Multilayer recurrent neural networks for online robust pole assignment
Multilayer recurrent neural networks for online robust pole assignment
复制标题
DOI：
10.1109/tcsi.2003.818622
复制
发表时间：
2003-11
影响因子：
5.1
通讯作者：
Sanqing Hu;Jun Wang
中科院分区：
文献类型：
--
作者：
Sanqing Hu;Jun Wang
本文基于一个新的问题模型，提出了两种用于鲁棒极点配置的多层递归神经网络。一种是状态无关的退火神经网络，另一种是状态相关的退火神经网络。所提出的递归神经网络由三层组成，能够实时地通过鲁棒极点配置来综合线性控制系统。证明了状态相关的退火神经网络对任意设计参数都是收敛的。此外，神经网络指数收敛于鲁棒极点配置问题的最优解，基于神经网络的受扰闭环系统在适当的设计参数下是全局指数稳定的。这些理想的性质使得神经网络有可能应用于慢时变的线性控制系统。仿真结果表明了该神经网络方法的有效性、优越性和运行特性。
In this brief, two multilayer recurrent neural networks are presented for robust pole assignment based on a new problem formulation. One is called state-independent annealing neural network and the other is called state-dependent annealing neural network. The proposed recurrent neural networks are composed of three layers and are shown to be capable of synthesizing linear control systems via robust pole assignment in real time. The state-dependent annealing neural network is proven to converge for any design parameters. Moreover, the neural network converges exponentially to an optimal solution of the robust pole assignment problem and the perturbed closed-loop control system based on the neural network is globally exponentially stable with appropriate design parameters. These desirable properties make it possible to apply the neural network to slowly time-varying linear control systems. Simulation results are shown to illustrate the effectiveness, advantages, and operating characteristics of the proposed neural network approach.