Refrigerator refrigerating capacity adjusting method

Abstract

The invention discloses a refrigerator refrigerating capacity adjusting method which comprises the following steps that S1, environment data are collected in real time through a plurality of sensors, and future environment changes are accurately predicted through a machine learning algorithm; s2, constructing an environment change prediction model by using a machine learning algorithm; s3, the refrigerator intelligent refrigeration adjusting system analyzes and models use habits of the user, and predicts future refrigeration requirements; s4, according to the prediction data obtained in the step S1 and the step S3, the refrigerant flow and the working mode of the compressor are dynamically adjusted; s5, the refrigerator intelligent refrigeration adjusting system dynamically adjusts a refrigeration strategy according to comprehensive analysis of the real-time temperature data and the prediction result, and the operation mode of the refrigerator is continuously optimized; and S6, regularly storing the use data and the environment data of the user in a local or cloud storage. According to the method, future refrigeration requirements can be accurately predicted, the refrigeration strategy is dynamically adjusted, and the energy efficiency is improved to the maximum extent.

Description

Technical Field

[0001] The present invention relates to the technical field of refrigerators, and in particular to a method for adjusting the refrigeration capacity of a refrigerator. Background Art

[0002] As people's living standards continue to improve, the requirements for intelligent and energy-saving home appliances are becoming more stringent. As one of the most commonly used home appliances, the improvement of refrigerator energy efficiency and the optimization of refrigeration mode have always been the focus of technology research and development. Traditional refrigerators generally adopt fixed refrigeration modes and operation strategies, lacking flexibility and adaptability. Although this approach can achieve basic temperature control functions, it often causes energy waste, excessive temperature fluctuations, and shortened equipment life due to failure to take into account environmental changes, user usage behavior, and real-time fluctuations in refrigerator load. Especially when the ambient temperature changes greatly or user demand fluctuates frequently, the performance of traditional refrigerators is difficult to meet actual needs.

[0003] Refrigerator systems in the prior art are usually unable to effectively integrate data from multiple sensors, nor can they dynamically adjust refrigeration strategies based on user behavior patterns and environmental changes. Temperature control relies on preset values ​​and lacks a flexible real-time adjustment mechanism, which results in the inability to accurately match refrigeration needs under different usage conditions, causing unnecessary energy consumption and temperature control fluctuations. In addition, traditional refrigerators have weak predictive capabilities for user habits, and most systems only adjust refrigeration based on simple door opening sensors or time settings, failing to fully consider the impact of user behavior and environmental factors on refrigeration needs. This prevents the refrigerator system from achieving intelligent, energy-saving, and precise adjustment. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for adjusting the refrigeration capacity of a refrigerator, comprising the following steps:

[0006] S1: Collect environmental data in real time through multiple sensors, and use machine learning algorithms to accurately predict future environmental changes as the basis for subsequent cooling capacity adjustment;

[0007] S2: Process the collected sensor data in real time and use machine learning algorithms to build an environmental change prediction model;

[0008] S3: The refrigerator intelligent refrigeration regulation system records the user's daily usage in real time through built-in sensors. Through artificial intelligence algorithms, the refrigerator intelligent refrigeration regulation system analyzes and models the user's usage habits, combines historical data, and predicts future refrigeration needs;

[0009] S4: dynamically adjusting the refrigerant flow rate and the compressor working mode according to the prediction data obtained in step S1 and step S3;

[0010] S5: The temperature sensor in the refrigerator continuously monitors the temperature of the refrigeration area and the freezing area, and feeds back to the refrigerator intelligent refrigeration adjustment system in real time. The refrigerator intelligent refrigeration adjustment system dynamically adjusts the refrigeration strategy based on the comprehensive analysis of the real-time temperature data and the above-mentioned prediction results, and continuously optimizes the operation mode of the refrigerator;

[0011] S6: Regularly store user usage data and environmental data in local or cloud storage. Whenever new data comes in, the refrigerator intelligent refrigeration control system will retrain and optimize the prediction model based on the latest data.

[0012] As a preferred solution of the refrigerator refrigeration capacity adjustment method described in the present invention, the sensors are installed outside and inside the refrigerator, and the sensors include a temperature sensor, a humidity sensor, a door opening frequency sensor, an airflow sensor, a weight sensor, an infrared sensor and a wireless radio frequency identification sensor. The temperature sensor is used to monitor the temperature data inside and outside the refrigerator in real time, the humidity sensor is used to monitor the humidity changes inside the refrigerator in real time, the door opening frequency sensor is used to monitor the switch state and door opening frequency of the refrigerator door, the airflow sensor is used to monitor the airflow pattern and distribution in the refrigerator, the weight sensor is installed at the bottom of the refrigerator shelf or drawer to monitor the weight change of food, the infrared sensor is installed on the inner wall or above the shelf to identify the storage status and changes of food, and the wireless radio frequency identification sensor is used to read the food information with RFID tags to realize intelligent identification and management.

[0013] As a preferred solution of the refrigerator refrigeration capacity adjustment method of the present invention, the daily usage data in S3 includes:

[0014] Door opening frequency, i.e. the frequency of opening and closing the refrigerator door and the duration of each door opening;

[0015] Food storage, i.e. the quantity, type and location of food;

[0016] Usage time period, that is, recording usage patterns in different time periods of the day.

[0017] As a preferred solution of the refrigerator refrigeration capacity adjustment method of the present invention, wherein: constructing the environmental change prediction model in S2 includes the following steps:

[0018] S21: Use multiple sensors to collect real-time environmental data inside and outside the refrigerator, perform data cleaning and feature engineering, generate time series features related to environmental changes, and prepare data sets that can be used to train prediction models;

[0019] S22: Select appropriate machine learning models for training, and improve the prediction accuracy of the models through hyperparameter optimization and cross-validation methods to ensure that the models can effectively capture the laws of environmental changes;

[0020] S23: Deploy the trained prediction model to the refrigerator intelligent refrigeration adjustment system, input the collected environmental data in real time for short-term prediction, and dynamically adjust the refrigeration strategy according to the prediction results;

[0021] S24: Regularly incorporate new environmental data into the training set, continuously optimize the model through incremental learning or online learning, and dynamically adjust the prediction model based on actual environmental changes and user feedback to ensure continuous and efficient prediction and adjustment.

[0022] As a preferred solution of the refrigerator refrigeration capacity adjustment method described in the present invention, the feature engineering includes generating time series features, extracting features related to user behavior, and enhancing the generalization ability of the model by combining external environment data.

[0023] As a preferred solution of the refrigerator cooling capacity adjustment method of the present invention, the analyzing and modeling of the user's usage habits in S3 includes the following steps:

[0024] S31: Collect the user's door opening frequency, food storage conditions and usage time data through the built-in sensors of the refrigerator, and perform denoising, standardization and normalization on the data to ensure the consistency and reliability of the data;

[0025] S32: extracting the user's high-frequency usage time period, storage preference, and usage pattern characteristics from the collected data, and identifying the user's typical behavior pattern through cluster analysis and association rule learning methods;

[0026] S33: Using machine learning algorithms, a prediction model is trained based on the extracted user features to predict the user's future cooling needs;

[0027] S34: By evaluating the difference between the prediction results and the actual usage, adjust the parameters of the model, and optimize the model through incremental learning or online learning to make it better adapt to the changes in user behavior;

[0028] S35: Deploy the optimized user behavior prediction model to the refrigerator intelligent refrigeration control system, analyze user data in real time and dynamically adjust the refrigeration strategy based on the prediction results to improve refrigeration efficiency and respond to user needs.

[0029] As a preferred solution of the refrigerator refrigeration capacity adjustment method of the present invention, the dynamically adjusting the refrigerant flow rate and the compressor working mode in S4 includes the following steps:

[0030] S41: The refrigerator intelligent refrigeration regulation system receives data from environmental sensors and prediction data from user behavior models in real time;

[0031] S42: The refrigerator intelligent refrigeration adjustment system combines the environmental change prediction data in step S1 and the user usage habit prediction data in step S3, evaluates the future refrigeration demand through a machine learning model, and predicts the required refrigeration capacity and temperature changes of the refrigeration and freezing areas within a specific time period;

[0032] S43: Based on the above prediction results, the refrigerator intelligent refrigeration adjustment system calculates the optimal refrigerant flow rate that meets the current demand;

[0033] S44: The refrigerator intelligent refrigeration adjustment system determines whether to switch the working mode of the compressor according to the predicted refrigeration demand and temperature change trend;

[0034] S45: The refrigerator intelligent refrigeration regulation system directly adjusts the working state of the compressor through the control signal and changes the refrigerant flow in real time;

[0035] S46: After the refrigeration system starts working, the temperature sensor continuously monitors the actual temperature of the refrigeration and freezing areas, and feeds the data back to the refrigerator intelligent refrigeration adjustment system. If there is a deviation between the actual temperature and the expected temperature, the system will further adjust the refrigerant flow or the compressor working mode to quickly restore to the target temperature range;

[0036] S47: Based on continuous data feedback, the refrigerator intelligent refrigeration control system continuously learns the user's usage habits and environmental changes, and gradually optimizes the adjustment strategy of refrigerant flow and compressor working mode to adapt to different usage scenarios and environmental conditions.

[0037] As a preferred solution of the refrigerator refrigeration capacity adjustment method of the present invention, the refrigerator intelligent refrigeration adjustment system in S5 dynamically adjusts the refrigeration strategy according to the comprehensive analysis of the real-time temperature data and the above-mentioned prediction results, and continuously optimizes the operation mode of the refrigerator, which specifically includes the following steps:

[0038] S51: Real-time collection of temperature sensor data from the refrigeration area and the freezing area, and upload to the refrigerator intelligent refrigeration adjustment system, then calculate the current temperature value T real With the target set temperature T set Temperature deviation between:

[0039] ΔT=T ral -T set

[0040] If |ΔT| exceeds the set threshold, the cooling strategy needs to be adjusted;

[0041] S52: Combine the prediction data of step S1 and step S3 to adjust the set temperature T set :

[0042] If the external ambient temperature is predicted to rise, T set To reduce temperature fluctuations;

[0043] If it is predicted that the user will frequently open and close the door, the temperature will be appropriately lowered in advance to prevent the temperature from rising too high in a short period of time;

[0044] If it is predicted that it will not be used for a long time at night, then T set To save energy;

[0045] S53: Calculate the required cooling capacity Q need :

[0046] Q need =C·m·ΔT

[0047] Where C is the specific heat capacity, and m is the mass of the air and food in the refrigerator;

[0048] Then, according to Q need Determine the refrigerant flow adjustment factor F refrigerant :

[0049]

[0050] If the temperature drops too quickly, Then reduce the refrigerant flow to avoid overcooling;

[0051] If the temperature drops too slowly, Increasing the refrigerant flow rate improves cooling efficiency;

[0052] S54: Intelligent control of the compressor working mode, including the following steps:

[0053] Adjust the compressor working mode based on the temperature fluctuation trend:

[0054] If the temperature drops too quickly or is lower than the target temperature, the compressor speed is reduced or the system enters intermittent operation mode;

[0055] If the temperature rises or approaches the set threshold, the compressor power is increased or the system enters continuous cooling mode;

[0056] If it is predicted that the user will use the refrigerator frequently, the compressor power will be increased in advance to reduce temperature fluctuations;

[0057] Dynamic adjustment of compressor frequency fcomp :

[0058]

[0059] Among them, K3 and K4 are adjustment coefficients to ensure that the compressor responds to the temperature change trend;

[0060] S55: Dynamic adjustment of fan speed, including the following steps:

[0061] Adjust the fan speed in the refrigeration and freezing areas to promote cold air circulation and optimize refrigeration uniformity;

[0062] Calculate the fan speed V fan :

[0063]

[0064] Among them, K5 represents the influence of temperature deviation on fan speed, and K6 represents the influence of temperature change rate on fan speed;

[0065] When the temperature deviation is large, K5 will increase the fan speed to improve air flow and speed up the cooling process;

[0066] When the temperature approaches the target value, K5 will reduce the fan speed to reduce energy consumption;

[0067] When the temperature changes rapidly, K6 will increase the fan speed to help quickly respond to temperature changes and balance temperature stability;

[0068] S56: Combine long-term operation data to optimize various adjustment parameters to make the cooling strategy more energy-efficient and efficient. In addition, when the user does not use it for a long time, it enters energy-saving mode.

[0069] As a preferred solution of the refrigerator refrigeration capacity adjustment method of the present invention, the mathematical expression for calculating the optimal refrigerant flow rate that meets the current demand is as follows:

[0070]

[0071] in:

[0072] is the optimal refrigerant flow rate, in kg / s or L / s, indicating the optimal refrigerant flow rate required by the refrigerator under the current environmental conditions and requirements;

[0073] Q need The cooling capacity currently required by the refrigerator, in W or J, indicates the heat removal capacity that the system needs to provide in order to meet the temperature requirements of the refrigerator's internal refrigeration / freezing area;

[0074] T ambientis the ambient temperature outside the refrigerator, in degrees Celsius or Kelvin, indicating the external factors that affect the refrigeration demand inside the refrigerator;

[0075] T inside The internal temperature of the refrigerator is in degrees Celsius or Kelvin, which indicates the actual temperature inside the refrigerator, usually the temperature of the refrigerator or freezer area;

[0076] Δt is the time interval, which indicates the time interval for monitoring and adjustment of the control system. The unit is usually seconds. The time interval reflects the response speed of the refrigerant flow adjustment.

[0077] F refrigerant is the refrigerant flow adjustment coefficient, which indicates the sensitivity of the refrigerator refrigeration system to the flow under different working conditions. It helps to adjust the response intensity of the refrigerant flow to different demands.

[0078] is an exponential function used to adjust the external ambient temperature T ambient The effect on refrigerant flow rate. The purpose of this item is to adjust the flow rate ratio as the ambient temperature increases to avoid excessive or insufficient refrigerant flow.

[0079] T threshold is the temperature threshold, used to adjust the external ambient temperature T in the exponential function ambient The threshold determines the sensitivity of the external ambient temperature to the refrigerant flow adjustment;

[0080] C1, C2, C3, C4 are constant coefficients. These coefficients are the adjustment constants of the system. The specific values ​​are determined according to the design of the refrigerator, the characteristics of the refrigeration system and experimental data. They control the influence of different variables in the formula. Among them:

[0081] C1 controls the target cooling capacity Q need The degree of influence on the optimal refrigerant flow rate;

[0082] C2: Control temperature difference (T ambient -T inside ) on the optimal refrigerant flow rate;

[0083] C3: the influence of the control time interval Δt on the optimal refrigerant flow rate;

[0084] C4: The degree of influence of the control index adjustment part on the flow;

[0085] Q1 need +C2(T ambient -T inside )+C3Δt: is the molecular part, which takes into account the target cold Q need , temperature difference (T ambient-T inside ) and time interval Δt, which determine the demand for the optimal refrigerant flow rate;

[0086] The denominator is used to adjust the sensitivity of the flow rate, taking into account the adjustment factor F of the refrigerant flow rate. refrigerant , and the influence of external temperature on flow rate. The role of the exponential term is to dynamically adjust the external temperature and help the system optimize the cooling strategy under different environmental conditions.

[0087] As a preferred solution of the refrigerator refrigeration capacity adjustment method of the present invention, the refrigerator intelligent refrigeration adjustment system includes:

[0088] The sensor acquisition module is used to monitor the environmental data inside and outside the refrigerator in real time, including temperature, humidity, door opening frequency, airflow status, food weight changes, and food storage conditions;

[0089] Data processing and storage module, used to collect and store sensor data, analyze historical data and establish user usage models;

[0090] The machine learning prediction module can predict future usage habits based on user behavior data and dynamically adjust the cooling capacity based on environmental changes;

[0091] The intelligent control module can adjust the compressor, fan and refrigerant flow parameters according to the prediction results to optimize the cooling efficiency and reduce energy consumption.

[0092] Beneficial effects of the present invention:

[0093] 1. The present invention can accurately predict future environmental changes and refrigeration needs by combining environmental data collected in real time by multiple sensors and user behavior patterns analyzed based on artificial intelligence algorithms. This prediction method that combines environmental changes with user habits enables refrigerators to adapt to upcoming environmental changes and user demand fluctuations in advance, dynamically adjust refrigerant flow and compressor operating mode, thereby improving energy efficiency and extending equipment life. Compared with traditional refrigerators, this prediction-based intelligent adjustment is more forward-looking and avoids energy waste and problems of too low or too high temperatures.

[0094] 2. The present invention uses temperature sensors to monitor the temperature of the refrigeration area and the freezing area in real time, and feeds the data back to the refrigerator's intelligent refrigeration adjustment system. The system dynamically adjusts the refrigeration strategy based on a comprehensive analysis of the real-time temperature and predicted data. This closed-loop feedback mechanism enables the refrigerator to continuously optimize the operating mode according to environmental changes and usage conditions to ensure that the refrigeration and freezing areas are always kept within the most suitable temperature range. This dynamic adjustment not only improves the user experience, but also automatically optimizes energy efficiency in different environments and usage conditions, avoiding the cumbersome process of manual adjustment of traditional refrigerators.

[0095] 3. The present invention introduces a model optimization mechanism based on machine learning, allowing the refrigerator intelligent refrigeration adjustment system to automatically update and optimize its prediction model every time new data enters. This mechanism enables the system to self-learn and improve based on historical usage data, environmental changes, and actual user usage, gradually improving prediction accuracy and adjustment strategies. This adaptability enables the refrigerator to adapt to the user's changing usage patterns in the long term and operate efficiently under different environmental conditions, avoiding the limitations of static adjustment solutions and greatly improving the intelligence and energy efficiency management capabilities of the refrigerator. BRIEF DESCRIPTION OF THE DRAWINGS

[0096] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0097] Figure 1 The present invention is a flowchart of a refrigerator refrigeration capacity adjustment method. DETAILED DESCRIPTION

[0098] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0099] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0100] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0101] Secondly, the present invention is described in detail with reference to the schematic diagram. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0102] Example 1

[0103] Reference Figure 1 , which is a first embodiment of the present invention, provides a refrigerator refrigeration capacity adjustment method, comprising the following steps:

[0104] S1: Collect environmental data in real time through multiple sensors, and use machine learning algorithms to accurately predict future environmental changes as the basis for subsequent cooling capacity adjustment.

[0105] The detailed instructions are as follows:

[0106] Data collection: Temperature sensors, humidity sensors, door opening and closing detection sensors and airflow sensors are arranged inside and outside the refrigerator to collect real-time data such as ambient temperature, humidity, opening and closing status and door opening frequency, as well as airflow patterns and distribution in the refrigerator. Weight sensors are installed at the bottom of refrigerator shelves or drawers to monitor changes in food weight. Infrared sensors are installed on the walls or shelves inside the refrigerator to identify the storage status and changes of food. Wireless radio frequency identification sensors are installed on the walls or shelves inside the refrigerator to read food information with RFID tags to achieve intelligent identification and management.

[0107] S2: Process the collected sensor data in real time and use machine learning algorithms to build an environmental change prediction model.

[0108] The detailed instructions are as follows:

[0109] By processing the collected sensor data in real time (denoising and standardization), a machine learning algorithm (such as long short-term memory network LSTM) is used to build an environmental change prediction model. The model can accurately predict the temperature and humidity change trends within the next hour, with prediction periods of 10 minutes, 30 minutes and 1 hour.

[0110] In the above, the construction of environmental data collection and prediction model ensures that the refrigerator can understand the changing trends of external temperature and humidity in advance, thereby providing an accurate basis for subsequent refrigeration capacity adjustment and reducing energy waste caused by external environmental fluctuations.

[0111] S3: The refrigerator intelligent refrigeration regulation system records the user's daily usage in real time through built-in sensors. Through artificial intelligence algorithms, the refrigerator intelligent refrigeration regulation system analyzes and models the user's usage habits, combines historical data, and predicts future refrigeration needs.

[0112] The detailed instructions are as follows:

[0113] User behavior data recording: The system records the user's daily usage in real time through built-in sensors. The data includes:

[0114] Door opening frequency: the frequency of opening and closing the refrigerator door, and the duration of each door opening.

[0115] Food storage conditions: including the quantity, type and storage location of food (refrigerated area, frozen area, etc.).

[0116] Usage time: Record usage patterns at different times of the day (for example, the door is opened more frequently at night).

[0117] Artificial intelligence modeling and demand forecasting: Through artificial intelligence algorithms (such as support vector machines (SVMs), neural networks (NNs), etc.), the system analyzes and models user usage habits, combines historical data, and predicts refrigeration demand within the next 2 hours. The system will adjust the refrigeration strategy based on the predicted door opening frequency, food storage volume, and time period to ensure that the refrigerator is always in the best working condition.

[0118] By recording and analyzing user behavior, this step enables the system to accurately predict the user's refrigeration needs and avoid unnecessary increase in refrigeration capacity, thereby improving the refrigerator's energy efficiency and user experience.

[0119] S4: Dynamically adjust the refrigerant flow rate and the compressor operating mode according to the prediction data obtained in step S1 and step S3.

[0120] The detailed instructions are as follows:

[0121] Refrigerant flow control: Based on the predicted data obtained in step S1 and step S3, the control system accurately adjusts the refrigerant flow through the electronic expansion valve.

[0122] High demand conditions: When the ambient temperature is predicted to rise or the user frequently opens the door, the system increases the refrigerant flow rate to quickly restore the temperature inside the refrigerator.

[0123] Low demand conditions: When it is predicted that the ambient temperature will drop or the user's usage frequency will decrease, the system will reduce the refrigerant flow, reduce the compressor load, and enter energy-saving mode.

[0124] Compressor operating mode adjustment: The compressor speed is adjusted through frequency conversion technology to ensure that the refrigerant flow and compressor power match the actual needs of the refrigerator. The system automatically selects the best operating state of the compressor (such as partial load, full load or low load operation) in frequency conversion mode according to the prediction results.

[0125] The dynamic adjustment of the refrigerant flow rate and the compressor working mode in this step can achieve precise refrigeration, reduce unnecessary energy consumption, and at the same time extend the service life of the refrigerator and improve its working efficiency.

[0126] S5: The temperature sensor in the refrigerator continuously monitors the temperature of the refrigeration area and the freezing area, and feeds back to the refrigerator intelligent refrigeration regulation system in real time. The refrigerator intelligent refrigeration regulation system dynamically adjusts the refrigeration strategy based on the comprehensive analysis of the real-time temperature data and the above-mentioned prediction results, and continuously optimizes the operation mode of the refrigerator.

[0127] The detailed instructions are as follows:

[0128] Real-time temperature monitoring and feedback: The temperature sensor in the refrigerator continuously monitors the temperature of the refrigeration and freezing areas, and provides real-time feedback to the main control system.

[0129] Adjust cooling strategy: Based on the comprehensive analysis of real-time temperature data and the above-mentioned prediction results, the system automatically adjusts the cooling strategy.

[0130] When the temperature is high: If the temperature in a certain area is high, the system will immediately increase the refrigerant flow and compressor power to give priority to the high temperature area.

[0131] When the temperature is low: If the temperature is too low, the system will reduce the refrigerant flow, reduce the compressor power, and enter energy-saving mode.

[0132] Continuous optimization and learning: The system continuously collects and analyzes usage data to continuously optimize prediction algorithms and control strategies to improve its intelligence.

[0133] In this step, real-time feedback and continuous optimization are used to ensure that the refrigerator can adapt to various environmental changes and changes in user needs, and always maintain the optimal refrigeration state, thereby maximizing energy efficiency and user satisfaction.

[0134] S6: Regularly store user usage data and environmental data in local or cloud storage. Whenever new data comes in, the refrigerator intelligent refrigeration control system will retrain and optimize the prediction model based on the latest data to adapt to seasonal changes or changes in user usage habits.

[0135] Specifically, constructing the environmental change prediction model in S2 includes the following steps:

[0136] S21: Use a variety of sensors (temperature sensors, humidity sensors, airflow sensors, RFID sensors, etc.) to collect real-time environmental data inside and outside the refrigerator (including temperature, humidity, airflow conditions, food storage conditions, etc. inside and outside the refrigerator) and perform data cleaning (processing missing values, abnormal data (such as extreme values ​​caused by sensor failure), and using interpolation or mean filling methods to correct data) and feature engineering to generate time series features related to environmental changes and prepare data sets that can be used to train prediction models.

[0137] Feature engineering includes the following:

[0138] Generate time series features, such as daily average temperature change trend, humidity fluctuation trend, seasonal characteristics, etc.

[0139] Extract features related to user behavior, such as door opening frequency, food storage change trends, etc.

[0140] Combined with external environmental data, such as weather forecast data (temperature, humidity, air pressure), etc., to enhance the generalization ability of the model.

[0141] S22: Select appropriate machine learning models (such as LSTM, SVR, etc.) for training, and improve the prediction accuracy of the model through hyperparameter optimization and cross-validation methods to ensure that the model can effectively capture the laws of environmental changes.

[0142] The detailed instructions are as follows:

[0143] Select the model type:

[0144] For time series data, long short-term memory network (LSTM) or temporal convolutional network (TCN) can be used for modeling.

[0145] If traditional machine learning methods are used, models such as random forest regression (RF), gradient boosted decision tree (GBDT), and support vector regression (SVR) can be selected.

[0146] Model training:

[0147] The sliding window method is used for time series training, such as using the data of the past 24 / 48 / 72 hours as input to predict environmental changes in the next 24 hours.

[0148] Perform hyperparameter optimization and use Grid Search or Bayesian Optimization to adjust hyperparameters to improve prediction accuracy.

[0149] Model Evaluation:

[0150] The mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) were used to evaluate the prediction effect.

[0151] The cross validation method is used to verify the generalization ability of the model.

[0152] S23: Deploy the trained prediction model to the refrigerator intelligent refrigeration control system, input the collected environmental data in real time for short-term prediction, and dynamically adjust the refrigeration strategy according to the prediction results.

[0153] The detailed instructions are as follows:

[0154] Model deployment: Deploy the trained model to the refrigerator’s intelligent refrigeration control system as part of the environmental prediction module.

[0155] Real-time data input: The system inputs the data obtained by sensors in real time into the prediction model to obtain the prediction results of short-term environmental changes.

[0156] Feedback Mechanism:

[0157] The prediction results are used to dynamically adjust the cooling strategy, such as reducing the cooling power in advance to adapt to the upcoming increase in ambient temperature, or reducing energy consumption in low temperature environments.

[0158] If the actual environmental changes deviate significantly from the predicted results, the model's adaptive adjustment mechanism will be triggered to continuously optimize the prediction accuracy.

[0159] S24: Regularly incorporate new environmental data into the training set, continuously optimize the model through incremental learning or online learning, and dynamically adjust the prediction model based on actual environmental changes and user feedback to ensure continuous and efficient prediction and adjustment.

[0160] The detailed instructions are as follows:

[0161] Data update: The system stores new environmental data locally or in the cloud periodically (e.g., weekly or monthly) and merges it into the training dataset.

[0162] Model retraining: Based on the latest data, use incremental learning or online learning methods to optimize the model and adapt to long-term environmental change trends.

[0163] Dynamic adjustment: Based on user feedback, if the model is found to have large prediction errors under certain circumstances (such as seasonal changes or changes in refrigerator storage conditions), an automatic model update mechanism will be triggered to ensure that the prediction results always maintain high accuracy.

[0164] Through the above steps, the refrigerator can accurately predict future environmental changes, realize intelligent refrigeration adjustment, optimize energy consumption and improve the preservation effect. The real-time adaptive ability and long-term optimization mechanism of the model ensure the stability and efficiency of the system.

[0165] Specifically, analyzing and modeling user usage habits in S3 includes the following steps:

[0166] S31: The built-in sensors in the refrigerator are used to collect data on the user’s door opening frequency, food storage conditions, and usage period. The data is then denoised, standardized, and normalized to ensure data consistency and reliability.

[0167] The detailed instructions are as follows:

[0168] Door opening frequency: records the frequency of opening and closing the refrigerator door and the duration of each door opening, reflecting the user's door opening habits.

[0169] Food storage: Record the type, quantity, storage location, etc. of food in the refrigerator to understand the user's food storage preferences.

[0170] Usage time: record usage patterns in different time periods of the day, and analyze the user's door opening frequency and food storage and access habits in different time periods.

[0171] These data need to be cleaned to remove invalid data, fill in missing values, and standardize the data into a format that the model can recognize.

[0172] S32: Extract the user's high-frequency usage time periods, storage preferences, and usage pattern characteristics from the collected data, and identify the user's typical behavior patterns through cluster analysis and association rule learning methods.

[0173] The detailed instructions are as follows:

[0174] Extract features such as users' high-frequency usage time periods and door opening duration from the door opening frequency.

[0175] Extract characteristics such as food type preferences and storage location change patterns from food storage conditions.

[0176] Extract the user's daily usage peak and off-peak periods from the usage period.

[0177] Based on these features, methods such as cluster analysis and association rule learning are used to identify typical user behavior patterns, such as a trend of higher door opening frequency during a certain period of time, or a preference for the storage method of certain food categories.

[0178] S33: Using machine learning algorithms, such as decision trees, random forests, or deep learning models, a prediction model is trained based on the extracted user features to predict the user's future cooling needs.

[0179] The detailed instructions are as follows:

[0180] Select a suitable machine learning algorithm and build a prediction model through feature training to predict users' future demand for refrigerator cooling capacity in different time periods.

[0181] The model is trained using the training set and optimized using the validation set, and the accuracy of the model is improved through methods such as cross-validation. For example, if a user is found to frequently open the door and store a large amount of food during a specific period of time, it is predicted that a higher cooling capacity may be required during this period to cope with frequent temperature fluctuations.

[0182] S34: By evaluating the difference between the prediction results and the actual usage, adjust the parameters of the model, and optimize the model through incremental learning or online learning to make it better adapt to changes in user behavior.

[0183] The detailed instructions are as follows:

[0184] The model's predictions are evaluated by comparing the deviation between the predicted cooling demand and the actual demand.

[0185] Adjust the model parameters based on the evaluation results, such as using different algorithms, adding features, changing the training method, etc.

[0186] By using incremental learning or online learning, the model can continuously adapt to changes in user behavior to maintain accurate predictions of different usage habits.

[0187] S35: Deploy the optimized user behavior prediction model to the refrigerator intelligent refrigeration control system, analyze user data in real time and dynamically adjust the refrigeration strategy based on the prediction results to improve refrigeration efficiency and respond to user needs.

[0188] The detailed instructions are as follows:

[0189] Integrate the established user behavior prediction model with the refrigerator intelligent refrigeration control system to obtain new user data in real time for prediction.

[0190] After each prediction, the refrigerant flow rate, compressor operating mode, etc. are dynamically adjusted based on the current environmental data (such as temperature and humidity) and the user's usage behavior to optimize the cooling capacity.

[0191] Through the above steps, the refrigerator refrigeration system can respond to the user's usage habits in real time, provide personalized cooling capacity adjustment, improve energy efficiency, extend the service life of the refrigerator, and improve the user experience.

[0192] Specifically, dynamically adjusting the refrigerant flow rate and the compressor working mode in S4 includes the following steps:

[0193] S41: The refrigerator intelligent refrigeration regulation system receives real-time data from environmental sensors (such as temperature, humidity, airflow, etc.) and predictive data from user behavior models; these data help determine the current temperature requirements inside the refrigerator and the changing trends of the external environment.

[0194] S42: The refrigerator intelligent refrigeration regulation system combines the environmental change prediction data in step S1 and the user usage habit prediction data in step S3, evaluates the future refrigeration demand through a machine learning model, and predicts the required refrigeration capacity and temperature changes in the refrigeration and freezing areas within a specific time period.

[0195] S43: Based on the above prediction results, the refrigerator intelligent refrigeration regulation system calculates the optimal refrigerant flow rate to meet the current demand. This process takes into account multiple factors, such as the internal temperature of the refrigerator, the external ambient temperature, the frequency of door opening, and the food storage conditions, to ensure that the refrigerant flow rate matches the demand, thereby improving energy efficiency.

[0196] S44: The refrigerator intelligent refrigeration adjustment system determines whether it is necessary to switch the working mode of the compressor according to the predicted refrigeration demand and temperature change trend. For example, when the refrigeration demand is high, the refrigerator intelligent refrigeration adjustment system may adjust the compressor to operate in a higher working mode (such as high pressure and long operation); conversely, when the demand is low, the refrigerator intelligent refrigeration adjustment system may switch to a low pressure and intermittent operation mode to save energy.

[0197] S45: The refrigerator intelligent refrigeration regulation system directly adjusts the working state of the compressor through the control signal, changing the refrigerant flow in real time. The regulation process continuously monitors the temperature changes inside the refrigerator through the feedback loop to ensure that the adjustment of the refrigerant flow and the compressor mode matches the current actual demand.

[0198] S46: After the refrigeration system starts working, the temperature sensor continuously monitors the actual temperature of the refrigeration and freezing areas and feeds the data back to the refrigerator intelligent refrigeration adjustment system. If there is a deviation between the actual temperature and the expected temperature, the system will further adjust the refrigerant flow or compressor working mode to quickly restore to the target temperature range.

[0199] S47: Based on continuous data feedback, the refrigerator intelligent refrigeration regulation system constantly learns user usage habits and environmental changes, and gradually optimizes the regulation strategy of refrigerant flow and compressor working mode to adapt to different usage scenarios and environmental conditions, thereby improving overall energy efficiency and operating performance.

[0200] Furthermore, the intelligent refrigeration regulation system of the refrigerator in S5 dynamically adjusts the refrigeration strategy based on the comprehensive analysis of the real-time temperature data and the above-mentioned prediction results, and continuously optimizes the operation mode of the refrigerator, which specifically includes the following steps:

[0201] S51: Collecting temperature data and calculating deviation

[0202] The temperature sensor data of the refrigeration area and the freezing area are collected in real time and uploaded to the refrigerator intelligent refrigeration adjustment system, and then the current temperature value T is calculated. real With the target set temperature T set Temperature deviation between:

[0203] ΔT=T ral -T set

[0204] If |ΔT| exceeds the set threshold, the cooling strategy needs to be adjusted.

[0205] S52: Dynamically adjust target temperature based on forecast data

[0206] Combine the prediction data of step S1 and step S3 to adjust the set temperature T set :

[0207] If the external ambient temperature is predicted to rise, T set To reduce temperature fluctuations.

[0208] If it is predicted that the user will open and close the door frequently (such as taking out and putting out food at dinner time), the temperature will be lowered appropriately in advance to prevent the temperature from rising too high in a short period of time.

[0209] If it is predicted that it will not be used for a long time at night, then T set To save energy.

[0210] S53: Dynamic regulation of refrigerant flow

[0211] Calculate the required cooling capacity Q need :

[0212] Q need =C·m·ΔT

[0213] Among them, C is the specific heat capacity, and m is the mass of air and food in the refrigerator.

[0214] Then, according to Q need Determine the refrigerant flow adjustment factor F refrigerant :

[0215]

[0216] If the temperature drops too quickly, The refrigerant flow rate is reduced to avoid overcooling.

[0217] If the temperature drops too slowly, Increasing the refrigerant flow rate improves cooling efficiency.

[0218] S54: Intelligent control of compressor working mode

[0219] Adjust the compressor working mode based on the temperature fluctuation trend:

[0220] If the temperature drops too quickly or is below the target temperature, the compressor speed is reduced or the system enters intermittent operation mode.

[0221] If the temperature rises or approaches the set threshold, the compressor power is increased or the system enters continuous cooling mode.

[0222] If it is predicted that the user will use the refrigerator frequently, the compressor power will be increased in advance to reduce temperature fluctuations.

[0223] Dynamic adjustment of compressor frequency f comp :

[0224]

[0225] Among them, K3 and K4 are adjustment coefficients to ensure that the compressor responds to temperature change trends.

[0226] S55: Dynamic adjustment of fan speed

[0227] Adjust the fan speed in the refrigeration and freezing areas to promote cold air circulation and optimize cooling uniformity.

[0228] Calculate the fan speed V fan :

[0229]

[0230] Among them, K5 represents the influence of temperature deviation on fan speed, and K6 represents the influence of temperature change rate on fan speed.

[0231] When the temperature deviation is large, K5 will increase the fan speed to improve air flow and speed up the cooling process.

[0232] When the temperature approaches the target value, the K5 will reduce the fan speed to reduce energy consumption.

[0233] When the temperature changes rapidly, K6 will increase the fan speed to help quickly respond to temperature changes and balance temperature stability.

[0234] S56: Adaptive energy efficiency optimization strategy

[0235] Combined with long-term operation data, various adjustment parameters are optimized, such as dynamic adjustment of K value, to make the refrigeration strategy more energy-saving and efficient. In addition, when the user does not use it for a long time, it enters the energy-saving mode (lowering the set temperature and reducing the frequency of compressor startup).

[0236] Specifically, the mathematical expression for calculating the optimal refrigerant flow rate to meet current demand is as follows:

[0237]

[0238] in:

[0239] It is the optimal refrigerant flow rate, in kg / s or L / s, indicating the optimal refrigerant flow rate required by the refrigerator under the current environmental conditions and requirements.

[0240] Q need The cooling capacity currently required by the refrigerator, in units of W or J, represents the heat removal capacity that the system needs to provide in order to meet the temperature requirements of the refrigerator / freezer area inside the refrigerator. This cooling capacity will be calculated based on factors such as the temperature difference between the inside and outside of the refrigerator and the food storage conditions (refer to step S53).

[0241] T ambient is the ambient temperature outside the refrigerator, in degrees Celsius or Kelvin, indicating external factors that affect the refrigeration demand inside the refrigerator.

[0242] T inside The internal temperature of the refrigerator is measured in degrees Celsius or Kelvin, which indicates the actual temperature inside the refrigerator, usually the temperature of the refrigerator or freezer area.

[0243] Δt is the time interval, which indicates the time interval for monitoring and adjustment of the control system. The unit is usually seconds. The time interval reflects the response speed of the refrigerant flow adjustment.

[0244] F refrigerant The refrigerant flow adjustment coefficient indicates the sensitivity of the refrigerator refrigeration system to the flow under different working conditions. It helps to adjust the response intensity of the refrigerant flow to different demands. It is usually a dimensionless coefficient.

[0245] is an exponential function used to adjust the external ambient temperature T ambient The effect on refrigerant flow. The purpose of this item is to adjust the flow ratio as the ambient temperature rises to avoid too much or too little refrigerant flow. Explanation: When the ambient temperature T ambient When the ambient temperature is high, the value of this exponential term is close to 0, which effectively reduces the impact on the flow regulation. ambient When it is low, the value of the exponential term is close to 1, increasing the regulatory impact of the flow.

[0246] T threshold is the temperature threshold, used to adjust the external ambient temperature T in the exponential function ambientThis threshold determines the sensitivity of the external ambient temperature to the refrigerant flow adjustment and is usually set according to the design conditions or environmental standards of the refrigerator.

[0247] C1, C2, C3, C4 are constant coefficients. These coefficients are the adjustment constants of the system. The specific values ​​are determined according to the design of the refrigerator, the characteristics of the refrigeration system and experimental data. They control the influence of different variables in the formula. Among them:

[0248] C1 controls the target cooling capacity Q need The degree of influence on the optimal refrigerant flow rate.

[0249] C2: Control temperature difference (T ambient -T inside ) on the optimal refrigerant flow rate.

[0250] C3: The influence of the control time interval Δt on the optimal refrigerant flow rate.

[0251] C4: The degree of influence of the control index adjustment part on the flow.

[0252] Q1 need +C2(T ambient -T inside )+C3Δt: is the molecular part, which takes into account the target cold Q need , temperature difference (T ambient -T inside ) and time interval Δt, which determine the demand for the optimal refrigerant flow rate.

[0253] The denominator is used to adjust the sensitivity of the flow rate, taking into account the adjustment factor F of the refrigerant flow rate. refrigerant , and the influence of external temperature on flow rate. The role of the exponential term is to dynamically adjust the external temperature and help the system optimize the cooling strategy under different environmental conditions.

[0254] Specifically, the refrigerator intelligent refrigeration regulation system includes:

[0255] The sensor acquisition module is used to monitor the environmental data inside and outside the refrigerator in real time, including temperature, humidity, door opening frequency, airflow status, food weight changes, and food storage conditions;

[0256] Data processing and storage module, used to collect and store sensor data, analyze historical data and establish user usage models;

[0257] The machine learning prediction module can predict future usage habits based on user behavior data and dynamically adjust the cooling capacity based on environmental changes;

[0258] The intelligent control module can adjust the compressor, fan and refrigerant flow parameters according to the prediction results to optimize the cooling efficiency and reduce energy consumption.

[0259] In summary, the present invention can accurately predict future environmental changes and refrigeration needs by combining environmental data collected in real time by multiple sensors and user behavior patterns analyzed based on artificial intelligence algorithms. This prediction method that combines environmental changes with user habits enables the refrigerator to adapt to upcoming environmental changes and user demand fluctuations in advance, dynamically adjust the refrigerant flow and compressor working mode, thereby improving energy efficiency and extending the life of the equipment. Compared with traditional refrigerators, this prediction-based intelligent adjustment is more forward-looking and avoids energy waste and problems of too low or too high temperature. The present invention monitors the temperature of the refrigeration area and the freezing area in real time through a temperature sensor, and feeds the data back to the refrigerator intelligent refrigeration adjustment system. The system dynamically adjusts the refrigeration strategy based on a comprehensive analysis of the real-time temperature and the predicted data. This closed-loop feedback mechanism enables the refrigerator to continuously optimize the operating mode according to environmental changes and usage conditions to ensure that the refrigeration and freezing areas are always kept within the most suitable temperature range. This dynamic adjustment not only improves the user experience, but also can automatically optimize energy efficiency in different environments and usage conditions, avoiding the cumbersome process of manual adjustment of traditional refrigerators. The present invention introduces a model optimization mechanism based on machine learning, allowing the refrigerator intelligent refrigeration adjustment system to automatically update and optimize its prediction model every time new data enters. This mechanism enables the system to self-learn and improve based on historical usage data, environmental changes, and actual user usage, gradually improving prediction accuracy and adjustment strategies. This adaptability enables the refrigerator to adapt to users' changing usage patterns over the long term and operate efficiently under different environmental conditions, avoiding the limitations of static adjustment solutions and greatly improving the intelligence and energy efficiency management capabilities of the refrigerator.

[0260] Example 2

[0261] Referring to Table 1, which is a second embodiment of the present invention, this embodiment is different from the first embodiment in that, in order to verify its beneficial effects, operating data and related instructions of the present invention in an actual environment are provided.

[0262] Experimental environment:

[0263] Experimental location: Home environment (assuming the test is conducted in a common home environment with large external temperature fluctuations)

[0264] Monitoring time: 2 weeks

[0265] Test objects: Ordinary traditional refrigerators and smart refrigerators based on the present invention

[0266] Data table:

[0267]

[0268] illustrate:

[0269] Temperature fluctuation range: The intelligent adjustment system of the refrigerator of the present invention dynamically adjusts the refrigeration strategy according to environmental changes and user needs, successfully reducing the temperature fluctuations in the refrigeration and freezing areas, and ensuring that the temperature always remains within the set range. Compared with traditional refrigerators, the refrigerator of the present invention has higher temperature control accuracy.

[0270] Refrigerant flow and compressor operating mode: The refrigerator of the present invention predicts the refrigeration demand through machine learning models and intelligently adjusts the refrigerant flow and compressor operating mode. When the load demand is low, the refrigerator compressor enters the intermittent operation mode to save energy, and adjusts to the high-efficiency operation mode when the demand is higher. In contrast, the compressor of traditional refrigerators is usually started frequently, resulting in low energy efficiency.

[0271] Improved energy efficiency: The refrigerator of the present invention performs well in optimizing energy efficiency, reducing total energy consumption by about 20% (from 3.0 kWh / day to 2.4 kWh / day). This shows that the refrigerator can operate efficiently in different usage scenarios and avoid energy waste.

[0272] Refrigeration demand satisfaction: The refrigerator of the present invention uses multiple data sources (environmental data and user habit data) to accurately predict future refrigeration demand and adjust the refrigeration strategy according to demand. Through intelligent adjustment, the prediction accuracy of the system is greatly improved, and the refrigeration demand satisfaction reaches 95%, which is much higher than the 75% of traditional refrigerators.

[0273] User satisfaction: Based on user experience feedback, the intelligent temperature control and energy-saving effects of the refrigerator of the present invention have been highly evaluated by users, and satisfaction has been significantly improved.

[0274] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for adjusting the refrigeration capacity of a refrigerator, characterized in that: The following steps are involved: S1: Collect environmental data in real time through multiple sensors, and use machine learning algorithms to accurately predict future environmental changes as the basis for subsequent cooling capacity adjustment; S2: Process the collected sensor data in real time and use machine learning algorithms to build an environmental change prediction model; S3: The refrigerator intelligent refrigeration regulation system records the user's daily usage in real time through built-in sensors. Through artificial intelligence algorithms, the refrigerator intelligent refrigeration regulation system analyzes and models the user's usage habits, combines historical data, and predicts future refrigeration needs; S4: dynamically adjusting the refrigerant flow rate and the compressor working mode according to the prediction data obtained in step S1 and step S3; S5: The temperature sensor in the refrigerator continuously monitors the temperature of the refrigeration area and the freezing area, and feeds back to the refrigerator intelligent refrigeration adjustment system in real time. The refrigerator intelligent refrigeration adjustment system dynamically adjusts the refrigeration strategy based on the comprehensive analysis of the real-time temperature data and the above-mentioned prediction results, and continuously optimizes the operation mode of the refrigerator; S6: Regularly store user usage data and environmental data in local or cloud storage. Whenever new data comes in, the refrigerator intelligent refrigeration control system will retrain and optimize the prediction model based on the latest data.

2. The refrigerator refrigeration capacity adjustment method according to claim 1, characterized in that: The sensors are installed outside and inside the refrigerator. The sensors include a temperature sensor, a humidity sensor, a door opening frequency sensor, an airflow sensor, a weight sensor, an infrared sensor and a wireless radio frequency identification sensor. The temperature sensor is used to monitor the temperature data inside and outside the refrigerator in real time, the humidity sensor is used to monitor the humidity changes inside the refrigerator in real time, the door opening frequency sensor is used to monitor the switch state and door opening frequency of the refrigerator door, the airflow sensor is used to monitor the airflow pattern and distribution in the refrigerator, the weight sensor is installed at the bottom of the refrigerator shelf or drawer to monitor the weight change of food, the infrared sensor is installed on the internal wall or above the shelf to identify the storage status and changes of food, and the wireless radio frequency identification sensor is used to read the food information with RFID tags to realize intelligent identification and management.

3. The refrigerator refrigeration capacity adjustment method according to claim 1, characterized in that: The daily usage data of S3 includes: Door opening frequency, i.e. the frequency of opening and closing the refrigerator door and the duration of each door opening; Food storage, i.e. the quantity, type and location of food; Usage time period, that is, recording usage patterns in different time periods of the day.

4. The refrigerator refrigeration capacity adjustment method according to claim 1, characterized in that: The construction of the environmental change prediction model in S2 includes the following steps: S21: Use multiple sensors to collect real-time environmental data inside and outside the refrigerator, perform data cleaning and feature engineering, generate time series features related to environmental changes, and prepare data sets that can be used to train prediction models; S22: Select appropriate machine learning models for training, and improve the prediction accuracy of the models through hyperparameter optimization and cross-validation methods to ensure that the models can effectively capture the laws of environmental changes; S23: deploy the trained prediction model to the refrigerator intelligent refrigeration adjustment system, input the collected environmental data in real time for short-term prediction, and dynamically adjust the refrigeration strategy according to the prediction results; S24: Regularly incorporate new environmental data into the training set, continuously optimize the model through incremental learning or online learning, and dynamically adjust the prediction model based on actual environmental changes and user feedback to ensure continuous and efficient prediction and adjustment.

5. The refrigerator refrigeration capacity adjustment method according to claim 4, characterized in that: The feature engineering includes generating time series features, extracting features related to user behaviors, and enhancing the generalization ability of the model by combining external environment data.

6. The refrigerator refrigeration capacity adjustment method according to claim 1, characterized in that: Analyzing and modeling the user's usage habits in S3 includes the following steps: S31: Collect the user's door opening frequency, food storage conditions and usage time data through the built-in sensors of the refrigerator, and perform denoising, standardization and normalization on the data to ensure the consistency and reliability of the data; S32: extracting the user's high-frequency usage time period, storage preference, and usage pattern characteristics from the collected data, and identifying the user's typical behavior pattern through cluster analysis and association rule learning methods; S33: Using machine learning algorithms, a prediction model is trained based on the extracted user features to predict the user's future cooling needs; S34: By evaluating the difference between the prediction results and the actual usage, adjust the parameters of the model, and optimize the model through incremental learning or online learning to make it better adapt to the changes in user behavior; S35: Deploy the optimized user behavior prediction model to the refrigerator intelligent refrigeration control system, analyze user data in real time and dynamically adjust the refrigeration strategy based on the prediction results to improve refrigeration efficiency and respond to user needs.

7. The refrigerator refrigeration capacity adjustment method according to claim 1, characterized in that: The dynamic adjustment of the refrigerant flow rate and the compressor working mode in S4 comprises the following steps: S41: The refrigerator intelligent refrigeration regulation system receives data from environmental sensors and prediction data from user behavior models in real time; S42: The refrigerator intelligent refrigeration adjustment system combines the environmental change prediction data in step S1 and the user usage habit prediction data in step S3, evaluates the future refrigeration demand through a machine learning model, and predicts the required refrigeration capacity and temperature changes of the refrigeration and freezing areas within a specific time period; S43: Based on the above prediction results, the refrigerator intelligent refrigeration adjustment system calculates the optimal refrigerant flow rate that meets the current demand; S44: The refrigerator intelligent refrigeration adjustment system determines whether to switch the working mode of the compressor according to the predicted refrigeration demand and temperature change trend; S45: The refrigerator intelligent refrigeration regulation system directly adjusts the working state of the compressor through the control signal and changes the refrigerant flow in real time; S46: After the refrigeration system starts working, the temperature sensor continuously monitors the actual temperature of the refrigeration and freezing areas, and feeds the data back to the refrigerator intelligent refrigeration adjustment system. If there is a deviation between the actual temperature and the expected temperature, the system will further adjust the refrigerant flow or the compressor working mode to quickly restore to the target temperature range; S47: Based on continuous data feedback, the refrigerator intelligent refrigeration control system continuously learns the user's usage habits and environmental changes, and gradually optimizes the adjustment strategy of refrigerant flow and compressor working mode to adapt to different usage scenarios and environmental conditions.

8. The refrigerator refrigeration capacity adjustment method according to claim 1, characterized in that: The intelligent refrigerator refrigeration adjustment system in S5 dynamically adjusts the refrigeration strategy according to the comprehensive analysis of the real-time temperature data and the above-mentioned prediction results, and continuously optimizes the operation mode of the refrigerator, which specifically includes the following steps: S51: Real-time collection of temperature sensor data from the refrigeration area and the freezing area, and upload to the refrigerator intelligent refrigeration adjustment system, then calculate the current temperature value T real With the target set temperature T set Temperature deviation between: ΔT=T real -T set If |ΔT| exceeds the set threshold, the cooling strategy needs to be adjusted; S52: Combine the prediction data of step S1 and step S3 to adjust the set temperature T set : If the external ambient temperature is predicted to rise, T set To reduce temperature fluctuations; If it is predicted that the user will frequently open and close the door, the temperature will be appropriately lowered in advance to prevent the temperature from rising too high in a short period of time; If it is predicted that it will not be used for a long time at night, then T set To save energy; S53: Calculate the required cooling capacity Q need : Q need =C·m·ΔT Where C is the specific heat capacity, and m is the mass of the air and food in the refrigerator; Then, according to Q need Determine the refrigerant flow adjustment factor F refrigerant : If the temperature drops too quickly, Then reduce the refrigerant flow to avoid overcooling; If the temperature drops too slowly, Increasing the refrigerant flow rate improves cooling efficiency; S54: Intelligent control of the compressor working mode, including the following steps: Adjust the compressor working mode based on the temperature fluctuation trend: If the temperature drops too quickly or is lower than the target temperature, the compressor speed is reduced or the system enters intermittent operation mode; If the temperature rises or approaches the set threshold, the compressor power is increased or the system enters continuous cooling mode; If it is predicted that the user will use the refrigerator frequently, the compressor power will be increased in advance to reduce temperature fluctuations; Dynamic adjustment of compressor frequency f comp : Among them, K3 and K4 are adjustment coefficients to ensure that the compressor responds to the temperature change trend; S55: Dynamic adjustment of fan speed, including the following steps: Adjust the fan speed in the refrigeration and freezing areas to promote cold air circulation and optimize refrigeration uniformity; Calculate the fan speed V fan : Among them, K5 represents the influence of temperature deviation on fan speed, and K6 represents the influence of temperature change rate on fan speed; When the temperature deviation is large, K5 will increase the fan speed to improve air flow and speed up the cooling process; When the temperature approaches the target value, K5 will reduce the fan speed to reduce energy consumption; When the temperature changes rapidly, K6 will increase the fan speed to help quickly respond to temperature changes and balance temperature stability; S56: Combine long-term operation data to optimize various adjustment parameters to make the cooling strategy more energy-efficient and efficient. In addition, when the user does not use it for a long time, it enters energy-saving mode.

9. The refrigerator refrigeration capacity adjustment method according to claim 7, characterized in that: The mathematical expression for calculating the optimal refrigerant flow rate that meets the current demand is as follows: in: is the optimal refrigerant flow rate, in kg / s or L / s, indicating the optimal refrigerant flow rate required by the refrigerator under the current environmental conditions and requirements; Q need The cooling capacity currently required by the refrigerator, in W or J, indicates the heat removal capacity that the system needs to provide in order to meet the temperature requirements of the refrigerator's internal refrigeration / freezing area; T ambient is the ambient temperature outside the refrigerator, in degrees Celsius or Kelvin, indicating the external factors that affect the refrigeration demand inside the refrigerator; T inside The internal temperature of the refrigerator is in degrees Celsius or Kelvin, which indicates the actual temperature inside the refrigerator, usually the temperature of the refrigerator or freezer area; Δt is the time interval, which indicates the time interval for monitoring and adjustment of the control system. The unit is usually seconds. The time interval reflects the response speed of the refrigerant flow adjustment. F refrigerant is the refrigerant flow adjustment coefficient, which indicates the sensitivity of the refrigerator refrigeration system to the flow under different working conditions. It helps to adjust the response intensity of the refrigerant flow to different demands. is an exponential function used to adjust the external ambient temperature T ambient The effect on refrigerant flow rate. The purpose of this item is to adjust the flow rate ratio as the ambient temperature increases to avoid excessive or insufficient refrigerant flow. T threshold is the temperature threshold, used to adjust the external ambient temperature T in the exponential function ambient The threshold determines the sensitivity of the external ambient temperature to the refrigerant flow adjustment; C1, C2, C3, C4 are constant coefficients. These coefficients are the adjustment constants of the system. The specific values ​​are determined according to the design of the refrigerator, the characteristics of the refrigeration system and experimental data. They control the influence of different variables in the formula. Among them: C1 controls the target cooling capacity Q need The degree of influence on the optimal refrigerant flow rate; C2: Control temperature difference (T ambient -T inside ) on the optimal refrigerant flow rate; C3: the influence of the control time interval Δt on the optimal refrigerant flow rate; C4: The degree of influence of the control index adjustment part on the flow; Q1 need +C2(T ambient -T inside )+C3Δt: is the molecular part, which takes into account the target cold Q need , temperature difference (T ambient -T inside ) and time interval Δt, which determine the demand for the optimal refrigerant flow rate; The denominator is used to adjust the sensitivity of the flow rate, taking into account the adjustment factor F of the refrigerant flow rate. refrigerant , and the influence of external temperature on flow rate. The role of the exponential term is to dynamically adjust the external temperature and help the system optimize the cooling strategy under different environmental conditions.

10. The refrigerator refrigeration capacity adjustment method according to claim 1, characterized in that: The refrigerator intelligent refrigeration adjustment system comprises: The sensor acquisition module is used to monitor the environmental data inside and outside the refrigerator in real time, including temperature, humidity, door opening frequency, airflow status, food weight changes, and food storage conditions; Data processing and storage module, used to collect and store sensor data, analyze historical data and establish user usage models; The machine learning prediction module can predict future usage habits based on user behavior data and dynamically adjust the cooling capacity based on environmental changes; The intelligent control module can adjust the compressor, fan and refrigerant flow parameters according to the prediction results to optimize the cooling efficiency and reduce energy consumption.

Images