Analysis of rulebase coherence in fuzzy control systems

Abstract

In rule-based fuzzy control systems there is a need to evaluate the rulebase to detect redundant or contradictory rules, and to monitor the performance of the knowledge acquisition process, knowledge coming either from an human expert or from a learning mechanisms if present. When faulty situations are detected corrective steps should be taken by the knowledge engineer or by a rulebase-maintenance metaknowledge. In this paper, a new ideal defuzzifier framework is presented with its use to develop matrix expressions for the consistency of the rules in a base and asessing the quality and quantity of the knowledge represented by them.