In this article, an adaptive neural fault-tolerant control (FTC) scheme is proposed for the medium-scale unmanned autonomous helicopter subject to external disturbance, actuator fault, and input saturation. Multiple approximators are constructed to handle the unknown terms and promote the control design. The nonlinear coupled function terms are approximated by virtue of the radial basis function neural networks. The unknown disturbance is tackled by the developed disturbance observer. Meanwhile, two auxiliary systems are introduced to handle the actuator fault and input saturation, respectively. In the framework of the backstepping method, a multiapproximator-based adaptive FTC strategy is presented, which assures the boundedness of all closed-loop system signals. Simulation results are presented to validate the availability of the designed controller.

In this paper, the issue of prescribed performance-based fault tolerant control is investigated for the medium-scale unmanned autonomous helicopter with external disturbance, system uncertainty and actuator fault. The altitude and attitude combination unmanned autonomous helicopter model is established. An error transformation function is proposed to guarantee that the tracking error satisfies the prescribed performance. The parameter adaptation method is adopted to handle the external unknown disturbance and the radial basis function neural networks are employed to approximate the interaction functions including the system uncertainty. The auxiliary system is introduced to weaken the effect of actuator fault, which can effectively avoid the singularity. Based on the backstepping control technology, an adaptive neural fault tolerant control scheme is developed to ensure the boundness of all closed-loop system signals and the specified tracking error performance. Simulation studies on the medium-scale unmanned autonomous helicopter are performed to demonstrate the efficiency of the designed control strategy.

This paper investigates the problem of adaptive fault tolerant tracking control for uncertain nonlinear systems in the event of external disturbances, actuator faults and input saturation. In order to guarantee the transient and steady-state control performance, the prescribed performance function is employed to impose the anticipant performance criterion on the output tracking error. By using the error transformation, the original inequality error constraint is converted to an unconstrained issue. For the conversion systems, the negative effect resulting from the external disturbances is restrained via the adaptive control approach. The radial basis function neural network (RBFNN) is adopted to handle the unknown nonlinear functions. The Nussbaum gain technique is utilised to deal with the nonlinear terms arising from the actuator faults and input saturation. Combining with the backstepping control strategy, an adaptive neural fault tolerant control (FTC) scheme is developed for the uncertain nonlinear systems. It is rigorously proved that the proposed controller is capable of ensuring the boundness of all closed-loop signals as well as the specified tracking performance. Simulation results on two examples are given to illustrate the effectiveness of the presented control approach.