Title :
Recurrent neural networks for recursive identification of nonlinear dynamic process
Author :
Dong, Jia-Wen ; Qian, Ji-Xin ; Sun, You-Xian
Author_Institution :
Inst. of Ind. Process Control, Zhejiang Univ., Hangzhou, China
Abstract :
In this paper, modified Elman-type recurrent neural networks (1990) were developed to identify the dynamic nonlinear systems with generalised backpropagation recursive algorithm. Analysis shows that introduction of adjustable self-connections of context units provides network ability to model high order input-output mapping, unbiased estimates can be achieved without the need to fit additive noise model. An industrial application example shows its efficiency
Keywords :
backpropagation; identification; nonlinear dynamical systems; recurrent neural nets; adjustable self-connections; context units; generalised backpropagation recursive algorithm; nonlinear dynamic process; recurrent neural networks; recursive identification; Context modeling; Electrical equipment industry; Industrial control; Multi-layer neural network; Neural networks; Neurofeedback; Parameter estimation; Process control; Recurrent neural networks; System identification;
Conference_Titel :
Industrial Technology, 1994., Proceedings of the IEEE International Conference on
Conference_Location :
Guangzhou
Print_ISBN :
0-7803-1978-8
DOI :
10.1109/ICIT.1994.467030
