A Rule-Based Scalar Tuning Fuzzy Control System

Abstract

A rule-based scalar tuning fuzzy control system is proposed in this paper. A fuzzy controller with three scalar factors is considered to directly control the plant, and a scalar tuning mechanism through a fuzzy inference method is used to dynamically generate appropriate scalar factors for the fuzzy controller at each sampling time. A state evaluator is used to estimate a critic score to indicate the current state of the system, and to provide this score to a parameter modifier to create a modifiable value. A scalar making mechanism is proposed such that the rule-based fuzzy control system has the powerful ability to automatically select the consequent parameters in the scalar tuning mechanism such that the controlled system has a better performance. Finally, the inverted pendulum control problem is used to illustrate the effectiveness of the rule-based tuning control scheme.