Hierarchical Algorithms of Quasi-Linear ARX Neural Networks for Identification of Nonlinear Systems

Abu Jami’in, Mohammad and Yuyun, - and Julianto, Eko (2017) Hierarchical Algorithms of Quasi-Linear ARX Neural Networks for Identification of Nonlinear Systems. Engineering Letters, 25 (3).

[img] Text
2017 Engineering letters.pdf

Download (841kB)

Abstract

A quasi-linear ARX neural network model (QARXNN) is a nonlinear model built using neural networks (NN). It has a linear-ARX structure where NN is an embedded system to give the parameters for the regression vector. There are two contributions in this paper, 1) Hierarchical Algorithms is proposed for the training of QARXNN model, 2) an adaptive learning is implemented to update learning rate in NN training to ensure global minima. First, the system is estimated by using LSE algorithm. Second, nonlinear sub-model performed using NN is trained to refine error of LSE algorithm. The linear parameters obtained from LSE algorithm is set as bias vector for the output nodes of NN. Global minima point is reached by adjusting the learning rate based on Lyapunov stability theory to ensure convergence of error. The proposed algorithm is used for the identification and prediction of nonlinear dynamic systems. Finally, the experiments and numerical simulations reveal that the proposed method gives satisfactory results. Index Terms—System Identification, quasi linear-ARX neural network, hierarchical algorithm, convergence of error, nonlinear system

Item Type: Article
Subjects: T Technology > T Technology (General)
Divisions: Jurusan Teknik Kelistrikan Kapal > D3 Teknik Kelistrikan Kapal
Depositing User: Unnamed user with email repository@ppns.ac.id
Date Deposited: 22 Jan 2019 08:38
Last Modified: 28 Jan 2019 02:36
URI: http://repository.ppns.ac.id/id/eprint/1412

Actions (login required)

View Item View Item