Adaptive Neural Network Control Of Chaos In Permanent Magnet Synchronous Motor

Permanent magnet synchronous motors have been used as variable-speed drives, especially for speed control and position, but it exhibits chaotic performance under certain parameter's changes. This work presents the use of a B-Spline neural network scheme to stabilize chaos and to adjust the rotor speed of synchronous motors. The B-spline neural network is an efficient tool to implement the adaptive speed control, with the possibility of carrying out this task on-line, taking into account the systems nonlinearities. One of the main tasks is the adjustment of the proportional-integral parameters for rotor speed controller. In this work, a neural network algorithm is used to solve this problem. A nonlinear observer is designed for estimation of the rotor speed and load torque. The results of numerical simulations demonstrate that the permanent magnet synchronous motors with the B-Spline control scheme has a good dynamic performance and steady state accuracy.