Computational Intelligence: Synergies of Fuzzy Logic, Neural Networks and Evolutionary Computing

8

Evolutionary Fuzzy Systems

8.1 Introduction

Although fuzzy systems have been applied successfully to many complex industrial processes, they experience a deficiency in knowledge acquisition and rely to a great extent on empirical and heuristic knowledge, which, in many cases, cannot be elicited objectively. One of the most important considerations in designing fuzzy systems is the construction of the membership functions for each linguistic variable, as well as the rule base. In most existing applications, the fuzzy rules are generated by an expert in the area, especially for control problems with only a few inputs. The correct choice of MFs is by no means trivial but plays a crucial role in the success of an application. Previously, the generation of MFs had been a task mainly done either interactively, by trial and error, or by human experts. With an increasing number of inputs and linguistic variables, the possible number of rules for the system increases exponentially, which makes it difficult for the experts to define a complete set of rules and associated MFs for a reasonable performance of the system. There are many different methodologies available in the literature for systematic design of fuzzy systems (FS) and especially fuzzy logic controllers (FLC). However, three main methods have emerged: nonlinear systems analysis, neural fuzzy and direct optimization. The nonlinear systems analysis approach is beyond the scope of this book and not addressed further here. Interested ...