Robust identification approach for nonlinear state-space models

被引：10

作者：

Liu, Xin ^{[1
]}

Yang, Xianqiang ^{[1
,2
]}

机构：

[1] Harbin Inst Technol, Sch Astronaut, Harbin 150080, Heilongjiang, Peoples R China

[2] Harbin Inst Technol, State Key Lab Robot & Syst, Harbin 150080, Heilongjiang, Peoples R China

来源：

NEUROCOMPUTING | 2019年 / 333卷

基金：

中国国家自然科学基金;

关键词：

Nonlinear system identification; Robustness; Student's t-distribution; Particle smoother; Expectation-maximization algorithm; SYSTEM-IDENTIFICATION; MULTIMODEL APPROACH; LPV APPROACH;

D O I：

10.1016/j.neucom.2018.12.017

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The identification of nonlinear state-space model (NSSM) with output observations corrupted by outliers is investigated in this paper. The outlier is commonly encountered in practical industrial processes which should not be ignored in nonlinear processes modeling. The statistical scheme based on the Student's t-distribution is applied to resist the outlier and the expectation-maximization (EM) algorithm is employed to simultaneously identify the undetermined model and noise parameters. A particle smoother is introduced and used to approximately calculate the desired Q-function. The usefulness of the proposed approach is demonstrated via the numerical and mechanical examples. (C) 2018 Elsevier B.V. All rights reserved.

引用

页码：329 / 338

页数：10

共 44 条

[31] System identification of nonlinear state-space models
Schon, Thomas B.
Wills, Adrian
Ninness, Brett
[J]. AUTOMATICA, 2011, 47 (01) : 39 - 49
[32] Valid data based normalized cross-correlation (VDNCC) for topography identification
Tong, Mingsi
Pan, Yunlu
Li, Zhan
Lin, Weiyang
[J]. NEUROCOMPUTING, 2018, 308 : 184 - 193
[33] Veaux R. D., 1993, COMPUT CHEM ENG, V17
[34] Recursive prediction error identification and scaling of non-linear state space models using a restricted black box parameterization
Wigren, T
[J]. AUTOMATICA, 2006, 42 (01) : 159 - 168
[35] ON THE CONVERGENCE PROPERTIES OF THE EM ALGORITHM
WU, CFJ
[J]. ANNALS OF STATISTICS, 1983, 11 (01) : 95 - 103
[36] LPV model identification with an unknown scheduling variable in the presence of missing observations - a robust global approach
Yang, Xianqiang
Liu, Xin
Han, Boxuan
[J]. IET CONTROL THEORY AND APPLICATIONS, 2018, 12 (10) : 1465 - 1473
[37] Local Identification of LPV Dual-Rate System With Random Measurement Delays
Yang, Xianqiang
Yang, Xuebo
[J]. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2018, 65 (02) : 1499 - 1507
[38] Robust Global Identification and Output Estimation for LPV Dual-Rate Systems Subjected to Random Output Time-Delays
Yang, Xianqiang
Yin, Shen
[J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2017, 13 (06) : 2876 - 2885
[39] Multiple model approach to linear parameter varying time-delay system identification with EM algorithm
Yang, Xianqiang
Gao, Huijun
[J]. JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS, 2014, 351 (12): : 5565 - 5581
[40] Yassin I M., 2013, Scientific Research Journal (SCIRJ), V1, P14, DOI https://www.scirj.org/papers-0813/scirj-august-2013-edition-03.pdf

← 1 2 3 4 5 →