Development of Relationship Between Steel Billet Temperature and Data on Its Heating History for Continuous Furnace of Rolling-Mill Shop

Zhukov, Petr; Fomin, Andrey; Glushchenko, Anton

doi:10.1109/summa50634.2020.9280683

Cited by 2 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [ 22 ], a smart steel manufacturing framework is proposed in an Industry 4.0 context: an automatic identification tracking method for steel products is developed that is based on a vision-based approach. In [ 23 ], the Data Mining concept that is used to processes technological data is applied to steel billet heating in a continuous furnace of a rolling-mill shop. A regression dependence of the steel billet temperature that is based on its furnace heating history is obtained.…”

Section: Introductionmentioning

confidence: 99%

Data Analysis and Modelling of Billets Features in Steel Industry

Zanoli

Pepe

Moscoloni³

et al. 2022

Sensors

View full text Add to dashboard Cite

This study proposes a data analysis and modelization method for the rolling mill process of billets in steel plants. By exploiting rolling mill signals and advanced data processing algorithms, a reliable billet tracking system is designed, which tracks each workpiece from the furnace entrance to the rolling mill stands’ exit area. Based on the stored information, two problems are addressed: the data analysis of the temperature sensors (a thermal imaging camera and pyrometers) and the current that is related to the rolling mill stands’ absorption, and subsequently, a mathematical modelization of the billets’ temperature along their path in the rolling mill is produced. The data analysis suggested that we should perform hardware modifications: the thermal imaging camera was repositioned to avoid the effect of scale formation on the temperature measurements. The modelization phase provided the basis for future control and/or diagnosis applications that will exploit a temperature decay model.

show abstract

Section: Introductionmentioning

confidence: 99%