Fuzzy control system design by fuzzy clustering and self-organization

Document Type

Conference Proceeding

Publication Date

1-1-1996

Abstract

We propose a two-step method for designing fuzzy rules when no plant model or control surface table is available. The first step learns heuristic fuzzy rules by performing on-line adaptive control via trial and error. One simple rule is to choose control y(t) such that both the plant-state error x(t) and the change of error Δx(t) move toward zero in the same rate, up to some constant factor. The second step applies fuzzy clustering to the rule-data generated by the first step to obtain more general and robust fuzzy control rules. Our experiments with the inverted pendulum problem show good performance.

Publication Source (Journal or Book title)

Biennial Conference of the North American Fuzzy Information Processing Society - NAFIPS

First Page

456

Last Page

460

This document is currently not available here.

Share

COinS