PSO based neuro fuzzy sliding mode control for a robot manipulator

Abstract

This paper presents the control strategy of two degrees of freedom (2DOF) rigid robot manipulator based on the coupling of artificial neuro fuzzy inference system (ANFIS) with sliding mode control (SMC). Initially SMC with proportional integral derivative (PID) sliding surface is adapted to control the robot manipulator. The parameters of the sliding surface are obtained by minimizing a quadratic performance indices using particle swarm optimization (PSO). Variations of SMC i.e. boundary sliding mode control (BSMC) and boundary sliding mode control with PID sliding surface (PIDBSMC) are developed for optimized performance index. Finally an ANFIS adaptive controller is proposed to generate the adaptive control signal and found to be more robust with regard to disturbances in input torque.