Adaptive model-free fault-tolerant control based on integral reinforcement learning for a highly flexible aircraft with actuator faults

Abstract

This article presents an adaptive model-free fault-tolerant control scheme based on integral reinforcement learning (IRL) technique for tracking control of a highly flexible aircraft (HFA) with actuator faults. To begin, the integral of the tracking error is introduced as a new state to construct an augmented system for the control design. Following that, the off-policy IRL method is applied to obtain the optimal feedback control law online in order to solve the tracking problem without system knowledge. Furthermore, in order to effectively handle system uncertainties, external disturbances, and actuator faults, an adaptive model-free fault-tolerant controller with an observer-like reference model is developed. The designed controller can guarantee that the closed-loop system is uniformly bounded and the tracking error asymptotically approaches zero by choosing design parameters appropriately. Finally, numerical simulations demonstrate the desirable fault accommodation capability of the proposed fault-tolerant strategy.