An induction motor drive system performance enhancement using dynamically focused learning fuzzy controller

Abstract

A Fuzzy Logic Controller (FLC), with a Dynamically Focussed Learning (DFL) algorithm is proposed, developed and implemented to improve the performance of an induction motor drive system. In standard direct fuzzy controller, utilization of the rule-base is mostly poor, especially when error input gets smaller and the control action is produced by only a few rules in the center of the rule-base. With such a small number of rules, the fuzzy controller performs inadequately because the resulting control surface can capture very approximate control actions. This poor utilization of the rule-base may degrade the controller performance. A possible solution to this problem may be to redesign the rule-base such that the rule base has move rules at the center. However, this solution limits the ability of the controller to a limited input range and specific inputs. Instead, a DFL fuzzy controller is proposed, which ensures that the fuzzy controller can utilize the entire rule base by auto-tuning algorithm. Computer simulation and experimental results on a 5 hp induction machine are presented to substantiate the proposed scheme.