ROBUST ADAPTIVE CONTROL OF TRANSVERSE FLUX PERMANENT MAGNET MACHINES USING NEURAL NETWORKS

This paper deals with modelling and adaptive output tracking of a Transverse Flux Permanent Magnet Machine (TFPM) as a non-linear system with unknown nonlinearities by utilizing High Gain Observer (HGO) and Radial Basis Function (RBF) networks. The technique of feedback linearization and H ∞ control are used to design an adaptive control law for compensating the unknown nonlinearity parts, such the effect of cogging torque, as a disturbance is decreased onto the rotor angle and angular velocity tracking performances. Finally, the capability of the proposed method is shown in the simulation results.