Title :
Global exponential stability of recurrent neural networks for synthesizing linear feedback control systems via pole assignment
Author :
Zhang, Yunong ; Wang, Jun
Author_Institution :
Dept. of Autom. & Comput.-Aided Eng., Chinese Univ. of Hong Kong, Shatin, China
fDate :
5/1/2002 12:00:00 AM
Abstract :
Global exponential stability is the most desirable stability property of recurrent neural networks. The paper presents new results for recurrent neural networks applied to online computation of feedback gains of linear time-invariant multivariable systems via pole assignment. The theoretical analysis focuses on the global exponential stability, convergence rates, and selection of design parameters. The theoretical results are further substantiated by simulation results conducted for synthesizing linear feedback control systems with different specifications and design requirements
Keywords :
asymptotic stability; control system synthesis; feedback; linear systems; multivariable control systems; neurocontrollers; pole assignment; recurrent neural nets; convergence rates; design parameter selection; feedback gains; global exponential stability; linear feedback control systems; linear time-invariant multivariable systems; online computation; pole assignment; recurrent neural networks; simulation; Computational modeling; Computer networks; Control system synthesis; Convergence; Gain; MIMO; Network synthesis; Neurofeedback; Recurrent neural networks; Stability analysis;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2002.1000129