A case study on neuro-fuzzy architectures applied to the system identification of a reduced scale fighter aircraft

Abstract

This study investigates different architectures of Neuro-Fuzzy applied to unsteady aerodynamic modeling based on experimental data from a reduced-scale aircraft, known as Generic Future Fighter. The comparison is made considering different fuzzy inference methods, membership function shapes, number of membership functions to describe the input variables and different output functions, in the case of Takagi-Sugeno inference method. All these comparisons are made using the differential evolution as an optimization tool. In the end, the results present the best Neuro-Fuzzy configuration applied to the system identification of the GFF. Furthermore, the conclusion presents insights about the possible future implementation of the methodology.