Switched Reluctance Motors (SRMs) have gained significant attention in recent decades due to their robust construction, magnet-free design, fault-tolerant capability, and suitability for high-speed and high-temperature operations condition.Despite their mechanical robustness, SRMs present significant control challenges due to their doubly salient structure and highly nonlinear electromagnetic characteristics. Traditional control approaches for SRMs often rely on extensive lookup tables,Model Predictive Control (MPC) has emerged as a promising alternative for SRM control, Finite Control Set MPC (FCS-MPC) and Continuous Control Set MPC (CCS-MPC),Physics-Informed Neural Networks (PINNs) have recently emerged as a powerful paradigm that integrates physical laws directly into neural network .

Чжу С. (науч. рук. Демидова Г.Л.) Model predictive control in switched reluctance motor drives finite control set, continuous control set, and integration with physics-informed neural networks // Сборник тезисов докладов конгресса молодых ученых. Электронное издание. – СПб: Университет ИТМО, [2026]. URL: https://kmu.itmo.ru/digests/article/16684