Wiener system identification using B-spline functions with De Boor recursion

Hong, Xia; Mitchell, Richard; Chen, S.

doi:10.1049/ic.2011.0138

Cited by 1 publication

(1 citation statement)

References 13 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, intelligent methodologies have been employed to compensate for the aforementioned shortcomings. The kernel-based methods such as wavelet (Aadaleesan et al, 2008), B-spline (Hong and Chen, 2011; Hong et al, 2013), recurrent neural networks (Hsu and Wang, 2009; Peng and Dubay, 2011) and support vector machine (Tötterman and Toivonen, 2009) are some of them.…”

Section: Introductionmentioning

confidence: 99%

Online identification of non-linear dynamic systems by Wiener model using subspace method and neural networks

Sadeghi

Farrokhi

2016

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

This paper presents a method for online identification of non-linear dynamic systems using the Wiener model. For the linear dynamic part the subspace identification method with the multivariable output-error state-space algorithm is employed, whereas for the non-linear static part the multi-layer perceptron neural network with Levenberg–Marquardt algorithm is used. The stability and convergence of the proposed method is shown using the Lyapunov direct method and the region solution of the linear matrix inequality (LMI) approach. The proposed method is tested by simulations performed on the continuous stirred tank reactor (CSTR) plant, which is presented by non-linear differential equations. Moreover, the method is applied on the input–output data that are obtained from a practical system of the CSTR plant as well as the pH neutralization plant. The results show significant improvements in online identification of the non-linear dynamic systems compared with the recently reported methods in literature.

show abstract