Error Tracking-Based Neuro-Adaptive Learning Control for Pneumatic Artificial Muscle Systems With Output Constraint

Abstract

Pneumatic muscle actuators are widely used in the manufacture of bionic robots and rehabilitation medical equipment. However, due to complicated inherent nonlinearities, time-varying characteristics and uncertainties, it is still a challenge to carry out the accurate dynamic modeling and controller design for PAM systems. To address above issues, we propose an error tracking-based neuro-adaptive iterative learning control scheme to get satisfactory non-uniform angle trajectory tracking performance. First, the error-tracking method is used to overcome the nonzero initial state error in iterative learning controller design for the PAM system. Second, a difference-learning neural network is utilized to compensate for unknown uncertainties in the PAM system dynamics. Moreover, a barrier Lyapunov function is applied to design controller so as to restrict the the difference between system out error and the desired error trajectory within the preset bound during each iteration. And the stability of the closed-loop system is proven theoretically by using Lyapunov synthesis. Finally, simulation results demonstrate the effectiveness of the proposed control scheme.