未知控制方向的严反馈非线性系统神经网络自适应控制

Adaptive neural network control for strict-feedback nonlinear systems with unknown control direction

摘要:

针对一类未知控制方向的单输入单输出严反馈非线性系统,提出一种神经网络自适应控制方法。首先应用Nussbaum型函数解决控制系数符号未知问题,然后应用RBF神经网络和反演设计方法对系统进行系统化设计。该控制方法放宽了现有文献中许多苛刻的条件,如匹配条件、增长条件等,避免了控制器奇异问题,同时解决了反演设计中的“计算膨胀”问题,并应用Lyapunov稳定性理论证明了闭环系统的全局稳定性。最后给出了数字仿真实例,证明了该设计方法的有效性。

Abstract:

Adaptive neural network control is presented for a class of SISO strict-feedback nonlinear systems with unknown control direction. Nussbaum-type function is used to solve the difficulty of unknown sign of control coefficients. A systematic procedure is developed based on RBF neural networks and backstepping design techniques, which relaxes some rigorous restrictions on the plants in the literature at present stage, such as matching condition, growth condition. The possible singularities of the controller is avoided and the “computer explosion” problem is resolved in the developed control scheme. Global stability of the closed-loop systems is guaranteed. Finally, numerical simulation studies are presented to demonstrate the effectiveness of the proposed method.