Modelling the strip thickness in hot steel rolling mills using least-squares support vector machines

Yuri A.W. Shardt; Siamak Mehrkanoon; Kai Zhang; Xu Yang; Johan Suykens; Steven X. Ding; Kaixiang Peng

doi:10.1002/cjce.22956

Modelling the strip thickness in hot steel rolling mills using least-squares support vector machines

Yuri A.W. Shardt, Siamak Mehrkanoon, Kai Zhang, Xu Yang^*, Johan Suykens, Steven X. Ding, Kaixiang Peng

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

The development and implementation of better control strategies to improve the overall performance of a plant is often hampered by the lack of available measurements of key quality variables. One way to resolve this problem is to develop a soft sensor that is capable of providing process information as often as necessary for control. One potential area for implementation is in a hot steel rolling mill, where the final strip thickness is the most important variable to consider. Difficulties with this approach include the fact that the data may not be available when needed or that different conditions (operating points) will produce different process conditions. In this paper, a soft sensor is developed for the hot steel rolling mill process using least-squares support vector machines and a properly designed bias update term. It is shown that the system can handle multiple different operating conditions (different strip thickness setpoints, and input conditions).

Original language	English
Pages (from-to)	171-178
Number of pages	8
Journal	Canadian Journal of Chemical Engineering
Volume	96
Issue number	1
DOIs	https://doi.org/10.1002/cjce.22956
Publication status	Published - Jan 2018

Bibliographical note

Funding Information:
Yuri Shardt would like to thank the “Programms zur Fo€rderung des exzellenten wissenschaftlichen Nachwuchses” of the University of Duisburg-Essen for funding parts of this research. Xu Yang would like to thank the National Natural Science Foundation of China (Grant #61673053), the Beijing Natural Science Foundation (Grant #4162041), and the Fundamental Research Funds for Central Universities (Grant #FRF-BR-16-025A) for funding. Johan Suykens and Siamak Mehrkanoon acknowledge support from KU Leuven, the Flemish government, FWO, the Belgian Federal Science Policy Office, and the European Research Council (ERC Project AdG A-DATADRIVE-B (290923), CoE PFV/10/002 (OPTEC), GOA MANET, IUAP DYSCO, FWO Grant No. G.0377.12).

Funding Information:
Yuri Shardt would like to thank the “Programms zur Förderung des exzellenten wissenschaftlichen Nachwuchses” of the University of Duisburg-Essen for funding parts of this research. Xu Yang would like to thank the National Natural Science Foundation of China (Grant #61673053), the Beijing Natural Science Foundation (Grant #4162041), and the Fundamental Research Funds for Central Universities (Grant #FRF-BR-16- 025A) for funding. Johan Suykens and Siamak Mehrkanoon acknowledge support from KU Leuven, the Flemish government, FWO, the Belgian Federal Science Policy Office, and the European Research Council (ERC Project AdG A-DATADRIVEB (290923), CoE PFV/10/002 (OPTEC), GOA MANET, IUAP DYSCO, FWO Grant No. G.0377.12).

Publisher Copyright:
© 2017 Canadian Society for Chemical Engineering.

Funding

Yuri Shardt would like to thank the “Programms zur Fo€rderung des exzellenten wissenschaftlichen Nachwuchses” of the University of Duisburg-Essen for funding parts of this research. Xu Yang would like to thank the National Natural Science Foundation of China (Grant #61673053), the Beijing Natural Science Foundation (Grant #4162041), and the Fundamental Research Funds for Central Universities (Grant #FRF-BR-16-025A) for funding. Johan Suykens and Siamak Mehrkanoon acknowledge support from KU Leuven, the Flemish government, FWO, the Belgian Federal Science Policy Office, and the European Research Council (ERC Project AdG A-DATADRIVE-B (290923), CoE PFV/10/002 (OPTEC), GOA MANET, IUAP DYSCO, FWO Grant No. G.0377.12). Yuri Shardt would like to thank the “Programms zur Förderung des exzellenten wissenschaftlichen Nachwuchses” of the University of Duisburg-Essen for funding parts of this research. Xu Yang would like to thank the National Natural Science Foundation of China (Grant #61673053), the Beijing Natural Science Foundation (Grant #4162041), and the Fundamental Research Funds for Central Universities (Grant #FRF-BR-16- 025A) for funding. Johan Suykens and Siamak Mehrkanoon acknowledge support from KU Leuven, the Flemish government, FWO, the Belgian Federal Science Policy Office, and the European Research Council (ERC Project AdG A-DATADRIVEB (290923), CoE PFV/10/002 (OPTEC), GOA MANET, IUAP DYSCO, FWO Grant No. G.0377.12).

Keywords

Process systems engineering
Soft sensors
Steel mill
Support vector machines

Access to Document

10.1002/cjce.22956

Cite this

@article{987aea39b68245b8a4b26ca59a7ccf4c,

title = "Modelling the strip thickness in hot steel rolling mills using least-squares support vector machines",

abstract = "The development and implementation of better control strategies to improve the overall performance of a plant is often hampered by the lack of available measurements of key quality variables. One way to resolve this problem is to develop a soft sensor that is capable of providing process information as often as necessary for control. One potential area for implementation is in a hot steel rolling mill, where the final strip thickness is the most important variable to consider. Difficulties with this approach include the fact that the data may not be available when needed or that different conditions (operating points) will produce different process conditions. In this paper, a soft sensor is developed for the hot steel rolling mill process using least-squares support vector machines and a properly designed bias update term. It is shown that the system can handle multiple different operating conditions (different strip thickness setpoints, and input conditions).",

keywords = "Process systems engineering, Soft sensors, Steel mill, Support vector machines",

author = "Shardt, \{Yuri A.W.\} and Siamak Mehrkanoon and Kai Zhang and Xu Yang and Johan Suykens and Ding, \{Steven X.\} and Kaixiang Peng",

note = "Funding Information: Yuri Shardt would like to thank the “Programms zur Fo€rderung des exzellenten wissenschaftlichen Nachwuchses” of the University of Duisburg-Essen for funding parts of this research. Xu Yang would like to thank the National Natural Science Foundation of China (Grant \#61673053), the Beijing Natural Science Foundation (Grant \#4162041), and the Fundamental Research Funds for Central Universities (Grant \#FRF-BR-16-025A) for funding. Johan Suykens and Siamak Mehrkanoon acknowledge support from KU Leuven, the Flemish government, FWO, the Belgian Federal Science Policy Office, and the European Research Council (ERC Project AdG A-DATADRIVE-B (290923), CoE PFV/10/002 (OPTEC), GOA MANET, IUAP DYSCO, FWO Grant No. G.0377.12). Funding Information: Yuri Shardt would like to thank the “Programms zur F{\"o}rderung des exzellenten wissenschaftlichen Nachwuchses” of the University of Duisburg-Essen for funding parts of this research. Xu Yang would like to thank the National Natural Science Foundation of China (Grant \#61673053), the Beijing Natural Science Foundation (Grant \#4162041), and the Fundamental Research Funds for Central Universities (Grant \#FRF-BR-16- 025A) for funding. Johan Suykens and Siamak Mehrkanoon acknowledge support from KU Leuven, the Flemish government, FWO, the Belgian Federal Science Policy Office, and the European Research Council (ERC Project AdG A-DATADRIVEB (290923), CoE PFV/10/002 (OPTEC), GOA MANET, IUAP DYSCO, FWO Grant No. G.0377.12). Publisher Copyright: {\textcopyright} 2017 Canadian Society for Chemical Engineering.",

year = "2018",

month = jan,

doi = "10.1002/cjce.22956",

language = "English",

volume = "96",

pages = "171--178",

journal = "Canadian Journal of Chemical Engineering",

issn = "0008-4034",

publisher = "John Wiley and Sons Inc.",

number = "1",

}

TY - JOUR

T1 - Modelling the strip thickness in hot steel rolling mills using least-squares support vector machines

AU - Shardt, Yuri A.W.

AU - Mehrkanoon, Siamak

AU - Zhang, Kai

AU - Yang, Xu

AU - Suykens, Johan

AU - Ding, Steven X.

AU - Peng, Kaixiang

N1 - Funding Information: Yuri Shardt would like to thank the “Programms zur Fo€rderung des exzellenten wissenschaftlichen Nachwuchses” of the University of Duisburg-Essen for funding parts of this research. Xu Yang would like to thank the National Natural Science Foundation of China (Grant #61673053), the Beijing Natural Science Foundation (Grant #4162041), and the Fundamental Research Funds for Central Universities (Grant #FRF-BR-16-025A) for funding. Johan Suykens and Siamak Mehrkanoon acknowledge support from KU Leuven, the Flemish government, FWO, the Belgian Federal Science Policy Office, and the European Research Council (ERC Project AdG A-DATADRIVE-B (290923), CoE PFV/10/002 (OPTEC), GOA MANET, IUAP DYSCO, FWO Grant No. G.0377.12). Funding Information: Yuri Shardt would like to thank the “Programms zur Förderung des exzellenten wissenschaftlichen Nachwuchses” of the University of Duisburg-Essen for funding parts of this research. Xu Yang would like to thank the National Natural Science Foundation of China (Grant #61673053), the Beijing Natural Science Foundation (Grant #4162041), and the Fundamental Research Funds for Central Universities (Grant #FRF-BR-16- 025A) for funding. Johan Suykens and Siamak Mehrkanoon acknowledge support from KU Leuven, the Flemish government, FWO, the Belgian Federal Science Policy Office, and the European Research Council (ERC Project AdG A-DATADRIVEB (290923), CoE PFV/10/002 (OPTEC), GOA MANET, IUAP DYSCO, FWO Grant No. G.0377.12). Publisher Copyright: © 2017 Canadian Society for Chemical Engineering.

PY - 2018/1

Y1 - 2018/1

N2 - The development and implementation of better control strategies to improve the overall performance of a plant is often hampered by the lack of available measurements of key quality variables. One way to resolve this problem is to develop a soft sensor that is capable of providing process information as often as necessary for control. One potential area for implementation is in a hot steel rolling mill, where the final strip thickness is the most important variable to consider. Difficulties with this approach include the fact that the data may not be available when needed or that different conditions (operating points) will produce different process conditions. In this paper, a soft sensor is developed for the hot steel rolling mill process using least-squares support vector machines and a properly designed bias update term. It is shown that the system can handle multiple different operating conditions (different strip thickness setpoints, and input conditions).

AB - The development and implementation of better control strategies to improve the overall performance of a plant is often hampered by the lack of available measurements of key quality variables. One way to resolve this problem is to develop a soft sensor that is capable of providing process information as often as necessary for control. One potential area for implementation is in a hot steel rolling mill, where the final strip thickness is the most important variable to consider. Difficulties with this approach include the fact that the data may not be available when needed or that different conditions (operating points) will produce different process conditions. In this paper, a soft sensor is developed for the hot steel rolling mill process using least-squares support vector machines and a properly designed bias update term. It is shown that the system can handle multiple different operating conditions (different strip thickness setpoints, and input conditions).

KW - Process systems engineering

KW - Soft sensors

KW - Steel mill

KW - Support vector machines

UR - https://www.scopus.com/pages/publications/85046969444

U2 - 10.1002/cjce.22956

DO - 10.1002/cjce.22956

M3 - Article

AN - SCOPUS:85046969444

SN - 0008-4034

VL - 96

SP - 171

EP - 178

JO - Canadian Journal of Chemical Engineering

JF - Canadian Journal of Chemical Engineering

IS - 1

ER -

Modelling the strip thickness in hot steel rolling mills using least-squares support vector machines

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this