Simplification of fuzzy rule based systems using orthogonal transformation

It is known that removal of those redundant fuzzy rules from a rule base can result in a more compact fuzzy model with better generalizing ability. In this paper we propose a number of orthogonal transformation based methods which provide new or alternative tools for rule extraction. A common attribute of these methods is that they all work on a truth value matrix and employ some measure index to detect the rules that should be retained and eliminated. The performance of these methods is illustrated using a nonlinear plant modeling example.