Adaptive controller method for Permanent Magnet Synchronous Motor speed-regulation

Permanent Magnet Synchronous Motors (PMSM) have been used as variable speed drives, especially for speed control and position. This work present the performance of a B-Spline Neural Network (BSNN) scheme to adjusting the rotor speed of PMSG and estimation the load torque. The B-spline neural network is an efficient tool to implement the adaptive control speed and estimation of load torque, with the possibility of carrying out this task on-line, taking into account the systems non-linearities. One of the main tasks within is adjust the proportional-integral parameters for speed rotor controller. In this work, a neural network algorithm solves this. Results show that the proposed coordination scheme is comparable with an inner-loop sliding mode current control scheme, without requiring a strict model analysis. A nonlinear observer is designed for estimation of the rotor speed and load torque. To illustrate the performance of the proposed controller, the simulation studies are presented separately for the BSNN and sliding mode control. The results are compared with each other and discussed in detail.