Title :
Research on applications of three layers neural network in dynamic modeling of jig system
Author :
Ming, Li ; Dunwei, Gong ; Shifan, Xu
Author_Institution :
Coll. of Inf. & Electr. Eng., China Univ. of Mining & Technol., Xuzhou, China
Abstract :
The recurrent neural network has strong dynamic approximating capability. It can be used to describe a kind of complex nonlinear time-varying dynamic system. In the paper a model of a three layer recurrent neural network is proposed. The dynamic backpropagation method is put forth to train the weights of the network. Simulation shows the model has good performance in approximating dynamic systems
Keywords :
multilayer perceptrons; nonlinear dynamical systems; recurrent neural nets; complex nonlinear time-varying dynamic system; dynamic backpropagation method; dynamic modeling; jig system; strong dynamic approximating capability; three layer recurrent neural network; Educational institutions; Intelligent networks; Neural networks; Nonlinear dynamical systems; Recurrent neural networks;
Conference_Titel :
Intelligent Control and Automation, 2000. Proceedings of the 3rd World Congress on
Conference_Location :
Hefei
Print_ISBN :
0-7803-5995-X
DOI :
10.1109/WCICA.2000.863427