Application of nonlinear time series analysis to the prediction of silicon content of pig iron

被引：34

作者：

Waller, M ^{[1
]}

Saxén, H ^{[1
]}

机构：

[1] Abo Akad Univ, Heat Engn Lab, FIN-20500 Turku, Finland

来源：

ISIJ INTERNATIONAL | 2002年 / 42卷 / 03期

关键词：

D O I：

10.2355/isijinternational.42.316

中图分类号：

TF [冶金工业];

学科分类号：

0806 ;

摘要：

The application of nonlinear time series analysis for the prediction of silicon content of pig iron is discussed. The predictive properties of the nonlinear time series models implemented as radial basis function networks and (time variant) linear time series models as well as parametrically linear (time variant) finite impulse response models were compared. The analysis showed detection of a clear nonlinearity in the signal.

引用

页码：316 / 318

页数：3

共 18 条

[1]

Abarbanel H, 1996, ANAL OBSERVED CHAOTI

[2]

[Anonymous], NEURAL COMPUTATION

[3]

BOX GEP, 1994, TIME SERIES ANAL

[4] Recurrence plots revisited [J].

Casdagli, MC .

PHYSICA D, 1997, 108 (1-2) :12-44

[5] PRACTICAL IDENTIFICATION OF NARMAX MODELS USING RADIAL BASIS FUNCTIONS [J].

CHEN, S ;

BILLINGS, SA ;

COWAN, CFN ;

GRANT, PM .

INTERNATIONAL JOURNAL OF CONTROL, 1990, 52 (06) :1327-1350

[6] REVERSIBILITY AS A CRITERION FOR DISCRIMINATING TIME-SERIES [J].

DIKS, C ;

VANHOUWELINGEN, JC ;

TAKENS, F ;

DEGOEDE, J .

PHYSICS LETTERS A, 1995, 201 (2-3) :221-228

[7] Practical implementation of nonlinear time series methods: The TISEAN package [J].

Hegger, R ;

Kantz, H ;

Schreiber, T .

CHAOS, 1999, 9 (02) :413-435

[8]

Kantz H, 1997, Nonlinear Time Series Analysis

[9] DETERMINING EMBEDDING DIMENSION FOR PHASE-SPACE RECONSTRUCTION USING A GEOMETRICAL CONSTRUCTION [J].

KENNEL, MB ;

BROWN, R ;

ABARBANEL, HDI .

PHYSICAL REVIEW A, 1992, 45 (06) :3403-3411

[10] Fast Learning in Networks of Locally-Tuned Processing Units [J].

Moody, John ;

Darken, Christian J. .

NEURAL COMPUTATION, 1989, 1 (02) :281-294

← 1 2 →