Adaptive Linear Movement Oven With Localized Gradient Real Time Temperature Control For Precision Cooking

Abstract: FIELD OF INVENTION [001] This invention resides within the domain of Food Processing, specifically Cooking Appliances. It leverages Artificial Intelligence and advanced sensor technology, including a RGB camera and a thermal sensor, to enable real-time monitoring and adaptive control of the cooking process. BACKGROUND OF THE INVENTION [002] Traditional ovens often rely on static heating and manual intervention, leading to inconsistent cooking results, energy losses, and suboptimal food quality. While some ovens incorporate basic sensors, these systems lack the sophistication to adapt to the dynamic changes occurring during the cooking process. Existing ovens lack localized gradient-based heat control mechanisms and adaptive linear movement. Existing solutions, such as those utilizing simple temperature sensors or relying solely on timer-based controls, fall short in achieving precise and consistent cooking outcomes across various food types and sizes. [003] Basic Sensor-Equipped Ovens: These ovens utilize rudimentary sensors, such as simple temperature probes, to monitor internal temperatures. However, they lack the ability to adapt cooking parameters in real-time based on the dynamic changes observed during the cooking process. [004] Timer-Based Ovens: These conventional ovens rely on fixed cooking times, often leading to overcooked or undercooked food due to variations in food density, size, and initial temperature. [005] AI-Powered Cooking Systems:Some emerging systems incorporate AI for recipe suggestions and basic cooking parameter adjustments, they often lack the advanced sensor integration and adaptive movement mechanisms found in this invention. While existing AI-powered cooking systems incorporate sensor-based monitoring, they fail to integrate a localized temperature gradient-controlled adaptive movement system. Traditional ovens rely solely on rotational plates, which often result in uneven heat distribution, leading to overcooked or undercooked food portions. The disclosed invention addresses these inefficiencies by integrating real-time AI-driven temperature-based control, ensuring optimized heat exposure across all food surfaces. [006] This background highlights the limitations of existing cooking technologies and sets the stage for the innovative approach presented in this invention. OBJECTIVE OF THE INVENTION [007] The primary objective of this invention is a mechanized rotating plate with linear movement, guided by AI algorithms to ensure even and precise cooking by dynamically adjusting its position based on localized temperature gradients. [008] Another objective of this invention is to revolutionize home cooking by minimizing user intervention and maximizing cooking consistency and quality. This is achieved through AI-powered control mechanisms that dynamically adjust cooking parameters based on real-time sensor data. [009] By incorporating an RGB camera and a thermal sensor within the cooking cavity, the system continuously monitors the food's appearance and internal temperature. This real-time data is then processed by an AI algorithm to dynamically adjust cooking parameters, including power levels, cooking time, and the movement of a mechanized rotating plate. [010] This innovative approach, featuring adaptive linear movement of the plate based on localized temperature gradients, ensures even and precise cooking across all portions of the food, minimizing overcooking or undercooking. [011] This invention aims to provide a superior cooking experience that is both convenient and efficient, while delivering consistently high-quality results. SUMMARY OF THE INVENTION [012] The following summary is provided to facilitate a clear understanding of the new features in the disclosed embodiment and it is not intended to be a full, detailed description. A detailed description of all the aspects of the disclosed invention can be understood by reviewing the full specification, the drawing and the claims and the abstract, as a whole. [013] This invention introduces an Adaptive Linear Movement Oven that revolutionizes home cooking through AI-powered precision and control. [014] The oven incorporates an RGB camera and a thermal sensor to continuously monitor the food's appearance and internal temperature. This real-time data is analyzed by an AI algorithm, which dynamically adjusts cooking parameters, including power levels, cooking time, and the movement of a mechanized rotating plate. [015] The key innovation lies in the adaptive linear movement of the plate, which is precisely controlled based on localized temperature gradients detected by the thermal sensor. This ensures even and precise cooking across all portions of the food, minimizing overcooking or undercooking. [016] This technology enhances the cooking experience by minimizing user intervention, optimizing cooking efficiency, and delivering consistently high-quality results. This invention introduces a first-of-its-kind AI-powered oven that dynamically adjusts the movement of a linearly adaptive rotating plate based on localized thermal gradients. Unlike prior systems that rely on static or rotational movement, the integrated AI module continuously monitors real-time food texture, color, and internal temperature, making autonomous cooking decisions. This innovation optimizes heat distribution, reduces energy consumption, and enhances cooking consistency. BRIEF DESCRIPTION OF THE DRAWINGS [017] The manner in which the present invention is formulated is given a more particular description below, briefly summarized above, may be had by reference to the components, some of which is illustrated in the appended drawing It is to be noted; however, that the appended drawing illustrates only typical embodiments of this invention and are therefore should not be considered limiting of its scope, for the system may admit to other equally effective embodiments. [018] Throughout the drawings, the same drawing reference numerals will be understood to refer to the same elements and features. [019] The features and advantages of the present invention will become more apparent from the following detailed description a long with the accompanying figures, which forms a part of this application and in which: [020] Fig 1: Shows Adaptive Linear Movement Oven with localized gradient real-time temperature control; [021] Fig. 2: Shows prototype (POC) of Adaptive Linear Movement Oven with localized gradient real-time temperature control; and [022] Fig. 3: Diagram showing temperature vs time plot for testing proposed oven, in accordance with our present invention. DETAILED DESCRIPTION OF THE INVENTION [023] The principles of operation, design configurations and evaluation values in these non-limiting examples can be varied and are merely cited to illustrate at least one embodiment of the invention, without limiting the scope thereof. [024] The embodiments disclosed herein can be expressed in different forms and should not be considered as limited to the listed embodiments in the disclosed invention. The various embodiments outlined in the subsequent sections are constructed such that it provides a complete and a thorough understanding of the disclosed invention, by clearly describing the scope of the invention, for those skilled in the art. [025] Throughout this specification various indications have been given as to preferred and alternative embodiments of the invention. It should be understood that it is the appended claims, including all equivalents, which are intended to define the spirit and scope of this invention. [026] This invention introduces an innovative Adaptive Linear Movement Oven that revolutionizes home cooking through AI-powered precision and control. At the heart of this system lies a innovative integration of sensors, including an RGB camera for capturing visual data and a thermal sensor for monitoring internal temperatures. These sensors work in tandem to provide real-time insights into the cooking process. The captured data is then analyzed by an AI algorithm, which dynamically adjusts critical cooking parameters such as power levels, cooking time, and, most significantly, the movement of a mechanized rotating plate. The AI model applies convolutional neural networks (CNN) for image classification, image processing and reinforcement learning algorithms for temperature-based movement adaptation. [027] The key innovation lies in the adaptive linear movement of this rotating plate. Unlike traditional ovens that rely solely on rotational movement, this system introduces precise linear control. The main controller, driven by the AI algorithm, guides the plate's movement based on localized temperature gradients detected by the thermal sensor. The rotating plate is mounted on a servo-controlled linear actuator, which repositions the food dynamically based on real-time thermal gradients. This ensures that undercooked areas are consistently exposed to optimal cooking energy (microwave, infrared, other heating means etc.), resulting in even and precise cooking across the entire food item. The RGB camera, meanwhile, captures high-resolution images throughout the cooking process, allowing the AI algorithm to analyze visual cues such as color changes, texture variations, and the presence of smoke. This visual information, combined with the thermal data, provides a comprehensive understanding of the food's state and guides the system in making real-time adjustments to the cooking process. [028] The system's intelligence extends beyond basic sensor readings. The AI algorithm continuously learns and adapts based on past cooking experiences. By analyzing historical data from previous cooking sessions, the system can refine future cooking processes for similar food types, enhancing consistency and precision. The system stores previous cooking profiles and continuously refines the temperature-movement relationship, making each cycle more precise. This adaptive learning capability ensures that the oven becomes increasingly adept at achieving optimal cooking results over time. [029] Furthermore, this innovative oven enhances the user experience through a range of advanced features. A connectivity module enables real-time monitoring and control of the cooking process via mobile devices, allowing users to remotely track progress, adjust parameters, and even receive notifications when the food is ready. Voice control integration provides a convenient hands-free interface, allowing users to interact with the oven using simple voice commands. [030] Beyond core cooking functions, the oven incorporates additional safety and convenience features. A humidity sensor monitors the moisture levels within the cavity, enabling the system to adjust cooking parameters to achieve desired levels of crispiness for various food types. A smoke detector acts as a safety measure, alerting the user and automatically adjusting cooking settings to prevent overcooking and potential fire hazards. [031] This invention represents a significant advancement in home cooking technology. By combining advanced sensor technology, sophisticated AI algorithms, and a novel system of adaptive linear movement, this oven delivers unprecedented levels of precision, efficiency, and convenience. [032] It empowers users to achieve consistently high-quality cooking results with minimal effort, while enhancing the overall cooking experience. Experimental validation results: Tests Conducted: • Validation of food recognition accuracy using the digital camera and AI model. • Temperature monitoring and control tests with the thermal sensor. • Performance testing of the rotating plate's linear movement for even cooking. • Connectivity tests for real-time updates and remote control. Results: • High accuracy in food recognition and classification. • Consistent temperature control and cooking results. The thermal sensor effectively monitored temperature gradients, ensuring consistent cooking results. • Effective distribution of microwave energy for even cooking. The rotating plate's linear movement demonstrated superior cooking uniformity compared to traditional ovens. • Reliable connectivity and user interface for remote monitoring. Parameter Traditional Ovens AI-Powered Oven (Proposed) Cooking Time Reduction 0% 18% Faster Energy Savings 0% 10-15% Lower Consumption Cooking Evenness ±10°C ±2°C Precision Detailed Experimental Results and Discussion: Initialization of thermal camera and Testing: [033] Thermal imaging camera measures radiated infrared energy and convert the data to corresponding maps of temperatures. A true thermal image is a grey scale image with hot items shown in white and cold items in black. In such images, temperatures between the two extremes are shown as gradients of grey. The thermal imaging camera used can add color, which is artificially generated by the camera's video enhancement electronics, based upon the thermal attributes seen by the camera. Cool tones (blue and purple) are cooler temperatures, and warmer tones (yellow, red) are warmer temperatures. [034] The thermal camera uses Bi-cubical interpolation to make 64 pixels look like many more. In image processing, bicubic interpolation is often chosen over bilinear or nearest-neighbor interpolation in image resampling, when speed is not an issue. In contrast to bilinear interpolation, which only takes 4 pixels (2×2) into account, bicubic interpolation considers 16 pixels (4×4). Images resampled with bicubic interpolation are smoother and have fewer interpolation artefacts. [035] The thermal camera also provides temperature data at each image pixel. It uses an 8 x 8 array of pixels, meaning temperature reading of 64 different points can be obtained. Cursors can be positioned on each point, and the corresponding temperature is read out on the screen or display. For testing, we used a small-sized pizza of 5”. Took readings and image data after successive intervals of 15 seconds while heating it inside a microwave oven. Table 1 shows the successive thermographs obtained for a small-sized pizza after an interval of 15 seconds. [036] Table 1 Acquired thermographs at different time intervals for a test oven [037] A graph of the results (Fig. 1) obtained while testing the setup to generate various thermographs can be plotted. It can help in understanding the dependency of temperature on time in the case of a microwave oven. [038] Implementation and Validation of the algorithm: [039] The proposed algorithm for the setup works on two conditions: [040] Temperature: The thermal camera gives output in the form of an array (8 x 8) of 64 pixels which gives 64 temperature values across the whole region or projected area. A matrix of 64 elements formed is solved by using bi-cubical interpolation in order to obtain a single approximate value of temperature across the projected area. This acquired temperature is then compared with the set-point temperatures of the specific food item to be cooked. This is done according to the autocook routines already embedded inside the microwave oven control scheme. If the acquired temperature goes above the set-point temperature (1st condition), then the heating power will cut off based on the 2nd condition. [041] Thermograph area covered with red color: Another output that we can derive from a thermal camera is in the form of a heat-map or thermography. This heat map shows the regions in red colour where the set-point temperature is achieved or crossed. It shows that the percentage of a region covered by a circular object pizza in shape, also the utensil for making pancakes and noodles is circular in shape. Hence, by fixing these parameters we can easily apply the control algorithm based on the area. For neglecting the irregularities in shape and tolerances in size we have used the cut-off area as 75% percent rather than 78.54%. When an area percentage of 75 is crossed by the red region inside a square shape projected region, the control algorithm will switch-off the heating of food if both the conditions 1 and 2 are met simultaneously. The tests conducted validate the algorithm. [042] Testing on the prototype: [043] The working prototype for realization of working of the microwave oven mounted with a thermal camera is built. The prototype walls are made up of a high-gloss white acrylic plastic material. The heating element used for creating an effect of cooking is a wired heat bed. A LED strip is employed inside the cavity to illuminate the cooking area. This helps the standard camera to recognize the food item better. The two cameras are fixed on the top, one next to another to capture respective images. A cabinet door supported by hinges is used to provide access for placing and removing food items. A handle is fixed on the front door, to hold the while opening and closing. A magnetic stopper is also used to keep the door in a closed position. [044] The testing of the prototype as shown in Table 2 is done starting from room temperature i.e. nearly 25 degrees Celsius. The upper limit for temperature is set to 50-degree Celsius so that the prototype body and items in contact with the heat bed do not get affected by the heat. The temperature readings and thermographs are taken after an interval of every 10 seconds. The thermograph at the beginning shows violet colour and then slowly moves from dark blue to light blue to finally a greener shade. Then the colours after 70 seconds move from yellow to slight orange and finally reach red. The colours on the periphery remain on the cooler side so violet and blue are prevalent on the periphery of the food item. While we can see hotter colour tones towards the inner regions. After some time, the colours become more uniform in their spread and better thermographic data can be inferred from the analysis. Table 2 Acquired thermographs at different time intervals for the prototype S. No. Thermographs Time(t) [in seconds] Temperature(T) [in oC] 1. t = 0 T = 25 2. t = 10 T = 25.06 3. t = 20 T = 25.16 4. t = 30 T = 25.36 5. t = 40 T = 25.62 6. t = 50 T = 26 7. t = 60 T = 26.4 8. t = 70 T = 26.9 9. t = 80 T = 27.5 10. t = 90 T = 28.2 11. t = 100 T = 28.9 12. t = 110 T = 29.8 13. t = 120 T = 30.8 14. t = 130 T = 31.82 15. t = 140 T = 32.85 16. t = 150 T = 34 17. t = 160 T = 35.2 18. t = 170 T = 36.5 19. t = 180 T = 37.82 20. t = 190 T = 39.2 21. t = 200 T = 41 22. t = 210 T = 42.6 23. t = 220 T = 44.3 24. t = 230 T = 46.1 25. t = 240 T = 48 26. t = 250 T = 50.25 [045] From the above collection of thermographs, it can be inferred that the heating is not uniform in the first 40 seconds of the experimental testing. While it starts to shift towards uniformity in distribution of heat over the area in the subsequent seconds of heating. The green region starts to show up in 20 seconds of testing at 25.16 oC and covers predominantly the area at 25.62 oC.The yellow region of heating starts to show in 70 seconds of heating at temperature reading of 26.9. After this temperature, the thermographs again become slightly non-uniform and the peripheral region starts to heat more than the inner one.

Patent Information

Applicants

Inventors

Specification

Documents

Application Documents