An Adaptive FNN Control for Torque-Ripple Reduction of SR Motor Drive

Abstract

The purpose of this paper is to implement a novel approach to learning control for torque-ripple reduction of switched reluctance motor (SRM) using an adaptive fuzzy neural network (AFNN) control. First, the dynamic models of a SRM drive system are builted though SRM experimental tests and parameters measurements. Then, in order to reduce torque ripple, an AFNN speed control system that combined FNN and compensated control with adaptive law is developed to control SRM drive system. The AFNN control system produces smooth torque up to the motor base speed. Finally, the effectiveness of the proposed control scheme is demonstrated by experimental results.Index Terms--Switched reluctance motor, fuzzy neural network, torque-ripple reduction, adaptive law. this paper presents an adaptive fuzzy neural network (AFNN) controller for torque-ripple reduction of SRM's.The purpose of this paper is to investigate and implement a novel approach to learning control for torque-ripple reduction of switched reluctance machines (SRM) using an adaptive fuzzy neural network (AFNN) control. Finally, some experimental results are provided to demonstrate the effectiveness of the proposed control schemes. II. CONFIGURATION OF SRM DRIVEThe machine model of a switched reluctance motor (SRM) can be described in matrix as follows [1][2][3][4][5] PXabcd Vabcd -rsabcd (1)

Torque ripple minimisation of switched reluctance motor using sense coils

“…A neural network based system [18] has been proposed to update the stored current profile with the objective of reducing torque ripple. An adaptive fuzzy neural network has been used in [19], Mansouri Borujeni et al [20] use a particle swarm optimisation based approach to optimise controller gain, turn on and turn off angles. These methods require offline inductance measurement and intensive computation.…”

A sense winding system and dynamic current profiling to reduce torque ripple of SRM

“…The DTC methods proposed in Ai-de et al 19 and Sayouti et al 20 aim at reducing the torque ripple. Fuzzy logic control and artificial neural networks (ANNs) have also been used [22][23][24] to generate current profiles that minimize the torque ripple. Fuzzy logic control and artificial neural networks (ANNs) have also been used [22][23][24] to generate current profiles that minimize the torque ripple.…”

“…Direct instantaneous torque control (DITC) is discussed in Petrus et al, 21 and a comparative study of torque ripple and copper losses with current profiling techniques is made. Fuzzy logic control and artificial neural networks (ANNs) have also been used [22][23][24] to generate current profiles that minimize the torque ripple. These methods also require rotor angle from a position sensor.…”