Artificial intelligence (AI) and other data-driven methods offer solutions for complex systems that are difficult to model with classical methods. In this webinar, potentials and limitations of these solutions in ironmaking solutions are discussed. Preconditions regarding required data quality and completeness of data sets, reliability, combination with classical approaches are covered. Various applications are presented, such as smart sensors based on AI methods as well as the deployment and integration of data driven models into control systems.
- Blast furnace operators
- Plant managers
- Automation engineers
- Process optimization experts
- Data analytics experts
- Learn why generating insights from data in steel industry is different to a lot of other industries
- Learn about limitations applying data-driven methods at ironmaking
- Learn about potentials using data-driven methods in metals industry via various best practice examples
Product Manager, Primetals Technologies
Dieter graduated as a technical physicist from Johannes Kepler University in Linz/Austria and joined Primetals Technologies more than 25 years ago. After years in development, project management and project supervision in various international projects, he served as head of the European Steel Technology Platform project “Intelligent Manufacturing” and became Head of Energy and Environmental Care. For more than 5 years he has been product manager for Ironmaking Automation.