The role of neural networks in the optimisation of rolling processes

Jari Larkiola, Antti Korhonen, P. Myllykoski (Corresponding Author), L. Cser

Research output: Contribution to journalArticleScientificpeer-review

47 Citations (Scopus)

Abstract

Applications of neural networks in the rolling of steel are reviewed. The first papers on the topic were published in 1991 and since then the number of publications has steadily increased. In most applications today, so-called back propagation networks are used.
After briefly reviewing the various neural network types, the results of two case studies at Rautaruukki cold strip mill are presented. In the first case an efficiency model for tandem cold rolling was developed. By using the model it is possible to study whether a new product with a given width, strength or thickness can be produced, and the optimised mill settings can then be determined. A 1.8% improvement in efficiency was obtained with the model.
The second case concerns the prediction of the mechanical properties of steel strips and temper rolling force by using neural network modelling and measured process data.
The location of the coils in annealing stacks and their vanadium content were found to explain the deviation in mechanical properties. The temper rolling force could be predicted with good accuracy, which can be exploited in determining mill pre-settings.
Original languageEnglish
Pages (from-to)16-23
JournalJournal of Materials Processing Technology
Volume80-81
DOIs
Publication statusPublished - 1998
MoE publication typeNot Eligible

Fingerprint

Steel
Neural networks
Strip mills
Mechanical properties
Vanadium
Cold rolling
Backpropagation
Annealing

Cite this

Larkiola, Jari ; Korhonen, Antti ; Myllykoski, P. ; Cser, L. / The role of neural networks in the optimisation of rolling processes. In: Journal of Materials Processing Technology. 1998 ; Vol. 80-81. pp. 16-23.
@article{2d85597ed5694d599d73ec4afae40a68,
title = "The role of neural networks in the optimisation of rolling processes",
abstract = "Applications of neural networks in the rolling of steel are reviewed. The first papers on the topic were published in 1991 and since then the number of publications has steadily increased. In most applications today, so-called back propagation networks are used. After briefly reviewing the various neural network types, the results of two case studies at Rautaruukki cold strip mill are presented. In the first case an efficiency model for tandem cold rolling was developed. By using the model it is possible to study whether a new product with a given width, strength or thickness can be produced, and the optimised mill settings can then be determined. A 1.8{\%} improvement in efficiency was obtained with the model. The second case concerns the prediction of the mechanical properties of steel strips and temper rolling force by using neural network modelling and measured process data. The location of the coils in annealing stacks and their vanadium content were found to explain the deviation in mechanical properties. The temper rolling force could be predicted with good accuracy, which can be exploited in determining mill pre-settings.",
author = "Jari Larkiola and Antti Korhonen and P. Myllykoski and L. Cser",
year = "1998",
doi = "10.1016/S0924-0136(98)00206-4",
language = "English",
volume = "80-81",
pages = "16--23",
journal = "Journal of Materials Processing Technology",
issn = "0924-0136",
publisher = "Elsevier",

}

The role of neural networks in the optimisation of rolling processes. / Larkiola, Jari; Korhonen, Antti; Myllykoski, P. (Corresponding Author); Cser, L.

In: Journal of Materials Processing Technology, Vol. 80-81, 1998, p. 16-23.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - The role of neural networks in the optimisation of rolling processes

AU - Larkiola, Jari

AU - Korhonen, Antti

AU - Myllykoski, P.

AU - Cser, L.

PY - 1998

Y1 - 1998

N2 - Applications of neural networks in the rolling of steel are reviewed. The first papers on the topic were published in 1991 and since then the number of publications has steadily increased. In most applications today, so-called back propagation networks are used. After briefly reviewing the various neural network types, the results of two case studies at Rautaruukki cold strip mill are presented. In the first case an efficiency model for tandem cold rolling was developed. By using the model it is possible to study whether a new product with a given width, strength or thickness can be produced, and the optimised mill settings can then be determined. A 1.8% improvement in efficiency was obtained with the model. The second case concerns the prediction of the mechanical properties of steel strips and temper rolling force by using neural network modelling and measured process data. The location of the coils in annealing stacks and their vanadium content were found to explain the deviation in mechanical properties. The temper rolling force could be predicted with good accuracy, which can be exploited in determining mill pre-settings.

AB - Applications of neural networks in the rolling of steel are reviewed. The first papers on the topic were published in 1991 and since then the number of publications has steadily increased. In most applications today, so-called back propagation networks are used. After briefly reviewing the various neural network types, the results of two case studies at Rautaruukki cold strip mill are presented. In the first case an efficiency model for tandem cold rolling was developed. By using the model it is possible to study whether a new product with a given width, strength or thickness can be produced, and the optimised mill settings can then be determined. A 1.8% improvement in efficiency was obtained with the model. The second case concerns the prediction of the mechanical properties of steel strips and temper rolling force by using neural network modelling and measured process data. The location of the coils in annealing stacks and their vanadium content were found to explain the deviation in mechanical properties. The temper rolling force could be predicted with good accuracy, which can be exploited in determining mill pre-settings.

U2 - 10.1016/S0924-0136(98)00206-4

DO - 10.1016/S0924-0136(98)00206-4

M3 - Article

VL - 80-81

SP - 16

EP - 23

JO - Journal of Materials Processing Technology

JF - Journal of Materials Processing Technology

SN - 0924-0136

ER -