On-line torque estimation in a switched reluctance motor for torque ripple minimisation

This paper considers torque ripple minimisation control for switched reluctance motors (SRMs) and presents a novel on-line approach to the estimation of instantaneous torque. An adaptive B-spline neural network is used to learn the non-linear flux linkage and torque characteristics of an SRM. The training of the B-spline neural network is accomplished on-line in real-time, and the system does not require a priori knowledge of the SRM´s electromagnetic characteristics. The potential of the torque estimation method is demonstrated in simulation and experimentally using a 550 W 8/6 four-phase SRM operating in saturation, and it has been applied successfully to torque ripple minimisation.