Aplicação de sistemas neuro-fuzzy e evolução diferencial na modelagem e controle de veículo de duas rodas

Abstract

This work proposes the neuro-fuzzy modeling and control applied to the static stability of a two-wheeled inverted pendulum vehicle, using differential evolution as optimization technique. During the modeling phase, the uncertainties related to the parameters and also to the neuro-fuzzy model response are determined. It is possible to verify that the neuro-fuzzy system is capable of satisfactorily adjusts to the data experimentally extracted from the vehicle. In the determination of the neuro-fuzzy controller, three strategies of parameter adjustment are tested, two of them being proposed in this text, and the results are compared between them and those obtained through classical controllers, and it is verified experimentally and through tests that the proposed approaches present a great capacity to adapt to the constraints imposed on the plant, guaranteeing the static stability and the energy efficiency of the system.