Evaluation using online support-vector-machines and fuzzy reasoning. Application to condition monitoring of speeds rolling process

被引：24

作者：

Bouhouche, Salah ^{[1
]}

Yazid, Laib Laksir ^{[1
]}

Hocine, Sissaoui ^{[1
]}

Bast, Juergen ^{[2
]}

机构：

[1] CSC, Iron & Steel Appl Res Unit, Annaba 23000, Algeria

[2] TU Bergakad Freiberg, Inst Maschinenbau, HGUM, D-9596 Freiberg, Germany

来源：

CONTROL ENGINEERING PRACTICE | 2010年 / 18卷 / 09期

关键词：

Online support vector machine (SVM) regression; Condition monitoring; Intelligent modeling; Fuzzy reasoning; Quality evaluation; Hot rolling; BREAKOUT;

D O I：

10.1016/j.conengprac.2010.05.010

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

A method for process condition monitoring and evaluation, which combines the online support vector machine (SVM) regression and the fuzzy sets methods, is proposed. To account for the time dependence, the proposed approach is based on moving windows in order to take into account the past and new data for the model's adaptation. The fuzzy analysis is then applied to the generated residual data to give an evaluation of the condition monitoring. The proposed approach is applied to hot rolling for constructing a complementary condition monitoring system, which permits an online quality evaluation in the rolling process. Simulation results based on residual data show that the new approach is easily implementable. (C) 2010 Elsevier Ltd. All rights reserved.

引用

页码：1060 / 1068

页数：9

共 27 条

[1]

[Anonymous], 2002, Principal components analysis

[2]

[Anonymous], THESIS HELSINKI U TE

[3]

Bouhouche Salah, 2007, American Journal of Applied Sciences, V4, P637, DOI 10.3844/ajassp.2007.637.644

[4]

CHEN BJ, 2001, LOAD FORECASTING USI

[5]

David L., 2008, ADV DATA MINING TECH

[6] Soft-sensor development for fed-batch bioreactors using support vector regression [J].

Desai, K ;

Badhe, Y ;

Tambe, SS ;

Kulkarni, BD .

BIOCHEMICAL ENGINEERING JOURNAL, 2006, 27 (03) :225-239

[7]

DIMUTHU CK, 2000, ECOLOGY AGENT ORG, V7, P53

[8] Multiscale nonlinear principal component analysis (NLPCA) and its application for chemical process monitoring [J].

Geng, ZQ ;

Zhu, QX .

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2005, 44 (10) :3585-3593

[9] Robust recursive principal component analysis modeling for adaptive monitoring [J].

Jin, HD ;

Lee, YH ;

Lee, G ;

Han, CH .

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2006, 45 (02) :696-703

[10] Data-driven Soft Sensors in the process industry [J].

Kadlec, Petr ;

Gabrys, Bogdan ;

Strandt, Sibylle .

COMPUTERS & CHEMICAL ENGINEERING, 2009, 33 (04) :795-814

← 1 2 3 →