A refrigerator intelligent control method and system

Abstract

The present invention relates to the field of refrigerator control technology, and discloses a refrigerator intelligent control method and system, including: obtaining characteristic data of frost layer on the surface of refrigerator evaporator from time T-N to time T, and obtaining predicted frost layer influence coefficient of frost layer on the surface of refrigerator evaporator at time T+N according to a pre-constructed frost layer influence coefficient regression model; comparing the predicted frost layer influence coefficient of frost layer on the surface of refrigerator evaporator with a preset frost layer influence standard coefficient threshold to obtain a comparison result; according to the comparison result, inputting the predicted frost layer influence coefficient of frost layer on the surface of refrigerator evaporator into a pre-configured optimal heating power machine learning model to obtain the optimal heating power for heating refrigerator evaporator; controlling refrigerator heater to defrost refrigerator evaporator according to the optimal heating power; the present invention is conducive to timely predicting and judging whether refrigerator evaporator needs to be defrosted, avoiding inaccurate defrosting, and calculating the optimal defrosting heating power, which is conducive to saving electricity.

Description

Technical Field

[0001] The present invention relates to the field of refrigerator control technology, and more specifically, to a refrigerator intelligent control method and system. Background Art

[0002] As a daily household appliance, refrigerators play a vital role in family life. One of the core functions of refrigerators is to keep food fresh, and the realization of this function is highly dependent on the temperature control inside the refrigerator. The temperature control is mainly achieved through the evaporator inside the refrigerator. The evaporator absorbs internal heat through the evaporation process of the refrigerant, thereby reducing the temperature inside the refrigerator and ensuring that the storage environment of food is always at a low temperature. However, during the daily use of the refrigerator, the frost layer caused by moisture condensation often adheres to the surface of the evaporator. As time goes by, the frost layer gradually accumulates, which affects the heat exchange efficiency of the evaporator, thereby weakening the refrigeration effect of the refrigerator, increasing energy consumption, and even shortening the shelf life of food. Therefore, the defrost function occupies an important position in the design and use of refrigerators.

[0003] There are two main defrosting methods for existing refrigerators. The first is manual defrosting, which requires the user to manually cut off the power and clear the frost layer in the refrigerator. This method is not only cumbersome, time-consuming and labor-intensive, but also may damage the refrigerator structure and cause damage to the refrigerator if the user is negligent. The second is automatic timed defrosting, which automatically starts the defrosting program at a preset time interval. Although this method reduces the user's operating burden, it is unable to perceive the actual thickness of the frost layer and environmental conditions in real time, which often leads to inaccurate defrosting and incomplete defrosting, affecting the refrigeration effect of the refrigerator, increasing actual power consumption, or excessive defrosting causing energy waste, and may shorten the service life of the refrigerator. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a refrigerator intelligent control method and system.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A refrigerator intelligent control method, the method comprising:

[0007] Step 1: Obtain characteristic data of the frost layer on the surface of the refrigerator evaporator from time TN to time T, and obtain the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator at time T+N according to the pre-built frost layer influence coefficient regression model, where T and N are positive integers greater than zero;

[0008] Step 2: comparing the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator with a preset frost layer influence standard coefficient threshold to obtain a comparison result, wherein the comparison result includes a first comparison result and a second comparison result;

[0009] Step 3: According to the second comparison result, the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator is input into the preconfigured optimal heating power machine learning model to obtain the optimal heating power for heating the refrigerator evaporator;

[0010] Step 4: Controlling the refrigerator heater to defrost the refrigerator evaporator according to the optimal heating power.

[0011] Furthermore, the generation logic of the frost layer influence coefficient regression model is as follows:

[0012] Acquire a historical frost layer impact sample set, and divide the historical frost layer impact sample set into a frost layer impact training set and a frost layer impact test set, wherein the frost layer impact sample set includes frost layer impact feature data and a corresponding frost layer impact coefficient, and the frost layer impact feature data includes the thickness of the frost layer on the surface of the corresponding refrigerator evaporator at each moment in a time period, the density of the frost layer, and the surface area of ​​the frost layer;

[0013] Constructing a first regression network, taking the frost layer impact feature data in the frost layer impact training set as the input of the first regression network, taking the frost layer impact coefficient in the frost layer impact training set as the output of the first regression network, training the first regression network, and obtaining a frost layer impact coefficient regression network;

[0014] The frost influence coefficient regression network is validated using the frost influence test set, and the frost influence coefficient regression network with an accuracy greater than or equal to the output is used as the frost influence coefficient regression model.

[0015] Furthermore, the logic for obtaining the frost layer influence coefficient is as follows:

[0016] The frost layer on the surface of the refrigerator evaporator is divided equally into R subdivided areas;

[0017] The thickness value, density value and surface area of ​​the frost layer in each subdivided area are obtained; the frost layer influence coefficient is obtained by formula calculation according to the thickness value, density value and surface area of ​​the frost layer in each subdivided area; the calculation formula is: ; In the formula, represents the frost layer influence coefficient, represents the thickness of the frost layer in the ith subdivision area, represents the density value of the frost layer in the ith subdivision area, Represents the surface area of ​​the frost layer in the i-th subdivision area.

[0018] Furthermore, the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator is compared with a preset frost layer influence standard coefficient threshold, including:

[0019] If the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator is less than the preset frost layer influence standard coefficient threshold, the refrigerator evaporator is marked as "normal frost layer accumulation", "normal frost layer accumulation" is used as the first comparison result, and T+N+M is set, and the process returns to step 1, where M is a positive integer greater than zero;

[0020] If the predicted frost influence coefficient of the frost layer on the surface of the refrigerator evaporator is greater than or equal to the preset frost influence standard coefficient threshold, the refrigerator evaporator is marked as "excessive frost accumulation" and "excessive frost accumulation" is used as the second comparison result.

[0021] Furthermore, the generation logic of the preconfigured optimal heating power machine learning model is as follows:

[0022] Acquire historical refrigerator evaporator defrost training data, and divide the historical refrigerator evaporator defrost training data into a refrigerator evaporator defrost training set and a refrigerator evaporator defrost test set; the historical refrigerator evaporator defrost training data includes a frost layer influence coefficient and its corresponding optimal heating power;

[0023] A second regression network is constructed, the refrigeration influence coefficient in the refrigerator evaporator defrost training set is used as input data of the second regression network, and the optimal heating power in the refrigerator evaporator defrost training set is used as output data of the second regression network, and the second regression network is trained to obtain a heating power regression network;

[0024] The refrigerator evaporator defrost test set is used to verify the heating power regression network model, and the heating power regression network with an output less than or equal to the preset test error threshold is used as the preconfigured optimal heating power machine learning model.

[0025] Furthermore, the generation logic of the optimal heating power in the historical refrigerator evaporator defrosting training data is as follows:

[0026] S31: Initialize the population: randomly generate an original population, wherein the original population includes N individuals, each individual represents a heating power, and N is an integer greater than zero;

[0027] S32: Fitness evaluation: based on each individual, the time required for completely melting the frost layer under each individual is obtained, the time required for completely melting the frost layer and the heating power are input into a pre-constructed fitness function, and the fitness of each individual is calculated;

[0028] S33: Selection: Use the roulette method to select two individuals with high fitness in the original population as the father and mother;

[0029] S34: Crossover: Perform crossover operation on the father and mother to produce new individuals;

[0030] S35: mutation: using Gaussian mutation method to perform mutation operation on the new individuals, obtaining M new individuals, combining the M new individuals into a new population, and replacing the original population with the new population, and returning to step S32;

[0031] S36: Repeat the above steps S32 to S35 until the fitness of the individuals in the original population or the new population is greater than or equal to the preset fitness threshold, and output the heating power represented by the corresponding individual as the optimal heating power for heating the refrigerator evaporator.

[0032] Furthermore, the generation logic of the time required to completely melt the frost layer is as follows:

[0033] The frost layer influence coefficient and heating power corresponding to the second comparison result are input into the defrost time regression model to obtain the time required to completely melt the frost layer;

[0034] The generation logic of the defrost time regression model is as follows:

[0035] Obtain historical defrost time training data, and divide the historical defrost time training data into a defrost time training set and a defrost time test set; the historical defrost time training data includes a frost layer influence coefficient, a heating power, and a corresponding time required to completely melt the frost layer;

[0036] A third regression network is constructed, the frost layer influence coefficient and the heating power in the defrost time training set are used as input data of the third regression network, and the time required to completely melt the frost layer is used as output data of the third regression network, and the third regression network is trained to obtain a defrost time regression network;

[0037] The defrost time test set is used to verify the defrost time regression network model, and the defrost time regression network with an output less than or equal to the preset error threshold is used as the defrost time regression model.

[0038] Furthermore, the generation logic of the fitness function is as follows:

[0039] The calculation formula of the pre-constructed fitness function is: ; Where: represents fitness, is the heating power, The time required for the frost to completely melt.

[0040] A refrigerator intelligent control system, characterized in that it includes:

[0041] Information acquisition module 201: used to obtain characteristic data of frost layer on the surface of refrigerator evaporator from time TN to time T, and to obtain predicted frost layer influence coefficient of frost layer on the surface of refrigerator evaporator at time T+N according to a pre-built frost layer influence coefficient regression model, where T and N are positive integers greater than zero;

[0042] Comparison and judgment module 202: used to compare the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator with a preset frost layer influence standard coefficient threshold to obtain a comparison result, wherein the comparison result includes a first comparison result and a second comparison result;

[0043] Data calculation module 203: used for inputting the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator into a preconfigured optimal heating power machine learning model according to the second comparison result, so as to obtain the optimal heating power for heating the refrigerator evaporator;

[0044] The defrost control module 204 is used to control the refrigerator heater to defrost the refrigerator evaporator according to the optimal heating power for heating the refrigerator evaporator.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] (1) The present application discloses a refrigerator intelligent control method and system, including: obtaining characteristic data of the frost layer on the surface of the refrigerator evaporator from time TN to time T, and obtaining a predicted refrigeration influence coefficient of the frost layer on the surface of the refrigerator evaporator at time T+N according to a pre-constructed refrigeration influence coefficient regression model; comparing the predicted refrigeration influence coefficient of the frost layer on the surface of the refrigerator evaporator with a preset refrigeration influence standard coefficient threshold to obtain a comparison result; based on the above steps, the present invention determines whether to defrost by judging the influence of the frost layer on the refrigerator evaporator on the refrigeration system, thereby avoiding repeated excessive defrosting and saving electricity.

[0047] (2) The present application discloses a refrigerator intelligent control method and system, including: according to the second comparison result, inputting the predicted refrigeration influence coefficient of the frost layer on the surface of the refrigerator evaporator into a preconfigured optimal heating power machine learning model to obtain the optimal heating power for heating the refrigerator evaporator and the corresponding time required for complete defrosting; based on the above steps, it is beneficial to avoid incomplete defrosting, save electricity and shorten the defrosting time while completely defrosting. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 The present invention provides a flowchart of a refrigerator intelligent control method.

[0049] Figure 2 This is a module diagram of a refrigerator intelligent control system provided by the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and a similar second unit may be referred to as a first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0052] Example 1

[0053] See also Figure 1 As shown, this embodiment discloses a refrigerator intelligent control method, the method comprising:

[0054] Step 1: Obtain characteristic data of the frost layer on the surface of the refrigerator evaporator from time TN to time T, and obtain the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator at time T+N according to the pre-built frost layer influence coefficient regression model, where T and N are positive integers greater than zero;

[0055] It should be noted that: the characteristic data of the frost layer on the surface of the refrigerator evaporator includes the thickness of the frost layer and the density of the frost layer; the thickness of the frost layer and the density of the frost layer are obtained by sensors, and the sensors include but are not limited to infrared sensors, ultrasonic sensors, optical sensors, cameras, etc.;

[0056] In implementation, obtaining the thickness of the frost layer on the surface of the refrigerator evaporator includes:

[0057] Use infrared sensors to obtain the distance of the refrigerator evaporator in the initial state and the distance at time T;

[0058] It should be noted that: the initial state is the thickness of the frost layer on the surface of the refrigerator evaporator when the refrigerator is not in use, and the default value is 0; the infrared sensor is vertically installed above the refrigerator evaporator;

[0059] The distance in the initial state is taken as the first distance, and the distance at time T is taken as the second distance;

[0060] Calculating the difference between the first distance and the second distance, and using the difference between the first distance and the second distance as the thickness of the frost layer on the surface of the refrigerator evaporator;

[0061] Specifically, the generation logic of the frost layer influence coefficient regression model is as follows:

[0062] Acquire a historical frost layer impact sample set, and divide the historical frost layer impact sample set into a frost layer impact training set and a frost layer impact test set, wherein the frost layer impact sample set includes frost layer impact feature data and a corresponding frost layer impact coefficient, and the frost layer impact feature data includes the thickness of the frost layer on the surface of the corresponding refrigerator evaporator at each moment in a time period, the density of the frost layer, and the surface area of ​​the frost layer;

[0063] Constructing a first regression network, taking the frost layer impact feature data in the frost layer impact training set as the input of the first regression network, taking the frost layer impact coefficient in the frost layer impact training set as the output of the first regression network, training the first regression network, and obtaining a frost layer impact coefficient regression network;

[0064] The frost layer influence coefficient regression network is validated using the frost layer influence test set, and the frost layer influence coefficient regression network with an accuracy greater than or equal to the accuracy is output as the frost layer influence coefficient regression model;

[0065] It should be noted that: the surface area of ​​the evaporator is obtained by the technicians in advance and stored in the system database; the first regression network is a specific one of the algorithms such as logistic regression, support vector machine regression, random forest regression, neural network regression, etc.;

[0066] Among them, the logic for obtaining the frost impact coefficient in the historical frost impact sample set is as follows:

[0067] The frost layer on the surface of the refrigerator evaporator is divided equally into R subdivided areas;

[0068] The thickness value, density value and surface area of ​​the frost layer in each subdivided area are obtained; the frost layer influence coefficient is obtained by formula calculation according to the thickness value, density value and surface area of ​​the frost layer in each subdivided area; the calculation formula is: ; In the formula, represents the frost layer influence coefficient, Indicates the thickness of the frost layer in the ith subdivision area. represents the density value of the frost layer in the ith subdivision area, represents the surface area of ​​the frost layer in the i-th subdivision area;

[0069] Step 2: comparing the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator with a preset frost layer influence standard coefficient threshold to obtain a comparison result, wherein the comparison result includes a first comparison result and a second comparison result;

[0070] It should be noted that the preset frost layer influence standard coefficient threshold is obtained through multiple tests and summaries, which will not be elaborated in detail.

[0071] Specifically, the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator is compared with the preset frost layer influence standard coefficient threshold, including:

[0072] If the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator is less than the preset frost layer influence standard coefficient threshold, the refrigerator evaporator is marked as "normal frost layer accumulation", "normal frost layer accumulation" is used as the first comparison result, and T+N+M is set, and the process returns to step 1, where M is a positive integer greater than zero;

[0073] If the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator is greater than or equal to the preset frost layer influence standard coefficient threshold, the refrigerator evaporator is marked as "excessive frost accumulation", and "excessive frost accumulation" is used as the second comparison result;

[0074] It should be noted that: "Normal frost accumulation" means that the frost layer has not reached the critical point for defrosting, and the impact on the refrigeration system is small; "Excessive frost accumulation" means that the frost layer exceeds the critical point for defrosting and intervention is required, otherwise it will affect the refrigeration system;

[0075] Step 3: According to the second comparison result, the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator is input into the preconfigured optimal heating power machine learning model to obtain the optimal heating power for heating the refrigerator evaporator;

[0076] In implementation, the generation logic of the preconfigured optimal heating power machine learning model is as follows:

[0077] Acquire historical refrigerator evaporator defrost training data, and divide the historical refrigerator evaporator defrost training data into a refrigerator evaporator defrost training set and a refrigerator evaporator defrost test set; the historical refrigerator evaporator defrost training data includes a frost layer influence coefficient and its corresponding optimal heating power;

[0078] A second regression network is constructed, the refrigeration influence coefficient in the refrigerator evaporator defrost training set is used as input data of the second regression network, and the optimal heating power in the refrigerator evaporator defrost training set is used as output data of the second regression network, and the second regression network is trained to obtain a heating power regression network;

[0079] The heating power regression network is validated using the refrigerator evaporator defrost test set, and the heating power regression network with a test error threshold less than or equal to the preset test error threshold is output as the preconfigured optimal heating power machine learning model.

[0080] It should be noted that: like the above-mentioned first regression network, the second regression network is specifically one of regression algorithm models such as linear regression, random forest, decision tree, polynomial regression, support vector machine or neural network.

[0081] The optimal heating power in the historical refrigerator evaporator defrosting training data is obtained by genetic algorithm processing, and its specific logic is as follows:

[0082] S31: Initialize the population: randomly generate an original population, wherein the original population includes N individuals, each individual represents a heating power, and N is an integer greater than zero;

[0083] S32: Fitness evaluation: based on each individual, the time required for completely melting the frost layer under each individual is obtained, the time required for completely melting the frost layer and the heating power are input into a pre-constructed fitness function, and the fitness of each individual is calculated;

[0084] In implementation, the time required to completely melt the frost layer is generated by the following logic:

[0085] The frost layer influence coefficient and heating power corresponding to the second comparison result are input into the defrost time regression model to obtain the time required to completely melt the frost layer;

[0086] The generation logic of the defrost time regression model is as follows:

[0087] Obtain historical defrost time training data, and divide the historical defrost time training data into a defrost time training set and a defrost time test set; the historical defrost time training data includes a frost layer influence coefficient, a heating power, and a corresponding time required to completely melt the frost layer;

[0088] A third regression network is constructed, the frost layer influence coefficient and the heating power in the defrost time training set are used as input data of the third regression network, and the time required to completely melt the frost layer is used as output data of the third regression network, and the third regression network is trained to obtain a defrost time regression network;

[0089] The defrost time regression network is validated using the defrost time test set, and the defrost time regression network with an error less than or equal to a preset error threshold is output as the defrost time regression model.

[0090] An example is: assuming that the frost layer influence coefficient is Q, Q>0, and the time J is 6:00, the frost layer is defrosted with a heating power of W; when the time reaches 6:05, Q is displayed as zero, which means that it takes 5 minutes to completely melt the frost layer;

[0091] In genetic algorithms, fitness evaluation is one of the core steps, which is used to determine the fitness of each individual, that is, to determine how well each individual performs in a given problem; the design of the fitness function directly affects the efficiency of the algorithm and the quality of the final solution;

[0092] The calculation formula of the pre-constructed fitness function is: ; Where: represents fitness, is the heating power, The time required to completely melt the frost layer;

[0093] S33: Selection: Use the roulette method to select two individuals with high fitness in the original population as the father and mother;

[0094] It should be understood that the roulette method is a commonly used selection method, which is used in genetic algorithms to select individuals with higher fitness to enter the next generation; it simulates the process of roulette, and each individual obtains a corresponding "roulette" area according to its fitness; the higher the fitness of the individual, the larger the corresponding area, and the higher the probability of being selected;

[0095] S34: Crossover: Perform crossover operation on the father and mother to produce new individuals;

[0096] It should be noted that: the crossover operation on the paternal parent and the maternal parent is implemented based on a crossover operation, and the crossover operation includes but is not limited to one of a single-point crossover, a uniform crossover or a sequential crossover, etc.;

[0097] It should be understood that: in genetic algorithms, crossover is an important genetic operation used to generate a new generation of candidate solutions; the basic idea of ​​crossover is to simulate the sexual reproduction process in biological genetics, in which two parents produce offspring by combining their genetic information; this process helps to introduce diversity in the solution space and may produce new individuals that are more adaptable to the environment;

[0098] S35: mutation: using Gaussian mutation method to perform mutation operation on the new individuals, obtaining M new individuals, combining the M new individuals into a new population, and replacing the original population with the new population, and returning to step S32;

[0099] It should be understood that the Gaussian variation method can achieve fine-tuning of the heating power by adding a small random value that follows the Gaussian distribution to the current heating power. Due to the characteristics of the Gaussian distribution, this variation tends to make small-scale adjustments, which is very suitable for refining and optimizing the heating power that is already close to the optimal solution.

[0100] S36: Repeat the above steps S32 to S35 until the fitness of the individuals in the original population or the new population is greater than or equal to the preset fitness threshold, and output the heating power represented by the corresponding individual as the optimal heating power for heating the refrigerator evaporator;

[0101] Step 4: controlling the refrigerator heater to defrost the refrigerator evaporator according to the optimal heating power;

[0102] An exemplary explanation is: assuming that when the comparison result is the second comparison result, it means that the frost layer of the refrigerator evaporator exceeds the critical point of defrosting and intervention is required, otherwise it will affect the refrigeration system, and then according to the second comparison result, the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator is input into the preconfigured optimal heating power machine learning model to obtain the optimal heating power for heating the refrigerator evaporator; the present invention determines whether to defrost by judging the impact of the frost layer on the refrigerator evaporator on the refrigeration system, thereby avoiding repeated excessive defrosting and saving electricity; and then by determining the optimal heating power and the corresponding time required for complete defrosting, it is beneficial to avoid incomplete defrosting.

[0103] Example 2

[0104] See also Figure 2 As shown, based on the above embodiment 1, this embodiment discloses a refrigerator intelligent control system, the system comprising:

[0105] Information acquisition module 201: used to obtain characteristic data of frost layer on the surface of refrigerator evaporator from time TN to time T, and to obtain predicted frost layer influence coefficient of frost layer on the surface of refrigerator evaporator at time T+N according to a pre-built frost layer influence coefficient regression model, where T and N are positive integers greater than zero;

[0106] Comparison and judgment module 202: used to compare the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator with a preset frost layer influence standard coefficient threshold to obtain a comparison result, wherein the comparison result includes a first comparison result and a second comparison result;

[0107] Data calculation module 203: used for inputting the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator into a preconfigured optimal heating power machine learning model according to the second comparison result, so as to obtain the optimal heating power for heating the refrigerator evaporator;

[0108] The defrost control module 204 is used to control the refrigerator heater to defrost the refrigerator evaporator according to the optimal heating power.

[0109] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0110] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0111] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0112] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0113] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0114] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0115] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0116] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0117] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0118] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A refrigerator intelligent control method, characterized in that: The method comprises: Step 1: Obtain characteristic data of the frost layer on the surface of the refrigerator evaporator from time TN to time T, and obtain the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator at time T+N according to the pre-built frost layer influence coefficient regression model, where T and N are positive integers greater than zero; Step 2: comparing the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator with a preset frost layer influence standard coefficient threshold to obtain a comparison result, wherein the comparison result includes a first comparison result and a second comparison result; Step 3: According to the second comparison result, the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator is input into the preconfigured optimal heating power machine learning model to obtain the optimal heating power for heating the refrigerator evaporator; The generation logic of the preconfigured optimal heating power machine learning model is as follows: Acquire historical refrigerator evaporator defrost training data, and divide the historical refrigerator evaporator defrost training data into a refrigerator evaporator defrost training set and a refrigerator evaporator defrost test set; the historical refrigerator evaporator defrost training data includes a frost layer influence coefficient and its corresponding optimal heating power; A second regression network is constructed, the refrigeration influence coefficient in the refrigerator evaporator defrost training set is used as input data of the second regression network, and the optimal heating power in the refrigerator evaporator defrost training set is used as output data of the second regression network, and the second regression network is trained to obtain a heating power regression network; The heating power regression network is validated using the refrigerator evaporator defrost test set, and the heating power regression network with a test error threshold less than or equal to the preset test error threshold is output as the preconfigured optimal heating power machine learning model. Step 4: Controlling the refrigerator heater to defrost the refrigerator evaporator according to the optimal heating power.

2. A refrigerator intelligent control method according to claim 1, characterized in that: The generation logic of the frost layer influence coefficient regression model is as follows: Acquire a historical frost layer impact sample set, and divide the historical frost layer impact sample set into a frost layer impact training set and a frost layer impact test set, wherein the frost layer impact sample set includes frost layer impact feature data and a corresponding frost layer impact coefficient, and the frost layer impact feature data includes the thickness of the frost layer on the surface of the corresponding refrigerator evaporator at each moment in a time period, the density of the frost layer, and the surface area of ​​the frost layer; Constructing a first regression network, taking the frost layer impact feature data in the frost layer impact training set as the input of the first regression network, taking the frost layer impact coefficient in the frost layer impact training set as the output of the first regression network, training the first regression network, and obtaining a frost layer impact coefficient regression network; The frost influence coefficient regression network is validated using the frost influence test set, and the frost influence coefficient regression network with an accuracy greater than or equal to the output is used as the frost influence coefficient regression model.

3. A refrigerator intelligent control method according to claim 2, characterized in that: The logic for obtaining the frost layer influence coefficient is as follows: The frost layer on the surface of the refrigerator evaporator is divided equally into R subdivided areas; Obtain the thickness value, density value and surface area of ​​the frost layer in each subdivided area; perform formula calculation based on the thickness value, density value and surface area of ​​the frost layer in each subdivided area to obtain the frost layer influence coefficient; The calculation formula is: ; In the formula, represents the frost layer influence coefficient, represents the thickness of the frost layer in the ith subdivision area, represents the density value of the frost layer in the ith subdivision area, Represents the surface area of ​​the frost layer in the i-th subdivision area.

4. A refrigerator intelligent control method according to claim 3, characterized in that: The predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator is compared with the preset frost layer influence standard coefficient threshold, including: If the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator is less than the preset frost layer influence standard coefficient threshold, the refrigerator evaporator is marked as "frost accumulation is normal", "frost accumulation is normal" is used as the first comparison result, and T+N+M is set, and the process returns to step 1, where M is a positive integer greater than zero; If the predicted frost influence coefficient of the frost layer on the surface of the refrigerator evaporator is greater than or equal to the preset frost influence standard coefficient threshold, the refrigerator evaporator is marked as "excessive frost accumulation" and "excessive frost accumulation" is used as the second comparison result.

5. A refrigerator intelligent control method according to claim 4, characterized in that: The generation logic of the optimal heating power in the historical refrigerator evaporator defrosting training data is as follows: S31: Initialize the population: randomly generate an original population, wherein the original population includes N individuals, each individual represents a heating power, and N is an integer greater than zero; S32: Fitness evaluation: based on each individual, the time required for completely melting the frost layer under each individual is obtained, the time required for completely melting the frost layer and the heating power are input into a pre-constructed fitness function, and the fitness of each individual is calculated; S33: Selection: Use the roulette method to select two individuals with high fitness in the original population as the father and mother; S34: Crossover: Perform crossover operation on the father and mother to produce new individuals; S35: mutation: using Gaussian mutation method to perform mutation operation on the new individuals, obtaining M new individuals, combining the M new individuals into a new population, and replacing the original population with the new population, and returning to step S32; S36: Repeat the above steps S32 to S35 until the fitness of the individuals in the original population or the new population is greater than or equal to the preset fitness threshold, and output the heating power represented by the corresponding individual as the optimal heating power for heating the refrigerator evaporator.

6. A refrigerator intelligent control method according to claim 5, characterized in that: The generation logic of the time required to completely melt the frost layer is as follows: The frost layer influence coefficient and heating power corresponding to the second comparison result are input into the defrost time regression model to obtain the time required to completely melt the frost layer; The generation logic of the defrost time regression model is as follows: Obtain historical defrost time training data, and divide the historical defrost time training data into a defrost time training set and a defrost time test set; the historical defrost time training data includes a frost layer influence coefficient, a heating power, and a corresponding time required to completely melt the frost layer; A third regression network is constructed, the frost layer influence coefficient and the heating power in the defrost time training set are used as input data of the third regression network, and the time required to completely melt the frost layer is used as output data of the third regression network, and the third regression network is trained to obtain a defrost time regression network; The defrost time test set is used to verify the defrost time regression network model, and the defrost time regression network with an output less than or equal to the preset error threshold is used as the defrost time regression model.

7. A refrigerator intelligent control method according to claim 6, characterized in that: The generation logic of the fitness function is as follows: The calculation formula of the pre-constructed fitness function is: ; Where: represents fitness, is the heating power, The time required for the frost to completely melt.

8. A refrigerator intelligent control system, implemented based on a refrigerator intelligent control method according to any one of claims 1 to 7, characterized in that: The system comprises: An information acquisition module (201) is used to acquire characteristic data of the frost layer on the surface of the refrigerator evaporator from time TN to time T, and to acquire a predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator at time T+N according to a pre-constructed frost layer influence coefficient regression model, where T and N are positive integers greater than zero; A comparison and judgment module (202): used to compare the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator with a preset frost layer influence standard coefficient threshold to obtain a comparison result, wherein the comparison result includes a first comparison result and a second comparison result; A data calculation module (203): used to input the predicted frost layer influence coefficient of the frost layer on the surface of the refrigerator evaporator into a pre-configured optimal heating power machine learning model according to the second comparison result, so as to obtain the optimal heating power for heating the refrigerator evaporator; The defrosting control module (204) is used to control the refrigerator heater to defrost the refrigerator evaporator according to the optimal heating power for heating the refrigerator evaporator.

Images