Intelligent refrigerator energy-saving control method, system, equipment, medium and product

Abstract

The invention is suitable for the technical field of refrigerators, and provides an intelligent refrigerator energy-saving control method, system, device, medium and product, and the intelligent refrigerator energy-saving control method comprises the steps that thermal imaging data of food materials in a refrigerator and user behavior data are collected in real time, data preprocessing and feature processing are conducted on the thermal imaging data of the food materials and the user behavior data, and a sensing data stream is generated; a refrigerator three-dimensional thermodynamic twinborn model is constructed, and cooling capacity demand distribution is obtained in combination with a quantum annealing algorithm; based on the sensing data flow and the cooling capacity demand distribution, a cooling capacity prediction demand is obtained, and a multi-temperature-zone refrigeration power distribution scheme is generated; on the basis of the cooling capacity prediction demand, cooling capacity directional transmission and dynamic refrigerating capacity distribution are conducted through the phase change energy storage unit, the demand change of a user can be rapidly responded, the refrigerator can better keep the freshness of food materials, meanwhile, the refrigerating strategy is intelligently adjusted, unnecessary energy consumption is avoided, and therefore the energy efficiency is improved.

Description

Technical Field

[0001] This application belongs to the technical field of refrigerators, and particularly relates to an intelligent refrigerator energy-saving control method, system, device, medium, and product. Background Art

[0002] As an essential electrical appliance in modern families, the energy consumption of refrigerators accounts for 15%-20% of the total household electricity consumption. Energy-saving control technology has always been the focus of industry research. With the popularization of multi-temperature zone refrigerators, how to reduce energy consumption while ensuring the freshness preservation effect of food ingredients has become the core issue of technological research.

[0003] The existing refrigerator energy-saving control technology mainly relies on the PID control algorithm fed back by temperature sensors and combines user behavior data for simple frequency conversion optimization. However, the accuracy of traditional temperature and humidity sensors is relatively low, resulting in large fluctuations in temperature control, increasing the start-stop frequency of the compressor. In addition, the frequency conversion optimization of the refrigerator usually adjusts the compressor speed through frequency conversion technology to achieve precise temperature control, but its control logic is still based on fixed temperature thresholds, and the start-stop logic of the compressor is simple, lacking adaptability to environmental temperature changes, leading to unreasonable cold quantity distribution and significant energy consumption waste.

[0004] Therefore, there is an urgent need for a new control scheme that integrates high-precision perception and efficient energy storage to reduce the energy consumption of refrigerators. Summary of the Invention

[0005] The embodiments of this application provide an intelligent refrigerator energy-saving control method, system, device, medium, and product, which can solve one of the above-mentioned existing technical problems.

[0006] In a first aspect, the embodiments of this application provide an intelligent refrigerator energy-saving control method, including:

[0007] Real-time collect the thermal imaging data of food ingredients in the refrigerator and user behavior data, perform data preprocessing and feature processing on the thermal imaging data of food ingredients and the user behavior data, and generate a perception data stream;

[0008] Construct a three-dimensional thermodynamic twin model of the refrigerator, and obtain the cold quantity demand distribution in combination with the quantum annealing algorithm;

[0009] Based on the perception data stream and the cold quantity demand distribution, obtain the predicted cold quantity demand, and generate a multi-temperature zone refrigeration power distribution scheme;

[0010] Based on the predicted cold quantity demand, perform directional cold quantity transmission through a phase change energy storage unit to dynamically distribute the refrigeration quantity.

[0011] Further, the real-time collection of the thermal imaging data of food ingredients in the refrigerator and user behavior data includes:

[0012] Deploy non-contact infrared thermal imaging sensors at the top of each temperature zone in the refrigerator to generate real-time thermal radiation maps of the food surface and obtain food thermal imaging data;

[0013] Deploy a millimeter-wave biometric radar in the refrigerator to detect the hand movement trajectory of the user and obtain refrigerator door opening and closing events.

[0014] Further, the data preprocessing and feature processing of the food thermal imaging data and the user behavior data include:

[0015] Adopt a timestamp synchronization algorithm to align the food thermal imaging data, the hand movement trajectory, and the refrigerator door opening and closing events;

[0016] Based on the food thermal imaging data, calculate the equivalent thermal resistance of the food in each temperature zone. The specific calculation formula of the equivalent thermal resistance is:

[0017]

[0018] Among them, Q conv represents the convective heat transfer quantity, Q conv =h·A·ΔT, where h represents the convective heat transfer coefficient, A represents the surface area of the food in the temperature zone, and ΔT represents the temperature difference between the food surface temperature and the temperature zone temperature;

[0019] Based on the hand movement trajectory and the refrigerator door opening and closing events, calculate the user behavior entropy of each temperature zone. The specific calculation formula of the user behavior entropy is:

[0020] H action =-∑p(x i )logp(x i );

[0021] Among them, x i represents the frequency and duration distribution of access actions.

[0022] Further, the construction of the three-dimensional thermodynamic twin model of the refrigerator and the acquisition of the cooling demand distribution by combining the quantum annealing algorithm include:

[0023] Adopt an unstructured tetrahedral mesh to locally encrypt the dense area of the food in the refrigerator and generate the refrigerator mesh structure;

[0024] When the change in the food position is detected, trigger the network reconstruction mechanism to dynamically update the refrigerator mesh structure;

[0025] Discretize each grid unit in the refrigerator mesh structure into a control volume, construct a cooling demand distribution equation through the Hamiltonian, and use the quantum annealing algorithm to solve the cooling demand distribution equation to obtain the cooling demand distribution.

[0026] Further, the construction of the three-dimensional thermodynamic twin model of the refrigerator includes multi-physical field coupling construction and dynamic loading of boundary conditions. The multi-physical field coupling construction is the coupling construction of the thermal-fluid field inside the refrigerator, and the dynamic loading of boundary conditions includes environmental interaction and the coupling construction of the compressor-condenser inside the refrigerator.

[0027] Further, obtaining the predicted cooling demand based on the sensed data stream and the cooling demand distribution and generating a multi-temperature zone refrigeration power allocation scheme includes:

[0028] Based on the LSTM prediction model, using the user behavior entropy of the sensed data stream, the cooling demand distribution, and the environmental temperature change rate as input features, and outputting the predicted cooling demand within a preset time;

[0029] Based on the pre-trained refrigeration control model, generating a multi-temperature zone refrigeration power allocation scheme through the predicted cooling demand.

[0030] Further, based on the predicted cooling demand, performing directional transmission of cooling through the phase change energy storage unit and dynamically allocating the cooling capacity, including:

[0031] If it is detected that the actual cooling capacity is greater than the predicted cooling demand, then based on the cooling transmission mechanism, the redundant cooling capacity is transmitted to the phase change energy storage unit;

[0032] When the environmental temperature is lower than 15°C, the compressor enters the low-power mode and the phase change energy storage unit is started for cooling storage;

[0033] When the refrigerator suddenly encounters a high-temperature load, the phase change energy storage unit is used for cooling release.

[0034] Further, the phase change energy storage unit includes a primary energy storage unit and a secondary energy storage unit. The primary energy storage unit is used to respond to the sudden cooling demand of the refrigerator, and the secondary energy storage unit is used to balance the regular cooling demand of the refrigerator.

[0035] Further, when the refrigerator suddenly encounters a high-temperature load, then performing cooling release through the phase change energy storage unit includes:

[0036] According to the sudden cooling demand required when the refrigerator suddenly encounters a high-temperature load, dynamically allocating the release ratio of the primary energy storage unit and the secondary energy storage unit;

[0037] For the release ratio of the primary energy storage unit, its specific calculation formula is as follows:

[0038]

[0039] Among them, Q required represents the sudden cooling demand, ΔT represents the temperature difference between the surface temperature of the food ingredient and the temperature of the temperature zone.

[0040] In a second aspect, an embodiment of the present application provides an energy-saving control system for an intelligent refrigerator, including:

[0041] A first processing module: configured to collect real-time thermal imaging data and user behavior data of food ingredients in the refrigerator, perform data preprocessing and feature processing on the thermal imaging data of the food ingredients and the user behavior data, and generate a perception data stream;

[0042] A second processing module: configured to construct a three-dimensional thermodynamic twin model of the refrigerator, and obtain a cold quantity demand distribution by combining a quantum annealing algorithm;

[0043] A third processing module: configured to obtain a predicted cold quantity demand based on the perception data stream and the cold quantity demand distribution, and generate a multi-temperature zone refrigeration power allocation scheme;

[0044] A fourth processing module: configured to perform directional cold quantity transmission through a phase change energy storage unit based on the predicted cold quantity demand, and dynamically allocate the refrigeration quantity.

[0045] In a third aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned intelligent refrigerator energy-saving control method is implemented.

[0046] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, including a computer program stored in the computer-readable storage medium. When the computer program is executed by a processor, the above-mentioned intelligent refrigerator energy-saving control method is implemented.

[0047] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the above-mentioned intelligent refrigerator energy-saving control method is implemented.

[0048] The beneficial effects of the embodiments of the present application compared with the prior art are:

[0049] The present application discloses an intelligent refrigerator energy-saving control method. By collecting the thermal imaging data of the food materials in the refrigerator and the user behavior data in real time, it can more accurately understand the temperature distribution inside the refrigerator, the storage state of the food materials, and the user's usage habits, which helps the refrigerator adjust the refrigeration strategy more intelligently, avoid unnecessary energy consumption, and thus improve energy efficiency. In addition, by constructing a three-dimensional thermodynamic twin model of the refrigerator, combining with the quantum annealing algorithm to obtain the cold quantity demand distribution, and at the same time generating a multi-temperature zone refrigeration power allocation scheme based on the sensed data stream and the cold quantity demand distribution, the refrigerator can more accurately predict and meet the cold quantity demands of different temperature zones, ensure that each temperature zone can obtain just the right amount of refrigeration, and thus improve the refrigeration efficiency. In addition, through the phase change energy storage unit for directional cold quantity transmission and dynamic cold quantity distribution, the refrigerator can respond more quickly to the changes in user needs, enable the refrigerator to better maintain the freshness of the food materials, reduce the waiting time for the user for the refrigerator to return to the set temperature, significantly reduce the energy consumption of the refrigerator, and help reduce carbon emissions and energy waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0051] Figure 1 It is a schematic flowchart of an intelligent refrigerator energy-saving control method provided by an embodiment of the present invention;

[0052] Figure 2 It is a schematic structural diagram of an intelligent refrigerator energy-saving control system provided by an embodiment of the present invention;

[0053] Figure 3 It is a schematic structural diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, the detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0055] It should be understood that, as used in the specification of this application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0056] It should also be understood that the term "and / or" as used in the specification of this application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0057] As used in the specification of this application and the appended claims, the term "if" can be interpreted, depending on the context, as "when", "once", "in response to determining", or "in response to detecting". Similarly, the phrase "if determined" or "if [the described condition or event] is detected" can be interpreted, depending on the context, as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]".

[0058] In addition, in the description of the specification of this application and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0059] Reference to "one embodiment" or "some embodiments" or the like described in the specification of this application means that a specific feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0060] Please refer to Figure 1 As shown, the present invention is an intelligent refrigerator energy-saving control method, including the following steps:

[0061] S100. Real-time collect the thermal imaging data of the food materials in the refrigerator and the user behavior data, perform data preprocessing and feature processing on the thermal imaging data of the food materials and the user behavior data, and generate a perception data stream;

[0062] In this embodiment, by collecting the thermal imaging data of the ingredients in the refrigerator and the user behavior data in real time, it is possible to more accurately understand the temperature distribution inside the refrigerator, the storage status of the ingredients, and the user's usage habits, which helps the refrigerator to adjust the refrigeration strategy more intelligently, avoid unnecessary energy consumption, and thus improve energy efficiency.

[0063] In some of these embodiments, the real-time collection of the thermal imaging data of the ingredients in the refrigerator and the user behavior data includes:

[0064] Deploy non-contact infrared thermal imaging sensors at the top of each temperature zone in the refrigerator to generate the thermal radiation map of the ingredient surface in real time and obtain the thermal imaging data of the ingredients;

[0065] Deploy a millimeter-wave bio-radar in the refrigerator to detect the hand movement trajectory of the user and obtain the refrigerator door opening and closing events.

[0066] In this embodiment, non-contact infrared thermal imaging sensors are deployed at the top of each temperature zone in the refrigerator and captured at a sampling rate of 5 frames per second, and then the thermal radiation map of the ingredient surface is generated to obtain the thermal imaging data of the ingredients. Among them, the non-contact infrared thermal imaging sensor is a graphene-based sensor, and the graphene-based sensor uses graphene as a thermoelectric signal amplifier, and can thus detect the temperature change inside the refrigerator and has high sensitivity.

[0067] In this embodiment, a millimeter-wave bio-radar array is integrated on the refrigerator door body. Specifically, the millimeter-wave radar is a radar operating in the millimeter-wave frequency band, usually with a frequency between 30 GHz and 300 GHz and a wavelength between 1 and 10 millimeters, and thus has characteristics such as high resolution and strong penetrability. By embedding it in the refrigerator door body frame and aligning its horizontal detection direction with the user's standing direction, it can identify behaviors such as the user approaching, staying, and turning, and at the same time identify the hand movement trajectory of the user. Specifically, when it is detected that the hand approaches the refrigerator door body (distance ≤ 0.5 m) and the speed drops below 0.3 m / s, it is determined as the access intention, and the cold quantity pre-distribution mechanism is triggered. In addition, the above-mentioned radars are installed on the top, left and right side walls of each temperature zone in the refrigerator to form a cross-detection network for monitoring the access operations of the user inside the refrigerator. At the same time, the opening and closing state of the refrigerator door is sensed through the millimeter-wave bio-radar, and then the refrigerator door opening and closing events are generated.

[0068] In some of these embodiments, the data preprocessing and feature processing of the thermal imaging data of the ingredients and the user behavior data include:

[0069] Adopt a timestamp synchronization algorithm to align the thermal imaging data of the ingredients, the hand movement trajectory, and the refrigerator door opening and closing events;

[0070] Based on the thermal imaging data of the ingredients, calculate the equivalent thermal resistance of the ingredients in each temperature zone. The specific calculation formula of the equivalent thermal resistance is:

[0071]

[0072] Among them, Q conv represents the convective heat transfer amount, and Q conv = h·A·ΔT, where h represents the convective heat transfer coefficient, A represents the surface area of the food in the temperature zone, and ΔT represents the temperature difference between the surface temperature of the food and the temperature of the temperature zone;

[0073] Based on the hand movement trajectory and the refrigerator door opening / closing event, calculate the user behavior entropy of each temperature zone. The specific calculation formula of the user behavior entropy is:

[0074] H action = -∑p(x i ) log p(x i );

[0075] Among them, x i represents the frequency and duration distribution of the access actions.

[0076] In this embodiment, the preprocessing and feature processing operations of the food thermal imaging data and the user behavior data are completed on the embedded GPU, specifically including data denoising, timestamp alignment, and feature extraction, to generate a structured perception data stream for subsequent energy-saving control of the refrigerator. By performing data processing on the edge computing node of the embedded GPU, the cloud load can be reduced and the real-time requirement can be met.

[0077] In this embodiment, the food thermal imaging data, the hand movement trajectory, and the refrigerator door opening / closing event are aligned to ensure the accurate association between the corresponding thermodynamic data of the refrigerator and the user behavior.

[0078] In this embodiment, the equivalent thermal resistance of the food is extracted from the food thermal imaging data. Specifically, where h is the convective heat transfer coefficient and A is the surface area of the food. It can be seen that the equivalent thermal resistance of the food in each temperature zone depends on the convective heat transfer coefficient and the surface area of the food, and the convective heat transfer coefficient represents the heat transferred in the convective manner and is used to reflect the cold air flow intensity in the refrigerator.

[0079] In some embodiments, multi-spectral vision sensors are also deployed in each temperature zone. A multi-spectral imaging module is integrated through multiple multi-spectral vision sensors. The multi-spectral vision sensors collect the reflection spectra of the food surface to generate an imaging result of the food. The surface area of the food is further calculated through the imaging result of the food. Specifically, the multi-spectral vision sensors collect the reflection spectral data of the food surface at different wavelengths. Based on the collected reflection spectral data, a multi-spectral imaging result of the food is generated. It can be understood that the multi-spectral imaging result contains detailed texture, color, and structure information of the food surface. By preprocessing the generated multi-spectral imaging result, including denoising, enhancing contrast, etc., the accuracy of subsequent processing is improved. At the same time, features of the food surface, such as edges and contours, are extracted from the preprocessed image. Image processing algorithms, such as edge detection and contour tracking, are used to accurately identify the surface shape of the food. According to the extracted features, the surface area of the food is calculated using geometric measurement or image analysis techniques. Further, for foods with regular shapes, geometric formulas are directly applied for calculation; for foods with irregular shapes, methods such as image segmentation and grid division are used for approximate calculation.

[0080] In this embodiment, the user behavior entropy represents the randomness of the user's access actions, and is specifically measured by the access probability of the user within a historical time period. It can be understood that p(x i ) represents the access probability of the user within a historical time period, and the historical time period is set by the developer according to specific business requirements. In a preferred embodiment, it is specifically the access probability per hour within the past week.

[0081] S200. Construct a three-dimensional thermodynamic twin model of the refrigerator and obtain the cold quantity demand distribution by combining with the quantum annealing algorithm;

[0082] In this embodiment, a three-dimensional thermodynamic twin model of the refrigerator is constructed, and the cold quantity demand distribution is obtained by combining with the quantum annealing algorithm. At the same time, a multi-temperature zone refrigeration power allocation scheme is generated based on the perception data stream and the cold quantity demand distribution, enabling the refrigerator to more accurately predict and meet the cold quantity demands of different temperature zones, ensuring that each temperature zone can obtain just the right amount of refrigeration, thereby improving the refrigeration efficiency.

[0083] In some of these embodiments, the above step S200 includes:

[0084] Adopt unstructured tetrahedral meshes to locally encrypt the dense area of the food in the refrigerator to generate a refrigerator mesh structure;

[0085] When the change in the food position is detected, trigger the network reconstruction mechanism to dynamically update the refrigerator mesh structure;

[0086] Discretize each grid cell in the refrigerator grid structure into a control volume, construct a cooling demand distribution equation through the Hamiltonian, and use the quantum annealing algorithm to solve the cooling demand distribution equation to obtain the cooling demand distribution.

[0087] In this embodiment, a deep technical coupling is formed between the three-dimensional thermodynamic twin model and the quantum annealing algorithm through data-driven optimization and physical-computational closed-loop feedback, improving the energy efficiency, accuracy, and reliability of the refrigerator. It can be understood that the three-dimensional thermodynamic twin model is used to simulate the temperature distribution and heat flow inside the refrigerator, while the quantum annealing algorithm is used to optimize the cooling distribution. Specifically, in the three-dimensional thermodynamic twin model, the refrigerator space is meshed to generate a refrigerator grid structure, and at the same time, the cooling distribution problem in the three-dimensional thermodynamic twin model is mapped to the Ising model and solved using the quantum annealing algorithm.

[0088] In this embodiment, according to the geometric dimensions of the refrigerator, determine the three-dimensional range of its internal space, set the size of the basic grid unit, and use unstructured tetrahedral meshing technology to divide the internal space of the refrigerator into multiple grid cells. Identify the ingredient-dense areas in each temperature zone inside the refrigerator through multi-spectral vision sensors deployed inside the refrigerator. In the ingredient-dense areas, reduce the size of the grid cells and perform local refinement to increase the grid density and calculation accuracy in the ingredient-dense areas. Combine the divided grid cells to form the grid structure inside the refrigerator and save the data of the grid structure, including the vertex coordinates, face information, etc. of each grid cell.

[0089] In this embodiment, the ingredients inside the refrigerator are monitored in real time. When a significant change in the ingredient position is detected, trigger the network reconstruction mechanism. According to the information on the change in the ingredient position, determine the grid area that needs to be re-divided, extract the grid cells in the grid area that needs to be re-divided, and prepare for reconstruction. Specifically, in the affected area, re-divide the grid cells according to the new ingredient position distribution. In the ingredient-dense areas, continue to use local refinement to ensure the fineness and calculation accuracy of the grid structure, while keeping the grid structure in the unaffected area unchanged to reduce the calculation amount and improve the reconstruction efficiency. Combine the reconstructed grid cells with the grid structure in the unaffected area to form a new refrigerator grid structure, and at the same time update the data of the grid structure, including the vertex coordinates, face information, etc. of each grid cell, to ensure that the new grid structure can accurately reflect the distribution of the ingredients inside the refrigerator.

[0090] In this embodiment, each grid cell in the refrigerator grid structure is discretized into a control volume, and a cooling demand distribution equation is constructed through the Hamiltonian. Specifically, the state of each control volume is represented as σ ∈ {-1, +1}, where -1 indicates that the current grid cell does not require refrigeration, and +1 indicates that the current grid cell urgently requires refrigeration. The constructed cooling demand distribution equation is specifically as follows: where N represents the number of control volumes, and h i represents the cooling demand intensity of the i-th control volume itself, which is usually determined by the temperature deviation, and J i,j represents the heat coupling intensity between the i-th and j-th control volumes, which is usually related to the thermal conductivity and the distance between the two control volumes.

[0091] In this embodiment, the quantum annealing algorithm is used to solve the above cooling demand distribution equation, minimize H, and then balance the local cooling demand and the global energy consumption, and finally output the optimal By the cooling demand of each grid unit in the refrigerator can be obtained, and a cooling demand distribution can be generated.

[0092] In some embodiments, the construction of the three-dimensional thermodynamic twin model of the refrigerator includes the construction of multi-physical field coupling and the dynamic loading of boundary conditions. The construction of multi-physical field coupling is the coupling construction of the thermal-fluid field in the refrigerator, and the dynamic loading of boundary conditions includes the coupling construction of environmental interaction and the compressor-condenser in the refrigerator.

[0093] In this embodiment, through the coupling construction of the thermal-fluid field, the temperature distribution, air flow and heat transfer process inside the refrigerator can be more accurately simulated. The dynamic loading of boundary conditions takes into account the environmental interaction and the real-time working conditions of key components inside the refrigerator, such as compressors and condensers, so that the three-dimensional thermodynamic twin model of the refrigerator can more realistically reflect the performance of the refrigerator in actual use.

[0094] S300. Obtain the predicted cooling demand based on the sensed data stream and the cooling demand distribution, and generate a multi-temperature zone refrigeration power distribution scheme;

[0095] In this embodiment, by introducing the LSTM prediction model, key features such as the user behavior entropy, cooling demand distribution, and environmental temperature change rate in the sensed data stream are fully utilized. As a result, the finally generated predicted cooling demand can comprehensively reflect the user's usage habits, the refrigeration demand of the refrigerator, and the changes in the external environment. For the distribution of refrigeration power, based on the pre-trained refrigeration control model, a multi-temperature zone refrigeration power distribution scheme is generated according to the predicted cooling demand, so as to ensure that each temperature zone obtains an appropriate amount of refrigeration power to meet different refrigeration demands. Further, by optimizing the refrigeration power distribution, over-energy consumption of the refrigeration system and local overcooling or overheating phenomena can be avoided, and the energy efficiency ratio and refrigeration effect of the refrigerator can be improved.

[0096] In some embodiments, the above step S300 includes:

[0097] Based on the LSTM prediction model, use the user behavior entropy of the sensed data stream, the cooling demand distribution, and the environmental temperature change rate as input features, and output the predicted cooling demand within a preset time;

[0098] Based on the pre-trained refrigeration control model, a multi-temperature zone refrigeration power distribution scheme is generated through the predicted cooling demand.

[0099] In this embodiment, an LSTM prediction model is trained based on historical data, where the input data includes user behavior entropy, cooling demand distribution, and environmental temperature change rate. The user behavior entropy and cooling demand distribution are solved through steps S100 and S200. For the environmental temperature change rate, its calculation formula is specifically where t 0 represents the preset time.

[0100] Specifically, when obtaining the predicted cooling demand within the next 30 minutes, the user behavior entropy, cooling demand distribution, and environmental temperature change rate in the 30 minutes before the current moment are input into the LSTM prediction model. The LSTM prediction model outputs the baseline Q base (t) of the cooling demand in the next 30 minutes. For the above baseline of the cooling demand, adjustment prediction is performed according to the cooling demand distribution to generate the final cooling demand curve. The calculation formula for adjustment prediction according to the cooling demand distribution is specifically: In some embodiments, curve fitting is performed on the generated cooling demand curve. Specifically, cubic spline interpolation is performed on the discrete prediction points of the cooling demand curve to generate a smooth curve.

[0101] In this embodiment, an XGBoost model is trained based on the historical cooling demand curve to generate a refrigeration control model. Through the generated refrigeration control model, the cooling demand curve can be converted into actuator instructions, and the actuator instructions are transmitted to the actuator through the CAN bus, such as adjusting the compressor frequency or damper opening.

[0102] In some embodiments, a real-time feedback closed-loop module is also provided. When comparing the prediction with the actual cooling consumption every 1 minute and the error exceeds 15%, the cooling demand distribution is re-optimized through the quantum annealing algorithm, and at the same time, the input features of the LSTM prediction model are updated to start incremental learning, and its learning rate = 0.0001.

[0103] S400. Based on the predicted cooling demand, cold quantity is directionally transmitted through the phase change energy storage unit to dynamically allocate the cooling capacity.

[0104] In this application, a phase change energy storage unit is introduced. When the refrigeration capacity of the refrigerator is excessive, such as during the night low - electricity - price period or when the ambient temperature is relatively low, the phase change energy storage unit can absorb and store the excess cold energy, thereby avoiding waste of cold energy and improving energy utilization efficiency. In addition, when the refrigerator faces high - temperature loads or a sudden increase in cold - energy demand, such as during the day's high - temperature period, frequent door opening, or storing room - temperature food ingredients, the phase change energy storage unit can quickly release the stored cold energy to meet the refrigeration demand, thus reducing the dependence on the compressor of the refrigerator, reducing energy consumption. Based on this, the phase change energy storage unit and the refrigeration control system of the refrigerator work together, which helps to maintain the temperature stability inside the refrigerator, thereby preventing the food ingredients in the refrigerator from deteriorating due to temperature fluctuations, while reducing unnecessary energy consumption and lowering the operating frequency of the compressor, thus reducing its wear and failure rate.

[0105] In some of the embodiments, the above - mentioned step S400 includes:

[0106] If it is detected that the actual refrigeration capacity is greater than the predicted cold - energy demand, redundant cold energy is transmitted to the phase change energy storage unit based on the cold - energy transmission mechanism;

[0107] When the ambient temperature is lower than 15°C, the compressor enters the low - power - consumption mode, and the phase change energy storage unit is started to store cold energy;

[0108] When the refrigerator suddenly encounters a high - temperature load, cold energy is released through the phase change energy storage unit.

[0109] In this embodiment, for each temperature zone, its actual refrigeration capacity is monitored. If the actual refrigeration capacity is greater than the predicted cold - energy demand within a preset time, redundant cold energy is transmitted to the phase change energy storage unit. The cold - energy transmission mechanism is to direct 80% of the cold energy in the temperature zone to the phase change energy storage unit, while 20% maintains the basic refrigeration. Further, according to the refrigeration temperature of the refrigerator and the phase - change temperature range of the phase - change material, a suitable phase - change material is selected to ensure that the phase - change material can undergo a phase change and store cold energy within the operating temperature range of the refrigerator. Furthermore, a cold - energy transmission system is arranged inside the refrigerator. Specifically, the phase change energy storage unit and the refrigeration unit inside the refrigerator are connected by pipelines, and a flow control valve is installed at the cold - energy output end of the refrigeration unit to adjust the proportion of cold energy flowing to the phase change energy storage unit and the refrigerator temperature zone.

[0110] In some embodiments, a redundant refrigerant pipeline is also provided inside the refrigerator. When it is detected that the temperature of the phase - change unit is < - 15°C or > 20°C, an emergency pressure - relief valve is triggered, and the system pressure is quickly balanced through the above - mentioned redundant refrigerant pipeline.

[0111] In some embodiments, when the ambient temperature is lower than 15°C, the compressor enters the low-power mode and forcibly starts cold energy storage. It can be understood that in a low-temperature environment, the refrigeration capacity required by the refrigerator is relatively small. Therefore, by making the compressor enter the low-power mode, the energy consumption can be significantly reduced. At the same time, the phase change energy storage unit is used to store the excess cold energy, which not only saves energy but also extends the service life of the compressor and improves the overall economy of the refrigerator. In addition, when the refrigerator suddenly encounters a high-temperature load, such as frequent door opening or putting in a large amount of hot food, the phase change energy storage unit releases cold energy, thereby quickly reducing the temperature inside the refrigerator to meet the refrigeration demand under the high-temperature load. This not only improves the comfort of using the refrigerator but also effectively protects the food and beverages in the refrigerator from spoiling due to excessive temperature.

[0112] In some of these embodiments, the phase change energy storage unit includes a primary energy storage unit and a secondary energy storage unit. The primary energy storage unit is used to respond to the sudden cold energy demand of the refrigerator, and the secondary energy storage unit is used to balance the regular cold energy demand of the refrigerator.

[0113] In this embodiment, through the phase change energy storage unit for directional cold energy transmission and dynamic distribution of refrigeration capacity, the refrigerator can respond more quickly to the changing needs of users, enabling the refrigerator to better maintain the freshness of the ingredients. At the same time, it reduces the time for users to wait for the refrigerator to return to the set temperature, significantly reducing the energy consumption of the refrigerator and helping to reduce carbon emissions and energy waste.

[0114] Specifically, in the phase change energy storage unit, the primary energy storage unit and the secondary energy storage unit achieve collaborative optimization through hierarchical temperature adaptation and cold energy release on demand. Among them, the primary energy storage unit is used to respond to the sudden cold energy demand of the refrigerator, that is, to quickly respond to high-priority cold energy demands. For example, when the user deposits a large amount of room-temperature ingredients, the primary energy storage unit quickly releases cold energy to quickly cool the deposited room-temperature ingredients. At this time, the secondary energy storage unit also releases cold energy synchronously, combined with the compressor to increase the cooling rate of the refrigerator and avoid temperature overshoot.

[0115] It can be understood that the phase change materials of the primary energy storage unit and the secondary energy storage unit are different, which are used to match different energy storage requirements and temperature zone requirements. At the same time, the series / parallel switching of the primary energy storage unit and the secondary energy storage unit is realized through the refrigerant valve.

[0116] In some of these embodiments, when the refrigerator suddenly encounters a high-temperature load, cold energy is released through the phase change energy storage unit, including:

[0117] According to the sudden cold energy demand required when the refrigerator suddenly encounters a high-temperature load, dynamically allocate the release ratio of the primary energy storage unit and the secondary energy storage unit;

[0118] For the release ratio of the primary energy storage unit, its specific calculation formula is as follows:

[0119]

[0120] Among them, Q required represents the sudden cooling demand, ΔT represents the temperature difference between the surface temperature of the food ingredient and the temperature of the temperature zone.

[0121] In this embodiment, when the refrigerator suddenly faces a high-temperature load, such as when a large amount of hot food is put in or the external environmental temperature rises sharply, the required sudden cooling capacity will increase significantly. At this time, by dynamically allocating the release ratios of the primary energy storage unit and the secondary energy storage unit, the system can quickly respond to this change in cooling demand, ensure the stability of the internal temperature of the refrigerator, and thus avoid overusing energy-consuming components such as compressors, thereby improving the overall energy efficiency of the refrigerator.

[0122] Specifically, the release ratios of the primary energy storage unit and the secondary energy storage unit are adjusted based on the temperature difference between the surface temperature of the food ingredients in the refrigerator and the temperature of the temperature zone when the refrigerator suddenly encounters a high-temperature load. It can be understood that the surface temperature of the food ingredients is an important indicator reflecting their freshness and preservation status. Therefore, by adjusting the release ratios of the primary energy storage unit and the secondary energy storage unit based on the temperature difference of the food ingredient surface temperature, it can be ensured that the food ingredients can obtain timely and appropriate cooling supply when suddenly encountering a high-temperature load, thereby protecting their quality from damage.

[0123] Specifically, when ΔT > 5°C, Among them, Q required represents the sudden cooling demand required when suddenly encountering a high-temperature load. When calculating Q required it is calculated based on the temperature difference between the surface temperature of the food ingredient and the temperature of the temperature zone, in combination with the equivalent thermal resistance R th and is calculated through the equivalent thermal resistance calculation formula in step S100: It can be seen from this that

[0124] In this embodiment, when ΔT > 5°C, Among them, 0.8 represents the maximum linear gain coefficient, indicating that for every 10°C increase in ΔT urgently, the release ratio of the primary energy storage increases by 80%, and 0.2 represents the basic release ratio, ensuring that even when ΔT urgently approaches 0, 20% of the primary energy storage still participates in cooling to ensure the minimum response ability, which is associated with the setting in the cooling transfer mechanism that 80% of the cooling in the temperature zone is directed to the phase change energy storage unit, while 20% maintains the basic refrigeration.

[0125] In this embodiment, when ΔT ≤ 5°C, α = 0.5·e -0.1t, where 0.5 represents the initial release ratio, indicating that at the critical point of ΔT = 5°C, the initial proportion of the first-stage energy storage is 50%, and 0.1 represents the time decay factor coefficient, which is used to control the rate at which the release ratio decreases exponentially with time. 0.1 means a 10% decay per unit time. Specifically, the release rate is adjusted by regulating the flow control valve, thereby adjusting the refrigerant flow rate.

[0126] It can be understood that the above coefficients are obtained through iterative optimization by combining experimental data, theoretical models, and user requirements to ensure the linear response ability of the cooling capacity supply in the event of an emergency, while achieving a balance between performance and cost.

[0127] Please refer to Figure 2 As shown, the present invention also provides an intelligent refrigerator energy-saving control system, and the system includes:

[0128] The first processing module 201: is used to collect the thermal imaging data of the food materials and the user behavior data in the refrigerator in real time, perform data preprocessing and feature processing on the thermal imaging data of the food materials and the user behavior data, and generate a perception data stream;

[0129] The second processing module 202: is used to construct a three-dimensional thermodynamic twin model of the refrigerator and obtain the cooling capacity demand distribution by combining the quantum annealing algorithm;

[0130] The third processing module 203: is used to obtain the predicted cooling capacity demand based on the perception data stream and the cooling capacity demand distribution, and generate a multi-temperature zone refrigeration power allocation scheme;

[0131] The fourth processing module 204: is used to perform directional transmission of the cooling capacity through the phase change energy storage unit based on the predicted cooling capacity demand, and dynamically allocate the cooling capacity.

[0132] It can be understood that the content in the embodiment of the intelligent refrigerator energy-saving control method as Figure 1 shown is applicable to the embodiment of this intelligent refrigerator energy-saving control system. The specific functions realized by the embodiment of this intelligent refrigerator energy-saving control system are the same as those in the embodiment of the intelligent refrigerator energy-saving control method as Figure 1 shown, and the beneficial effects achieved are also the same as those in the embodiment of the intelligent refrigerator energy-saving control method as Figure 1 shown.

[0133] It should be noted that the information interaction, execution process, etc. between the above systems, due to being based on the same concept as the method embodiment of the present invention, for their specific functions and the technical effects brought, please refer to the method embodiment part for details, and will not be elaborated here.

[0134] Those skilled in the art can clearly understand that, for the convenience and conciseness of description, only the above-mentioned division of each functional unit and module is used as an example. In practical applications, the above functions can be allocated to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment and will not be elaborated here.

[0135] Please refer to Figure 3 As shown, the embodiment of the present invention further provides a computer device 3, including: a memory 302, a processor 301, and a computer program 303 stored on the memory 302. When the computer program 303 is executed on the processor 301, it implements the intelligent refrigerator energy-saving control method described in any one of the above methods.

[0136] The computer device 3 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art can understand that Figure 3 This is only an example of the computer device 3 and does not constitute a limitation on the computer device 3. It may include more or fewer components than shown in the figure, or combine some components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0137] The so-called processor 301 may be a central processing unit (CPU), and the processor 301 may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0138] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as the hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc., equipped on the computer device 3. Further, the memory 302 may also include both the internal storage unit and the external storage device of the computer device 3. The memory 302 is used to store an operating system, application programs, a BootLoader, data, and other programs, such as the program code of the computer program. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0139] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it implements the intelligent refrigerator energy-saving control method described in any one of the above methods.

[0140] This application also provides a computer program product, including a computer program, which implements the methods in the above embodiments when executed by a processor.

[0141] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above embodiment methods of this application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the photographing device / computer device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0142] The foregoing embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A smart refrigerator energy saving control method, characterized in that: include: Collecting food thermal imaging data and user behavior data in the refrigerator in real time, performing data preprocessing and feature processing on the food thermal imaging data and the user behavior data, and generating a perception data stream; Construct a three-dimensional thermodynamic twin model of the refrigerator and use the quantum annealing algorithm to obtain the cooling demand distribution; Based on the sensing data stream and the cooling demand distribution, a cooling demand forecast is obtained, and a multi-temperature zone cooling power allocation plan is generated; Based on the predicted cooling demand, the cooling capacity is dynamically allocated by transmitting cooling capacity in a directional manner through the phase change energy storage unit.

2. The method according to claim 1, characterized in that The real-time collection of thermal imaging data of food in the refrigerator and user behavior data includes: Deploy non-contact infrared thermal imaging sensors on the top of each temperature zone of the refrigerator to generate real-time thermal radiation maps of the food surface and obtain thermal imaging data of the food; Deploy millimeter-wave bio-radar in the refrigerator to detect the user's hand movement trajectory and obtain refrigerator door opening and closing events.

3. The method according to claim 2, characterized in that The data preprocessing and feature processing of the food thermal imaging data and the user behavior data includes: Using a timestamp synchronization algorithm, the food thermal imaging data, the hand motion trajectory and the refrigerator door switch event are aligned; Based on the food thermal imaging data, the equivalent thermal resistance of the food in each temperature zone is calculated, and the calculation formula of the equivalent thermal resistance is specifically: Among them, Q conv represents the convective heat transfer, Q conv =h·A·ΔT, where h represents the convection heat transfer coefficient, A represents the surface area of ​​the food in the temperature zone, and ΔT represents the temperature difference between the surface temperature of the food and the temperature of the temperature zone; Based on the hand motion trajectory and the refrigerator door switch event, the user behavior entropy of each temperature zone is calculated. The calculation formula of the user behavior entropy is specifically: H action =-∑p(x i )logp(x i ); Among them, x i Indicates the frequency and duration distribution of access actions.

4. The method according to claim 1, characterized in that The three-dimensional thermodynamic twin model of the refrigerator is constructed, and the cooling demand distribution is obtained by combining the quantum annealing algorithm, including: Using unstructured tetrahedral grids, local encryption is performed on the food-dense areas in the refrigerator to generate the refrigerator grid structure; When a change in the position of food is detected, a network reconstruction mechanism is triggered to dynamically update the refrigerator grid structure; Each grid unit in the refrigerator grid structure is discretized into a control body, a cooling demand distribution equation is constructed through Hamiltonian, and a quantum annealing algorithm is used to solve the cooling demand distribution equation to obtain the cooling demand distribution.

5. The method according to claim 4, characterized in that The construction of the three-dimensional thermodynamic twin model of the refrigerator includes the construction of multi-physical field coupling and dynamic loading of boundary conditions. The multi-physical field coupling is the coupling construction of the thermal-fluid field in the refrigerator, and the dynamic loading of the boundary conditions includes the coupling construction of environmental interaction and the compressor-condenser in the refrigerator.

6. The method according to claim 4, characterized in that The step of obtaining a predicted cooling demand based on the sensing data stream and the cooling demand distribution and generating a multi-temperature zone cooling power allocation plan includes: Based on the LSTM prediction model, the user behavior entropy of the perception data stream, the cooling demand distribution and the ambient temperature change rate are used as input features to output the cooling demand forecast within a preset time; Based on the pre-trained refrigeration control model, a multi-temperature zone refrigeration power allocation plan is generated through the cooling capacity prediction demand.

7. The method according to claim 1, characterized in that Based on the predicted cooling demand, the phase change energy storage unit is used to transmit cooling directional energy and dynamically allocate cooling capacity, including: If it is detected that the actual cooling capacity is greater than the predicted cooling capacity requirement, the redundant cooling capacity is transmitted to the phase change energy storage unit based on the cooling capacity transmission mechanism; When the ambient temperature is lower than 15°C, the compressor enters a low power consumption mode and starts the phase change energy storage unit to store cold energy; When the refrigerator suddenly encounters a high temperature load, the cold energy is released through the phase change energy storage unit.

8. The method according to claim 7, characterized in that The phase change energy storage unit includes a primary energy storage unit and a secondary energy storage unit. The primary energy storage unit is used to respond to sudden cooling demand of the refrigerator, and the secondary energy storage unit is used to balance the normal cooling demand of the refrigerator.

9. The method according to claim 8, characterized in that When the refrigerator suddenly encounters a high temperature load, the phase change energy storage unit is used to release cold energy, including: Dynamically allocate the release ratio of the primary energy storage unit and the secondary energy storage unit according to the sudden cooling demand required when the refrigerator suddenly encounters a high temperature load; The specific calculation formula for the release ratio of the primary energy storage unit is as follows: Among them, Q required Indicates sudden cooling demand. ΔT represents the temperature difference between the surface temperature of the food and the temperature in the temperature zone.

10. An intelligent refrigerator energy-saving control system, characterized in that: include: The first processing module is used to collect the food thermal imaging data and user behavior data in the refrigerator in real time, perform data preprocessing and feature processing on the food thermal imaging data and the user behavior data, and generate a perception data stream; The second processing module is used to construct a three-dimensional thermodynamic twin model of the refrigerator and obtain the cooling demand distribution in combination with the quantum annealing algorithm; The third processing module is used to obtain the predicted cooling demand based on the sensing data stream and the cooling demand distribution, and generate a multi-temperature zone cooling power allocation plan; The fourth processing module is used to dynamically allocate cooling capacity by transmitting cooling capacity in a directional manner through a phase change energy storage unit based on the predicted cooling demand.

11. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images