| Thermal analysis is critical for preventing component failures in electric motors, such as magnet demagnetisation and insulation degradation, by en-suring that operating temperatures remain within safe limits. Industrial ap-plications commonly rely on Lumped Parameter Thermal Network (LPTN) models; however, these models often lack sufficient accuracy to capture complex thermal dynamics. This paper investigates the potential of Phys-ics-Informed Neural Networks (PINNs) to improve dynamic thermal tem-perature prediction in Battery Electric Vehicle propulsion motors, with a focus on Permanent Magnet Synchronous Motors (PMSMs). The perfor-mance of a PINN is compared with a Feedforward Neural Network (FNN) and a traditional 4-node LPTN model. The models were trained and evaluat-ed using data from a PMSM prototype under dynamic random-walk driving cycles to emulate realistic operating conditions. The dataset was enhanced with physically meaningful features, including copper and residual losses, while Exponentially Weighted Moving Averages were incorporated to cap-ture temporal dependencies. The PINN integrates physical knowledge by embedding LPTN-derived Ordinary Differential Equations (ODEs) within its loss function. Results show that both neural network models signifi-cantly outperform the LPTN baseline, which achieved an average Root Mean Square Error (RMSE) of 2.074. The FNN achieved the highest accura-cy, with an RMSE of 0.709, followed by the PINN, with an RMSE of 0.824. The study demonstrates the feasibility of PINN for real-time thermal moni-toring of PMSMs. It highlights the advantages and limitations of i |
*** Title, author list and abstract as submitted during Camera-Ready version delivery. Small changes that may have occurred during processing by Springer may not appear in this window.