Twenty years of fuzzy control: experiences gained and lessons learnt

Abstract

The author examines fuzzy control from its inception to its recent widespread acceptance in industrial use and reflects upon matters such as its earlier dismissal, the reasons for its appeal, the nature of scientific research and engineering innovations. The focus is on rule-based fuzzy controllers. It is argued that the dominant position of analytic control theory prevented fuzzy control from being taken seriously until its increasing application in Japan. Many of the arguments against fuzzy control were framed in the language of that dominant theory and also countered in that language. It is further argued that fuzzy control and allied other techniques such as self-organizing fuzzy control, neural networks, genetic algorithms, and so on, provide an alternate paradigm to the analytic control theory. This paradigm consists of nonanalytic approaches to control and is based on decision-making approaches from artificial intelligence.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>