Robust backpropagation training algorithm for multilayered neural tracking controller

Author

Song, Qing ; Xiao, Jizhong ; Soh, Yeng Chai

Author_Institution

Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore

Volume

10

Issue

5

fYear

1999

fDate

9/1/1999 12:00:00 AM

Firstpage

1133

Lastpage

1141

Abstract

A robust backpropagation training algorithm with a dead zone scheme is used for the online tuning of the neural-network (NN) tracking control system. This assures the convergence of the multilayer NN in the presence of disturbance. It is proved in this paper that the selection of a smaller range of the dead zone leads to a smaller estimate error of the NN, and hence a smaller tracking error of the NN tracking controller. The proposed algorithm is applied to a three-layered network with adjustable weights and a complete convergence proof is provided. The results can also be extended to the network with more hidden layers

Keywords

backpropagation; convergence; discrete time systems; feedforward neural nets; neurocontrollers; nonlinear systems; tracking; backpropagation; convergence; discrete time systems; multilayered neural networks; neurocontrol; nonlinear syste; tracking; Backpropagation algorithms; Control systems; Convergence; Error correction; Neural networks; Neurons; Noise robustness; Nonlinear control systems; Robot control; Robust control;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.788652

Filename

788652