Enhancement of a single-input fuzzy logic control system using a novel method
Shih-Chih Lee, Ching‐Long Shih · Journal of the Chinese Institute of Engineers · 2011
Despite its excellent performance as a controller for linear and non-linear systems, the fuzzy logic controller (FLC) has certain limitations. For instance, large-scale complex fuzzy systems like multi-input, single-output, or multi-output systems create complex applications with large amounts of rules. This study presents a novel framework that reduces the number of rules for an FLC based on a single-input fuzzy logic controller. Controller parameters are then optimized based on a genetic algorithm, and subsequently eliminating the trial and error approach involved in controller design. Reliability of the proposed method is verified with three complex and strong nonlinear systems, i.e. a twin-rotor multi-input–multi-output system, an inverted pendulum and cart system, and permanent magnet linear synchronous motor systems. Simulation and experiment results demonstrate that the proposed framework performs well in terms of the number of rules in the rules base and robustness. Moreover, the fuzzy rule number of the proposed approach decreases only with the number of linguistic labels for the membership function.