ISBN: 978-981-11-3671-9 DOI: 10.18178/wcse.2017.06.205
Identification of Nonlinear System Based on Additive Legendre Neural Network
Abstract— In this paper, an efficient identification method based on additive Legendre neural network
(ALNN) model and hybrid evolutionary method is proposed to identify nonlineat systems. In order to
improve efficiency of Legendre neural network (LNN), additive Legendre neural network is proposed. For
finding the optimal structure and parameters of ALNN model, a new hybrid evolutionary method besed on
binary particle swarm optimization (BPSO) algorithm and firefly algorithm is employed. Two nonlinear
system identification experiments are used to test ALNN model. The results reveal that ALNN model
performs better than LNN and other classic neural networks.
Index Terms— additive, Legendre neural network, binary particle swarm optimization, firefly algorithm.
Bin Yang
School of Information Science and Engineering, Zaozhuang University, CHINA
ISBN: 978-981-11-3671-9 DOI: 10.18178/wcse.2017.06.17Xsrc="http://www.wcse.org/uploadfile/2019/0823/20190823055609629.png" style="width: 120px; height: 68px;" />[Download]
Cite: Bin Yang, "Identification of Nonlinear System Based on Additive Legendre Neural Network," Proceedings of 2017 the 7th International Workshop on Computer Science and Engineering, pp. 1174-1178, Beijing, 25-27 June, 2017.