Development and implementation of a neuro fuzzy technique for position sensor elimination in a SRM

This article has the objective to present a brief revision of the techniques more generally used in the position sensor elimination in a switched reluctance motor. For each speed level, different techniques are indicated for a good system operation. A new technique of position sensor elimination is presented, based in intelligent techniques with neural nets and fuzzy logic. It uses only phase voltages and the reference current signals to obtain the speed/position estimation. Experimental and simulation results are presented showing its good performance.