Identification of fuzzy systems by means of an auto-tuning algorithm and its application to nonlinear systems (Q1590979)

The study concerns a design procedure of rule-based systems. Two types of methods for rule-based fuzzy modeling are considered. This classification concerns the form of the conclusion part of the rules that can be either constant or formed by some linear functions. Both triangular and Gaussian-like membership functions are studied. The optimization hinges on an auto-tuning algorithm that covers a modified constrained optimization method known as a complex method. Several numerical examples are given. It would be interesting to use the global optimization method (Alienor) based on \(\alpha\)-dense curves in \(\mathbb{R}^n\).