An efficient computational method to implement type-2 fuzzy logic in control applications

Abstract

A novel structure of type 2 fuzzy logic controller is presented. The method is highly efficient regarding computational time and implementation effort. Type-2 input membership functions were optimized using the Human Evolutionary Model (HEM) considering as the objective function the Integral of Squared Error at the controllers output. Statistical tests were achieved considering how the error at the controller's output is diminished in presence of uncertainty, demonstrating that the proposed method outperforms an optimized traditional type-2 fuzzy controller for the same test conditions. © 2007 Springer-Verlag Berlin Heidelberg.