TY - JOUR
T1 - High-performance prediction of molten steel temperature in tundish through gray-box model
AU - Okura, Toshinori
AU - Ahmad, Iftikhar
AU - Kano, Manabu
AU - Hasebe, Shinji
AU - Kitada, Hiroshi
AU - Murata, Noboru
PY - 2013
Y1 - 2013
N2 - A novel gray-box model is proposed to estimate molten steel temperature in a continuous casting process at a steel making plant by combining a first-principle model and a statistical model. The first-principle model was developed on the basis of computational fluid dynamics (CFD) simulations to simplify the model and to improve estimation accuracy. Since the derived first-principle model was not able to estimate the molten steel temperature in the tundish with sufficient accuracy, statistical models were developed to estimate the estimation errors of the first-principle model through partial least squares (PLS) and random forest (RF). As a result of comparing the three models, i.e., the first-principle model, the PLS-based graybox model, and the RF-based gray-box model, the RF-based gray-box model achieved the best estimation performance. Thus, the molten steel temperature in the tundish can be estimated with accuracy by adding estimates of the first-principle model and those of the statistical RF model. The proposed gray-box model was applied to the real process data and the results demonstrated its advantage over other models.
AB - A novel gray-box model is proposed to estimate molten steel temperature in a continuous casting process at a steel making plant by combining a first-principle model and a statistical model. The first-principle model was developed on the basis of computational fluid dynamics (CFD) simulations to simplify the model and to improve estimation accuracy. Since the derived first-principle model was not able to estimate the molten steel temperature in the tundish with sufficient accuracy, statistical models were developed to estimate the estimation errors of the first-principle model through partial least squares (PLS) and random forest (RF). As a result of comparing the three models, i.e., the first-principle model, the PLS-based graybox model, and the RF-based gray-box model, the RF-based gray-box model achieved the best estimation performance. Thus, the molten steel temperature in the tundish can be estimated with accuracy by adding estimates of the first-principle model and those of the statistical RF model. The proposed gray-box model was applied to the real process data and the results demonstrated its advantage over other models.
KW - Gray-box modeling
KW - Soft-sensor
KW - Steel making process
KW - Virtual sensing
UR - http://www.scopus.com/inward/record.url?scp=84873828903&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84873828903&partnerID=8YFLogxK
U2 - 10.2355/isijinternational.53.76
DO - 10.2355/isijinternational.53.76
M3 - Article
AN - SCOPUS:84873828903
VL - 53
SP - 76
EP - 80
JO - Transactions of the Iron and Steel Institute of Japan
JF - Transactions of the Iron and Steel Institute of Japan
SN - 0915-1559
IS - 1
ER -