Refrigerator adaptive energy-saving control system based on multi-modal perception

Abstract

The present application relates to the field of refrigeration technology, and more particularly to a refrigerator adaptive energy-saving control system based on multi-modal perception, comprising a data acquisition module, a refrigeration adjustment module, a wind-assisted module, a gas pressure-assisted module and a data processing module, wherein: the data acquisition module is used to capture the temperature distribution, humidity conditions and air pressure conditions in the refrigerator, and send these data information to the data processing module. The present application sets up a thermal camera and a wind-assisted module, the thermal camera captures the ice layer position, so that the fan is aligned with the ice layer, and the surface of the ice layer is accelerated to sublimate through air flow. When the air passes through the surface of the ice layer, it will transfer heat to the ice layer with lower temperature due to the operation of the evaporator, accelerating the disappearance of the ice layer while reducing the temperature of the flowing air, thereby reducing the power consumption of the refrigeration adjustment module and improving the refrigeration quality.

Description

Technical Field

[0001] This invention relates to the field of refrigeration technology, and in particular to an adaptive energy-saving control system for freezers based on multimodal sensing. Background Technology

[0002] Refrigerators are refrigeration equipment widely used in homes, supermarkets, and cold chain logistics, primarily for the long-term preservation of food. With increasing demands for environmental protection and energy conservation, the intelligentization and energy efficiency of freezers have become key areas of technological development. Traditional freezers achieve cooling primarily through the periodic starting and stopping of compressors, while modern freezers improve energy efficiency through enhanced control systems and refrigeration technologies.

[0003] Ice buildup is a common problem in freezers. Excessive ice buildup hinders heat exchange, reduces cooling efficiency, increases the compressor's workload, and further exacerbates energy consumption. Current freezer defrosting methods are mostly timed defrosting, where heating elements are activated at fixed intervals to melt the ice on the evaporator. However, the thickness and distribution of ice vary depending on humidity, door opening frequency, and the items stored. Timed defrosting may result in defrosting at unnecessary times, and the heating elements often have a large heating range, leading to inaccurate defrosting and wasted energy. Furthermore, while ice can store cold energy during accumulation, traditional defrosting methods often treat it as an obstacle that must be removed, failing to fully utilize its low-temperature characteristics. This results in the defrosting process consuming energy without achieving efficient resource utilization.

[0004] In summary, existing freezers have significant shortcomings in defrosting, energy saving, and ice utilization, and there is an urgent need for a more intelligent and energy-efficient control solution to address these issues. Summary of the Invention

[0005] To overcome the shortcomings of existing de-icing technologies, such as high power consumption and the inability to utilize ice as a resource, this application provides an adaptive energy-saving control system for refrigerated cabinets based on multimodal perception.

[0006] The technical solution is: a multimodal sensing-based adaptive energy-saving control system for refrigerated display cases, comprising a data acquisition module, a refrigeration regulation module, a fan-assisted module, a pressure-assisted module, and a data processing module, wherein:

[0007] The data acquisition module includes a temperature sensor, a thermal camera, a light camera, a humidity sensor, and a pressure sensor, which are used to capture the temperature distribution, humidity, and pressure inside the freezer and send this data to the data processing module.

[0008] The refrigeration control module includes a compressor, condenser, expansion valve, filter, evaporator, accumulator and refrigerant. It is used to continuously convert the refrigerant in the refrigeration control module between liquid and gaseous states, thereby cooling the inside of the freezer. The cooling speed is controlled by the data processing module.

[0009] The wind-assisted module includes an adjustable-angle fan to circulate air inside the freezer, ensuring that the cooled air circulates fully throughout the freezer and improving its cooling efficiency.

[0010] The air pressure auxiliary module includes an electronically controlled air pressure valve, an air pressure pump, and an air storage chamber. It is used to regulate the air pressure inside the freezer to change the relative humidity and absolute humidity inside the freezer. When the relative humidity in the air storage chamber is not 100%, the relative humidity and temperature of the air in the air storage chamber are kept consistent with those inside the freezer.

[0011] The data processing module receives data from the data acquisition module, performs feature extraction and feature splicing on the data, and obtains feature values ​​of the state inside the freezer through a neural network. It then adjusts the temperature in a timely manner through the refrigeration regulation module and the fan-assisted module, and adjusts the air pressure and humidity through the air pressure-assisted module.

[0012] Preferably, the temperature sensor includes an external sensor and an internal sensor. The external sensor is used to detect the ambient temperature outside the freezer, and the internal sensor is used to detect the cooling temperature inside the freezer. By comparing the temperature difference between the two temperature sensors, the data processing module is provided with a basis for temperature adjustment, so that the data processing module can adjust the cooling effect in a timely manner and prevent the compressor from frequently starting and stopping or operating at low frequency due to the small temperature difference between the inside and outside of the freezer, which would increase the power consumption of the compressor.

[0013] Preferably, the wind-assisted module uses a fan to control the temperature of the freezer, blowing the cold air generated by heat exchange at the evaporator of the refrigeration regulating module into the freezer to accelerate the circulation of cold air inside the freezer. The fan will push all the cold air around the evaporator into the freezer, so that the cold air is evenly distributed inside the freezer.

[0014] Preferably, the electronically controlled air pressure valve in the air pressure auxiliary module is used to control the air inside the freezer and the air from the outside environment to enter and exit the air storage chamber. The air storage chamber isolates the inside of the freezer from the outside environment, thereby avoiding the direct exchange of gas between the freezer and the outside environment when the air pressure inside the freezer is adjusted, which would result in a large loss of temperature and an increase in humidity inside the freezer.

[0015] Preferably, during refrigeration, the data processing module preprocesses the light-sensing and thermal-sensing images through resolution adjustment, image cropping, and normalization. Then, it stitches the light-sensing and thermal-sensing images together to form a four-channel image containing three color channels and a thermal channel. The neural network of the data processing module obtains the image features of the four-channel image through a convolution followed by linear transformation, and expands this into a one-dimensional image feature matrix. This one-dimensional image feature matrix is ​​then combined with data from the temperature sensor, humidity sensor, and air pressure sensor to form a one-dimensional multimodal matrix. This one-dimensional multimodal matrix, through linear layer operations and nonlinear transformations of the neural network, obtains the refrigerator's adjustment data features. These features include the target power of the compressor, the target power of the fan, and the target air pressure inside the refrigerator. Adjusting the compressor power adjusts the refrigeration module's performance during refrigeration. The cooling effect inside the freezer depends on the compressor's power; a higher compressor power results in a stronger cooling module. Adjusting the fan power regulates the airflow within the freezer, thus controlling its distribution. Controlling the airflow in the storage chamber adjusts the air pressure, relative humidity, and absolute humidity. When the air pressure inside the freezer increases, the moisture density rises, causing both relative and absolute humidity to increase before reaching saturation vapor pressure. This high humidity inhibits moisture evaporation from food. When the freezer door is opened, the pressure difference causes moisture to escape quickly, followed by a return to normal air pressure, reducing both relative and absolute humidity. The cold air then lingers around the freezer door, preventing high-humidity outside air from entering and keeping the freezer dry.

[0016] Preferably, when the placement of food in the freezer causes localized airflow difficulties, a light sensor can be used to collect the location of the food and a thermal sensor can be used to collect the surface temperature of the food. Based on the temperature of the densely packed food, the visual neural network of the data processing module can quickly determine the location of the airflow obstruction and adjust the angle of the fan in the wind-assisted module in a timely manner. This allows cold air to circulate more smoothly from the densely packed food, improving the cooling effect inside the freezer, reducing the power required for cooling, and ensuring that the food can be stored for a longer period of time.

[0017] Preferably, when a localized area of ​​the freezer needs to be cooler than other areas, a light sensor can be used to detect the location of the food inside the freezer. This allows the fan to actively blow cold air onto the area requiring a lower localized temperature, resulting in that area being cooler than other areas. The air pressure inside the freezer is adjusted by storing or releasing air in the air storage chamber of the air pressure assist module. This increases the air pressure and moisture density inside the freezer, thereby regulating the relative and absolute humidity of the air inside the freezer. This inhibits the evaporation of moisture from the food, reduces moisture evaporation caused by cold air blowing onto the area requiring a lower localized temperature, and ensures the quality of the food in that area.

[0018] Preferably, thermal images are acquired using a thermal camera and analyzed by a data processing module. Based on the low-temperature distribution inside the freezer and a convolutional neural network, the module can identify the ice layer that has not yet formed on the inner wall of the freezer and determine its location. The data processing module then controls a fan-assisted module to direct the fan towards the ice layer. Since only a small amount of ice adheres to the inside of the freezer, air flows over the surface of the ice layer, accelerating its sublimation without affecting the cooling effect. As the air passes over the surface of the ice layer, it transfers heat to the ice layer, which is even cooler due to the evaporator's operation. This accelerates the disappearance of the ice layer while lowering the temperature of the flowing air. Thus, the ice layer helps to alleviate the cooling burden on the cooling regulation module, reducing its energy consumption and improving cooling quality.

[0019] Preferably, when the wind-assisted module sublimates the unformed ice layer, the moisture from the unformed ice layer enters the air inside the freezer, causing an increase in the freezer's humidity. To prevent excessive humidity inside the freezer from causing mold growth and food spoilage, the data processing module can control the air pressure-assisted module based on humidity data collected by the humidity sensor. When the humidity inside the freezer is normal, the data processing module will lower the air pressure inside the freezer, reducing the moisture density and accelerating the sublimation process on the ice surface. As the ice sublimates, the humidity inside the freezer gradually approaches saturation. At this point, the data processing module controls the electronically controlled air pressure valve of the air pressure-assisted module to discharge the high-humidity air inside the freezer into the air storage chamber. The air storage chamber is pressurized by an air pressure pump, causing the moisture inside to exceed the saturation vapor pressure, thus condensing the moisture into water droplets and expelling them from the device before they freeze. At this time, the air in the air storage chamber still has a low temperature, which can be used to maintain the humidity inside the freezer, thereby reducing energy waste during the defrosting process.

[0020] Preferably, the data processing module divides a day into multiple time segments and records the number of times the freezer door is opened and closed in different time segments. Based on the number of times the freezer door is opened and closed in different time segments, an exponential decay curve that gradually approaches 0 is fitted. This exponential decay curve is used to represent the probability that the freezer user will form a habit of opening and closing the freezer door at fixed time segments every day. The exponential decay curve is used to assign weights to the user's behavior of opening and closing the freezer, thereby predicting the time segments when the freezer user opens and closes the freezer. Based on this prediction, the freezer temperature, humidity and air pressure are adjusted to reduce the amount of moisture entering the freezer and the loss of cold air inside the freezer caused by opening and closing the freezer door.

[0021] This invention utilizes a thermal camera and a wind-assisted module. The thermal camera captures the location of the ice layer, allowing a fan to be aimed at the ice layer. By allowing air to flow over the ice surface, the surface of the ice layer is accelerated to sublimate without affecting the cooling effect. As the air passes over the ice surface, it transfers heat to the ice layer, which is even colder due to the operation of the evaporator. This accelerates the disappearance of the ice layer and reduces the temperature of the flowing air. In this way, the ice layer is used to share the cooling burden of the cooling regulation module, reducing the power consumption of the cooling regulation module and improving the cooling quality.

[0022] This invention incorporates a light-sensing camera, a thermal-sensing camera, and a wind-assisted module. The light-sensing camera collects the position of the food inside the freezer, and the thermal-sensing camera collects the surface temperature of the food. Based on the temperature of densely packed food areas, the visual neural network of the data processing module can quickly determine the location of airflow obstruction and adjust the fan angle of the wind-assisted module in a timely manner. This allows cold air to circulate more smoothly from densely packed food areas, improving the cooling effect inside the freezer, reducing the power required for cooling, and ensuring longer food storage time.

[0023] This invention divides a day into multiple time segments using a data processing module and records the number of times the freezer door is opened and closed in different time segments. It assigns weights to the user's actions of opening and closing the freezer, thereby predicting the time segments when the user opens and closes the freezer. Based on this prediction, it adjusts the freezer temperature, humidity, and air pressure to reduce moisture entering the freezer and cold air loss caused by opening and closing the freezer door. Attached Figure Description

[0024] Figure 1 This is a schematic diagram of the overall structure of the present invention;

[0025] Figure 2 This is a flowchart illustrating the cooling process of the data processing module of the present invention.

[0026] Figure 3 This is a flowchart illustrating the de-icing process of the data processing module of this invention. Detailed Implementation

[0027] The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments, but this is not intended to limit the present invention.

[0028] An adaptive energy-saving control system for refrigerated display cases based on multimodal sensing, such as Figure 1 As shown, it includes a data acquisition module, a cooling regulation module, a wind power assist module, a barometric pressure assist module, and a data processing module, wherein:

[0029] The data acquisition module includes a temperature sensor, a thermal camera, a light camera, a humidity sensor, and a pressure sensor, which are used to capture the temperature distribution, humidity, and pressure inside the freezer and send this data to the data processing module.

[0030] The refrigeration control module includes a compressor, condenser, expansion valve, filter, evaporator, accumulator and refrigerant. It is used to continuously convert the refrigerant in the refrigeration control module between liquid and gaseous states, thereby cooling the inside of the freezer. The cooling speed is controlled by the data processing module.

[0031] The wind-assisted module includes an adjustable-angle fan to circulate air inside the freezer, ensuring that the cooled air circulates fully throughout the freezer and improving its cooling efficiency.

[0032] The air pressure auxiliary module includes an electronically controlled air pressure valve, an air pressure pump, and an air storage chamber. It is used to regulate the air pressure inside the freezer to change the relative humidity and absolute humidity inside the freezer. When the relative humidity in the air storage chamber is not 100%, the relative humidity and temperature of the air in the air storage chamber are kept consistent with those inside the freezer.

[0033] The data processing module receives data from the data acquisition module, performs feature extraction and feature splicing on the data, and obtains feature values ​​of the state inside the freezer through a neural network. It then adjusts the temperature in a timely manner through the refrigeration regulation module and the fan-assisted module, and adjusts the air pressure and humidity through the air pressure-assisted module.

[0034] Specifically, the temperature sensor is used to capture the temperature of the air in a certain area inside the freezer, the thermal camera is used to capture the temperature distribution of all items in a certain area inside the freezer, and the light camera is used to capture the structure of all food in a certain area. The data processing module can identify the type of food and select the appropriate freezer temperature and humidity for the food. The humidity sensor is used to detect changes in humidity inside the freezer and provide a basis for the data processing module to control the humidity inside the freezer, preventing excessive humidity inside the freezer from causing mold growth and food spoilage, or excessively low humidity from causing food to lose moisture and reduce quality.

[0035] Specifically, the temperature sensor includes an external sensor and an internal sensor. The external sensor is used to detect the ambient temperature outside the freezer, while the internal sensor is used to detect the cooling temperature inside the freezer. By comparing the temperature difference between the two temperature sensors, the data processing module is provided with a basis for temperature adjustment, enabling the data processing module to adjust the cooling effect in a timely manner. This prevents the compressor from frequently starting and stopping or operating at low frequency due to an excessively small temperature difference between the inside and outside of the freezer, which would increase the compressor's power consumption. Traditional compressors will frequently start and stop when the temperature difference between the inside and outside of the freezer is too small, and this frequent starting and stopping consumes a lot of energy, resulting in wasted compressor energy. Variable frequency compressors will run at low speed when the temperature difference between the inside and outside of the freezer is too small, and the low speed will prevent the variable frequency compressor from forming a good lubrication effect, leading to component wear.

[0036] Specifically, when the refrigeration control module starts, the compressor compresses the gaseous refrigerant into a liquid state. The refrigerant liquefies under pressure, generating a large amount of heat, which is released into the condenser and then into the external environment. Subsequently, the refrigerant enters the expansion valve. As it flows out of the expansion valve, the refrigerant expands in volume, forming a gas-liquid mixture. After impurities in the refrigerant are filtered out by the filter, the refrigerant absorbs heat from inside the freezer in the evaporator and continues to evaporate. Finally, it absorbs energy at the accumulator, causing the refrigerant to completely vaporize. This completes one refrigeration cycle of the refrigeration control module. The refrigerant in the accumulator can then enter the compressor for multiple subsequent refrigeration cycles.

[0037] It is worth noting that, in order to ensure the compressor operates normally, when the freezer is used as a refrigerator, the temperature difference between the freezer and the outside environment should be at least 5 degrees Celsius to prevent cooked food and dairy products from growing a large amount of mold and producing toxins. When the freezer is used as a freezer, the temperature difference between the freezer and the outside environment should be at least 15 degrees Celsius to prevent frozen food from thawing.

[0038] The wind-assisted module uses a fan to control the temperature of the freezer. It blows the cold air generated by heat exchange at the evaporator of the refrigeration regulating module into the freezer, accelerating the circulation of cold air inside the freezer. The fan will push all the cold air around the evaporator into the freezer, so that the cold air is evenly distributed inside the freezer. This avoids the cold air from accumulating at the evaporator, which would reduce the refrigeration efficiency due to the low temperature difference between the cold air and the evaporator, and effectively reduces the energy waste of refrigeration.

[0039] Specifically, the electronically controlled air pressure valve in the air pressure auxiliary module is used to control the air inside the freezer and the air from the outside environment to enter and exit the air storage chamber. The air storage chamber isolates the inside of the freezer from the outside environment, thereby avoiding the direct exchange of gas with the outside environment when the air pressure inside the freezer is adjusted, which would result in a large loss of temperature and an increase in humidity inside the freezer.

[0040] Specifically, the air storage chamber in the air pressure auxiliary module is located inside the freezer and shares the same refrigeration regulation module with the freezer for temperature control, thereby ensuring that the temperature inside the freezer is consistent with the temperature inside the air storage chamber. Since saturated moisture pressure is only related to temperature, the lower the temperature, the lower the saturated moisture pressure. The outside air temperature is higher than the temperature inside the air storage chamber, resulting in a higher saturated moisture pressure and higher absolute humidity. When outside air enters the air storage chamber, the temperature of the outside air decreases inside the air storage chamber, causing the saturated water vapor pressure to decrease. Water vapor in the outside air condenses, resulting in lower absolute humidity and higher relative humidity in the outside air inside the air storage chamber.

[0041] like Figure 2As shown, during refrigeration, the data processing module preprocesses the light and heat images through resolution adjustment, image cropping, and normalization. Then, it stitches the light and heat images together into a four-channel image. The neural network of the data processing module obtains the image features of the four-channel image through a convolution followed by linear transformation, and expands this into a one-dimensional image feature matrix. This one-dimensional image feature matrix is ​​then combined with data from the temperature, humidity, and pressure sensors to form a one-dimensional multimodal matrix. This one-dimensional multimodal matrix is ​​used to obtain the freezer adjustment data features through linear layer operations and nonlinear transformations of the neural network. These features include the target power of the compressor, the target power of the fan, and the target air pressure inside the freezer. Adjusting the compressor power adjusts the refrigeration effect of the refrigeration module within the freezer; the higher the compressor power, the stronger the refrigeration effect. Adjusting the fan power regulates the flow of cold air within the freezer, thereby regulating the refrigeration... The distribution of cold air inside the freezer is controlled by adjusting the air pressure, relative humidity, and absolute humidity within the air storage chamber. When the air pressure inside the freezer increases, the moisture density inside the freezer increases, causing both the absolute and relative humidity to rise before reaching saturation vapor pressure. This high humidity inhibits the evaporation of moisture from the food. When the freezer door is opened, the pressure difference causes moisture to be released rapidly outwards. Subsequently, the air pressure inside the freezer returns to normal, causing both relative and absolute humidity to decrease. The cold air then lingers around the freezer door, preventing high-humidity outside air from entering the freezer, keeping the freezer dry, and avoiding temperature fluctuations. Compared to ordinary freezers, the lingering of cold air at the freezer door can reduce humidity fluctuations by approximately 60%, temperature changes by approximately 69%, cold air loss by approximately 40%, and compressor energy consumption by approximately 15% when the door is open.

[0042] When the placement of food inside the freezer causes localized airflow difficulties, a light sensor can be used to detect the location of the food and a thermal sensor can be used to detect the surface temperature of the food. Based on the temperature of the densely packed food, the visual neural network of the data processing module can quickly determine the location of the airflow obstruction and adjust the angle of the fan in the fan-assisted module in a timely manner. This allows cold air to circulate more smoothly from the densely packed food, improving the cooling effect inside the freezer, reducing the power required for cooling, and ensuring that the food can be stored for a longer period of time.

[0043] When a localized area of ​​the freezer needs to be cooler than other areas, a light sensor can detect the location of the food inside the freezer. This allows the fan to actively direct the cool air to the area requiring a lower temperature, resulting in that area being cooler than other areas. The air pressure is adjusted by storing or releasing air in the air storage chamber of the freezer's pressure assist module. This increases the air pressure and moisture density inside the freezer, inhibiting moisture evaporation from the food and reducing moisture loss when cold air is directed at the area requiring a lower temperature. This ensures the quality of the food in the area requiring a lower temperature.

[0044] like Figure 3 As shown, thermal images are acquired by a thermal camera and analyzed by a data processing module. Based on the low-temperature distribution inside the freezer and a convolutional neural network, the module can identify the ice layer that has not yet formed on the inner wall of the freezer and determine its location. The data processing module then controls the fan-assisted module to direct the fan towards the ice layer. Since only a small amount of ice adheres to the inside of the freezer, air flows over the surface of the ice layer, accelerating its sublimation without affecting the cooling effect. As the air passes over the surface of the ice layer, it transfers heat to the ice layer, which is even cooler due to the evaporator's operation. This accelerates the disappearance of the ice layer while lowering the temperature of the flowing air. Thus, the ice layer helps to share the cooling burden of the cooling regulation module, reducing its power consumption and improving the cooling quality.

[0045] When the wind-assisted module sublimates the unformed ice layer, the moisture from the unformed ice layer enters the air inside the freezer, causing an increase in humidity. To prevent excessive humidity from causing mold growth and food spoilage, the data processing module controls the air pressure-assisted module based on humidity data collected by the humidity sensor. When the humidity inside the freezer is normal, the data processing module lowers the air pressure inside the freezer, reducing the moisture density and lowering the melting point of the ice layer, thereby accelerating the sublimation process on the ice surface. As the ice layer sublimates, the air pressure decreases. As the humidity inside the freezer gradually approaches saturation, the data processing module controls the electronically controlled air pressure valve of the air pressure auxiliary module to discharge the high-humidity air inside the freezer into the air storage chamber. The air storage chamber is pressurized by the air pressure pump, causing the moisture content inside the air storage chamber to exceed the saturation vapor pressure. The relative humidity inside the air storage chamber temporarily exceeds 100%, resulting in supersaturation. This causes the moisture to condense into water droplets, which are then discharged from the device before freezing. At this time, the air inside the air storage chamber still has a low temperature, which can be used to maintain the humidity inside the freezer, thereby reducing energy waste during the defrosting process.

[0046] The data processing module divides a day into multiple time segments and records the number of times the freezer door is opened and closed in different time segments. Based on the number of times the freezer door is opened and closed in different time segments, an exponential decay curve that gradually approaches 0 is fitted. This exponential decay curve is used to represent the probability that the freezer user will form a habit of opening and closing the freezer door at fixed time segments every day. The exponential decay curve is used to assign weights to the user's behavior of opening and closing the freezer, thereby predicting the time segments when the freezer user will open and close the freezer. Based on this prediction, the freezer temperature, humidity and air pressure are adjusted to reduce the amount of moisture entering the freezer and the loss of cold air inside the freezer caused by opening and closing the freezer door.

[0047] Specifically, in this embodiment, the data processing module divides a day into 144 segments, recording the number of times the freezer door is opened and closed every 10 minutes. Based on the number of times the freezer door is opened and closed and the Ebbinghaus forgetting curve, each time segment is assigned a weight. The larger the weight, the higher the probability that the freezer door is opened in that time segment. This allows the refrigeration adjustment module to adjust the refrigeration in advance, slightly reducing the refrigeration effect. The temperature of the freezer is increased by 1 to 2 degrees Celsius in the time segment preceding the current time segment. Based on the ideal gas law, when the temperature inside the freezer increases, the air pressure also increases. The air pressure auxiliary module adjusts the pressure so that when the freezer door is opened, the cold air inside the freezer will prevent outside air from entering the freezer, thus significantly reducing the amount of outside moisture entering the freezer. Furthermore, the slight increase in the temperature inside the freezer reduces the energy consumption caused by the outflow of cold air when the freezer door is opened, further reducing the energy consumption of the freezer.

[0048] Specifically, the formula for calculating the weight of a time segment is as follows:

[0049] ;

[0050] in, A sequence representing a specific time segment of a day. It indicates the first day of each day. Weight of time segments within a time period This indicates the total number of days the data processing module has stored the freezer door opening and closing times. In this embodiment, the total number of days stored is defined as 30 days. Indicates the first Heavenly The probability of maintaining the open behavior of the freezer door in a given time segment is calculated based on an exponential decay curve fitted by the number of times the freezer door is opened and closed in different time segments. Indicates the first Heavenly The formula for the number of times the freezer door is opened during a given time period is important to understand. All variables mentioned in the formula are pure numbers and do not involve physical unit conversions.

[0051] The setting of time segment weights abstracts the state of the freezer being open into a probability. The freezer door is simultaneously in both open and closed states. The power of the compressor in the refrigeration module is adjusted based on the probability, thereby changing the temperature inside the freezer. The degree of temperature rise inside the freezer is proportional to this probability, thus reducing the temperature loss when cold air escapes when the freezer door is open, thereby reducing the waste of the freezer's electricity.

[0052] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A multimodal sensing-based adaptive energy-saving control system for refrigerated display cases, characterized in that, It includes a data acquisition module, a cooling regulation module, a wind-assisted module, a barometric pressure-assisted module, and a data processing module, among which: The data acquisition module includes a temperature sensor, a thermal camera, a light camera, a humidity sensor, and a pressure sensor, which are used to capture the temperature distribution, humidity, and pressure inside the freezer and send this data to the data processing module. The temperature sensor includes an external sensor and an internal sensor. The external sensor is used to detect the ambient temperature outside the freezer, and the internal sensor is used to detect the cooling temperature inside the freezer. By comparing the temperature difference between the two temperature sensors, the data processing module is provided with a basis for temperature adjustment, so that the data processing module can adjust the cooling effect in time and prevent the compressor from frequently starting and stopping or working at low frequency due to the small temperature difference between the inside and outside of the freezer, which would increase the power consumption of the compressor. The refrigeration control module includes a compressor, condenser, expansion valve, filter, evaporator, accumulator and refrigerant. It is used to continuously convert the refrigerant in the refrigeration control module between liquid and gaseous states, thereby cooling the inside of the freezer. The cooling speed is controlled by the data processing module. The wind-assisted module includes an adjustable-angle fan. The wind-assisted module uses the fan to control the temperature of the freezer and blows the cold air generated by heat exchange at the evaporator of the refrigeration regulating module into the freezer, accelerating the circulation of cold air inside the freezer. The fan will push all the cold air around the evaporator into the freezer, so that the cold air is evenly distributed inside the freezer. The fan is used to circulate the air inside the freezer, so that the cooled air inside the freezer circulates fully throughout the freezer, improving the refrigeration efficiency of the freezer. The air pressure auxiliary module includes an electronically controlled air pressure valve, an air pressure pump, and an air storage chamber. The electronically controlled air pressure valve in the air pressure auxiliary module is used to control the air entering and leaving the air storage chamber from the freezer and the external environment. The air storage chamber isolates the interior of the freezer from the external environment, thereby avoiding the direct exchange of gases between the freezer and the external environment when adjusting the air pressure, which would lead to a large loss of temperature and an increase in humidity inside the freezer. The air pressure auxiliary module is used to adjust the air pressure inside the freezer to change the relative humidity and absolute humidity inside the freezer. When the relative humidity in the air storage chamber is not 100%, the relative humidity and temperature of the air in the air storage chamber are consistent with those inside the freezer. The data processing module receives data from the data acquisition module, performs feature extraction and feature splicing on the data, and obtains feature values ​​of the state inside the freezer through a neural network. It then adjusts the temperature in a timely manner through the refrigeration regulation module and the fan-assisted module, and adjusts the air pressure and humidity through the air pressure-assisted module.

2. The adaptive energy-saving control system for a freezer based on multimodal sensing according to claim 1, characterized in that, During refrigeration, the data processing module preprocesses the light and heat images through resolution adjustment, image cropping, and normalization. It then stitches the light and heat images together to create a four-channel image containing three color channels and a heat channel. The neural network in the data processing module uses a convolution followed by linear operations to obtain the image features of the four-channel image, which are then unfolded into a one-dimensional image feature matrix. This one-dimensional image feature matrix is ​​combined with data from the temperature, humidity, and pressure sensors to form a one-dimensional multimodal matrix. This one-dimensional multimodal matrix is ​​then used for linear layer operations and nonlinear transformations in the neural network to obtain the freezer's regulation data features. These features include the target power of the compressor, the target power of the fan, and the target air pressure inside the freezer. Adjusting the compressor power regulates the refrigeration module's operation within the freezer. The higher the compressor power, the stronger the cooling effect of the refrigeration module. By adjusting the fan power, the flow of cold air inside the freezer is adjusted, thereby regulating the distribution of cold air inside the freezer. By controlling the air flow in the air storage chamber, the air pressure, relative humidity, and absolute humidity inside the freezer are adjusted. When the air pressure inside the freezer increases, the moisture density inside the freezer increases, so that the absolute humidity and relative humidity inside the freezer both increase before reaching the saturation vapor pressure. At this time, the high humidity inside the freezer inhibits the evaporation of moisture from the food. When the freezer door is opened, under the influence of the air pressure difference, the water vapor is quickly released to the outside. Subsequently, the air pressure inside the freezer recovers, thereby reducing the relative humidity and absolute humidity. The cold air will stay around the freezer door, thus preventing the high humidity outside air from entering the freezer and keeping the freezer dry.

3. The adaptive energy-saving control system for a freezer based on multimodal perception according to claim 2, characterized in that, When the placement of food inside the freezer causes localized airflow difficulties, a light sensor can be used to detect the location of the food and a thermal sensor can be used to detect the surface temperature of the food. Based on the temperature of the densely packed food, the visual neural network of the data processing module can quickly determine the location of the airflow obstruction and adjust the angle of the fan in the fan-assisted module in a timely manner. This allows cold air to circulate more smoothly from the densely packed food, improving the cooling effect inside the freezer, reducing the power required for cooling, and ensuring that the food can be stored for a longer period of time.

4. The adaptive energy-saving control system for a freezer based on multimodal sensing according to claim 3, characterized in that, When a localized area of ​​the freezer needs to be cooler than other areas, a light sensor can detect the location of the food inside. This allows the fan to actively direct the cool air to the area requiring a lower temperature, resulting in that area being cooler than the others. The air pressure adjustment module stores or releases air in its storage chamber to regulate the internal pressure, increasing both the air pressure and the moisture density. This, in turn, regulates the relative and absolute humidity of the air inside the freezer, inhibiting moisture evaporation from the food and reducing the amount of moisture lost when the cool air is directed at the area requiring a lower temperature. This ensures the quality of the food in the area requiring a lower temperature.

5. The adaptive energy-saving control system for a freezer based on multimodal perception according to claim 4, characterized in that, Thermal images are captured by a thermal camera and analyzed by a data processing module. Based on the low-temperature distribution inside the freezer and a convolutional neural network, the module can identify the ice layer that has not yet formed on the inner wall of the freezer and determine its location. The data processing module then controls a fan-assisted module to direct the fan towards the ice layer. Since only a small amount of ice adheres to the inside of the freezer, air flows over the surface of the ice layer, accelerating its sublimation without affecting the cooling effect. As the air passes over the surface of the ice layer, it transfers heat to the ice layer, which is even cooler due to the evaporator's operation. This accelerates the disappearance of the ice layer and lowers the temperature of the flowing air, thus reducing the cooling load on the cooling regulation module, decreasing its power consumption, and improving the cooling quality.

6. The adaptive energy-saving control system for a freezer based on multimodal perception according to claim 5, characterized in that, When the wind-assisted module sublimates the unformed ice layer, the moisture from the unformed ice layer enters the air inside the freezer, causing an increase in humidity. To prevent excessive humidity inside the freezer from causing mold growth and food spoilage, the data processing module controls the air pressure-assisted module based on humidity data collected by the humidity sensor. When the humidity inside the freezer is normal, the data processing module lowers the air pressure inside the freezer, reducing the moisture density and accelerating the sublimation process on the ice surface. As the ice sublimates, the humidity inside the freezer gradually approaches saturation. At this point, the data processing module controls the electronically controlled air pressure valve of the air pressure-assisted module to discharge the high-humidity air inside the freezer into the air storage chamber. The air storage chamber is pressurized by an air pump, causing the moisture inside to exceed the saturation vapor pressure, thus condensing the moisture into droplets and expelling them from the device before they freeze. At this point, the air in the air storage chamber still has a low temperature, which can be used to maintain the humidity inside the freezer, thereby reducing energy waste during the defrosting process.

7. The adaptive energy-saving control system for a freezer based on multimodal perception according to claim 6, characterized in that, The data processing module divides a day into multiple time segments and records the number of times the freezer door is opened and closed in different time segments. Based on the number of times the freezer door is opened and closed in different time segments, an exponential decay curve that gradually approaches 0 is fitted. This exponential decay curve is used to represent the probability that the freezer user will form a habit of opening and closing the freezer door at fixed time segments every day. The exponential decay curve is used to assign weights to the user's behavior of opening and closing the freezer, thereby predicting the time segments when the freezer user will open and close the freezer. Based on this prediction, the freezer temperature, humidity and air pressure are adjusted to reduce the amount of moisture entering the freezer and the loss of cold air inside the freezer caused by opening and closing the freezer door.

Images