Microwave ovens, which heat food using 2.45 GHz microwaves, are widely used as a familiar electromagnetic cooking device because of their convenience, but there is room for improvement, such as uneven warming caused by uneven distribution of the electric field inside the food. This study aims at a heating design that realizes control of the electric field distribution in the heating chamber by inverse analysis based on machine learning using numerical analysis results. This paper discusses the construction of PINNs (Physics-Informed Neural Networks), which has attracted attention in recent years, and its application to electromagnetic field system inverse analysis.
Ohnaka et al. (Wed,) studied this question.