Neural network torque estimator for switched reluctance motor

The neural network torque estimator is based on the identification model of SR motors. It is derived from this model using the concept of superposition of elementary models. The estimator can be applied in SRM controllers where the limitation of dynamic torque is of importance. It is also useful for torque ripple reduction.

[1]  Hai-Jiao Guo,et al.  Control of SR motor EV by instantaneous torque control using flux based commutation and phase torque distribution technique , 2008, 2008 13th International Power Electronics and Motion Control Conference.

[2]  C. Pavlitov,et al.  Generalized model for a class of Switched Reluctance Motors , 2008, 2008 13th International Power Electronics and Motion Control Conference.