DocumentCode :
2381993
Title :
Modular neural networks for friction modeling and compensation
Author :
Fun, Meng-Hock ; Hagan, Martin T.
Author_Institution :
Sch. of Electr. & Comput. Eng., Oklahoma State Univ., Stillwater, OK, USA
fYear :
1996
fDate :
15-18 Sep 1996
Firstpage :
814
Lastpage :
819
Abstract :
The modular neural network has been shown to be an effective alternative to multilayer feedforward networks, especially for implementing functions with sharp changes. The objective of this work is to use modular neural networks to model precision pointing systems whose performance is limited by nonlinear friction forces. The modular neural network models are used to develop friction compensation controllers. This paper also describes a new method for training modular networks, based on the Levenberg-Marquardt algorithm for nonlinear least squares. The algorithm is tested on several function approximation problems, and the performance is compared with standard steepest ascent and the Rprop algorithm
Keywords :
Hessian matrices; feedforward neural nets; friction; function approximation; least squares approximations; model reference adaptive control systems; modelling; Hessian matrix; Levenberg-Marquardt algorithm; friction compensation; friction modeling; function approximation; model reference adaptive control; modular neural network; multilayer feedforward networks; nonlinear friction; nonlinear least squares; pointing systems; Backpropagation algorithms; Computer networks; Friction; Neural networks; Newton method; Nonlinear equations; Performance analysis; Transfer functions;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control Applications, 1996., Proceedings of the 1996 IEEE International Conference on
Conference_Location :
Dearborn, MI
Print_ISBN :
0-7803-2975-9
Type :
conf
DOI :
10.1109/CCA.1996.558972
Filename :
558972
Link To Document :
بازگشت