J-071

Multi-level Intelligent Control Using Three-step Learning Strategy: Analysis and Implementation

Authors: Minrui Fei*, Lixiong Li*, Xiaoming Niu**
Affiliation: * School of Mechatronical Engineering & Automation, Shanghai University
** Science and Technology Commission of Shanghai Municipality

Abstract
Combining fuzzy control, three-step learning strategy and supervisory control, the novel synthetic method of intelligent control (SMIC) based on system response characteristics is proposed and analyzed theoretically. The SMIC has been implemented in our low cost distributed computer control system (DCCS). A simple example of electric furnace control system demonstrated the applicability of our low cost DCCS utilizing SMIC. The analyses and experiments show that the proposed SMIC has the capability of self-extracting fuzzy control rules or parameters from nonlinear plants with time delays, especially it can guarantee the learning convergence and the control stability. The proposed SMIC and its implementation are right and more effective, and have wider prospects in engineering applications.

Minrui Fei, Professor
Dean of School of Mechatronical Engineering & Automation
Shanghai University
Shanghai 200072
P.R.China
mrfei@usa.net (all time)
mrfei@srcap.stc.sh.cn (after September 1st)