Oven with machine learning based algorithm selection strategy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional microwave ovens are limited in their ability to control energy application, leading to inefficient cooking due to indiscriminate energy distribution and poor penetration of radiation, which can result in suboptimal cooking results, especially when trying to brown food.
Innovation Solution
An oven equipped with a solid-state EM energy system and control electronics that employ adaptive algorithms, allowing for real-time feedback and dynamic adjustment of EM energy application based on the food's properties and cooking conditions, enabling more precise and efficient cooking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If conventional microwave cooking is used to speed up the cooking process, then cooking time is reduced, but the ability to brown food and control energy application is lost
Solution Approach 1:
The system dynamically switches between different cooking algorithms (microwave, convection, combination) based on real-time feedback from sensors monitoring food temperature and cooking progress. This allows the oven to adapt energy application methods during cooking, maintaining both speed and control.
Solution Approach 2:
The oven incorporates sensors that continuously monitor cooking conditions and provide feedback to the control system. This feedback enables the system to adjust energy application in real-time, selecting appropriate algorithms to achieve browning while maintaining efficient cooking times.
2Productivity
If microwave energy is applied indiscriminately to cook food quickly, then cooking speed increases, but penetration of radiation into the food product becomes insufficient
Solution Approach 1:
The cooking process is divided into multiple stages with different energy application strategies. The system segments the cooking cycle to apply microwave energy for rapid heating followed by convection or combination modes for improved penetration and browning, ensuring both speed and thoroughness.
Solution Approach 2:
The system changes physical parameters of energy application by switching between different cooking algorithms that vary power levels, frequency, and energy type. This allows optimization of both cooking speed and radiation penetration depth based on food properties and cooking stage.
3Adaptability or versatility
If a combination of microwave and hot airflow is used to achieve browning, then browning capability is improved, but the limitations of microwave penetration remain
Solution Approach 1:
The system maintains continuous monitoring and adjustment of energy application throughout the cooking process. By continuously switching between microwave and convection modes based on real-time feedback, the oven ensures both browning capability and adequate penetration are maintained throughout cooking.
Solution Approach 2:
The oven employs a composite cooking approach combining multiple energy sources (microwave and convection) in a coordinated manner. This composite energy application method leverages the strengths of each source while compensating for their individual limitations, achieving both browning and penetration.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This solution allows for improved cooking performance and operator experience by ensuring uniform heating and optimal energy delivery, even as food properties change during cooking, enhancing the ability to achieve desired cooking outcomes such as browning.
Implementation Method 1
an EM heating system configured to provide EM energy into the cooking chamber using solid state electronic components
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An oven may include a cooking chamber configured to receive a food product, an EM heating system configured to provide EM energy into the cooking chamber using solid state electronic components, and control electronics configured to control the EM heating system. The control electronics are configured to enable user selection of a cooking program associated with cooking the food product. The control electronics select a first algorithm to direct application of the EM energy to the food product. The control electronics perform a learning process to receive feedback on execution of the cooking program during execution of the cooking program according to the first algorithm. Responsive to detecting a trigger event during the learning process, the control electronics are configured to select a second algorithm that is different from the first algorithm to direct application of the EM energy to the food product during execution of the cooking program.