Thermal Monitoring in Electric Machines using Physics-informed Neural Networks
Please login to view abstract download link
Physics-informed neural networks (PINNs) [1] have emerged as a new paradigm for solving numerical problems. In contrast to conventional data-driven techniques, physics-informed neural networks are data-efficient and obey the governing physics of a problem. This work presents results of PINNs applied to three-dimensional thermal modelling of an electric machine. Such models are essential for the thermal management of electric machines enabling safe and reliable operation of traction systems.
