Refrigerator defrosting control method, system, equipment and device

Abstract

The invention is suitable for the technical field of refrigerators, and provides a refrigerator defrosting control method, system, equipment and device.The refrigerator defrosting control method comprises the steps that a linear regression model is built based on historical refrigerator external environment temperature and historical door opening frequency data, and temperature threshold data and frequency threshold data are obtained; a refrigerator early warning signal is obtained by monitoring the temperature change trend and the frequency change trend of the refrigerator in a unit time area in real time; based on the refrigerator early warning signal, the frosting speed in the refrigerator is calculated; dynamically adjusting defrosting parameters of the refrigerator through a dynamic adjustment algorithm; on the basis of the defrosting parameters, the defrosting program of the refrigerator is started, the operation data of the defrosting program is recorded, on the basis of the operation data, the dynamic adjustment algorithm is optimized, the defrosting control strategy is generated, the defrosting process is accurately controlled, unnecessary energy consumption and refrigerant waste are avoided, energy consumption and emission of the refrigerator can be reduced, and the refrigerating efficiency of the refrigerator is improved. Therefore, the use experience and satisfaction degree of the user are improved, and the operation burden and maintenance cost of the user are reduced.

Description

Technical Field

[0001] The present application belongs to the technical field of refrigerators, and in particular, relates to a refrigerator defrosting control method, system, equipment and device. Background Art

[0002] After a period of use, a layer of frost will gradually form on the fin surface of the refrigerator evaporator. As the thickness of the frost layer increases, the heat transfer rate of the evaporator will decrease significantly, thus affecting the refrigeration efficiency of the refrigerator. In order to maintain the refrigeration performance of the refrigerator, the frost layer must be removed regularly.

[0003] In the prior art, the most commonly used defrosting method for refrigerators is to use electric heating to periodically melt the frost on the evaporator. The defrosting control parameters usually include the cumulative power-on time, the cumulative compressor running time, and the temperature inside the cabinet. When the cumulative power-on time or the compressor running time reaches the preset value, the defrosting heater will be started for defrosting. Although this defrosting control method is simple and easy to use, it has obvious defects. Specifically, the above-mentioned defrosting control method fails to fully reflect the actual degree of frosting on the refrigerator evaporator, and also does not consider the impact of changes in the use environment on the frosting speed. For example, the number of times the refrigerator door is opened will directly affect the amount of humid and hot air entering the refrigerator, and then affect the frosting speed of the evaporator. If the user opens the refrigerator door less frequently, the humid and hot air entering the refrigerator will be reduced, and the frosting will naturally be reduced. In this case, if the defrosting program is still forcibly started according to the fixed cumulative time, it will not only increase the energy consumption of the refrigerator, but also damage the service life of the evaporator due to excessive defrosting. In addition, the defrosting strategies of traditional refrigerators are mostly based on fixed time intervals or triggered by preset conditions, and lack the ability to respond in real time to environmental changes and the actual operating status of the refrigerator. This may not only lead to unnecessary energy consumption increases, but may also affect the stability of the internal temperature of the refrigerator due to untimely defrosting, thereby having a negative impact on the preservation effect of food.

[0004] In summary, it is necessary to develop a more intelligent and efficient refrigerator defrosting control method to overcome the shortcomings of the prior art. Summary of the invention

[0005] The embodiments of the present application provide a refrigerator defrost control method, system, equipment and device, which can solve one of the above-mentioned problems in the prior art.

[0006] In a first aspect, an embodiment of the present application provides a refrigerator defrosting control method, comprising:

[0007] Based on the historical refrigerator external environment temperature and historical door opening frequency data, a linear regression model is constructed to obtain the temperature threshold data and frequency threshold data of the refrigerator in a unit time area under the preset time;

[0008] Based on the temperature threshold data and the frequency threshold data, by monitoring the temperature change trend and frequency change trend of the refrigerator in the unit time area in real time, a refrigerator warning signal is obtained;

[0009] Based on the refrigerator warning signal, the frosting speed inside the refrigerator is calculated;

[0010] If the frosting speed is greater than the preset threshold speed, the defrosting parameters of the refrigerator are dynamically adjusted through a dynamic adjustment algorithm;

[0011] Based on the defrosting parameters, the defrosting program of the refrigerator is started, the operation data of the defrosting program is recorded, and based on the operation data, the dynamic adjustment algorithm is optimized to generate a defrosting control strategy.

[0012] Further, based on the historical external environment temperature of the refrigerator and the historical door opening frequency data, a linear regression model is constructed to obtain the temperature threshold data and frequency threshold data of the refrigerator in the unit time area under the preset time, including:

[0013] Based on the historical external environment temperature of the refrigerator and the historical door opening frequency data, a temperature data set and a door opening frequency data set are obtained;

[0014] Based on the temperature data set and the door opening frequency data set, the correlation degree between the environmental temperature and the door opening frequency is judged;

[0015] Based on the correlation degree, with the environmental temperature as the independent variable and the door opening frequency as the dependent variable, a linear regression model is fitted and generated;

[0016] Based on the temperature data set, an environmental temperature prediction model is constructed. Through the environmental prediction model, the environmental temperature of the refrigerator in each unit time area within the preset time is predicted to generate an environmental temperature prediction data set. The environmental temperature in the unit time area is the temperature threshold data corresponding to the unit time area;

[0017] Based on the linear regression model and the environmental temperature prediction data set, the door opening frequency of the refrigerator in each unit time area within the preset time is predicted to generate a door opening frequency prediction data set within the preset time. The door opening frequency in the unit time area is the frequency threshold data corresponding to the unit time area.

[0018] Further, the obtaining of the temperature data set and the door opening frequency data set based on the historical external environment temperature of the refrigerator and the historical door opening frequency data includes:

[0019] The external environment temperature of the refrigerator is obtained through an environmental temperature sensor, and a temperature time series data set is generated;

[0020] Obtain the occurrence time of the refrigerator door opening event from the door magnetic switch record, and generate a time series dataset of door opening events;

[0021] Based on the same unit time granularity, divide the preset time into multiple identical unit time regions;

[0022] Based on the unit time region, perform time alignment on the temperature time series dataset and the door opening event time series dataset to generate a temperature dataset and a door opening frequency dataset.

[0023] Furthermore, based on the temperature threshold data and the frequency threshold data, obtain a refrigerator warning signal by real-time monitoring of the temperature change trend and frequency change trend of the refrigerator within the unit time region, including:

[0024] Real-time obtain the external environment temperature and door opening frequency data of the refrigerator, and use the least squares method to perform linear regression fitting on the external environment temperature and door opening frequency data of the refrigerator within the unit time region respectively, to obtain the temperature slope value of the temperature change trend and the frequency slope value of the frequency change trend within the unit time region;

[0025] Compare the temperature slope value with the temperature threshold data under the corresponding unit time region to obtain temperature anomaly data points;

[0026] Compare the frequency slope value with the frequency threshold data under the corresponding unit time region to obtain frequency anomaly data points;

[0027] Adopt the ARIMA time series prediction model, and based on the temperature anomaly data points and the frequency anomaly data points, obtain a refrigerator warning signal within the preset time.

[0028] Furthermore, the calculation of the frosting speed in the refrigerator includes:

[0029] Based on the law of conservation of energy, establish a differential equation for the change of the refrigerator's cooling capacity and the amount of frost, and obtain the frosting speed by solving the differential equation;

[0030] The differential equation for the change of the refrigerator's cooling capacity and the amount of frost is:

[0031] d(cooling capacity) / dt = Q_cool - Q_frost - Q_heat_loss

[0032] Where, Q_cool represents the refrigeration capacity of the refrigerator, Q_frost represents the cooling capacity lost due to frosting of the refrigerator, and Q_heat_loss represents the cooling capacity lost due to heat transfer.

[0033] Furthermore, the specific calculation formula of Q_frost is:

[0034] Q_frost = d(m_frost * h_frost) / dt = h_frost * dm_frost / dt

[0035] where m_frost represents the amount of frosting, h_frost represents the latent heat per unit mass of frost, and dm_frost / dt represents the frosting rate of the refrigerator;

[0036] The specific calculation formula of the Q_heat_loss is as follows:

[0037] Q_heat_loss = U * A * (T_in - T_out) + k·F

[0038] where U represents the heat transfer coefficient of the refrigerator, A represents the area of heat exchange between the inside and the outside environment of the refrigerator, T_in represents the internal temperature of the refrigerator, T_out represents the external environmental temperature of the refrigerator, F represents the frequency threshold data, and k represents the influence coefficient of the refrigerator door opening event.

[0039] Furthermore, if the frosting rate is greater than the preset threshold rate, the defrosting parameters of the refrigerator are dynamically adjusted through a dynamic adjustment algorithm, including:

[0040] Calculating the deviation value between the frosting rate and the preset threshold rate;

[0041] Based on the deviation value, using the gradient descent method to obtain a new defrosting parameter value;

[0042] Based on the new defrosting parameter value and the old defrosting parameters, using the weighted average method to update the defrosting parameters of the refrigerator to the first defrosting parameters.

[0043] Furthermore, based on the operation data, optimizing the dynamic adjustment algorithm to generate a defrosting control strategy, including

[0044] Obtaining the external environmental temperature and the door opening frequency data of the refrigerator during the defrosting operation, calculating the influence weights of the external environmental temperature and the door opening frequency data of the refrigerator on the frosting rate using the Pearson correlation coefficient, and obtaining the weight distribution result;

[0045] According to the weight distribution result, using the external environmental temperature or the door opening frequency data of the refrigerator as the independent variable and the frosting rate as the dependent variable to fit a linear regression equation to generate a frosting rate prediction model;

[0046] Applying the frosting rate prediction model to the dynamic adjustment algorithm to generate a defrosting control strategy, and the defrosting control strategy is to adjust the compressor power and the fan speed of the refrigerator refrigeration system.

[0047] Further, applying the frosting speed prediction model to a dynamic adjustment algorithm to generate a defrosting control strategy includes:

[0048] Based on the frosting speed prediction model, obtain the predicted frosting speed of the refrigerator;

[0049] Input the operation data collected in real time during the defrosting operation of the refrigerator into a preset decision tree model, and output a second defrosting parameter through the decision tree model;

[0050] Based on the second defrosting parameter, dynamically adjust the compressor power and fan speed of the refrigerator.

[0051] Further, generating the defrosting control strategy further includes:

[0052] Preprocess the collected operation data to obtain a time series dataset, and based on the time series dataset, construct a multi-dimensional feature vector;

[0053] Adopt a time series analysis algorithm to perform modeling analysis on the multi-dimensional feature vector to obtain the defrosting duration;

[0054] Calculate the correlation coefficient between each dimension feature in the multi-dimensional feature vector and the defrosting effect, and obtain key factors highly correlated with the defrosting effect;

[0055] Based on the key factors, through a clustering algorithm, cluster different defrosting effects in the historical data to obtain defrosting strategy parameters, where the defrosting strategy parameters are the parameter thresholds at the start of the defrosting program;

[0056] Update the defrosting duration and the defrosting strategy parameters to the defrosting program.

[0057] In a second aspect, an embodiment of the present application provides a refrigerator defrosting control system, including:

[0058] A first processing module: used to construct a linear regression model based on historical refrigerator external environment temperature and historical door opening frequency data, and obtain temperature threshold data and frequency threshold data of the refrigerator within a unit time region at a preset time;

[0059] A second processing module: used to obtain a refrigerator warning signal by monitoring the temperature change trend and frequency change trend of the refrigerator within a unit time region based on the temperature threshold data and the frequency threshold data;

[0060] A third processing module: used to calculate the frosting speed inside the refrigerator based on the refrigerator warning signal;

[0061] A fourth processing module: used to, if the frosting speed is greater than a preset threshold speed, dynamically adjust the defrosting parameters of the refrigerator through a dynamic adjustment algorithm;

[0062] The fifth processing module: used to start the defrosting program of the refrigerator based on the defrosting parameters, record the operation data of the defrosting program, and optimize the dynamic adjustment algorithm based on the operation data to generate a defrosting control strategy.

[0063] In a third aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned refrigerator defrosting control method is implemented.

[0064] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned refrigerator defrosting control method is implemented.

[0065] The beneficial effects of the embodiments of the present application compared with the prior art are as follows:

[0066] A refrigerator defrosting control method of the present application can predict and set the temperature threshold data and frequency threshold data of the refrigerator within a unit time area at a preset time by constructing a linear regression model and using historical external environmental temperature and historical door opening frequency data of the refrigerator, which helps to identify in advance external environmental factors that may cause accelerated frosting, thereby improving the predictability and accuracy of defrosting. Based on the set temperature threshold data and frequency threshold data, the temperature change trend and frequency change trend of the refrigerator within a unit time area are monitored in real time. Once an abnormality is found, a refrigerator warning signal is immediately generated. This real-time monitoring mechanism helps to promptly discover and handle potential frosting problems and avoid too thick frost layer affecting the performance of the refrigerator. After receiving the warning signal, the defrosting speed inside the refrigerator is calculated, and the defrosting parameters of the refrigerator are dynamically adjusted according to the magnitude of the defrosting speed to ensure the refrigeration efficiency of the refrigerator during the defrosting process and extend the service life of the refrigerator. After starting the defrosting program, the dynamic adjustment algorithm is continuously optimized based on the operation data. This continuous optimization mechanism can continuously improve the accuracy and efficiency of defrosting control and form a more scientific and reasonable defrosting control strategy. By precisely controlling the defrosting process, unnecessary energy consumption and refrigerant waste are avoided, which helps to reduce the energy consumption and emissions of the refrigerator, thereby improving the user experience and satisfaction and reducing the user's operation burden and maintenance cost. Description of the Drawings

[0067] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0068] Figure 1 is a schematic flowchart of a refrigerator defrosting control method provided by an embodiment of the present invention;

[0069] Figure 2 is a schematic structural diagram of a refrigerator defrosting control system provided by an embodiment of the present invention;

[0070] Figure 3 is a schematic structural diagram of a computer device provided by an embodiment of the present invention. Detailed implementation manners

[0071] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0072] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0073] It should also be understood that the term "and / or" as used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0074] As used in the specification of the present application and the appended claims, the term "if" can be interpreted as "when", "once", "in response to determining", or "in response to detecting" depending on the context. Similarly, the phrase "if determined" or "if detected [the described condition or event]" can be interpreted as meaning "once determined", "in response to determining", "once detected [the described condition or event]", or "in response to detecting [the described condition or event]" depending on the context.

[0075] In addition, in the description of the specification of the present application and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0076] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that specific features, structures or characteristics described in connection with that embodiment are included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments" etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in another way.

[0077] Please refer to Figure 1 as shown, the present invention is a refrigerator defrosting control method, including the following steps:

[0078] S100. Based on historical refrigerator external environmental temperature and historical door opening frequency data, construct a linear regression model to obtain temperature threshold data and frequency threshold data of the refrigerator within a unit time region at a preset time;

[0079] In this application, by constructing a linear regression model and using historical refrigerator external environmental temperature and historical door opening frequency data, it is possible to predict and set temperature threshold data and frequency threshold data of the refrigerator within a unit time region at a preset time, which helps to identify in advance external environmental factors that may cause accelerated frosting, thereby improving the predictability and accuracy of defrosting.

[0080] In some of the embodiments, the above step S100 includes:

[0081] Based on historical refrigerator external environmental temperature and historical door opening frequency data, obtain a temperature data set and a door opening frequency data set;

[0082] Based on the temperature data set and the door opening frequency data set, judge the correlation degree between the environmental temperature and the door opening frequency;

[0083] Based on the correlation degree, with the environmental temperature as the independent variable and the door opening frequency as the dependent variable, fit and generate a linear regression model;

[0084] Based on the temperature data set, construct an environmental temperature prediction model, and predict the environmental temperature of the refrigerator under each unit time region within a preset time through the environmental prediction model to generate an environmental temperature prediction data set, and the environmental temperature under the unit time region is the temperature threshold data corresponding to the unit time region;

[0085] Based on the linear regression model and the environmental temperature prediction dataset, predict the door opening frequency of the refrigerator in each unit time region within a preset time, and generate a door opening frequency prediction dataset within the preset time. The door opening frequency in the unit time region is the frequency threshold data corresponding to the unit time region.

[0086] In this embodiment, the Pandas library is used to load the temperature dataset and the door opening frequency dataset, ensuring that the temperature dataset and the door opening frequency dataset are aligned in terms of timestamps, that is, each environmental temperature data point and each door opening frequency data point are in one-to-one correspondence in terms of timestamps. In addition, the data needs to be cleaned to remove missing values or outliers to ensure the accuracy and integrity of the data. Specifically, the correlation coefficient between the environmental temperature and the door opening frequency is calculated according to the corr() function in the Pandas library to obtain the correlation coefficient r. It can be understood that the value range of the correlation coefficient r is between -1 and 1, where 1 represents a perfect positive correlation, -1 represents a perfect negative correlation, and 0 represents no correlation. If the calculated correlation coefficient r is greater than the set threshold t, it is determined that there is a strong correlation between the environmental temperature and the door opening frequency. In a preferred embodiment, t is set to 0.7.

[0087] In this embodiment, if there is a strong correlation between the environmental temperature and the door opening frequency, the environmental temperature is used as the independent variable (X), and the door opening frequency is used as the dependent variable (y) to fit a linear regression model. By training the linear regression model, the regression coefficient (slope) and the intercept are obtained.

[0088] In this embodiment, the temperature dataset is cleaned to remove missing values, outliers or duplicate data to ensure the accuracy and consistency of the data. Then, according to the characteristics of the temperature data and the prediction requirements, useful features are extracted. For example, dates such as seasons, months, weeks, etc. can be extracted; time intervals, which are equivalent to the preset time, and unit time granularities such as hours, minutes, etc. are used as time features. Time series analysis techniques (such as moving average, exponential smoothing, etc.) are used to identify the long-term trends in the environmental temperature data. Seasonal analysis methods are used to analyze the seasonal variations in the environmental temperature data to understand the impact of different seasons on the environmental temperature. Periodic analysis is used to identify the periodic patterns in the environmental temperature data, such as the daily day-night changes, weekly periodic fluctuations, etc. Based on the above analysis results, a suitable machine learning model, such as the LSTM model, is selected. The above time features are input into the machine learning model for training to generate an environmental temperature prediction model. Based on the environmental temperature prediction model, according to the prediction requirements, corresponding features, such as time intervals and unit time granularities, are input. In a feasible embodiment, a preset time of 24 hours and a unit time granularity of 1 hour are input into the environmental temperature prediction model. Finally, the environmental temperature within each unit time region within the next 24 hours is output through the environmental temperature prediction model, thereby generating an environmental temperature prediction dataset.

[0089] In this embodiment, the environmental temperature prediction model can analyze the input preset time to obtain the date corresponding to the current environment, and then obtain the environmental temperature within the preset time on the corresponding date, so that the finally generated predicted environmental temperature conforms to seasonal and periodic changes. It can be understood that according to different dates, time intervals, and unit time granularities, the data in the environmental temperature prediction dataset are different, and the data in the corresponding door opening frequency prediction dataset are also different.

[0090] In this embodiment, through the linear regression model and the environmental temperature prediction dataset, a door opening frequency prediction dataset corresponding to the environmental temperature prediction dataset is obtained. It can be understood that in the case of time alignment, there is a temperature threshold data and a frequency threshold data corresponding to each unit time region, which correspond to the predicted environmental temperature in the environmental temperature prediction dataset and the predicted door opening frequency in the door opening frequency prediction dataset. Taking the environmental temperature prediction dataset and the door opening frequency prediction result dataset generated with the above preset time of 24 hours and a unit time granularity of 1 hour as an example, the environmental temperature prediction dataset includes the predicted environmental temperature per hour within the next 24 hours, and the 24 predicted environmental temperatures are respectively stored in the corresponding unit time regions. Similarly, the door opening frequency prediction dataset includes the predicted door opening frequency per hour within the next 24 hours, and the 24 predicted door opening frequencies correspond one-to-one with the 24 predicted environmental temperatures and are stored in the corresponding unit time regions. Specifically, if the above preset time of 24 hours is a certain day in the future, the 24 unit time regions can be sequentially divided into 00:00 - 01:00; 01:00 - 02:00......23:00 - 24:00. Each unit time region includes the temperature threshold data generated by the above environmental temperature prediction model, and then, according to the linear regression model and the temperature threshold data, the frequency threshold data corresponding to each unit time region is generated.

[0091] In some embodiments, obtaining the temperature dataset and the door opening frequency dataset based on the historical external environmental temperature of the refrigerator and the historical door opening frequency data includes:

[0092] Obtaining the external environmental temperature of the refrigerator through an environmental temperature sensor and generating a temperature time series dataset;

[0093] Obtaining the occurrence time of the refrigerator door opening event from the door magnetic switch record and generating a door opening event time series dataset;

[0094] Dividing the preset time into multiple identical unit time regions based on the same unit time granularity;

[0095] Based on the unit time region, perform time alignment on the temperature time series dataset and the door opening event time series dataset to generate a temperature dataset and a door opening frequency dataset.

[0096] In this embodiment, for the unit time region in the temperature dataset and the door opening frequency dataset, it is necessary to divide them based on the same unit time granularity, so that the finally generated temperature dataset and door opening frequency dataset can be aligned in time. Similarly, the preset times in the temperature dataset and the door opening frequency dataset also need to be within the same time region. Specifically, in one embodiment, if the data in the temperature dataset is the external environment temperature of the refrigerator in a certain month, when the unit time granularity is 1 hour, the temperature time series dataset can be divided in chronological order. For the door opening frequency dataset, obtain the occurrence time and corresponding occurrence frequency of the refrigerator door opening events in the same month, and divide them in chronological order, and match the temperature time series dataset and the door opening event time series dataset belonging to the same unit time region.

[0097] In this embodiment, when obtaining the historical external environment temperature of the refrigerator and the historical door opening frequency data, the historical external environment temperature of the refrigerator and the historical door opening frequency data at the corresponding time points can be selected according to the time date to be predicted for analysis and division to generate a temperature dataset and a door opening frequency dataset, thereby simplifying the data processing process and improving the accuracy of data prediction. For example, in one embodiment, the time to be predicted is February 18th, then the historical external environment temperature of the refrigerator and the historical door opening frequency data in February can be selected for data analysis and division. To ensure the accuracy of the data, historical data for at least the previous 5 years in February can be obtained for analysis.

[0098] S200. Based on the temperature threshold data and the frequency threshold data, obtain a refrigerator warning signal by real-time monitoring of the temperature change trend and frequency change trend of the refrigerator within the unit time region;

[0099] In this application, based on the set temperature threshold data and frequency threshold data, real-time monitor the temperature change trend and frequency change trend of the refrigerator within the unit time region. Once an abnormality is found, immediately generate a refrigerator warning signal. This real-time monitoring mechanism helps to timely detect and handle potential frosting problems and avoid the excessive frost layer from affecting the performance of the refrigerator.

[0100] In some of these embodiments, the above step S200 includes:

[0101] Real-time obtain the external environment temperature of the refrigerator and the door opening frequency data, and respectively perform linear regression fitting on the external environment temperature of the refrigerator and the door opening frequency data within the unit time region by using the least squares method to obtain the temperature slope value of the temperature change trend within the unit time region and the frequency slope value of the frequency change trend.

[0102] Compare the temperature slope value with the temperature threshold data in the corresponding unit time region to obtain temperature anomaly data points;

[0103] Compare the frequency slope value with the frequency threshold data in the corresponding unit time region to obtain frequency anomaly data points;

[0104] Adopt an ARIMA time series prediction model, and based on the temperature anomaly data points and the frequency anomaly data points, obtain a refrigerator warning signal within a preset time.

[0105] In this embodiment, the collected external environment temperature and door opening frequency data of the refrigerator are cleaned to remove noise and outliers, and then the external environment temperature and door opening frequency data of the refrigerator are sorted in chronological order to ensure data continuity. According to the time of the obtained external environment temperature and door opening frequency data of the refrigerator, select the corresponding unit time region from the environmental temperature prediction data set and the door opening frequency prediction data set, and determine the temperature threshold data and frequency threshold data corresponding to the currently collected external environment temperature and door opening frequency data of the refrigerator.

[0106] In this embodiment, the least squares method is used to perform linear regression fitting on the external environment temperature and door opening frequency data of the refrigerator in the unit time region respectively, to obtain a linear equation of temperature changing with time and a linear equation of door opening frequency changing with time. Based on the above two linear equations, the temperature slope value of the temperature change trend and the frequency slope value of the frequency change trend in the unit time region can be calculated.

[0107] In this embodiment, the temperature slope value is compared with the corresponding temperature threshold data. If it exceeds the temperature threshold data, it is marked as a temperature anomaly data point. Similarly, the frequency slope value is compared with the corresponding frequency threshold data. If it exceeds the frequency threshold data, it is marked as a frequency anomaly data point.

[0108] For the ARIMA time series prediction model, historical temperature anomaly data points and frequency anomaly data points are used as training data to train the ARIMA time series prediction model. Based on the trained ARIMA time series prediction model, the temperature anomaly signal and frequency anomaly signal within a preset time are predicted. If the prediction result shows that there is a temperature anomaly or frequency anomaly in the future preset time, such as 24 hours, 48 hours, etc., a refrigerator warning signal is generated.

[0109] S300. Calculate the frosting speed inside the refrigerator based on the refrigerator warning signal;

[0110] In this embodiment, when generating a refrigerator warning signal, it indicates that there is an abnormal temperature or frequency in the refrigerator. To a certain extent, the abnormal temperature or frequency will affect the frosting degree of the refrigerator. Therefore, when generating a refrigerator warning signal, it is necessary to calculate the current frosting speed inside the refrigerator and dynamically adjust the defrosting operation of the refrigerator based on this to ensure the refrigeration efficiency of the refrigerator during the defrosting process and extend the service life of the refrigerator.

[0111] In some of the embodiments, calculating the frosting speed inside the refrigerator includes:

[0112] Based on the law of conservation of energy, establish a differential equation for the change in the refrigerating capacity of the refrigerator and the amount of frost, and obtain the frosting speed by solving the differential equation;

[0113] The differential equation for the change in the refrigerating capacity of the refrigerator and the amount of frost is:

[0114] d(cooling capacity) / dt = Q_cool - Q_frost - Q_heat_loss

[0115] where Q_cool represents the refrigerating capacity of the refrigerator, Q_frost represents the cooling capacity lost due to frosting of the refrigerator, and Q_heat_loss represents the cooling capacity lost due to heat transfer.

[0116] In this embodiment, through the differential equation model, the frosting speed of the refrigerator under different operating conditions can be accurately predicted, realizing continuous monitoring of the frosting state inside the refrigerator, and timely discovering and handling potential frosting problems.

[0117] In some of the embodiments, the specific calculation formula for Q_frost is: Q_frost = d(m_frost * h_frost) / dt = h_frost * dm_frost / dt

[0118] where m_frost represents the amount of frost, h_frost represents the latent heat per unit mass of frost, and dm_frost / dt represents the frosting speed of the refrigerator;

[0119] The specific calculation formula for Q_heat_loss is:

[0120] Q_heat_loss = U * A * (T_in - T_out) + k·F

[0121] where U represents the heat transfer coefficient of the refrigerator, A represents the area of heat exchange between the inside and outside of the refrigerator, T_in represents the internal temperature of the refrigerator, T_out represents the external environmental temperature of the refrigerator, F represents the frequency threshold data, and k represents the influence coefficient of the refrigerator door opening event.

[0122] It can be understood that by substituting the above calculation formulas of \(Q_{heat\_loss}\) and \(Q_{frost}\) into the above differential equation of the change in the refrigerating capacity of the refrigerator and the amount of frost formation, the following is obtained:

[0123] d(cooling capacity) / dt

[0124] = \(Q_{cool}-h_{frost}*dm_{frost} / dt - U*A*(T_{in}-T_{out})+k·\)

[0125] F

[0126] Then, by solving the frost formation speed of the above differential equation, the following calculation formula can be obtained:

[0127] dm_{frost} / dt

[0128] = \((Q_{cool}-U*A*(T_{in}-T_{out})+k·F) / (\)

[0129] -h_{frost})

[0130] It can be understood that through the above formula, the frost formation speed of the refrigerator can be obtained, where F represents the frequency threshold data, and further, it represents the frequency threshold data of the unit time region corresponding to the current time point, which is used to measure the influence of the door opening frequency on the frost formation speed. k is an influence coefficient, which represents the proportional relationship between the heat exchange amount caused by each door opening and the door opening frequency. This coefficient depends on multiple factors such as the size of the refrigerator door, the heat preservation performance, and the temperature difference between the inside and outside of the refrigerator. It is usually fitted through experimental data. For example, measure the temperature changes and heat exchange amounts inside and outside the refrigerator under different conditions, and then estimate the value of k. Specifically, select refrigerator doors with different sizes and heat preservation performances for experiments, ensure that the temperature inside the refrigerator can be adjusted, and be equipped with temperature sensors to accurately measure the temperature difference between the inside and outside of the refrigerator. Determine external conditions such as the experimental time and ambient temperature to ensure the repeatability of the experiment. Set different door opening frequencies, such as opening the door once a minute, opening the door once every five minutes, etc. After each door opening, record the temperature change inside the refrigerator, use a calorimeter or other equipment to measure the heat exchange amount caused by the door opening, calculate the heat exchange amount caused by each door opening according to the experimental data, conduct statistical analysis on the door opening frequency and the corresponding heat exchange amount, observe the trend and relationship between them, use regression analysis methods, such as linear regression, polynomial regression, etc., take the door opening frequency as the independent variable and the heat exchange amount as the dependent variable, fit the mathematical relationship between them, and extract the influence coefficient k from the fitting result, which represents the proportional relationship between the heat exchange amount caused by each door opening and the door opening frequency.

[0131] S400. If the frost formation speed is greater than the preset threshold speed, then dynamically adjust the defrosting parameters of the refrigerator through a dynamic adjustment algorithm;

[0132] In some of these embodiments, the above step S400 includes:

[0133] Calculating the deviation value between the frosting speed and the preset threshold speed;

[0134] Based on the deviation value, using the gradient descent method to obtain a new defrosting parameter value;

[0135] Based on the new defrosting parameter value and the old defrosting parameter, using the weighted average method to update the defrosting parameter of the refrigerator to the first defrosting parameter.

[0136] In this embodiment, by defining an objective function to measure the deviation between the current frosting speed and the preset threshold speed, the objective function is usually a loss function, such as the mean square error (MSE) or the mean absolute error (MAE). The preset threshold speed is obtained through a large amount of experimental data statistics. At this threshold speed, it helps to maintain the temperature and humidity environment inside the refrigerator. Specifically, the objective function is:

[0137]

[0138] Where f current (θ) represents the frosting speed under the current defrosting parameter θ, f target represents the preset threshold speed, and L(θ) represents the loss value, that is, the deviation value between the frosting speed and the preset threshold speed.

[0139] Based on the above loss value, calculate the gradient of the objective function with respect to the defrosting parameter θ. The gradient is a vector that points in the direction of the fastest increase in the function value. Specifically, in the gradient descent method, update the parameter along the opposite direction of the gradient to minimize the objective function. Specifically, by taking the derivative of L(θ), we get:

[0140]

[0141] Where represents the derivative of the frosting speed with respect to the defrosting parameter.

[0142] Based on the derivative function of the gradient of the above defrosting parameter θ, generate the defrosting parameter. Specifically, Where α is the learning rate, which determines the step size of parameter update; θ old is the old defrosting parameter before update; θ new is the newly generated defrosting parameter.

[0143] In this embodiment, in order to improve the stability of the dynamic adjustment of the defrosting parameter, the weighted average method is used to smooth the update process between the old defrosting parameter and the new defrosting parameter. Specifically: θ updated =βθ new -(1 - β)θold , where β is the weighted average coefficient, which determines the weights of the new parameter value and the old parameter value in the update process. Specifically, if you want to respond more quickly to the new parameter value, you can increase the value of β; if you want to keep the current parameter value relatively stable, you can decrease the value of β; θ updated is the first defrosting parameter after the refrigerator is updated. This first defrosting parameter is used to adjust the defrosting strategy of the refrigeration system to be closer to the preset threshold speed.

[0144] S500. Based on the defrosting parameter, start the defrosting program of the refrigerator, record the operation data of the defrosting program, and based on the operation data, optimize the dynamic adjustment algorithm to generate a defrosting control strategy.

[0145] In this embodiment, based on the first defrosting parameter generated after the update, start the defrosting program of the refrigerator to generate a defrosting control strategy. Specifically, the defrosting control strategy is to adjust the compressor power and fan speed of the refrigerator's refrigeration system so that the frosting speed of the refrigerator meets the preset threshold speed. In some embodiments, the defrosting control strategy also includes the determination of the defrosting duration. During the startup process of the refrigerator's defrosting program, the dynamic adjustment algorithm also needs to be adjusted according to the corresponding operation data, so that the defrosting control strategy can be dynamically adjusted according to the corresponding environmental parameters during the actual operation of the defrosting program to ensure the balance between the refrigeration effect and the defrosting speed. In addition, the continuous optimization mechanism that continuously optimizes the dynamic adjustment algorithm through operation data can continuously improve the accuracy and efficiency of defrosting control, forming a more scientific and reasonable defrosting control strategy. Among them, the operation data includes the internal temperature of the refrigerator, the internal humidity of the refrigerator, the external environmental temperature of the refrigerator, the door opening frequency data, and the frosting speed.

[0146] In some of these embodiments, the optimizing the dynamic adjustment algorithm based on the operation data to generate a defrosting control strategy includes

[0147] Obtain the external environmental temperature of the refrigerator and the door opening frequency data during the defrosting operation, calculate the influence weights of the external environmental temperature of the refrigerator and the door opening frequency data on the frosting speed using the Pearson correlation coefficient, and obtain the weight distribution result;

[0148] According to the weight distribution result, take the external environmental temperature of the refrigerator or the door opening frequency data as the independent variable and the frosting speed as the dependent variable, fit a linear regression equation, and generate a frosting speed prediction model;

[0149] Apply the frosting speed prediction model to the dynamic adjustment algorithm to generate a defrosting control strategy, and the defrosting control strategy is to adjust the compressor power and fan speed of the refrigerator's refrigeration system.

[0150] In this embodiment, the Pearson correlation coefficient is used to calculate the correlation between the external environmental temperature of the refrigerator, the door opening frequency data, and the frosting speed respectively, obtaining a correlation coefficient matrix. According to the correlation coefficient matrix, the influence weights of the external environmental temperature and the door opening frequency on the frosting speed are determined, and a weight distribution table is generated. Specifically, when the correlation coefficient is any value between 0 and -1, it indicates that there is no correlation between the corresponding external environmental temperature of the refrigerator or the door opening frequency data and the frosting speed. Therefore, in the weight distribution table, its value is assigned as 0, and the correlation coefficient greater than 0 is used as the weight value to complete the weight distribution table.

[0151] In this embodiment, if the weight of the external environmental temperature in the weight distribution table is higher than that of the door opening frequency, the external environmental temperature is used as the independent variable and the frosting speed is used as the dependent variable to fit a linear regression equation to generate a frosting speed prediction model; if the weight of the door opening frequency in the weight distribution table is higher than that of the external environmental temperature, the door opening frequency data is used as the independent variable and the frosting speed is used as the dependent variable to fit a linear regression equation to generate a frosting speed prediction model. If the weights of the door opening frequency and the external environmental temperature in the weight distribution table are equivalent, the door opening frequency data and the external environmental temperature are used as the independent variables and the frosting speed is used as the dependent variable to fit a multiple linear regression model to generate a frosting speed prediction model.

[0152] In some embodiments, applying the frosting speed prediction model to a dynamic adjustment algorithm to generate a defrosting control strategy includes:

[0153] Based on the frosting speed prediction model, the predicted frosting speed of the refrigerator is obtained;

[0154] The operation data collected in real time during the defrosting operation of the refrigerator is input into a preset decision tree model, and a second defrosting parameter is output through the decision tree model;

[0155] Based on the second defrosting parameter, the compressor power and the fan speed of the refrigerator are dynamically adjusted.

[0156] In this embodiment, the operation data includes the internal temperature of the refrigerator, the internal humidity of the refrigerator, the external environmental temperature of the refrigerator, the door opening frequency data, and the frosting speed. Among them, the frosting speed is the predicted frosting speed of the refrigerator obtained through the frosting speed prediction model, and the second defrosting parameter is output through the decision tree model, thereby further regulating the defrosting control strategy.

[0157] For the decision tree model, the features of the decision tree model include the internal temperature of the refrigerator, the internal humidity of the refrigerator, the external environmental temperature of the refrigerator, the door opening frequency data, and the frosting speed. Each feature corresponds to a node in the decision tree. According to different feature values, the data is divided into different sub-nodes. When the data traverses to the leaf node of the decision tree, it means that a detailed division has been made based on a series of feature values. At the leaf node, the model calculates the optimal defrosting parameters according to the defrosting operation records under similar conditions in the historical data. The above defrosting parameters include the compressor power and the fan speed of the refrigerator, which are obtained based on the operation with the best defrosting effect in the historical data. Furthermore, when the operation data collected in real time during the defrosting operation of the refrigerator is input into the decision tree model, the second defrosting parameters that conform to the current frosting situation can be obtained.

[0158] In some of these embodiments, the generating of the defrost control strategy further includes:

[0159] Preprocess the collected operation data to obtain a time series data set, and based on the time series data set, construct a multi-dimensional feature vector;

[0160] Adopt a time series analysis algorithm to perform modeling analysis on the multi-dimensional feature vector to obtain the defrosting duration;

[0161] Calculate the correlation coefficient between each dimension feature in the multi-dimensional feature vector and the defrosting effect to obtain the key factors highly correlated with the defrosting effect;

[0162] Based on the key factors, through a clustering algorithm, cluster different defrosting effects in the historical data to obtain defrosting strategy parameters, where the defrosting strategy parameters are the parameter thresholds at the start of the defrosting program;

[0163] Update the defrosting duration and the defrosting strategy parameters to the defrosting program.

[0164] In this embodiment, the collected time series data such as the refrigerator internal temperature, refrigerator internal humidity, refrigerator external environment temperature, door opening frequency data and frosting speed are cleaned and preprocessed, outliers are removed, and time alignment and data normalization are performed to obtain a standardized time series data set. Based on the standardized time series data set, time statistical features such as mean and variance, as well as frequency domain features such as Fourier transform coefficients, are extracted to construct a multi-dimensional feature vector of the defrosting process; a time series analysis algorithm such as the ARIMA model is used to model and analyze the multi-dimensional feature vector to characterize the temperature and humidity change law of the defrosting process and the dynamic characteristics of the equipment frosting speed, and the ARIMA model is used to predict the optimal defrosting time under the current environmental conditions; at the same time, the multi-dimensional feature vector is calculated. The correlation coefficient between the characteristics of each dimension and the defrost effect is used to obtain the key factors that are highly correlated with the defrost effect; the K-Means clustering algorithm is used to cluster the different defrost effects in the historical data according to the key factors, and the defrost strategy parameters corresponding to the optimal defrost mode are mined, such as the defrost start temperature and humidity thresholds, etc. The defrost strategy parameters and the predicted optimal defrost duration are updated to the configuration file of the defrost program. The refrigerator then monitors the environmental parameters in real time according to the updated defrost strategy parameters and the predicted optimal defrost duration. When the defrost strategy parameters are met, the defrost program is started, and the defrost duration is controlled according to the predicted optimal defrost duration. At the same time, the defrost effect data is collected in real time and fed back to the historical data set to form a strategy optimization closed loop and continuously improve the system defrost performance.

[0165] In this application, by precisely controlling the defrosting process, unnecessary energy consumption and refrigerant waste are avoided, which helps to reduce the energy consumption and emissions of the refrigerator, thereby improving the user experience and satisfaction, and reducing the user's operating burden and maintenance costs.

[0166] See also Figure 2 As shown, the present invention also provides a refrigerator defrosting control system, the system comprising:

[0167] The first processing module 201 is used to construct a linear regression model based on the historical refrigerator external environment temperature and the historical door opening frequency data, and obtain the temperature threshold data and frequency threshold data of the refrigerator in a unit time area under a preset time;

[0168] The second processing module 202 is used to obtain a refrigerator warning signal by real-time monitoring the temperature change trend and frequency change trend of the refrigerator in a unit time area based on the temperature threshold data and the frequency threshold data;

[0169] The third processing module 203 is used to calculate the frost speed in the refrigerator based on the refrigerator warning signal;

[0170] Fourth processing module 204: If the frosting speed is greater than a preset threshold speed, it is used to dynamically adjust the defrosting parameters of the refrigerator through a dynamic adjustment algorithm;

[0171] Fifth processing module 205: It is used to start the defrosting program of the refrigerator based on the defrosting parameters, record the operation data of the defrosting program, and optimize the dynamic adjustment algorithm based on the operation data to generate a defrosting control strategy.

[0172] It can be understood that, as Figure 1 shown, the content in the embodiment of the refrigerator defrosting control method is applicable to the embodiment of the present refrigerator defrosting control system. The functions specifically implemented by the embodiment of the present refrigerator defrosting control system are the same as those in the embodiment of the refrigerator defrosting control method as Figure 1 shown, and the beneficial effects achieved are also the same as those in the embodiment of the refrigerator defrosting control method as Figure 1 shown.

[0173] It should be noted that for the information interaction, execution process, etc. between the above systems, since they are based on the same concept as the method embodiment of the present invention, for their specific functions and the technical effects brought, reference can be specifically made to the method embodiment part, and details will not be elaborated here.

[0174] Those skilled in the art can clearly understand that for the convenience and conciseness of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the system is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment, and details will not be elaborated here.

[0175] Please refer to Figure 3 shown. The embodiment of the present invention also provides a computer device 3, including: a memory 302, a processor 301, and a computer program 303 stored on the memory 302. When the computer program 303 is executed on the processor 301, the refrigerator defrosting control method described in any one of the above methods is implemented.

[0176] The computer device 3 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art can understand that Figure 3 merely examples of the computer device 3, which do not constitute a limitation on the computer device 3, may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0177] The so-called processor 301 may be a central processing unit (CPU), and the processor 301 may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0178] The memory 302 may be an internal storage unit of the computer device 3 in some embodiments, such as the hard disk or memory of the computer device 3. The memory 302 may also be an external storage device of the computer device 3 in other embodiments, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 3. Further, the memory 302 may also include both the internal storage unit and the external storage device of the computer device 3. The memory 302 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory 302 may also be used to temporarily store data that has been output or will be output.

[0179] The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it implements the refrigerator defrosting control method described in any one of the above methods.

[0180] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the method of the above embodiment in the present application, a computer program can be used to instruct the relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the photographing device / computer device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0181] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A refrigerator defrosting control method, characterized in that: include: Based on the historical refrigerator external environment temperature and historical door opening frequency data, a linear regression model is constructed to obtain the temperature threshold data and frequency threshold data of the refrigerator in a unit time area under the preset time; Based on the temperature threshold data and the frequency threshold data, a refrigerator warning signal is obtained by real-time monitoring of the temperature change trend and the frequency change trend of the refrigerator within a unit time area; Calculating the frost speed in the refrigerator based on the refrigerator warning signal; If the frosting speed is greater than a preset threshold speed, dynamically adjusting the defrosting parameters of the refrigerator through a dynamic adjustment algorithm; Based on the defrost parameters, a defrost program of the refrigerator is started, operation data of the defrost program is recorded, and based on the operation data, the dynamic adjustment algorithm is optimized to generate a defrost control strategy.

2. The method according to claim 1, characterized in that The method constructs a linear regression model based on the historical refrigerator external environment temperature and the historical door opening frequency data to obtain the temperature threshold data and frequency threshold data of the refrigerator in a unit time area under a preset time, including: Based on the historical refrigerator external environment temperature and historical door opening frequency data, a temperature data set and a door opening frequency data set are obtained; Based on the temperature data set and the door opening frequency data set, determining the degree of correlation between the ambient temperature and the door opening frequency; Based on the correlation, a linear regression model is generated by fitting with the ambient temperature as the independent variable and the door opening frequency as the dependent variable; Based on the temperature data set, an ambient temperature prediction model is constructed, and the ambient temperature of the refrigerator in each unit time zone within a preset time is predicted by the ambient temperature prediction model to generate an ambient temperature prediction data set, where the ambient temperature in the unit time zone is the temperature threshold data in the corresponding unit time zone; Based on the linear regression model and the ambient temperature prediction data set, the door opening frequency of the refrigerator in each unit time area within the preset time is predicted, and a door opening frequency prediction data set within the preset time is generated, and the door opening frequency in the unit time area is the frequency threshold data in the corresponding unit time area.

3. The method according to claim 2, characterized in that The step of obtaining a temperature data set and a door opening frequency data set based on historical refrigerator external environment temperature and historical door opening frequency data includes: The external ambient temperature of the refrigerator is obtained through the ambient temperature sensor, and a temperature time series data set is generated; Obtain the occurrence time of the refrigerator door opening event from the door magnetic switch record and generate a door opening event time series dataset; Based on the same unit time granularity, the preset time is divided into a plurality of the same unit time areas; Based on the unit time region, the temperature time series dataset and the door opening event time series dataset are time-aligned to generate a temperature dataset and a door opening frequency dataset.

4. The method according to claim 2, characterized in that The obtaining of a refrigerator warning signal based on the temperature threshold data and the frequency threshold data by real-time monitoring of the temperature change trend and the frequency change trend of the refrigerator within a unit time area includes: The external environment temperature and the door opening frequency data of the refrigerator are obtained in real time, and the least square method is used to perform linear regression fitting on the external environment temperature and the door opening frequency data of the refrigerator in a unit time area, respectively, to obtain the temperature slope value of the temperature change trend and the frequency slope value of the frequency change trend in the unit time area; Compare the temperature slope value with the temperature threshold data in the corresponding unit time area to obtain the temperature anomaly data point; Compare the frequency slope value with the frequency threshold data under the corresponding unit time area to obtain the frequency abnormality data point; The ARIMA time series prediction model is adopted to obtain a refrigerator warning signal within a preset time based on the temperature abnormality data points and the frequency abnormality data points.

5. The method according to claim 1, characterized in that The method of calculating the frosting speed in the refrigerator comprises: Based on the law of conservation of energy, a differential equation of the change in refrigerator cooling capacity and the amount of frost is established, and the frost rate is obtained by solving the differential equation. The differential equation of the refrigerator cooling capacity change and frosting amount is: d(cooling capacity) / dt=Q_cool―Q_frost―Q_heat_loss Among them, Q_cool represents the cooling capacity of the refrigerator, Q_frost represents the cooling capacity lost due to frost in the refrigerator, and Q_heat_loss represents the cooling capacity lost due to heat transfer.

6. The method according to claim 4, characterized in that The calculation formula of Q_frost is specifically: Q_frost=d(m_frost*h_frost) / dt=h_frost*dm_frost / dtwhere, m_frost represents the amount of frost, h_frost represents the potential heat of frost per unit mass, and dm_frost / dt represents the frost speed of the refrigerator; The calculation formula of Q_heat_loss is specifically: Q_heat_loss=U*A*(T_in―T_out)+k·F Among them, U represents the heat transfer coefficient of the refrigerator, A represents the area of ​​heat exchange between the inside of the refrigerator and the external environment, T_in represents the internal temperature of the refrigerator, T_out represents the external environment temperature of the refrigerator, F represents the frequency threshold data, and k represents the influence coefficient of the refrigerator door opening event.

7. The method according to claim 1, characterized in that If the frosting speed is greater than a preset threshold speed, dynamically adjusting the defrosting parameters of the refrigerator through a dynamic adjustment algorithm includes: Calculating a deviation value between the frosting speed and the preset threshold speed; Based on the deviation value, a new defrost parameter value is obtained by using a gradient descent method; Based on the new defrost parameter value and the old defrost parameter, the defrost parameter of the refrigerator is updated to the first defrost parameter by adopting the weighted average method.

8. The method according to claim 1, characterized in that The step of optimizing the dynamic adjustment algorithm based on the operating data and generating a defrost control strategy includes: The external environment temperature and door opening frequency data of the refrigerator during the defrosting operation are obtained, and the influence weights of the external environment temperature and door opening frequency data of the refrigerator on the frosting speed are calculated using the Pearson correlation coefficient to obtain the weight distribution result; According to the weight distribution result, the external environment temperature of the refrigerator or the door opening frequency data is used as an independent variable, and the frosting speed is used as a dependent variable, and a linear regression equation is fitted to generate a frosting speed prediction model; The frosting speed prediction model is applied to a dynamic adjustment algorithm to generate a defrost control strategy, wherein the defrost control strategy is to adjust the compressor power and fan speed of a refrigerator refrigeration system.

9. The method according to claim 8, characterized in that The frosting speed prediction model is applied to a dynamic adjustment algorithm to generate a defrosting control strategy, including: Based on the frosting speed prediction model, obtaining a predicted frosting speed of the refrigerator; Inputting the real-time collected operating data during the defrosting operation of the refrigerator into a preset decision tree model, and outputting a second defrosting parameter through the decision tree model; Based on the second defrost parameter, the compressor power and fan speed of the refrigerator are dynamically adjusted.

10. The method according to claim 9, characterized in that The generating of the defrost control strategy further includes: Preprocessing the collected operation data to obtain a time series data set, and constructing a multi-dimensional feature vector based on the time series data set; Using a time series analysis algorithm, modeling and analyzing the multi-dimensional feature vector to obtain the defrosting time; Calculate the correlation coefficient between each dimension feature in the multi-dimensional feature vector and the defrosting effect, and obtain the key factors that are highly correlated with the defrosting effect; Based on the key factors, different defrosting effects in the historical data are clustered by a clustering algorithm to obtain defrosting strategy parameters, where the defrosting strategy parameters are thresholds of various parameters when the defrosting program is started; The defrost duration and the defrost strategy parameters are updated into the defrost program.

11. A refrigerator defrosting control system, characterized in that: include: The first processing module is used to construct a linear regression model based on the historical refrigerator external environment temperature and historical door opening frequency data to obtain the temperature threshold data and frequency threshold data of the refrigerator in a unit time area under a preset time; The second processing module is used to obtain a refrigerator warning signal by real-time monitoring the temperature change trend and frequency change trend of the refrigerator in a unit time area based on the temperature threshold data and the frequency threshold data; The third processing module is used to calculate the frost speed in the refrigerator based on the refrigerator warning signal; A fourth processing module: used for dynamically adjusting the defrosting parameters of the refrigerator through a dynamic adjustment algorithm if the frosting speed is greater than a preset threshold speed; The fifth processing module is used to start the defrost program of the refrigerator based on the defrost parameters, record the operating data of the defrost program, and optimize the dynamic adjustment algorithm based on the operating data to generate a defrost control strategy.

12. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 10 is implemented.

13. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images