Monday 28th of September
| Timing | Speaker | Category |
|---|---|---|
| 13:00 | Welcome coffee | |
| 14:00 | Keynote speaker Valentina Colla Pisa University | |
| 14:40 | Keynote speaker Menno Van der Winden Umicore Deploying agentic AI within a large corporate to create bottom line impact | |
| 15:20 | Coffee break | |
| 15:40 | Robrecht Verhelle Bekaert A Robust Method for Multi Sensor Alignment applied during Hot Dip Galvanizing | Data Infrastructure & Industrial IoT |
| 16:00 | Jeroen Van Wittenberghe OCAS – ArcelorMittal On digital twins and fatigue crack sensors: how industrial IoT technology can increase the reliability of cranes in the steel industry | Data Infrastructure & Industrial IoT |
| 16:20 | Michael Sluydts ePotentia Can we trust generative AI for materials science? | Future Perspectives & Innovation |
| 16:40 | Tim De Grave ArcelorMittal Improving maintenance in steel plants: expert capture and enterprise data processing for MTTR reduction | Future Perspectives & Innovation |
Tuesday 29th of September
| Timing | Speaker | Category |
|---|---|---|
| 09:00 | Welcome coffee | |
| 09:20 | Keynote Speaker Gian-Marco Rignanese UC Louvain From high-throughput ab initio calculations to machine learning: the new era of materials informatics | |
| 10:00 | Keynote Speaker Ge Lei Imperial College London From trust to action: large language models for scientific discovery and decision support | |
| 10:40 | Coffee break | |
| 11:00 | Sergio Martin-del-Campo Viking Analytics Automatic fault detection in metal manufacturing via wireless vibration monitoring using behaviour-based analytics | Quality Assurance & Safety |
| 11:20 | Daniel Bartz Aurubis AG From pixels to PLC: architecting safe computer vision at the industrial edge | Quality Assurance & Safety |
| 11:40 | Jan Fransens Apixa NV Learning normality: anomaly detection as a scalable strategy for metallurgical surface inspection | Quality Assurance & Safety |
| 12:00 | Gaétan Symens CRM Group Zinc coating monitoring at hot dip galvanising | Quality Assurance & Safety |
| 12:20 | Lunch | |
| 13:40 | Thierry Decocq YQ Purchasing AI Prompt Engineering for Metallurgy Supply Chains | Supply Chain Optimization |
| 14:00 | David Waroquiers Matgenix Accelerating alloy and coating development using AI: A case study combining active learning and atomistic simulations | Alloy Development & Material Innovation |
| 14:20 | Pengru Zhao Université de Lorraine, CNRS, Université de Montpellier Deep learning-based grain boundary segmentation in backscattered electron images | Alloy Development & Material Innovation |
| 14:40 | Antoine Hilhorst UCLouvain, WEL Research Institute From data to discovery of TWIP alloys by linking stacking energies, composition, and mechanical properties | Alloy Development & Material Innovation |
| 15:00 | Jasper Somers Aluminium Duffel BV Integrating AI image analysis into filiform corrosion assessment of aluminium body sheet | Alloy Development & Material Innovation |
| 15:20 | Coffee break | |
| 15:40 | Pascal Jacques UCLouvain Machine learning approach for the development of new β-metastable Ti alloys best-suited for additive manufacturing | Alloy Development & Material Innovation |
| 16:00 | Michael Sluydts ePotentia, UGent Predicting real properties with fake data: how GenAI can help complete materials datasets | Alloy Development & Material Innovation |
| 16:20 | Alexis Miroux Aluminium Duffel BV Predicting the properties of aluminium rolled products from full‑scale production data | Alloy Development & Material Innovation |
| 16:40 | Nicolas Dubois Nyrstar Harnessing data science for zinc industry cellhouse – building a model that quantifies the impact of influencing factors on the current efficiency | Supply Chain Optimization |
| 18:30 | Conference dinner |
Wednesday 30th of September
| Timing | Speaker | Category |
|---|---|---|
| 09:00 | Welcome coffee | |
| 09:20 | Robert David Technord, ArcelorMittal Cowpers modeling and new driving paradigm | Process & Production Optimization |
| 09:40 | Olle Sandin Swerim Cross-process optimization in steel plate production through digital twin technology and distributed machine learning | Process & Production Optimization |
| 10:00 | Charles Snyers VUB Development of a model-free reinforcement learning-based MIMO controller for directed energy deposition using a simulation-based framework | Process & Production Optimization |
| 10:20 | Héléna Verbeeck UGent Toward reliable slag property prediction: from classical molecular dynamics to machine-learning force fields | Process & Production Optimization |
| 10:40 | Coffee break | |
| 11:00 | Els Nagels InsPyro Use of a digital twin do develop and optimize a H2 based alternative for Waelz kiln operations (Dust2Value project) | Process & Production Optimization |
| 11:20 | Philip Wolfram Aurubis AG Active learning for slag classification: from composition to environmental compliance | Environmental Compliance & Sustainability |
| 11:40 | Manuel Michiels Umicore AI-driven source attribution of fine dust emissions in precious metals recycling | Environmental Compliance & Sustainability |
| 12:00 | Akhilesh Swarnakar ESTEP Digitalisation as a decarbonisation accelerator: ESTEP’s integrated approach to sustainable steel production | Environmental Compliance & Sustainability |
This preliminary programme is not final and may be altered in the future.