Evolution of fuzzy controller design

This paper analyses and classifies different methods of fuzzy controller (FC) design. Not attempting to develop a mathematical theory it aims at providing some practical recommendations on how to design a FC and how to choose the right design method. The goal is to develop a more or less systematic procedure of FC design which can be used as a reference. Evolution of design approaches is analysed. The design process is considered as consisting of two stages: an initial choice of a controller structure and parameters and their further tuning. At the first stage the recommendations are given regarding the choice of the structure, scaling factors, rules and membership functions, though the main attention is paid to membership functions and scaling factors. Different methodologies such as neural networks, genetic/evolutionary algorithms are considered at the second stage.