3-Dimensional sliding mode adaptive MIMO recurrent fuzzy neural network control for two-link manipulator system

Abstract

A novel methodology of 3-dimensional sliding mode adaptive multi-inputs multi-outputs (MIMO) recurrent fuzzy neural network (SAMRFNN) control for two-link manipulator system is proposed. This control scheme consists of a sliding mode (SM) controller and a 3-dimensional adaptive multi-inputs multi-outputs (MIMO) recurrent fuzzy neural network (AMRFNN) controller. The SM controller is to cope with uncertain dynamics of system and external disturbances; and the AMRFNN controller is used to approach the ideal controller of SM controller such as to stabilize the system. The Lyapunov theorem based adaptive laws are derived to tune the SAMRFNN parameters such that the stability and convergence of those can be guaranteed. In the simulations, persistency excitation (PE) effects and results of all parameters have been discussed and demonstrated; meanwhile, better effectiveness and performances of the proposed SAMRFNN control are demonstrated by comparisons with the adaptive fuzzy neural network (AFNN) control and state feedback control.