ozone analyzer, and a negative ion sensor. The calibration storage room is in a sealed state. During the operation of the ion generator in the calibration storage room, the ozone analyzer in the calibration storage room collects the ozone concentration in the calibration storage room in real time, and the negative ion sensor in the calibration storage room collects the negative ion concentration in the calibration storage room in real time. The ozone conversion coefficient is calculated based on the collected ozone concentration and negative ion concentration.

[0119] In some embodiments, the ozone concentration estimation module 1402 is further configured to obtain the ozone decay rate in the open state, the ozone decay rate being used to reflect the rate of ozone decomposition in the storage room in the open state; and to determine the ozone concentration loss value based on the ozone decay rate and the cumulative door opening time.

[0120] In some embodiments, the refrigerator control device further includes a control module for controlling the ion generator to stop working when the predicted ozone concentration at the current detection time is greater than or equal to the ozone concentration threshold; controlling the ion generator to start working to increase the negative ion concentration when the predicted ozone concentration at the current detection time is less than the ozone concentration threshold and the ion generator is in a non-working state; and adjusting the operating parameters of the ion generator to increase the negative ion concentration when the predicted ozone concentration at the current detection time is less than the ozone concentration threshold and the ion generator is in a working state.

[0121] In some embodiments, the storage chamber further includes an adsorption device for adsorbing ozone, and a control module, which is further configured to control the adsorption device to operate at a first power when the predicted ozone concentration at the current detection time is greater than the ozone concentration threshold; and to control the adsorption device to operate at a second power when the predicted ozone concentration at the current detection time is less than the ozone concentration threshold, wherein the first power is greater than the second power.

[0122] In some embodiments, the control module is also used to acquire the operating current value of the ion generator; and to control the ion generator to stop working when the operating current value reaches the current threshold.

[0123] In some embodiments, a computer device is provided, which may be a controller, and its internal structure diagram may be as follows: Figure 15As shown, the computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data involved in the refrigerator control method. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a refrigerator control method.

[0124] In some embodiments, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the refrigerator control method described above.

[0125] In some embodiments, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the refrigerator control method described above.

[0126] In some embodiments, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the refrigerator control method described above.

[0127] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0128] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0129] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A refrigerator, characterized in that, include: The enclosure includes the storage compartment; An ion generator, located in the storage chamber, is used to generate negative ions through discharge to purify the gas, and ozone is generated during the discharge process. A negative ion sensor is installed in the storage room to collect the concentration of negative ions in the storage room; The controller is configured as follows: Based on the negative ion concentration in the storage room and the opening and closing information of the storage room, the ozone concentration is estimated to obtain the estimated value of the ozone concentration in the storage room at the current detection time. The estimated ozone concentration at the current detection time is input into the trained ozone concentration prediction model to predict the ozone concentration, thereby obtaining the predicted ozone concentration at the current detection time. The predicted ozone concentration at the current detection time is used to control the operation of the ion generator. The ozone concentration prediction model is obtained by training a machine learning model based on the difference between the measured ozone concentration in the sample storage room at the first detection time and the predicted ozone concentration at the first detection time. The predicted ozone concentration at the first detection time is predicted by the machine learning model based on the estimated ozone concentration in the sample storage room at the first detection time.

2. The refrigerator according to claim 1, characterized in that, The predicted ozone concentration at the first detection time is obtained by the machine learning model based on the estimated ozone concentration at the first detection time and the sample sequence. The sample sequence includes the measured ozone concentration values ​​of the sample storage room at multiple second detection times. The measured ozone concentration values ​​in the sample sequence are arranged in chronological order, and the second detection time is before the first detection time. When the controller executes the step of inputting the estimated ozone concentration at the current detection time into the trained ozone concentration prediction model to predict the ozone concentration and obtain the predicted ozone concentration at the current detection time, it is configured as follows: Obtain a historical sequence, which contains predicted ozone concentration values ​​of the storage room at multiple historical detection times. The predicted ozone concentration values ​​in the historical sequence are arranged in chronological order, and the historical detection times are before the current detection time. The estimated ozone concentration at the current detection time and the historical sequence are input into the ozone concentration prediction model to predict the ozone concentration, thereby obtaining the predicted ozone concentration at the current detection time.

3. The refrigerator according to claim 1, characterized in that, When the controller performs the ozone concentration estimation based on the negative ion concentration in the storage room and the door opening / closing information of the storage room to obtain the estimated ozone concentration value of the storage room at the current detection time, it is configured as follows: Based on the negative ion concentration in the storage room, the ozone concentration in the storage room is estimated up to the current detection time while the door is kept closed, and the cumulative ozone concentration value is obtained. Based on the door opening and closing information of the storage room, the cumulative door opening time of the storage room up to the current detection time is determined, and the ozone concentration loss value is determined based on the cumulative door opening time. The difference between the cumulative ozone concentration and the ozone concentration loss is determined as the estimated ozone concentration in the storage room at the current detection time.

4. The refrigerator according to claim 3, characterized in that, When the controller performs the operation of estimating the ozone concentration in the storage room based on the negative ion concentration in the storage room, while keeping the door closed, up to the current detection time, and obtaining the cumulative ozone concentration value, it is configured as follows: The cumulative value of negative ion concentration in the storage room up to the current detection time is calculated to obtain the current cumulative value of negative ion concentration; Obtain the ozone conversion coefficient, which is used to reflect the conversion relationship between the cumulative value of negative ion concentration and ozone concentration in the storage room when the door is closed; The current cumulative negative ion concentration is converted based on the ozone conversion coefficient to obtain the cumulative ozone concentration.

5. The refrigerator according to claim 4, characterized in that, The calibration storage room is equipped with an ion generator, an ozone analyzer, and a negative ion sensor. The calibration storage room is in a sealed state. During the operation of the ion generator in the calibration storage room, the ozone analyzer in the calibration storage room collects the ozone concentration in real time, and the negative ion sensor in the calibration storage room collects the negative ion concentration in real time. The ozone conversion coefficient is calculated based on the collected ozone concentration and negative ion concentration.

6. The refrigerator according to claim 3, characterized in that, When the controller executes the step of determining the ozone concentration loss value based on the cumulative door opening time, it is configured as follows: Obtain the ozone decay rate when the door is open, the ozone decay rate being used to reflect the rate of ozone decomposition in the storage room when the door is open; The ozone concentration loss value is determined based on the ozone decay rate and the cumulative door opening time.

7. The refrigerator according to any one of claims 1 to 6, characterized in that, The controller is also configured to: If the predicted ozone concentration at the current detection time is greater than or equal to the ozone concentration threshold, the ion generator is controlled to stop working. If the predicted ozone concentration at the current detection time is less than the ozone concentration threshold and the ion generator is not in operation, the ion generator is controlled to start working to increase the negative ion concentration. If the predicted ozone concentration at the current detection time is less than the ozone concentration threshold and the ion generator is in operation, the operating parameters of the ion generator are adjusted to increase the negative ion concentration.

8. The refrigerator according to claim 7, characterized in that, The storage chamber also includes an adsorption device for adsorbing ozone, and the controller is further configured to: If the predicted ozone concentration at the current detection time is greater than the ozone concentration threshold, the adsorption device is controlled to operate at the first power. If the predicted ozone concentration at the current detection time is less than the ozone concentration threshold, the adsorption device is controlled to operate at a second power, where the first power is greater than the second power.

9. The refrigerator according to any one of claims 1 to 6, characterized in that, The refrigerator also includes a comparator configured to: Obtain the operating current value of the ion generator; When the operating current value reaches the current threshold, the ion generator is controlled to stop working.

10. A refrigerator control method, characterized in that, The method includes: Based on the negative ion concentration in the storage room and the opening and closing information of the storage room, the ozone concentration is estimated to obtain the estimated value of the ozone concentration in the storage room at the current detection time. The estimated ozone concentration at the current detection time is input into a trained ozone concentration prediction model to predict the ozone concentration, thereby obtaining a predicted ozone concentration at the current detection time. This predicted ozone concentration is used to control the operation of the ion generator. The ozone concentration prediction model is trained on a machine learning model based on the difference between the measured ozone concentration in the sample storage room at the first detection time and the predicted ozone concentration at the first detection time. The predicted ozone concentration at the first detection time is predicted by the machine learning model based on the estimated ozone concentration in the sample storage room at the first detection time.

Images