Nonlinear-Observer-Based Neural Fault-Tolerant Control for a Rehabilitation Exoskeleton Joint with Electro-Hydraulic Actuator and Error Constraint

The rehabilitation exoskeleton is an effective piece of equipment for stroke patients and the aged. However, this complex human–robot system incurs many problems, such as modeling uncertainties, unknown interaction, external disturbance, actuator fault. This paper addresses adaptive fault-tolerant tracking control a lower limb joint driven by electro-hydraulic (EHA). First, model built considering principle hydraulic cylinder servo valve. Then, novel disturbance-observer-based neural scheme proposed, where network disturbance observer are incorporated to reduce influence nonlinear uncertainties disturbance. Meanwhile, barrier Lyapunov function constructed ensure stability closed-loop system. Finally, comparative simulations on validate effect proposed scheme.