干扰和执行器故障系统的自适应神经网络控制

Robust adaptive neural network control with disturbances and actuator failures

针对一类存在未知外部扰动和执行器故障的过驱飞行器系统的控制问题,提出了一种非线性自适应控制方案。在自适应控制方案中,设计了神经网络补偿算法逼近未知干扰项来消除环境干扰对系统的影响,提高了系统的鲁棒性。同时,控制律的输出作为控制分配器的输入,设计自适应控制分配算法来补偿执行器故障或输入饱和,从而提高了系统的稳定性和操作性,并利用李亚普诺夫稳定理论证明了所设计的控制系统能使误差系统最终一致渐近有界。最后,给出了一个数值仿真算例,验证了控制方法的有效性。

A novel nonlinear adaptive control scheme is proposed for an over-actuated control system with unknown external disturbance and actuator failure. Through the reconstructed directly neural network,the parameter updating laws are used for providing automatic disturbance rejection ability in real time,it improves the robustness of system. Adaptive control allocation effectively compensates actuator failures or avoids the input saturation to improve the stability and maneuver. The sufficient conditions of stability are derived from Lyapunov arguments. Simulation results show the effectiveness and feasibility of the approach.