Temperature control method and system for a thermally insulated cooker

Abstract

The application provides a temperature control method and system of a heat preservation food warmer, the method comprising: collecting temperature data and dish images of the heat preservation food warmer, performing dish grid area segmentation on the collected images by an edge computing node, extracting dish contour features, and calculating the residual dish amount proportion of each dish grid area; calculating the heat capacity value of each dish grid area according to the residual dish amount proportion, and then obtaining a heat capacity attenuation coefficient; calculating a temperature drop rate according to the temperature data and a target heat preservation temperature, dividing the temperature drop rate by the heat capacity attenuation coefficient to obtain a thermal stability index, identifying a heat compensation demand partition based on the thermal stability index, and calculating a heat loss compensation power for directional power updating, so as to realize accurate identification and directional heat compensation of a heat inertia attenuation serious partition, and effectively solve the problem of expanding partition temperature difference caused by uneven dish taking.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) technology, and in particular to a temperature control method and system for a food warmer. Background Technology

[0002] In the catering industry, food warmers are widely used in canteens, restaurants and other food service settings to keep cooked dishes warm and ensure that the dishes maintain a suitable temperature and taste during the meal service period.

[0003] Food warming ovens typically employ a zoned heating structure, dividing the oven body into multiple heating zones, each corresponding to a specific food compartment for different types of dishes. During actual meal service, due to the randomness and unevenness of diners' food-taking behavior, the frequency of food being taken from different compartments varies significantly, leading to varying degrees of food depletion over time in each compartment. The thermal inertia of food in compartments with less food differs fundamentally from that in compartments with ample food. Under the same external heat loss conditions, the temperature drops more rapidly in compartments with less food, while the temperature in compartments with ample food remains relatively stable. This difference in thermal inertia caused by food-taking behavior results in significant temperature imbalances between the compartments of the food warming oven. Excessively low temperatures lead to food quality deterioration, while excessively high temperatures result in energy waste and may even accelerate moisture evaporation and surface drying of the food.

[0004] Existing methods for controlling the temperature of insulated food ovens typically rely solely on feedback adjustments based on the deviation between the measured temperature of each zone and the target insulation temperature. This approach fails to adequately consider the changes in thermal inertia caused by variations in the amount of food in different food compartments. Consequently, it cannot accurately predict and compensate for zones with severe thermal inertia attenuation. This results in delayed temperature control, difficulty in fundamentally resolving issues such as uneven temperature distribution between zones, and the coexistence of overheating and underheating, which severely impacts the quality of food insulation and energy efficiency. Summary of the Invention

[0005] This invention provides a temperature control method and system for a food warmer, aiming to solve the technical problem of uneven temperature distribution in food warmers caused by differences in thermal inertia due to uneven food retrieval in different compartments.

[0006] To solve the above problems, the present invention adopts the following technical solution: In a first aspect, the present invention provides a temperature control method for a food warming oven, comprising: Temperature data of each zone inside the insulated food oven is collected by an array of temperature sensors deployed on the inner wall of the oven cavity, and the temperature data is uploaded to the edge computing node through an Internet of Things gateway. A visual inspection device deployed on the top of the insulated food oven cavity is used to collect images of the dishes in each compartment of the insulated food oven. The collected images are transmitted to the edge computing node, which is then used to segment the collected images into compartments and extract the outline features of the dishes in each compartment. Based on the degree of matching between the outline features of the dishes and the pre-stored outline of a full food state, the proportion of remaining dishes in each compartment is calculated. The edge computing node is invoked to calculate the heat capacity value of the dishes in each dining area based on the proportion of remaining dishes in each dining area. The heat capacity value of each dining area is then compared with the baseline heat capacity value in the pre-stored full-dish state to obtain the heat capacity decay coefficient of each dining area. The edge computing node is invoked to calculate the temperature drop rate of each partition based on the temperature data of each partition and the target insulation temperature. The temperature drop rate of each partition is divided by the heat capacity decay coefficient of the corresponding dining area to obtain the thermal stability index of each dining area. The partition corresponding to the target dining area with the thermal stability index greater than the preset stability threshold is marked as the thermal compensation requirement partition. The edge computing node is invoked to calculate the heat loss compensation power of the target dining area based on the heat capacity value of the target dining area, the target insulation temperature, and the temperature data of the corresponding partition. The current heating power of the heat compensation demand partition is updated based on the heat loss compensation power so that the temperature of the heat compensation demand partition approaches the target insulation temperature.

[0007] Furthermore, after marking the partition corresponding to the target dining area with a thermal stability index greater than a preset stability threshold as a thermal compensation requirement partition, the method further includes: For zones that do not require thermal compensation, the edge computing node is invoked to calculate the maintaining heating power based on the heat capacity value of the corresponding dining area and the target insulation temperature. The current heating power of the non-heat compensation demand zone is set to the maintenance heating power so that the temperature of the non-heat compensation demand zone is stabilized at the target insulation temperature.

[0008] Preferably, updating the current heating power of the heat compensation demand zone based on the heat loss compensation power includes: The heat loss compensation power is added to the current heating power of the heat compensation demand zone to obtain the target heating power value; The target heating power value is compared with the preset power upper limit value. When the target heating power value is greater than the preset power upper limit value, the preset power upper limit value is used as the updated heating power value of the heat compensation demand zone. When the target heating power value is less than or equal to the preset power upper limit value, the target heating power value is used as the updated heating power value of the heat compensation demand zone.

[0009] Furthermore, after updating the current heating power of the heat compensation demand zone according to the heat loss compensation power so that the temperature of the heat compensation demand zone approaches the target insulation temperature, the method further includes: During the feedback cycle following the power update, the actual heating power value and temperature data of the heat compensation demand zone are fed back to the edge computing node; The edge computing node is invoked to calculate the power deviation between the actual heating power value and the target heating power value, as well as the temperature deviation between the temperature data and the target insulation temperature; The power deviation value and the temperature deviation value are multiplied to obtain a comprehensive deviation value. The comprehensive deviation value is compared with a preset coupling threshold. When the comprehensive deviation value is greater than the preset coupling threshold, it is determined that there is a power-temperature mismatch in the thermal compensation demand zone. The positive and negative signs of the power deviation value and the temperature deviation value are extracted. When the power deviation is positive and the temperature deviation is negative, the heat loss compensation power is multiplied by the first attenuation ratio coefficient to obtain the corrected heat loss compensation power. When the power deviation value is negative and the temperature deviation value is positive, the heat loss compensation power is multiplied by the first amplification ratio coefficient to obtain the corrected heat loss compensation power. When the power deviation value and the temperature deviation value have the same sign, the ratio of the power deviation value to the temperature deviation value is calculated to obtain the power-temperature response ratio. The power-temperature response ratio is compared with a preset response ratio range. When the power-temperature response ratio is greater than the upper limit of the preset response ratio range, the heat loss compensation power is multiplied by the second attenuation ratio coefficient to obtain the corrected heat loss compensation power. When the power-temperature response ratio is less than the lower limit of the preset response ratio range, the heat loss compensation power is multiplied by the second amplification ratio coefficient to obtain the corrected heat loss compensation power. The current heating power of the heat compensation demand zone is updated again based on the revised heat loss compensation power.

[0010] Preferably, the step of calling the edge computing node to calculate the heat loss compensation power of the target dining area based on the heat capacity value of the target dining area, the target insulation temperature, and the temperature data of the corresponding partition includes: The edge computing node is invoked to calculate the temperature compensation requirement of the target dining area based on the difference between the target insulation temperature and the temperature data of the corresponding partition of the target dining area; Divide the temperature compensation requirement by the heat capacity value of the target serving area to obtain the temperature compensation requirement per unit heat capacity. The heat loss compensation power is obtained by multiplying the temperature compensation requirement per unit heat capacity by a preset compensation efficiency coefficient.

[0011] Furthermore, after calculating the heat loss compensation power of the target dining area, the method further includes: The edge computing node is invoked to identify the surface condition of the food in the acquired images, and the surface condition identification results are used to determine whether there is a dry crust on the surface of the food in each serving area. When a dry, crusty surface is detected on the food surface in the target serving area, the heat loss compensation power for the target serving area is adjusted downwards to reduce the heating power of the corresponding zone in the target serving area.

[0012] Furthermore, after calculating the heat loss compensation power of the target dining area, the method further includes: The edge computing node is invoked to record the proportion of remaining food in each dining area during adjacent sampling periods, and the rate of decrease in food quantity in each dining area is calculated. When the rate of decrease of food quantity in the target serving area exceeds the preset rate of decrease, the heat loss compensation power of the target serving area is adjusted downward to reduce the heating power of the corresponding zone of the target serving area.

[0013] Preferably, the edge computing node and the remote management terminal establish a two-way data channel through an Internet of Things communication protocol. The edge computing node uploads the temperature data of each zone, the proportion of remaining food in each dining area, the heat capacity decay coefficient, and the marking status of the heat compensation requirement zone to the remote management terminal. The remote management terminal sends remote configuration parameters of the target heat preservation temperature to the edge computing node.

[0014] Furthermore, after calculating the proportion of remaining food in each serving area, the process also includes: The edge computing node is invoked to compare the proportion of remaining food in each dining area with the preset minimum proportion of remaining food. When the proportion of remaining food in the target dining area is less than the preset minimum proportion of remaining food, a low food quantity alarm signal is generated and sent to the remote management terminal through the Internet of Things gateway.

[0015] Secondly, the present invention also provides a temperature control system for a food warming oven, comprising: The data acquisition module is used to collect temperature data of each zone inside the insulated food oven by means of a temperature sensor array deployed on the inner wall of the oven cavity, and upload the temperature data to the edge computing node through an Internet of Things gateway. The extraction module is used to acquire images of the dishes in each compartment of the insulated food oven through a visual inspection device deployed on the top of the oven cavity, transmit the acquired images to the edge computing node, call the edge computing node to segment the acquired images into compartment regions, extract the outline features of the dishes in each compartment region, and calculate the proportion of remaining dishes in each compartment region based on the degree of matching between the outline features of the dishes and the pre-stored outline of the full dish state. The calculation module is used to call the edge computing node to calculate the heat capacity value of the dishes in each dining area according to the proportion of the remaining dishes in each dining area, and to perform a ratio calculation between the heat capacity value of each dining area and the baseline heat capacity value in the pre-stored full dish state to obtain the heat capacity decay coefficient of each dining area. The marking module is used to call the edge computing node to calculate the temperature drop rate of each partition based on the temperature data of each partition and the target insulation temperature, divide the temperature drop rate of each partition by the heat capacity decay coefficient of the corresponding dining area to obtain the thermal stability index of each dining area, and mark the partition corresponding to the target dining area with the thermal stability index greater than the preset stability threshold as the thermal compensation requirement partition. The update module is used to call the edge computing node to calculate the heat loss compensation power of the target dining area based on the heat capacity value of the target dining area, the target insulation temperature and the temperature data of the corresponding partition, and update the current heating power of the heat compensation demand partition according to the heat loss compensation power, so that the temperature of the heat compensation demand partition approaches the target insulation temperature.

[0016] Compared with the prior art, the technical solution of the present invention has at least the following advantages: The temperature control method and system for a heat-insulating food oven provided by this invention acquires images of the food in each serving area using a visual inspection device. An edge computing node segments the acquired images into serving areas and extracts the outline features of the food. The remaining food quantity in each serving area is calculated, and then the real-time heat capacity value of the food in each serving area is calculated based on the remaining food quantity ratio, yielding a heat capacity decay coefficient. The heat capacity decay coefficient is correlated with the temperature drop rate to obtain a thermal stability index. Based on the thermal stability index, heat compensation demand zones are identified, and heat loss compensation power is calculated and updated in a targeted manner for these zones, thereby... The quantity of food in each serving area is converted into thermal parameters, establishing a quantitative correlation between food quantity decay and changes in thermal inertia. This allows temperature control to be differentiated based on the thermal inertia of each serving area, enabling precise identification and targeted thermal compensation for areas with severe thermal inertia decay. This effectively suppresses the widening trend of temperature differences between areas caused by uneven food consumption, bringing the temperature of each area closer to the target insulation temperature. This improves the temperature uniformity of each area in the insulated food oven, while avoiding overheating in areas that do not require thermal compensation, reducing overall energy consumption, and minimizing surface drying and quality deterioration of food caused by overheating. Attached Figure Description

[0017] Figure 1 This is a flowchart of one embodiment of the temperature control method for the insulated food stove of the present invention; Figure 2 This is a schematic diagram of the structure of one embodiment of the insulated food stove of the present invention; Figure 3 This is a system block diagram of one embodiment of the temperature control system for the insulated food oven of the present invention; Figure 4 This is a structural block diagram of one embodiment of the temperature control system for the insulated food stove of the present invention. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

[0019] Please refer to Figure 1 As shown, and in combination Figure 2-3 As shown, the present invention provides a temperature control method for a food warming oven, which specifically includes the following steps: S11. By deploying a temperature sensor array on the inner wall of the insulated food oven cavity, temperature data of each zone inside the insulated food oven is collected, and the temperature data is uploaded to the edge computing node through an Internet of Things gateway; S12. Using a visual inspection device deployed on the top of the insulated food oven cavity, images of the dishes in each compartment of the insulated food oven are acquired. The acquired images are transmitted to the edge computing node. The edge computing node is called to segment the acquired images into compartments, extract the outline features of the dishes in each compartment, and calculate the proportion of remaining dishes in each compartment based on the degree of matching between the outline features of the dishes and the pre-stored outline of the full dish state. S13. Call the edge computing node to calculate the heat capacity value of the dishes in each dining area according to the proportion of the remaining dishes in each dining area, and perform a ratio calculation between the heat capacity value of each dining area and the baseline heat capacity value in the pre-stored full dish state to obtain the heat capacity decay coefficient of each dining area. S14. Call the edge computing node to calculate the temperature drop rate of each partition based on the temperature data of each partition and the target insulation temperature. Divide the temperature drop rate of each partition by the heat capacity decay coefficient of the corresponding dining area to obtain the thermal stability index of each dining area. Mark the partition corresponding to the target dining area with the thermal stability index greater than the preset stability threshold as the thermal compensation requirement partition. S15. The edge computing node is invoked to calculate the heat loss compensation power of the target dining area based on the heat capacity value of the target dining area, the target insulation temperature and the temperature data of the corresponding partition. The current heating power of the heat compensation demand partition is updated based on the heat loss compensation power so that the temperature of the heat compensation demand partition approaches the target insulation temperature.

[0020] In this embodiment, the interior of the insulated food warmer is divided into multiple heating zones, each corresponding to a serving area for different types of dishes. An array of temperature sensors is deployed on the inner wall of the insulated food warmer's cavity, with each sensor corresponding to a heating zone, synchronously collecting temperature data from each zone at a fixed sampling period. The temperature sensor array is connected to an IoT gateway via wired or wireless means, and the IoT gateway uploads the collected temperature data to an edge computing node.

[0021] In addition, a visual inspection device is deployed on the top of the insulated food warmer cavity. The lens of this device faces inward to capture top-down images of the dishes in each serving area. The visual inspection device is connected to an edge computing node via a video transmission line, transmitting the captured image data to the edge computing node.

[0022] After receiving the acquired image, the edge computing node locates the boundary position of each grid area in the acquired image according to the pre-stored grid layout template, and divides the acquired image into multiple sub-image areas corresponding to the actual grid layout of the insulated food stove. Each sub-image area corresponds to one grid area.

[0023] Then, the edge computing node performs edge detection on the sub-images of each serving area to obtain the contour line between the dish and the serving area boundary. The area enclosed by the contour line is taken as the dish contour area, and the area value of the dish contour area is calculated. The area value of the dish contour area of ​​each serving area is compared with the pre-stored contour area value of the full-dish state to obtain the proportion of remaining dishes in each serving area. The pre-stored contour area value of the full-dish state is the standard area value of the dish contour area of ​​that serving area in the full-dish state, which is calibrated and stored during system initialization.

[0024] The real-time heat capacity value of a serving area is obtained by multiplying the proportion of remaining food in that area by the pre-stored baseline heat capacity value when the area is full. The baseline heat capacity value is the heat capacity value of the food in that serving area when it is full, which is calculated and stored during system initialization based on the full weight of the food in that serving area and the specific heat capacity of the food.

[0025] After obtaining the real-time heat capacity value, the edge computing node calculates the ratio between the real-time heat capacity value and the baseline heat capacity value to obtain the heat capacity decay coefficient of each serving area. The heat capacity decay coefficient characterizes the degree of decay of the current heat capacity of the serving area relative to the heat capacity when the food is full. The smaller the heat capacity decay coefficient, the less food is in the serving area and the weaker the thermal inertia.

[0026] Edge computing nodes acquire temperature data from the current sampling period and the previous sampling period, calculate the difference between the two data points, and divide this difference by the duration of a fixed sampling period to obtain the temperature drop rate for that zone. Dividing the temperature drop rate by the heat capacity decay coefficient yields the thermal stability index for each zone. The thermal stability index indicates how quickly the temperature of a zone decreases under unit heat capacity decay. A higher thermal stability index indicates a faster temperature drop under heat capacity decay, poorer thermal stability, and a greater need for priority thermal compensation.

[0027] The edge computing nodes compare the thermal stability index of each food compartment area with a preset stability threshold. The preset stability threshold is pre-calibrated by the system based on the cavity structure of the insulated food oven, the power of the heating element, and the environmental heat dissipation conditions. When the thermal stability index of a food compartment area is greater than the preset stability threshold, the edge computing node marks the corresponding partition of that food compartment area as a partition requiring heat compensation.

[0028] After marking, the edge computing node calculates the heat loss compensation power for the heat compensation requirement zone, updates the current heating power of the heat compensation requirement zone based on the heat loss compensation power, obtains the updated heating power value, and sends the updated heating power value to the heating power adjustment unit. The heating power adjustment unit adjusts the output power of the heating element in the corresponding zone according to the updated heating power value, so that the temperature of the heat compensation requirement zone approaches the target heat preservation temperature. This allows temperature control to be differentiated according to the thermal inertia state of each serving area, achieving accurate identification and targeted heat compensation for zones with severe thermal inertia attenuation. This effectively suppresses the trend of widening temperature differences between zones caused by uneven food consumption, making the temperature of each zone approach the consistent target heat preservation temperature, improving the temperature uniformity of each zone in the heat preservation oven, and avoiding overheating of non-heat compensation requirement zones, reducing overall energy consumption, and reducing surface drying and quality deterioration of food caused by overheating.

[0029] In one embodiment, after marking the partition corresponding to the target dining area with a thermal stability index greater than a preset stability threshold as a thermal compensation requirement partition, the method further includes: For zones that do not require thermal compensation, the edge computing node is invoked to calculate the maintaining heating power based on the heat capacity value of the corresponding dining area and the target insulation temperature. The current heating power of the non-heat compensation demand zone is set to the maintenance heating power so that the temperature of the non-heat compensation demand zone is stabilized at the target insulation temperature.

[0030] In this embodiment, the edge computing node acquires the real-time heat capacity value of the corresponding dining area in the non-heat compensation demand zone, as well as the temperature data of the zone in the current sampling period. The difference between the target insulation temperature and the current temperature data is calculated to obtain the temperature maintenance deviation. The temperature maintenance deviation is divided by the real-time heat capacity value of the dining area to obtain the temperature maintenance requirement per unit heat capacity. The temperature maintenance requirement per unit heat capacity is multiplied by a preset maintenance efficiency coefficient to obtain the maintenance heating power. The preset maintenance efficiency coefficient is pre-calibrated by the system based on the insulation performance of the oven cavity, the heat conversion efficiency of the heating element, and the environmental heat dissipation conditions; its value is less than the preset compensation efficiency coefficient used in the calculation of the heat compensation demand zone.

[0031] Then, the edge computing node maintains the heating power directly set to the current heating power value of the non-heat compensation demand zone and sends this current heating power value to the heating power adjustment unit. The heating power adjustment unit adjusts the output power of the heating element in the corresponding zone according to the current heating power value, so that the temperature of the non-heat compensation demand zone is stabilized at the target insulation temperature.

[0032] In this embodiment, the power calculation for non-heat-compensated demand zones also incorporates real-time heat capacity as a denominator parameter, making the maintenance heating power value related to the food quantity status of the corresponding dining area in that zone. When the food quantity in a non-heat-compensated demand zone gradually decreases and the real-time heat capacity value drops due to continuous food consumption by diners, under the same temperature maintenance deviation, the temperature maintenance requirement per unit heat capacity increases, and the maintenance heating power increases accordingly. This allows for early adaptation to the weakening trend of thermal inertia in that zone, preventing it from rapidly falling into the state of a heat-compensated demand zone due to heat capacity decay in subsequent processes.

[0033] In one embodiment, updating the current heating power of the heat compensation demand zone based on the heat loss compensation power includes: The heat loss compensation power is added to the current heating power of the heat compensation demand zone to obtain the target heating power value; The target heating power value is compared with the preset power upper limit value. When the target heating power value is greater than the preset power upper limit value, the preset power upper limit value is used as the updated heating power value of the heat compensation demand zone. When the target heating power value is less than or equal to the preset power upper limit value, the target heating power value is used as the updated heating power value of the heat compensation demand zone.

[0034] In this embodiment, the current heating power value is the actual output power value of the partition in the previous control cycle. It is fed back to the edge computing node and stored by the heating power adjustment unit after the power adjustment of the previous cycle is completed.

[0035] The preset power limit is pre-calibrated by the system based on the rated power of the heating element of the insulated food oven, the heat resistance limit of the cavity material, and safety operation specifications. When the target heating power value exceeds the preset power limit, it is determined that there is a risk of power over-limit in the heat compensation demand zone, and the preset power limit is used as the updated heating power value for the heat compensation demand zone.

[0036] When the target heating power value is less than or equal to the preset power upper limit, the edge computing node determines that the power demand of the heat compensation zone is within a safe range. It then directly uses the target heating power value as the updated heating power value for that zone, thus avoiding overload of the heating element due to excessively high calculated heat loss compensation power. This prevents the heating element from aging or being damaged due to prolonged operation at overrated power, extending the lifespan of the heat-insulating oven. Simultaneously, the preset power upper limit constraint keeps the power output of the heat compensation zone within a controllable range, preventing deformation of the cavity material or scorching of food due to localized overheating, ensuring equipment safety and food heat preservation quality.

[0037] In one embodiment, after updating the current heating power of the heat compensation demand zone according to the heat loss compensation power to make the temperature of the heat compensation demand zone approach the target insulation temperature, the method further includes: During the feedback cycle following the power update, the actual heating power value and temperature data of the heat compensation demand zone are fed back to the edge computing node; The edge computing node is invoked to calculate the power deviation between the actual heating power value and the target heating power value, as well as the temperature deviation between the temperature data and the target insulation temperature; The power deviation value and the temperature deviation value are multiplied to obtain a comprehensive deviation value. The comprehensive deviation value is compared with a preset coupling threshold. When the comprehensive deviation value is greater than the preset coupling threshold, it is determined that there is a power-temperature mismatch in the thermal compensation demand zone. The positive and negative signs of the power deviation value and the temperature deviation value are extracted. When the power deviation is positive and the temperature deviation is negative, the heat loss compensation power is multiplied by the first attenuation ratio coefficient to obtain the corrected heat loss compensation power. When the power deviation value is negative and the temperature deviation value is positive, the heat loss compensation power is multiplied by the first amplification ratio coefficient to obtain the corrected heat loss compensation power. When the power deviation value and the temperature deviation value have the same sign, the ratio of the power deviation value to the temperature deviation value is calculated to obtain the power-temperature response ratio. The power-temperature response ratio is compared with a preset response ratio range. When the power-temperature response ratio is greater than the upper limit of the preset response ratio range, the heat loss compensation power is multiplied by the second attenuation ratio coefficient to obtain the corrected heat loss compensation power. When the power-temperature response ratio is less than the lower limit of the preset response ratio range, the heat loss compensation power is multiplied by the second amplification ratio coefficient to obtain the corrected heat loss compensation power. The current heating power of the heat compensation demand zone is updated again based on the revised heat loss compensation power.

[0038] In this embodiment, after the heating power adjustment unit completes the power update for the heat compensation demand zone, it enters the feedback cycle. The duration of the feedback cycle is dynamically determined by the edge computing node based on the heat capacity attenuation coefficient of the corresponding compartment area of ​​the heat compensation demand zone. The larger the heat capacity attenuation coefficient, the shorter the feedback cycle, so as to achieve more frequent feedback correction for zones with weak thermal inertia.

[0039] During the feedback cycle, the heating power adjustment unit feeds back the actual heating power value of the heat compensation demand zone and the temperature data of the current sampling cycle to the edge computing node. After receiving the feedback data, the edge computing node calculates the difference between the actual heating power value and the target heating power value to obtain the power deviation value. At the same time, it calculates the difference between the current temperature data and the target insulation temperature to obtain the temperature deviation value.

[0040] Subsequently, the edge computing nodes multiply the power deviation value and the temperature deviation value to obtain the comprehensive deviation value. The sign of the comprehensive deviation value is determined by the signs of the power deviation value and the temperature deviation value, and its absolute value reflects the degree of coupling deviation between power output and temperature response.

[0041] The edge computing node compares the absolute value of the overall deviation with a preset coupling threshold. This preset coupling threshold is pre-calibrated by the system based on the heating element response characteristics, cavity heat conduction characteristics, and control accuracy requirements of the insulated food oven. When the absolute value of the overall deviation exceeds the preset coupling threshold, the edge computing node determines that there is a power-temperature mismatch in the heat compensation demand zone, meaning that the expected correspondence between power output and temperature response has not been established, and iterative correction of the heat loss compensation power is required.

[0042] After determining that a power-temperature mismatch exists, the edge computing nodes extract the positive and negative signs of the power deviation value and the temperature deviation value, and then combine the two signs for judgment: When the power deviation is positive and the temperature deviation is negative, it indicates that the actual heating power is higher than the target value, but the zone temperature is lower than the target insulation temperature, meaning the power output is excessive but the temperature has not reached the expected level. At this point, the edge computing node determines that there is a power overstatement in this zone and multiplies the current heat loss compensation power by the first attenuation ratio coefficient to obtain the corrected heat loss compensation power. The first attenuation ratio coefficient is pre-calibrated by the system based on the attenuation characteristics of the heating element's thermal conversion efficiency, and its value is less than 1.

[0043] When the power deviation is negative and the temperature deviation is positive, it indicates that the actual heating power is lower than the target value, but the zone temperature is higher than the target insulation temperature, meaning the power output is insufficient but the temperature is abnormally high. At this point, the edge computing node determines that the zone has abnormal temperature feedback or thermal interference, and multiplies the current heat loss compensation power by the first amplification ratio coefficient to obtain the corrected heat loss compensation power. The first amplification ratio coefficient is pre-calibrated by the system according to the cavity thermal interference compensation requirements, and its value is greater than 1.

[0044] When the power deviation and temperature deviation values ​​have the same sign, it indicates that the power output and temperature response are in the same direction. The edge computing nodes further calculate the ratio of the power deviation to the temperature deviation to obtain the power-temperature response ratio. The power-temperature response ratio characterizes the degree of power deviation corresponding to a unit temperature deviation and reflects the power-temperature response sensitivity of the heating system in that zone.

[0045] The edge computing node compares the power-temperature response ratio with a preset response ratio range. This preset range, pre-calibrated by the system based on the rated power-temperature response characteristics of the insulated boiler, includes an upper and lower limit. When the power-temperature response ratio exceeds the upper limit of the preset range, it indicates that the power output is too sensitive to temperature changes. The edge computing node then multiplies the current heat loss compensation power by a second attenuation coefficient to obtain a corrected heat loss compensation power, thereby reducing the sensitivity of power regulation. This second attenuation coefficient, pre-calibrated by the system based on power response overshoot suppression requirements, has a value less than 1.

[0046] When the power-temperature response ratio is less than the lower limit of the preset response ratio range, it indicates that the power output is too sluggish in response to temperature changes. The edge computing node multiplies the current heat loss compensation power by a second amplification factor to obtain the corrected heat loss compensation power, thereby improving the sensitivity of power regulation. The second amplification factor is pre-calibrated by the system according to the power response lag compensation requirements, and its value is greater than 1.

[0047] Finally, the edge computing node recalculates the target heating power value based on the corrected heat loss compensation power and sends it again to the heating power adjustment unit, which then updates the current heating power of the heat compensation demand partition, completing one iteration correction.

[0048] This embodiment addresses the issue of inconsistent power output and temperature response in zones requiring thermal compensation after power updates. An iterative correction mechanism gradually converges the power adjustment to match the temperature response, preventing continuous deviations caused by single power calculation errors. Furthermore, dynamic monitoring of the power-temperature response ratio and adaptive adjustment of the proportional coefficient adapt the power adjustment sensitivity to the zone's thermal inertia. Zones with weak thermal inertia receive smoother power adjustments, while zones with strong thermal inertia receive more aggressive power adjustments, thus improving the temperature control stability of each zone under different food quantity conditions.

[0049] In one embodiment, the step of calling the edge computing node to calculate the heat loss compensation power of the target dining area based on the heat capacity value of the target dining area, the target insulation temperature, and the temperature data of the corresponding partition includes: The edge computing node is invoked to calculate the temperature compensation requirement of the target dining area based on the difference between the target insulation temperature and the temperature data of the corresponding partition of the target dining area; Divide the temperature compensation requirement by the heat capacity value of the target serving area to obtain the temperature compensation requirement per unit heat capacity. The heat loss compensation power is obtained by multiplying the temperature compensation requirement per unit heat capacity by a preset compensation efficiency coefficient.

[0050] In this embodiment, the edge computing node obtains the target insulation temperature and the current temperature data of the corresponding partition of the target dining area. The target insulation temperature is subtracted from the current temperature data to obtain the temperature compensation requirement. The temperature compensation requirement represents the absolute difference between the current temperature of the partition and the target insulation temperature. A positive value indicates that the temperature of the partition is lower than the target insulation temperature, and temperature compensation is required.

[0051] The real-time heat capacity value is the heat capacity of the target serving area under the current food quantity, calculated based on the proportion of remaining food and the baseline heat capacity value. The temperature compensation requirement per unit heat capacity represents the heat input intensity required to raise a unit heat capacity of food from its current temperature to the target insulation temperature; its value is inversely proportional to the real-time heat capacity value. When the food quantity in the target serving area is small and the real-time heat capacity value is low, the temperature compensation requirement per unit heat capacity increases accordingly, reflecting the weak thermal inertia of this area and the need for a stronger heat input intensity to achieve temperature rise.

[0052] The preset compensation efficiency coefficient is pre-calibrated by the system based on the heating element's heat conversion efficiency, cavity heat loss rate, and heat conduction efficiency of the insulated food oven. It is used to convert heat demand into actual electrical power demand. The preset compensation efficiency coefficient is greater than 1 to compensate for heat loss to the environment during heating, ensuring that the effective heat input to the food meets temperature compensation requirements. This embodiment directly links the calculation of heat loss compensation power to the real-time heat capacity value of the target dining area, avoiding the problems of insufficient compensation in low heat capacity zones or excessive compensation in high heat capacity zones caused by fixed power compensation. When a zone with heat compensation demand experiences a sharp decrease in food quantity and a significant drop in heat capacity due to continuous food consumption, the temperature compensation demand per unit heat capacity automatically increases, and the heat loss compensation power increases accordingly. This ensures that the zone can still receive sufficient heat input even under extreme thermal inertia decay, thereby suppressing the trend of further temperature decline. At the same time, the preset compensation efficiency coefficient quantifies the compensation for heat loss, making the calculated power demand closer to the actual thermal demand, reducing the deviation between the calculated power value and the actual thermal effect, and improving the accuracy of power control.

[0053] In one embodiment, after calculating the heat loss compensation power of the target dining area, the method further includes: The edge computing node is invoked to identify the surface condition of the food in the acquired images, and the surface condition identification results are used to determine whether there is a dry crust on the surface of the food in each serving area. When a dry, crusty surface is detected on the food surface in the target serving area, the heat loss compensation power for the target serving area is adjusted downwards to reduce the heating power of the corresponding zone in the target serving area.

[0054] Specifically, the edge computing node extracts texture features from the sub-images of each serving area. These extracted features include the surface roughness, gloss, and crack density of the food. The extracted texture features are then input into a pre-stored template library of dried, crusted surfaces, which contains standard texture feature samples of various foods in this state. The surface state matching value is calculated by comparing the actual texture features of each serving area with the standard texture feature samples. When the surface state matching value is greater than a preset crusting threshold, the edge computing node determines that the food surface in that serving area exhibits a dried, crusted phenomenon.

[0055] When a dry, crusty coating is detected on the surface of food in the target serving area, the current heat loss compensation power is multiplied by a preset reduction ratio coefficient to obtain the corrected heat loss compensation power. The preset reduction ratio coefficient is pre-calibrated by the system based on the temperature tolerance characteristics of various types of food in the dry, crusty state; its value is less than 1, and different types of food correspond to different preset reduction ratio coefficients. Edge computing nodes execute the correction calculation based on the corresponding preset reduction ratio coefficient according to the type of food.

[0056] This embodiment addresses the issue of overheating of food surfaces that may occur after a heat compensation zone receives power compensation. When a heat compensation zone receives a higher heat loss compensation power due to its weak thermal inertia, if the food in the corresponding serving area is already in a dry, crusted state, continuing to heat it at the original compensation power will exacerbate surface moisture evaporation, leading to a worsening of the crust and even scorching. Therefore, by visually identifying the dry, crusted phenomenon and adjusting the compensation power accordingly, a balance is struck between meeting temperature compensation requirements and protecting the surface quality of the food, avoiding the dilemma of sacrificing food quality for achieving the desired temperature.

[0057] In one embodiment, after calculating the heat loss compensation power of the target dining area, the method further includes: The edge computing node is invoked to record the proportion of remaining food in each dining area during adjacent sampling periods, and the rate of decrease in food quantity in each dining area is calculated. When the rate of decrease of food quantity in the target serving area exceeds the preset rate of decrease, the heat loss compensation power of the target serving area is adjusted downward to reduce the heating power of the corresponding zone of the target serving area.

[0058] In this embodiment, the edge computing node retrieves the proportion of remaining food quantity in each food compartment stored in the local cache during the previous sampling period, and performs a difference calculation with the proportion of remaining food quantity calculated in the current sampling period to obtain the change in food quantity for each food compartment. Dividing the change in food quantity by the fixed duration between adjacent sampling periods yields the rate of decrease in food quantity for each food compartment. A positive rate of decrease indicates that the food quantity in that food compartment is decreasing, while a negative rate indicates that the food quantity is increasing.

[0059] The edge computing node compares the rate of food quantity decrease in the target serving area with a preset rate of decrease. The preset rate of decrease is pre-calibrated by the system based on the characteristics of the food supply period of the insulated food oven and the food consumption pattern, representing the critical state of rapid food quantity decay. When the rate of food quantity decrease in the target serving area is greater than the preset rate of decrease, the edge computing node determines that the target serving area is in a rapid food consumption state, and the heat capacity value of the food in the corresponding area will continue to decrease in subsequent sampling periods, further weakening thermal inertia.

[0060] Under this condition, the edge computing node adjusts the heat loss compensation power for the target serving area. Specifically, the current heat loss compensation power is multiplied by a preset reduction ratio coefficient to obtain the corrected heat loss compensation power. The preset reduction ratio coefficient is pre-calibrated by the system based on the predicted characteristics of the heat capacity decay of dishes under rapid food retrieval conditions. Its value is less than 1 and greater than the preset reduction ratio coefficient used for dry skin correction, in order to distinguish the correction intensity of the two different correction scenarios.

[0061] In this embodiment, when a heat compensation zone experiences a sharp decrease in food quantity due to concentrated food collection by diners, if the heat loss compensation power calculated based on the current heat capacity value continues to be output, the original compensation power will far exceed the actual heat demand as the food quantity and heat capacity value further decrease in subsequent cycles, leading to temperature overshoot and energy waste in the zone. Therefore, by dynamically monitoring the rate of food quantity decrease and adjusting the compensation power in advance, the power output is synchronized with the trend of heat capacity change. The compensation intensity is gradually reduced during the heat capacity decay process, achieving smooth tracking of food quantity changes by power regulation. Simultaneously, the preset slow-descent ratio coefficient is differentiated from the preset reduction ratio coefficient for drying and crusting correction, creating a differentiated correction strategy for rapid food collection correction and quality protection correction. This avoids confusion in power adjustment under the two correction scenarios, improving the targeting and accuracy of power correction.

[0062] In one embodiment, the edge computing node and the remote management terminal establish a two-way data channel through an Internet of Things (IoT) communication protocol. The edge computing node uploads the temperature data of each zone, the proportion of remaining food in each dining area, the heat capacity decay coefficient, and the marking status of the heat compensation requirement zone to the remote management terminal. The remote management terminal sends remote configuration parameters for the target heat preservation temperature to the edge computing node.

[0063] The IoT communication protocol uses a lightweight message transmission protocol, with edge computing nodes acting as message publishers and remote management terminals acting as message subscribers. Asynchronous data interaction between the two is achieved through a message broker server.

[0064] Edge computing nodes encapsulate the temperature data of each zone, the proportion of remaining food in each serving area, the heat capacity decay coefficient, and the marking status of the heat compensation requirement zone into structured data packets, and send them to the remote management terminal according to a fixed reporting cycle or event triggering method. The remote management terminal receives and parses the data packets, and displays the real-time food quantity status, heat capacity decay degree, and heat compensation requirement identifier of each serving area in the management interface, allowing managers to grasp the operating status of the insulated food oven.

[0065] When the remote management terminal sends remote configuration parameters for the target insulation temperature to the edge computing node, the administrator inputs the target insulation temperature setting through the management interface. The remote management terminal encapsulates the setting value into a configuration command message and forwards it to the edge computing node through a message broker server. After receiving the configuration command message, the edge computing node parses the target insulation temperature setting value, replaces the currently stored target insulation temperature with this setting value, and uses the updated target insulation temperature as the benchmark value for temperature regulation in subsequent control cycles. This enables the temperature control of the insulated food oven to have both edge autonomy and remote controllability. Administrators can monitor the food quantity status and heat compensation requirements of each zone without being physically present at the equipment site, improving the operation and maintenance efficiency of the insulated food oven. Simultaneously, the remote visualization of the heat compensation requirement zone marking status allows administrators to promptly identify zones with abnormal food quantity decay or abnormal temperature regulation.

[0066] In one embodiment, after calculating the proportion of remaining food in each serving area, the method further includes: The edge computing node is invoked to compare the proportion of remaining food in each dining area with the preset minimum proportion of remaining food. When the proportion of remaining food in the target dining area is less than the preset minimum proportion of remaining food, a low food quantity alarm signal is generated and sent to the remote management terminal through the Internet of Things gateway.

[0067] The preset minimum remaining food quantity ratio is pre-defined by the system based on the capacity of the insulated food oven's compartments, food placement guidelines, and replenishment strategy. This ratio represents the critical food quantity level at which a replenishment alert needs to be triggered for that compartment. When the remaining food quantity ratio of a target compartment is less than the preset minimum remaining food quantity ratio, the edge computing node determines that the target compartment is in a low food quantity state and generates a low food quantity alarm signal. The low food quantity alarm signal includes the identifier information of the target compartment, the current remaining food quantity ratio, and the alarm generation timestamp.

[0068] Edge computing nodes encapsulate low food quantity alarm signals into alarm messages and send them to remote management terminals via IoT gateways. Upon receiving the alarm message, the remote management terminal displays a low food quantity alarm icon in the corresponding food compartment area on the management interface. Managers can then replenish the food in the corresponding food compartment area in a timely manner based on the low food quantity alarm signal.

[0069] Please refer to Figure 4 As shown, embodiments of the present invention also provide a temperature control system for a food warmer, specifically including: The acquisition module 11 is used to acquire temperature data of each zone inside the insulated food oven by means of a temperature sensor array deployed on the inner wall of the oven cavity, and upload the temperature data to the edge computing node through an Internet of Things gateway; Extraction module 12 is used to acquire images of dishes in each compartment of the insulated food oven through a visual detection device deployed on the top of the oven cavity, transmit the acquired images to the edge computing node, call the edge computing node to segment the acquired images into compartment regions, extract the outline features of dishes in each compartment region, and calculate the proportion of remaining dishes in each compartment region based on the matching degree of the outline features of dishes with the pre-stored full-dish state outline. The calculation module 13 is used to call the edge computing node to calculate the heat capacity value of the dishes in each dining area according to the proportion of the remaining dishes in each dining area, and to perform a ratio calculation between the heat capacity value of each dining area and the baseline heat capacity value in the pre-stored full dish state to obtain the heat capacity decay coefficient of each dining area. The marking module 14 is used to call the edge computing node to calculate the temperature drop rate of each partition based on the temperature data of each partition and the target insulation temperature, divide the temperature drop rate of each partition by the heat capacity decay coefficient of the corresponding dining area to obtain the thermal stability index of each dining area, and mark the partition corresponding to the target dining area with the thermal stability index greater than the preset stability threshold as the thermal compensation requirement partition. Update module 15 is used to call the edge computing node to calculate the heat loss compensation power of the target dining area based on the heat capacity value of the target dining area, the target insulation temperature and the temperature data of the corresponding partition, and update the current heating power of the heat compensation demand partition based on the heat loss compensation power so that the temperature of the heat compensation demand partition approaches the target insulation temperature.

[0070] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0071] In one embodiment, the present invention also provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the temperature control method of the above-described food warming oven. The storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, or optical data storage device, etc.

[0072] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a storage medium, and when executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0073] It should be noted that the technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments have been described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A temperature control method for a food warming stove, characterized in that, include: Temperature data of each zone inside the insulated food oven is collected by an array of temperature sensors deployed on the inner wall of the oven cavity, and the temperature data is uploaded to the edge computing node through an Internet of Things gateway. A visual inspection device deployed on the top of the insulated food oven cavity is used to collect images of the dishes in each compartment of the insulated food oven. The collected images are transmitted to the edge computing node, which is then used to segment the collected images into compartments and extract the outline features of the dishes in each compartment. Based on the degree of matching between the outline features of the dishes and the pre-stored outline of a full food state, the proportion of remaining dishes in each compartment is calculated. The edge computing node is invoked to calculate the heat capacity value of the dishes in each dining area based on the proportion of remaining dishes in each dining area. The heat capacity value of each dining area is then compared with the baseline heat capacity value in the pre-stored full-dish state to obtain the heat capacity decay coefficient of each dining area. The edge computing node is invoked to calculate the temperature drop rate of each partition based on the temperature data of each partition and the target insulation temperature. The temperature drop rate of each partition is divided by the heat capacity decay coefficient of the corresponding dining area to obtain the thermal stability index of each dining area. The partition corresponding to the target dining area with the thermal stability index greater than the preset stability threshold is marked as the thermal compensation requirement partition. The edge computing node is invoked to calculate the heat loss compensation power of the target dining area based on the heat capacity value of the target dining area, the target insulation temperature, and the temperature data of the corresponding partition. The current heating power of the heat compensation demand partition is updated based on the heat loss compensation power so that the temperature of the heat compensation demand partition approaches the target insulation temperature.

2. The temperature control method for the heat-insulating stove according to claim 1, characterized in that, After marking the partition corresponding to the target dining area with a thermal stability index greater than a preset stability threshold as a thermal compensation requirement partition, the method further includes: For zones that do not require thermal compensation, the edge computing node is invoked to calculate the maintaining heating power based on the heat capacity value of the corresponding dining area and the target insulation temperature. The current heating power of the non-heat compensation demand zone is set to the maintenance heating power so that the temperature of the non-heat compensation demand zone is stabilized at the target insulation temperature.

3. The temperature control method for the heat-insulating stove according to claim 1, characterized in that, The step of updating the current heating power of the heat compensation demand zone based on the heat loss compensation power includes: The heat loss compensation power is added to the current heating power of the heat compensation demand zone to obtain the target heating power value; The target heating power value is compared with the preset power upper limit value. When the target heating power value is greater than the preset power upper limit value, the preset power upper limit value is used as the updated heating power value of the heat compensation demand zone. When the target heating power value is less than or equal to the preset power upper limit value, the target heating power value is used as the updated heating power value of the heat compensation demand zone.

4. The temperature control method for the insulated food stove according to claim 3, characterized in that, After updating the current heating power of the heat compensation demand zone according to the heat loss compensation power, so that the temperature of the heat compensation demand zone approaches the target insulation temperature, the method further includes: During the feedback cycle following the power update, the actual heating power value and temperature data of the heat compensation demand zone are fed back to the edge computing node; The edge computing node is invoked to calculate the power deviation between the actual heating power value and the target heating power value, as well as the temperature deviation between the temperature data and the target insulation temperature; The power deviation value and the temperature deviation value are multiplied to obtain a comprehensive deviation value. The comprehensive deviation value is compared with a preset coupling threshold. When the comprehensive deviation value is greater than the preset coupling threshold, it is determined that there is a power-temperature mismatch in the thermal compensation demand zone. The positive and negative signs of the power deviation value and the temperature deviation value are extracted. When the power deviation is positive and the temperature deviation is negative, the heat loss compensation power is multiplied by the first attenuation ratio coefficient to obtain the corrected heat loss compensation power. When the power deviation value is negative and the temperature deviation value is positive, the heat loss compensation power is multiplied by the first amplification ratio coefficient to obtain the corrected heat loss compensation power. When the power deviation value and the temperature deviation value have the same sign, the ratio of the power deviation value to the temperature deviation value is calculated to obtain the power-temperature response ratio. The power-temperature response ratio is compared with a preset response ratio range. When the power-temperature response ratio is greater than the upper limit of the preset response ratio range, the heat loss compensation power is multiplied by the second attenuation ratio coefficient to obtain the corrected heat loss compensation power. When the power-temperature response ratio is less than the lower limit of the preset response ratio range, the heat loss compensation power is multiplied by the second amplification ratio coefficient to obtain the corrected heat loss compensation power. The current heating power of the heat compensation demand zone is updated again based on the revised heat loss compensation power.

5. The temperature control method for the heat-insulating stove according to claim 1, characterized in that, The step of calling the edge computing node to calculate the heat loss compensation power of the target dining area based on the heat capacity value of the target dining area, the target insulation temperature, and the temperature data of the corresponding zone includes: The edge computing node is invoked to calculate the temperature compensation requirement of the target dining area based on the difference between the target insulation temperature and the temperature data of the corresponding partition of the target dining area; Divide the temperature compensation requirement by the heat capacity value of the target serving area to obtain the temperature compensation requirement per unit heat capacity. The heat loss compensation power is obtained by multiplying the temperature compensation requirement per unit heat capacity by a preset compensation efficiency coefficient.

6. The temperature control method for the heat-insulating stove according to claim 1, characterized in that, After calculating the heat loss compensation power of the target dining area, the method further includes: The edge computing node is invoked to identify the surface condition of the food in the acquired images, and the surface condition identification results are used to determine whether there is a dry crust on the surface of the food in each serving area. When a dry, crusty surface is detected on the food surface in the target serving area, the heat loss compensation power for the target serving area is adjusted downwards to reduce the heating power of the corresponding zone in the target serving area.

7. The temperature control method for the heat-insulating stove according to claim 1, characterized in that, After calculating the heat loss compensation power of the target dining area, the method further includes: The edge computing node is invoked to record the proportion of remaining food in each dining area during adjacent sampling periods, and the rate of decrease in food quantity in each dining area is calculated. When the rate of decrease of food quantity in the target serving area exceeds the preset rate of decrease, the heat loss compensation power of the target serving area is adjusted downward to reduce the heating power of the corresponding zone of the target serving area.

8. The temperature control method for the heat-insulating stove according to claim 1, characterized in that, The edge computing node and the remote management terminal establish a two-way data channel through the Internet of Things communication protocol. The edge computing node uploads the temperature data of each zone, the proportion of remaining food in each dining area, the heat capacity decay coefficient, and the marking status of the heat compensation requirement zone to the remote management terminal. The remote management terminal sends remote configuration parameters of the target heat preservation temperature to the edge computing node.

9. The temperature control method for the heat-insulating stove according to claim 1, characterized in that, After calculating the proportion of remaining food in each serving area, the method further includes: The edge computing node is invoked to compare the proportion of remaining food in each dining area with the preset minimum proportion of remaining food. When the proportion of remaining food in the target dining area is less than the preset minimum proportion of remaining food, a low food quantity alarm signal is generated and sent to the remote management terminal through the Internet of Things gateway.

10. A temperature control system for a food warmer, characterized in that, include: The data acquisition module is used to collect temperature data of each zone inside the insulated food oven by means of a temperature sensor array deployed on the inner wall of the oven cavity, and upload the temperature data to the edge computing node through an Internet of Things gateway. The extraction module is used to acquire images of the dishes in each compartment of the insulated food oven through a visual inspection device deployed on the top of the oven cavity, transmit the acquired images to the edge computing node, call the edge computing node to segment the acquired images into compartment regions, extract the outline features of the dishes in each compartment region, and calculate the proportion of remaining dishes in each compartment region based on the degree of matching between the outline features of the dishes and the pre-stored outline of the full dish state. The calculation module is used to call the edge computing node to calculate the heat capacity value of the dishes in each dining area according to the proportion of the remaining dishes in each dining area, and to perform a ratio calculation between the heat capacity value of each dining area and the baseline heat capacity value in the pre-stored full dish state to obtain the heat capacity decay coefficient of each dining area. The marking module is used to call the edge computing node to calculate the temperature drop rate of each partition based on the temperature data of each partition and the target insulation temperature, divide the temperature drop rate of each partition by the heat capacity decay coefficient of the corresponding dining area to obtain the thermal stability index of each dining area, and mark the partition corresponding to the target dining area with the thermal stability index greater than the preset stability threshold as the thermal compensation requirement partition. The update module is used to call the edge computing node to calculate the heat loss compensation power of the target dining area based on the heat capacity value of the target dining area, the target insulation temperature and the temperature data of the corresponding partition, and update the current heating power of the heat compensation demand partition according to the heat loss compensation power, so that the temperature of the heat compensation demand partition approaches the target insulation temperature.

Images