Fractional Order Sliding Mode Controller Based on Supervised Machine Learning Techniques for Speed Control of PMSM

Tracking the speed and current in permanent magnet synchronous motors (PMSMs) for industrial applications is challenging due to various external internal disturbances such as parameter variations, unmodelled dynamics, load disturbances. Inaccurate tracking of results severe system deterioration overheating. Therefore, design controller a PMSM essential ensure can operate efficiently under conditions parametric uncertainties significant variations. The present work proposes using machine learning (ML) techniques quick response insensitivity changes proposed ML designed by fractional-order sliding mode control (FOSMC) behavior. primary purpose FOSMC avoid self-tuning parameters reaches reference value finite time with faster convergence better precision. Furthermore, model does not require mathematical controller. In this work, several models are empirically evaluated on their estimation accuracy tracking, namely ordinary least squares, passive-aggressive regression, random forest, support vector machine. Finally, implemented real-time hardware-in-the-loop (HIL) simulation platform from PLECS Inc. Comparative experimental presented discussed. It shown comparative study that based outperformed traditional (SMC), which more commonly used industry terms accuracy.