无反步设计的严格反馈型非线性系统神经网络自适应跟踪控制

Neural network adaptive tracking control for strict-feedback nonlinear systems without backstepping

针对一类具有外部干扰、仅输出可测的SISO严格反馈型非线性系统,提出一种神经网络输出反馈跟踪控制方法。该方法将严格反馈型系统转换成标准仿射型系统,从而避免反步设计过程,且无需设计状态观测器。最终控制律和神经网络权值更新律中仅用到输出误差。基于Lyapunov方法证明了闭环系统所有信号有界,跟踪误差收敛到有界紧集内。最后,应用高机动导弹的位置跟踪控制验证了该方法的有效性。

An output feedback tracking control algorithm using neural network for a class of SISO strict-feedback nonlinear systems with external disturbances was presented under the constraints that only the system output variables can be measured. The method shows that the strict-feedback systems can be transformed into the standard affine form to avoid backstepping design. No state observer was employed in the algorithm. Only the output error was used in control laws and weights update laws. Moreover, all signals in the closed-loop system were guaranteed to be ultimately bounded by Lyapunov approach and output of the system converge, to a small neighborhood of the desired trajectory. Finally the tracking control of high maneuver missile was used to demonstrate the effectiveness of the control scheme.