An On-line Rule Weighting Mechanism Based on Normalized Acceleration for Fuzzy PID Controllers

Abstract

Abstract In this study, an on-line rule weighting method is proposed for fuzzy PID controllers. For this purpose, the relative importance or influence of the fired fuzzy rules is determined for certain regions of the transient phase of the unit step response of the closed loop system. Meta-rules for the adjustment of the rule weights are derived according to the error value and the relative information on the fastness or slowness of the system response to obtain an efficient and appropriate control signal. Then, the rule weight values are adjusted via a fuzzy inference mechanism in an on-line manner. The inputs of the fuzzy mechanism are the “normalized system error” and the “normalized acceleration”. The “normalized acceleration” gives the “relative rate” information about the fastness or slowness of the system response. The effectiveness of the proposed self tuning method is demonstrated on two processes by simulations.