Dp 335 en
Self-Learning Controller Design
Author: Cerman Otto
In many situations complex systems can be controlled successfully using fuzzy control systems. Fuzzy controller based on theory of fuzzy logic and fuzzy sets is successful tool for converting of linguistic control strategy from knowledge of an expert into the rule base of controller. Unfortunately, a lot of time is needed for finding these bases because up to the point they are often searched by trial-error method. In addition they are found out with difficulty for very complex systems too.
Most of plants have variable dynamics. For that reason classical controllers with fixed parameters are not sufficient because during variations of plant classical control systems are not optimal and situations like loss of material or energy can occur. In~these cases use of adaptive controller is needed.
Self-organizing or self-learning controllers belong to the group of adaptive fuzzy controllers. They can be seen as heuristic controllers in which control rules are generated and automatically improved. Their basic functions are: 1. to generate suitable control signals according to evaluation of system behaviour 2. to modify controller (most often knowledge base) in a suitable way to reach the required behaviour even during changes of operating points of systems.
The aim of this work is to study known methods, to choose suitable ones and subsequently to test them on several models.
- Cerman Otto, mailto:firstname.lastname@example.org