Physics-informed neural network for simulating magnetic field of coaxial magnetic gear

In the process of performance analysis and structure optimization of coaxial magnetic gear, an emerging method for precise magnetic field simulation remains a focal point in engineering research. In this study, we introduce a physics-informed neural network to model the magnetic field of a magnetic gear. We employed a physics-based loss function to optimize neural network parameters to solve the magnetic field of a Maxwell-controlled magnetic gear. Additionally, we developed a joint training model that leverages the continuity of the medium interface. The feasibility of the model was confirmed by solving the magnetic field of a permanent magnet, with an error margin of less than 5%. The model exhibited excellent precision in simulating magnetic field behavior within magnetic gears. We demonstrate that adjusting model parameters enables the creation of a proxy model, which effectively addresses analogous problems. Furthermore, leveraging transfer learning substantially diminishes training time for similar tasks, resulting in a 43% reduction in training cost. Finally, we propose an enhanced physical information neural network with data-physical drive fusion and use a special Poisson's equation solution in the magnetized region as a data drive during training. The enhanced physics-informed neural network effectively solved the magnetic field of a magnetic gear, resulting in a 50% improvement in solution accuracy. This study establishes the groundwork for analyzing and optimizing magnetic gears, providing new research insight for electromagnetic practitioners.