SuMRAS: a new SPMSM Parameter Identification in Cloud Computing Environment

This paper proposes an innovative Supervised model Reference Adaptive System (SuMRAS) for the rotor flux linkage identification in Surface Permanent Magnet Synchronous Machines (SPMSM). Estimations are updated in an autonomous way when convergence is reached. The proposed SuMRAS can be applied also to operating motors without requiring manual analysis, hence, it is suitable for large-scale implementation in cloud services. The effectiveness of the proposed approach is assessed in a real-world cloud environment through hardware-in-the-loop (HIL) experiments.