A neuro-fuzzy based approach for output tracking of transverse flux machines

This paper describes a design for adaptive control of transverse flux permanent magnet machines as nonlinear systems with unknown nonlinearities by utilizing Takagi-Sugeno-Kang type neuro-fuzzy networks. The technique of feedback linearization and H_infin control are used to design the adaptive control law for compensating the unknown nonlinear parts, such the effect of cogging torque, as a disturbance on the rotor angle and angular velocity tracking performances. Finally, the capability of the proposed method is shown by the simulation results