Neural control of high performance drives: an application to the PM synchronous motor drive

An increasing role of artificial neural networks (ANNs) in various engineering applications has spurred interest in power electronics and motor drives. In this paper, ANNs are utilized to achieve vector control end parameter compensation for the high performance control of the permanent magnet synchronous motor (PMSM). The overall system is capable of achieving concurrent mutual flux linkages and torque control in the presence of parameter variations and over a wide range of speed. A requirement of this system is an on-line estimation of the respective varying parameters. The proposed method is the most feasible and accurate for PMSM control. This study provides a generalized framework for ANN applications to high performance control of AC machines