无人直升机自适应神经网络姿态控制

回顾了自适应飞行控制技术、反馈线性化和模型逆理论，分析了误差动力特性．设计了自适应神经网络姿态控制系统。其中，模型逆基于悬停状态，基于神经网络的自适应控制律能够确保跟踪误差和控制信号的有界。仿真结果表明：模型逆增强的非线性神经网络能够对无人直升机的不确定性和建模误差进行自适应。而且对PD控制器和鲁棒项系数变化的仿真结果进行了比较。

ADAPTIVE NEURAL NETWORK ATTITUDE CONTROL FOR UNMANNED HELICOPTER

Adaptive flight control technology, feedback linearization, model inversion theory are reviewed and the error dynamic characteristics are analyzed, and an adaptive on-line neural network attitude control system is presented. The model inversion is under the hover condition. And the adaptive control law based on the neural network is designed to guarantee the boundedness of tracking error and control signals. Simulation results demonstrate that the nonlinear neural network augmented model inversion can self-adapt to the uncertainty and modeling errors of unmanned helicopters. Results are compared while the parameters of PD controller and robustness items are changed.