Realization of PID Control by Fuzzy Inference and its Application to Hybrid Control
Kenichiro Hayashi, Akifumi Otsubo and Kazuhiko Shiranita
Applied Electronics Division, Industrial Technology Center of Saga 114 Yaemizo, Nabeshima-cho, Saga-shi 849-0932, Japan Tel. +81-952-30-8161Fax: +81-952-25-1694
First, we propose a more practical method for realizing nonlinear and linear PID control by fuzzy inference. By applying the simplified direct inference of fuzzy inference to only a few simple fuzzy control rules, both nonlinear PID control based on a conventional PID controller and linear PID control are more simply realized than by previous methods. Next, we propose a hybrid control method in which fuzzy and PID control are hybridized for mutual compensation of both types of control. In this proposal, fuzzy control (nonlinear PID control) and PID control (linear PID control), realized by the simplified direct inference of fuzzy inference, are combined in parallel and used alternately. The main characteristics of this method are high-speed control realized by applying the simplified direct inference of fuzzy inference and smoothness of switching control guaranteed by fuzzy switching of fuzzy and PID control.