A method and system for optimizing the defrosting efficiency of a refrigerator

Abstract

The present invention discloses a method and system for optimizing the defrosting efficiency of a refrigerator, which relates to the technical field of efficiency optimization and comprises the following steps: obtaining historical airflow data and fan speed data of the refrigerator and performing preprocessing; setting a plurality of fan speed gears, and obtaining gas data and frost layer melting data of the plurality of fan speed gears; constructing a defrosting efficiency evaluation model based on machine learning based on the gas data and frost layer melting data of the plurality of fan speed gears; constructing a curve graph of fan speed gear and output based on the output of the defrosting efficiency evaluation model based on machine learning, and performing data analysis on the curve graph to obtain the optimal fan speed gear, thereby solving the problem of low defrosting efficiency of the refrigerator due to the failure to fully consider the influence of complex factors such as airflow, frost accumulation and melting on the defrosting effect.

Description

Technical Field

[0001] The present invention relates to the technical field of efficiency optimization, and more specifically, to a method and system for optimizing the defrosting efficiency of a refrigerator. Background Art

[0002] Refrigerator defrosting technology is widely used in many fields such as home appliances, food storage, supermarket refrigeration, etc. With the global climate change and the improvement of energy-saving and environmental protection awareness, the optimization of refrigerator defrosting efficiency has become an important research topic in the home appliance industry.

[0003] Traditional defrost efficiency optimization usually relies on engineers' experience or is adjusted based on simple rules. It does not fully consider the impact of complex factors such as airflow, frost accumulation and melting on the defrost effect, resulting in low defrost efficiency of refrigerators.

[0004] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method and system for optimizing the defrost efficiency of a refrigerator, so as to solve the problem of low defrost efficiency of the refrigerator caused by not fully considering the influence of complex factors such as airflow, frost accumulation and melting on the defrost effect.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for optimizing the defrost efficiency of a refrigerator comprises the following steps: obtaining historical airflow data and fan speed data of the refrigerator and performing preprocessing; setting a plurality of fan speed gears, and obtaining gas data and frost melting data of the plurality of fan speed gears; constructing a defrost efficiency evaluation model based on machine learning based on the gas data and frost melting data of the plurality of fan speed gears; constructing a curve graph of fan speed gear and output based on the output of the defrost efficiency evaluation model based on machine learning, and performing data analysis on the curve graph to obtain an optimal fan speed gear.

[0008] In a preferred embodiment, several fan speed gears are set, and the gas data and frost melting data of the several fan speed gears are obtained, specifically: the maximum fan speed value M and the minimum fan speed value N in the fan speed data are collected; based on the maximum fan speed value M and the minimum fan speed value N, a number of fan speed gears are divided in the [M, N] interval according to a preset ratio; the gas data and frost melting data of the several fan speed gears are obtained, the gas data including the cold air flow path unobstructed influence coefficient, and the frost melting data including the frost layer influence coefficient.

[0009] In a preferred embodiment, the specific method for obtaining the influence coefficient of the smooth flow of cold air is as follows: a geometric model of the refrigerator is established in CFD software and the length of the gas flow channel inside the refrigerator, the channel width and the internal gas bending angle are obtained, and the geometric model includes but is not limited to the internal structure of the refrigerator, fan layout, pipelines, evaporator and other components; CFD software is used to perform numerical simulation of airflow to obtain the airflow velocity at various positions inside the refrigerator; based on the airflow velocity at various positions inside the refrigerator, the standard deviation of the airflow velocity and the mean of the airflow velocity at all positions are calculated; the ratio of the mean of the airflow velocity at all positions to the standard deviation of the airflow velocity is used as the uniformity coefficient of the cold air flow velocity; a pressure sensor is used to obtain the pressure drop of the airflow in the pipeline, and the pressure loss value and the additional bending pressure loss value of the airflow in the pipeline are calculated; the pressure loss value and the additional bending pressure loss value of the airflow in the pipeline are weightedly summed to obtain the airflow resistance coefficient; the cold air flow velocity uniformity coefficient and the airflow resistance coefficient are input into the cold air flow path smooth influence coefficient calculation formula to obtain the air flow path smooth influence coefficient.

[0010] In a preferred embodiment, the specific method of obtaining the frost layer influence coefficient is as follows: setting a number of monitoring time periods, obtaining the frost layer accumulation and frost layer melting amount at different time points within the several monitoring time periods; calculating the average value and standard deviation of the frost layer accumulation and frost layer melting at different time points within the several monitoring time periods, and calculating the frost layer accumulation coefficient and frost layer melting coefficient based on the average value and standard deviation; respectively inputting the frost layer accumulation coefficient and frost layer melting coefficient into the frost layer influence coefficient formula to obtain the frost layer influence coefficient.

[0011] In a preferred embodiment, a defrost efficiency evaluation model based on machine learning is constructed based on the gas data and frost melting data of the several fan speed gears, specifically: constructing an evaluation model based on machine learning; dividing the gas data and frost melting data of the several fan speed gears into a training set, a test set and a validation set according to a preset ratio, inputting the training set into the evaluation model based on machine learning, initializing the training parameters and training the model; using the test set and the validation set to test and verify the trained model to obtain a trained defrost efficiency evaluation model based on machine learning; inputting the gas data and frost melting data of the several fan speed gears to be evaluated into the trained defrost efficiency evaluation model based on machine learning to obtain the refrigerator defrost efficiency evaluation coefficient.

[0012] In a preferred embodiment, based on the output of the defrost efficiency evaluation model based on machine learning, a curve graph of fan speed gear and output is constructed, and data analysis is performed on the curve graph to obtain the optimal fan speed gear, specifically: a curve graph is constructed with fan speed gear as the x-axis and defrost efficiency evaluation coefficient as the y-axis; based on the curve graph, the defrost efficiency evaluation change rate of each fan speed gear is calculated; the fan speed gears with the defrost efficiency evaluation change rate of 0 are counted to obtain several fan speed gears to be selected; the defrost efficiency evaluation coefficients corresponding to the several fan speed gears to be selected are sorted, and one or several fan speed gears to be selected with the highest defrost efficiency evaluation coefficients are selected as the optimal fan speed gear.

[0013] The technical effects and advantages of the method and system for optimizing the defrosting efficiency of a refrigerator provided by the present invention are as follows:

[0014] 1. The present invention effectively improves the efficiency of the refrigerator defrosting process by combining historical data and machine learning technology. The first step of the method is to obtain the historical airflow data and fan speed data of the refrigerator, and preprocess them to eliminate noise and outliers to ensure the accuracy of the data. Next, several fan speed gears are set, and the corresponding gas flow data and frost melting data are collected. These data are the key to optimizing the defrosting efficiency. By monitoring the airflow and frost state at different fan speeds, the defrosting performance under different working conditions can be deeply understood; after data collection and preprocessing, a defrosting efficiency evaluation model is constructed using a machine learning algorithm. The model can predict the effect of frost melting based on the input fan speed and airflow state, thereby evaluating the defrosting efficiency of different fan speed gears. By plotting the output of the model and the fan speed gear into a curve graph, the defrosting effect at different speeds can be intuitively observed, and the optimal fan speed gear can be further analyzed. This process combines data-driven and algorithm optimization to provide more precise guidance for the defrosting control of the refrigerator. The advantages of this method are its scientificity and efficiency. Through the machine learning model, the impact of various factors on defrosting efficiency can be systematically considered, avoiding the blindness and limitations of traditional empirical adjustments. The optimized fan speed gear can reduce energy consumption and extend equipment life while ensuring the rapid melting of the frost layer, significantly improving the performance and energy efficiency of the refrigerator. In addition, as the amount of data accumulates, the model can be continuously optimized and adjusted to meet the needs of different types of refrigerators, with strong adaptability and long-term effectiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The present invention is a schematic flow chart of a method for optimizing the defrosting efficiency of a refrigerator.

[0016] Figure 2 The schematic diagram is a structural diagram of a system for optimizing the defrosting efficiency of a refrigerator according to the present invention. DETAILED DESCRIPTION

[0017] 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.

[0018] Embodiment 1, Figure 1 A method for optimizing the defrosting efficiency of a refrigerator is provided, comprising the following steps:

[0019] S1, obtaining historical airflow data and fan speed data of the refrigerator and performing preprocessing;

[0020] In this example, the historical airflow data and fan speed data of the refrigerator are obtained and preprocessed, specifically:

[0021] Obtaining and preprocessing the historical airflow data and fan speed data of the freezer is a critical first step. The historical airflow data and fan speed data reflect the performance of the freezer under different working conditions, including the relationship between airflow velocity, flow path, fan speed and defrosting effect. By preprocessing these data, noise and outliers can be removed, data gaps can be filled, and data accuracy and completeness can be ensured, thus providing a reliable foundation for subsequent analysis and model building.

[0022] The preprocessing process includes operations such as data cleaning, standardization, and normalization to eliminate biases caused by different data formats or measurement errors. These operations can improve the consistency and comparability of the data, making it more suitable for training and testing machine learning algorithms. In addition, preprocessing can also reduce the risk of overfitting and improve the generalization ability of the model.

[0023] The advantage of this step is that it provides high-quality data support for the subsequent defrosting efficiency evaluation model. By ensuring the accuracy and consistency of the data, preprocessing can effectively avoid the impact of data quality issues on the training effect of the model, thereby improving the accuracy and reliability of the freezer defrosting efficiency optimization. The preprocessed data can provide a scientific basis for the optimization decision of fan speed and airflow conditions, and ultimately realize the intelligent and efficient defrosting process.

[0024] S2, setting a plurality of fan speed gears, and obtaining gas data and frost melting data of the plurality of fan speed gears;

[0025] In this example, several fan speed gears are set, and the gas data and frost melting data of the several fan speed gears are obtained, specifically:

[0026] Collect the maximum fan speed value M and the minimum fan speed value N in the fan speed data;

[0027] Based on the maximum fan speed value M and the minimum fan speed value N, a plurality of fan speed gears are divided in the interval [M, N] according to a preset ratio;

[0028] The gas data and frost melting data of the plurality of fan speed gears are obtained, wherein the gas data includes the influence coefficient of the cold air flow path patency, and the frost melting data includes the frost layer influence coefficient.

[0029] It should be noted that this method provides an effective decision-making basis for optimizing the defrosting efficiency of the refrigerator by setting multiple fan speed gears and collecting corresponding gas data and frost melting data. Specifically, the maximum speed value M and the minimum speed value N of the refrigerator fan are first collected, and based on these two values, several fan speed gears are divided according to a preset ratio in the [M, N] interval. This ensures that the fan speed is fully covered within a certain range, so as to more accurately evaluate the impact of different speeds on the defrosting effect.

[0030] At each fan speed level, the system collects two types of data: gas data and frost melting data. The gas data includes the cold air flow path smoothness influence coefficient and the gas efficiency coefficient, which reflect the efficiency and resistance of the air flow in the refrigerator; the frost melting data includes the frost influence coefficient, which is used to measure the melting effect of the frost layer at different speeds. By combining these data, a complete performance evaluation can be provided for each fan speed level.

[0031] The advantages of this method are its scientificity and efficiency. By reasonably dividing the gears between the maximum and minimum fan speeds, it can fully cover different working conditions, thereby providing rich data support for subsequent optimization. In addition, collecting and analyzing detailed data on gas flow and frost melting can provide in-depth understanding of the specific impact of various factors on the defrosting effect. Using these data, the defrosting efficiency of different fan speeds can be accurately evaluated, and the optimal speed gear can be selected, thereby improving the defrosting efficiency of the freezer, reducing energy consumption and extending the service life of the equipment. This method can adapt to different types of freezers, and is continuously optimized as data accumulates, with good adaptability and long-term benefits.

[0032] In this example, the specific method of obtaining the influence coefficient of the cold air flow path unobstructed is as follows:

[0033] Establishing a geometric model of the refrigerator in CFD software and obtaining the length and width of the gas flow channel inside the refrigerator and the internal gas bending angle, wherein the geometric model includes but is not limited to components such as the internal structure, fan layout, pipeline, and evaporator of the refrigerator;

[0034] Use CFD software to perform numerical simulation of airflow and obtain the airflow velocity at various locations inside the refrigerator;

[0035] Calculating the standard deviation of the airflow velocity and the mean of the airflow velocity at all positions based on the airflow velocity at each position inside the refrigerator;

[0036] The ratio of the mean of the air flow velocity at all the positions to the standard deviation of the air flow velocity is taken as the cold air flow velocity uniformity coefficient;

[0037] A pressure sensor is used to obtain the pressure drop of the airflow in the pipeline, and the pressure loss value of the airflow in the pipeline and the additional bending pressure loss value are calculated;

[0038] The airflow resistance coefficient is obtained by weighted summing the pressure loss value of the airflow in the pipeline and the additional bending pressure loss value;

[0039] The cold air flow velocity uniformity coefficient and the air flow resistance coefficient are input into the cold air flow path unobstructed influence coefficient calculation formula to obtain the air flow path unobstructed influence coefficient.

[0040] The specific calculation formula of the pressure loss value of the air flow in the pipeline is as follows:

[0041]

[0042] The specific calculation formula of the additional bending pressure loss value is as follows:

[0043]

[0044] The influence coefficient of the smooth flow path of cold air is calculated by the following formula:

[0045]

[0046] Among them, ΔPpipe is the pressure loss value of the cold air flow in the pipeline, f is the friction factor, D is the diameter of the pipe, L is the length of the pipe, ρ is the density of the cold air flow, v is the cold air flow velocity, ΔPbend is the additional bending pressure loss value, Kbend is the local resistance coefficient of the elbow, Kflow is the influence coefficient of the cold air flow path, ν is the uniformity coefficient of the cold air flow velocity, θ is the airflow resistance coefficient, and Lpath is the total length of the airflow path.

[0047] It should be noted that this method accurately obtains the influence coefficient of the cold air flow path of the refrigerator through multi-step analysis and simulation, thereby providing data support for the optimization of defrosting efficiency. First, a geometric model of the refrigerator is established in the CFD (computational fluid dynamics) software, including the internal structure of the refrigerator, fan layout, pipelines, evaporator and other components, to obtain the length, width and airflow bending angle of the gas flow channel inside the refrigerator. These geometric parameters are the basis for evaluating the flow of air. Subsequently, the CFD software is used to perform numerical simulation of the airflow to obtain the airflow velocity at various positions inside the refrigerator.

[0048] By calculating the standard deviation and mean of the airflow velocity at each position and taking the ratio of the two as the cold airflow velocity uniformity coefficient, the uniformity of the airflow inside the refrigerator can be evaluated. In addition, a pressure sensor is used to measure the pressure drop of the airflow in the pipeline, and the pressure loss value in the pipeline and the pressure loss value of the additional curved part are calculated, and the weighted sum is used to obtain the airflow resistance coefficient. Finally, the cold airflow velocity uniformity coefficient and the airflow resistance coefficient are combined to obtain the cold air flow path smoothness influence coefficient.

[0049] The advantage of this method is that it can comprehensively evaluate the patency of the airflow channel of the refrigerator through accurate numerical simulation and sensor data acquisition. By analyzing the uniformity of airflow velocity and airflow resistance, the design and operating conditions of the refrigerator can be optimized, thereby improving defrosting efficiency, reducing energy consumption and extending equipment life. In addition, this method can be adapted to different types of refrigerators and has strong scalability and accuracy.

[0050] In this example, the specific method of obtaining the frost layer influence coefficient is as follows:

[0051] Setting a number of monitoring time periods, and obtaining the frost accumulation amount and the frost melting amount at different time points within the number of monitoring time periods;

[0052] Calculating the average value and standard deviation of the frost accumulation amount and the frost melting amount at different time points within the plurality of monitoring time periods, and calculating the frost accumulation coefficient and the frost melting coefficient based on the average value and the standard deviation;

[0053] The frost layer accumulation coefficient and the frost layer melting coefficient are respectively input into the frost layer influence coefficient formula to obtain the frost layer influence coefficient.

[0054] Frost layer influence coefficient, the specific calculation formula is as follows:

[0055]

[0056] Among them, Kfrost is the frost influence coefficient, Vmelt is the frost melting coefficient, tmelt is the time for frost melting, κ is the adjustment coefficient of frost mass on frost influence coefficient, Vacc is the frost accumulation coefficient, tacc is the time for frost accumulation, M(t) is the frost mass, and Mmax is the maximum frost mass.

[0057] Furthermore, obtaining the frost layer influence coefficient has the following advantages in optimizing the defrosting efficiency of the refrigerator:

[0058] First, several monitoring time periods are set, and the frost accumulation and frost melting in each time period are regularly obtained. These data reflect the changes in the frost layer at different time points. By statistically analyzing these data, the average and standard deviation of the frost accumulation and frost melting in each monitoring time period are calculated, reflecting the stability and volatility of the frost accumulation and melting process.

[0059] Based on these statistical data, the frost accumulation coefficient and frost melting coefficient are calculated, which represent the efficiency and regularity of the frost accumulation and melting processes respectively. These two coefficients are input into the calculation formula of the frost influence coefficient to obtain the final frost influence coefficient, which is used to quantify the impact of frost formation and melting on the defrosting efficiency of the refrigerator.

[0060] The advantage of this method is that through systematic data collection and analysis, it can accurately measure the process of frost accumulation and melting, and quantify the specific impact of frost on defrosting efficiency. By optimizing the frost layer influence coefficient, the defrosting strategy of the refrigerator can be adjusted more effectively, energy waste can be reduced, the defrosting speed can be increased, and the long-term and efficient operation of the refrigerator can be ensured. This method is also highly adaptable and can be optimized and adjusted according to the working conditions and frost conditions of different refrigerators.

[0061] S3, constructing a defrost efficiency evaluation model based on machine learning based on the gas data of the plurality of fan speed gears and the frost layer melting data;

[0062] A defrost efficiency evaluation model based on machine learning is constructed based on the gas data of the several fan speed gears and the frost layer melting data, specifically:

[0063] Build machine learning-based evaluation models;

[0064] The gas data and frost melting data of the plurality of fan speed gears are divided into a training set, a test set and a validation set according to a preset ratio, the training set is input into the evaluation model based on machine learning, the training parameters are initialized and the model is trained;

[0065] The trained model is tested and verified using the test set and validation set to obtain a trained defrosting efficiency evaluation model based on machine learning;

[0066] The gas data and frost layer melting data of several fan speed gears to be evaluated are input into the trained defrost efficiency evaluation model based on machine learning to obtain the refrigerator defrost efficiency evaluation coefficient.

[0067] It should be noted that this method provides a scientific and efficient freezer defrost efficiency optimization solution by constructing a defrost efficiency evaluation model based on machine learning and using the gas data and frost melting data of the fan speed gear. First, the gas data and frost melting data under different fan speed gears are collected, and these data are divided into training set, test set and validation set according to the preset ratio. The training set is used for model training, and the test set and validation set are used to verify and tune the performance of the model. This ensures that the model can effectively learn the complex relationship between fan speed, airflow and frost melting during the training process, thereby improving the prediction accuracy.

[0068] Next, the training set data is input into the evaluation model based on machine learning, the training parameters are initialized and the model is trained. Through training, the model can identify and learn the inherent laws between gas flow, frost melting and fan speed, and optimize the relevant parameters. Subsequently, the trained model is verified using the test set and validation set to ensure that it has good generalization ability and low error, thereby obtaining an accurate defrost efficiency evaluation model.

[0069] The trained evaluation model can input the gas data and frost melting data of the fan speed gear to be evaluated, and output the defrost efficiency evaluation coefficient of the refrigerator. This coefficient can accurately evaluate the defrosting effect of different fan speeds and provide data support for the optimization of the defrost process of the refrigerator.

[0070] The advantage of this method is that it uses machine learning technology to model the relationship between complex airflow, frost melting and fan speed, avoiding the limitations of traditional empirical regulation. Through model training and verification, it can accurately predict the optimal fan speed gear, improve defrosting efficiency, reduce energy consumption and extend equipment life, and has good adaptability and long-term optimization capabilities.

[0071] In this example, the specific calculation formula for the refrigerator defrost efficiency evaluation coefficient is as follows:

[0072]

[0073] Among them, Kv is the refrigerator defrost efficiency evaluation coefficient, Kfrost is the frost layer influence coefficient, Kflow is the cold air flow path smooth influence coefficient, η1 is the preset proportional coefficient of the frost layer influence coefficient, η2 is the cold air flow path smooth influence coefficient, and e is an index.

[0074] It should be noted that the refrigerator defrost efficiency evaluation coefficient has the following advantages in the refrigerator defrost efficiency optimization method:

[0075] Accurately evaluate the defrosting effect: The defrosting efficiency evaluation coefficient can accurately reflect the defrosting effect of the freezer by comprehensively considering multiple factors such as airflow, frost accumulation and melting. Through this coefficient, the impact of different fan speeds, airflow conditions and frost state on the defrosting process can be comprehensively evaluated, thereby effectively guiding the adjustment of the defrosting strategy;

[0076] Optimize defrost cycle and time: Through accurate evaluation of the defrost efficiency of the freezer, the defrost cycle and time can be optimized, thereby avoiding the impact of frequent defrosting operations on the performance of the freezer and keeping the freezer running in the best working condition;

[0077] Improve freezer performance and energy efficiency: Through scientific evaluation of defrost efficiency, the optimal fan speed, airflow status and defrost parameters can be identified, thereby reducing frost formation and accelerating frost melting, ultimately improving the operating efficiency of the freezer, reducing energy consumption, and extending the service life of the equipment.

[0078] S4, based on the output of the defrost efficiency evaluation model based on machine learning, construct a curve graph of fan speed gear and output, and perform data analysis on the curve graph to obtain the optimal fan speed gear.

[0079] In this example, based on the output of the defrost efficiency evaluation model based on machine learning, a curve graph of fan speed gear and output is constructed, and data analysis is performed on the curve graph to obtain the optimal fan speed gear, specifically:

[0080] A curve graph is constructed with the fan speed gear as the x-axis and the defrost efficiency evaluation coefficient as the y-axis;

[0081] Based on the curve graph, calculating the defrost efficiency evaluation change rate of each fan speed gear;

[0082] Counting the fan speed gears with a defrosting efficiency evaluation change rate of 0, and obtaining a plurality of fan speed gears to be selected;

[0083] The defrost efficiency evaluation coefficients corresponding to the plurality of to-be-selected fan speed gears are sorted, and one or more to-be-selected fan speed gears with the highest defrost efficiency evaluation coefficients are taken as the optimal fan speed gear.

[0084] It should be noted that this method accurately constructs the relationship curve between the fan speed gear and the defrost efficiency evaluation coefficient through the output of the defrost efficiency evaluation model based on machine learning, and finds the optimal fan speed gear through data analysis. First, a curve chart of the fan speed gear and the defrost efficiency evaluation coefficient is constructed to intuitively display the impact of each fan speed gear on the defrost effect. Then, by calculating the defrost efficiency evaluation change rate of each fan speed gear, it is possible to identify the gear where the defrost efficiency does not change significantly at a specific fan speed, and then screen out the fan speed gear to be selected.

[0085] The advantages of this method are its scientificity and systematicity. By analyzing the defrosting efficiency under different speed gears in a data-driven way, the blindness of empirical adjustment is avoided, ensuring the maximization of the defrosting efficiency of the refrigerator. The gears with zero change rate are counted, which effectively reduces redundant operations and focuses only on the fan speed that significantly improves efficiency, further improving the accuracy and efficiency of the system. Finally, based on the sorting, the fan speed gear with the highest defrosting efficiency is selected to ensure that the refrigerator can operate in the best working state, which not only improves the defrosting efficiency but also reduces energy consumption. This method has good adaptability and long-term optimization capabilities, and can provide precise guidance for the operation of refrigerators.

[0086] Embodiment 2, Figure 2 A system for optimizing the defrosting efficiency of a refrigerator is provided, which is characterized by comprising a data acquisition module, a gear setting module, a model building module, and a defrosting optimization module:

[0087] A data acquisition module is used to acquire historical airflow data and fan speed data of the refrigerator and perform preprocessing;

[0088] A gear setting module, used to set a plurality of fan speed gears, and obtain gas data and frost melting data of the plurality of fan speed gears;

[0089] A model building module, used to build a defrost efficiency evaluation model based on machine learning based on the gas data and frost layer melting data of the plurality of fan speed gears;

[0090] The defrost optimization module is used to construct a curve graph of fan speed gear and output based on the output of the defrost efficiency evaluation model based on machine learning, and perform data analysis on the curve graph to obtain the optimal fan speed gear.

[0091] 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 in the formula are set by technicians in this field according to actual conditions.

[0092] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0093] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein 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 this application.

[0094] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0095] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0096] 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 method for optimizing the defrosting efficiency of a refrigerator, characterized in that: The following steps are involved: Obtain historical airflow data and fan speed data of the refrigerator and perform preprocessing; Setting a plurality of fan speed gears, and acquiring gas data and frost layer melting data of the plurality of fan speed gears; Constructing a defrost efficiency evaluation model based on machine learning based on the gas data of the plurality of fan speed gears and the frost layer melting data; Based on the output of the defrost efficiency evaluation model based on machine learning, a curve graph of fan speed gear and output is constructed, and data analysis is performed on the curve graph to obtain the optimal fan speed gear.

2. The method for optimizing the defrosting efficiency of a refrigerator according to claim 1, characterized in that: The step of setting a plurality of fan speed gears and obtaining the gas data and frost melting data of the plurality of fan speed gears is specifically as follows: Collect the maximum fan speed value M and the minimum fan speed value N in the fan speed data; Based on the maximum fan speed value M and the minimum fan speed value N, a plurality of fan speed gears are divided in the interval [M, N] according to a preset ratio; The gas data and frost melting data of the plurality of fan speed gears are obtained, wherein the gas data includes the influence coefficient of the cold air flow path patency, and the frost melting data includes the frost layer influence coefficient.

3. The method for optimizing the defrosting efficiency of a refrigerator according to claim 2, characterized in that: The specific method for obtaining the influence coefficient of the cold air flow path smoothness is as follows: Establishing a geometric model of the refrigerator in CFD software and obtaining the length and width of the gas flow channel inside the refrigerator and the internal gas bending angle, wherein the geometric model includes but is not limited to components such as the internal structure, fan layout, pipeline, and evaporator of the refrigerator; Use CFD software to perform numerical simulation of airflow and obtain the airflow velocity at various locations inside the refrigerator; Calculating the standard deviation of the airflow velocity and the mean of the airflow velocity at all positions based on the airflow velocity at each position inside the refrigerator; The ratio of the mean of the air flow velocity at all the positions to the standard deviation of the air flow velocity is taken as the cold air flow velocity uniformity coefficient; A pressure sensor is used to obtain the pressure drop of the airflow in the pipeline, and the pressure loss value of the airflow in the pipeline and the additional bending pressure loss value are calculated; The airflow resistance coefficient is obtained by weighted summing the pressure loss value of the airflow in the pipeline and the additional bending pressure loss value; The cold air flow velocity uniformity coefficient and the air flow resistance coefficient are input into the cold air flow path unobstructed influence coefficient calculation formula to obtain the air flow path unobstructed influence coefficient.

4. The method for optimizing the defrosting efficiency of a refrigerator according to claim 3, characterized in that: The specific method of obtaining the frost layer influence coefficient is as follows: Setting a number of monitoring time periods, and obtaining the frost accumulation amount and the frost melting amount at different time points within the number of monitoring time periods; Calculating the average value and standard deviation of the frost accumulation amount and the frost melting amount at different time points within the plurality of monitoring time periods, and calculating the frost accumulation coefficient and the frost melting coefficient based on the average value and the standard deviation; The frost layer accumulation coefficient and the frost layer melting coefficient are respectively input into the frost layer influence coefficient formula to obtain the frost layer influence coefficient.

5. The method for optimizing the defrosting efficiency of a refrigerator according to claim 4, characterized in that: A defrost efficiency evaluation model based on machine learning is constructed based on the gas data of the several fan speed gears and the frost layer melting data, specifically: Build machine learning-based evaluation models; The gas data and frost melting data of the plurality of fan speed gears are divided into a training set, a test set and a validation set according to a preset ratio, the training set is input into the evaluation model based on machine learning, the training parameters are initialized and the model is trained; The trained model is tested and verified using the test set and validation set to obtain a trained defrosting efficiency evaluation model based on machine learning; The gas data and frost layer melting data of several fan speed gears to be evaluated are input into the trained defrost efficiency evaluation model based on machine learning to obtain the refrigerator defrost efficiency evaluation coefficient.

6. The method for optimizing the defrosting efficiency of a refrigerator according to claim 5, characterized in that: Based on the output of the defrost efficiency evaluation model based on machine learning, a curve graph of fan speed gear and output is constructed, and data analysis is performed on the curve graph to obtain the optimal fan speed gear, specifically: A curve graph is constructed with the fan speed gear as the x-axis and the defrost efficiency evaluation coefficient as the y-axis; Based on the curve graph, calculating the defrost efficiency evaluation change rate of each fan speed gear; Counting the fan speed gears with a defrosting efficiency evaluation change rate of 0, and obtaining a plurality of fan speed gears to be selected; The defrost efficiency evaluation coefficients corresponding to the plurality of to-be-selected fan speed gears are sorted, and one or more to-be-selected fan speed gears with the highest defrost efficiency evaluation coefficients are taken as the optimal fan speed gear.

7. The method for optimizing the defrosting efficiency of a refrigerator according to claim 6, characterized in that: The cold air flow path smoothness influence coefficient, the specific calculation formula is as follows: The specific calculation formula of the pressure loss value of the air flow in the pipeline is as follows: The specific calculation formula of the additional bending pressure loss value is as follows: Among them, ΔPpipe is the pressure loss value of the cold air flow in the pipeline, f is the friction factor, D is the diameter of the pipe, L is the length of the pipe, ρ is the density of the cold air flow, v is the cold air flow velocity, ΔPbend is the additional bending pressure loss value, Kbend is the local resistance coefficient of the elbow, Kflow is the influence coefficient of the cold air flow path, ν is the uniformity coefficient of the cold air flow velocity, θ is the airflow resistance coefficient, and Lpath is the total length of the airflow path.

8. The method for optimizing the defrosting efficiency of a refrigerator according to claim 7, characterized in that: The specific calculation formula of the frost layer influence coefficient is as follows: Among them, Kfrost is the frost influence coefficient, Vmelt is the frost melting coefficient, tmelt is the frost melting time, κ is the adjustment coefficient of frost mass on frost influence coefficient, Vacc is the frost accumulation coefficient, tacc is the frost accumulation time, M(t) is the frost mass, and Mmax is the maximum frost mass.

9. The method for optimizing the defrosting efficiency of a refrigerator according to claim 8, characterized in that: The specific calculation formula of the refrigerator defrosting efficiency evaluation coefficient is as follows: Among them, Kv is the refrigerator defrost efficiency evaluation coefficient, Kfrost is the frost layer influence coefficient, Kflow is the cold air flow path smooth influence coefficient, η1 is the preset proportional coefficient of the frost layer influence coefficient, η2 is the cold air flow path smooth influence coefficient, and e is an index.

10. A system using a method for optimizing the defrosting efficiency of a refrigerator as claimed in any one of claims 1 to 9, characterized in that: Including data acquisition module, gear setting module, model building module, defrost optimization module: A data acquisition module is used to acquire historical airflow data and fan speed data of the refrigerator and perform preprocessing; A gear setting module, used to set a plurality of fan speed gears, and obtain gas data and frost melting data of the plurality of fan speed gears; A model building module, used to build a defrost efficiency evaluation model based on machine learning based on the gas data and frost layer melting data of the plurality of fan speed gears; The defrost optimization module is used to construct a curve graph of fan speed gear and output based on the output of the defrost efficiency evaluation model based on machine learning, and perform data analysis on the curve graph to obtain the optimal fan speed gear.

Images