Designing fuzzy membership functions using genetic algorithm with a new encoding method

Abstract

This article presents a new method for designing fuzzy membership functions using the genetic algorithm (GA) without the use of constraints. Conventional approaches to designing these functions often involve manual tuning or optimization techniques with limitations. However, this article introduces a constraint-free approach, as the GA requires all constraints to be met for a chromosome; if even one condition is not satisfied, the chromosome is discarded, regardless of its ideal values for other variables. Consequently, a high number of constraints, especially in the studied case, increases the likelihood of chromosome rejection, leading to a time-consuming design process and suboptimal results.