Application of Machine Learning for Defective Coil Prediction
Wednesday, 8 July 2020 • 10–11 a.m. EDT
Gina Verbanac; Danieli Automation S.p.A.
Gina Verbanac is a software design engineer with Danieli Automation, Digi&Met division. Verbanac has experience working with Industry 4.0 projects as a software engineer and Agile team leader. Verbanac’s previous work includes project leadership on a machine learning project for coil defect prediction, six years of experience as a software design engineer of level 2 (L2) systems for meltshops and continuous casters (CCMs), and more than five years as commissioner of a level 2 system for CCMs and flat cold machines. Verbanac’s research interests include clean code principles, artificial intelligence, astronomy, and canine psychology and behavior.
Availability of data from connected processes and breakthrough innovations in computing tools create exciting perspectives for artificial intelligence applications in the metals industry. Acciai Speciali Terni, in partnership with Danieli Automation and the University of Perugia, decided to embrace this opportunity combining longstanding process expertise with a modern digital infrastructure and machine-learning algorithms to extract actionable correlations from collected data. The initial step of this digital transformation process was focused on a predictive quality use case, with the target to highlight the correlations between the process parameters of the recently upgraded CC3 caster and surface defects identified on coils after rolling.
Philip Woodward; Danieli Taranis LLC
Phil Woodward is currently the Digimet sales manager for Danieli Taranis LLC in Birmingham, Ala., USA. Woodward has worked for system integration companies serving the metals industry for more than 30 years and has been involved with digitalization and Industry 4.0 since 2017. He holds a B.S. degree in computer science and mathematics from the University of Manchester in the U.K.
Woodward has been a member of AIST since 1995 and currently serves on the AIST Digital Transformation Organizing Committee.
AIST’s Electrical Applications/Sensors Subcommittee and Digitalization Applications Technology Committees.