基于神经网络的一类非线性系统自适应回馈递推控制  

Adaptive Backstepping Control Based on Neural Network for a class of Nonlinear Systems

作　　者：陈龙胜[1] 王长坤[1] 王进[1] 

机构地区：[1]南昌航空大学,江西南昌330063

出　　处：《南昌航空大学学报（自然科学版）》2009年第3期55-60,共6页Journal of Nanchang Hangkong University(Natural Sciences)

基　　金：江西省测控中心项目"飞机用单相静止交流检验设备的研制"(ZX200828004)

摘　　要：文章针对一类非线性系统,研究了一种基于回馈递推法的自适应神经网络控制方法。首先基于隐函数定理和中值定理推导出模型跟踪误差的动态特性,再利用多层感知器神经网络并设计适当的权值调整规则使其能够自适应的逼近和补偿误差提高系统的鲁棒性。基于Lyapunov方法证明了闭环系统所有信号有界且跟踪误差收敛到一个很小的邻域,所得到的闭环系统是一致稳定的。仿真结果验证了所研究算法的有效性。An adaptive backstepping control method based on neural networks is presented Ior a class ot nonlinear systems, Firsuy, with the implicit function theorem and mean value theorem, the dynamic characteristic of model tracking error is educed. Then, multi -layer perception neural network is implemented to compensate error by design of suitable weights, which improves the robust performance of the controller. All signals in the closed - loop system are guaranteed to be ultimately bounded by Lyapunov approach and system tracking errors converge to a small neighborhood, the closed -loop system is proved to be guaranteed stable. A simulation example shows the effectiveness of the control method.

关 键 词：回馈递推 隐函数定理 中值定理 自适应控制 神经网络 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]