Steel is one of our most versatile material and we build everything from it from cars to skyscrapers. To improve the material further and develop the “next generation steel”, we need to understand its properties on a microscopic scale.

In collaboration with the Institute for Physical Metallurgy and Materials Physics at RWTH Aachen University we investigate the behaviour of steel under stress using artificial intelligence. One of the key challenges in this area of research is to investigate statistical effects: Human experts can only look at a few damage sites manually - but if we want to understand the material on a larger scale, we need to look at a large number of damage sites and understand their properties.

Here are the most recent publications:

  • Kusche C, Reclik T, Freund M, Al-Samman T, Kerzel U, Korte-Kerzel S (2019) Large-area, high-resolution characterisation and classification of damage mechanisms in dual-phase steel using deep learning. PLoS ONE 14(5): e0216493. https://doi.org/10.1371/journal.pone.0216493 Journal
  • Medghalchi, S., Kusche, C.F., Karimi, E. et al. Damage Analysis in Dual-Phase Steel Using Deep Learning: Transfer from Uniaxial to Biaxial Straining Conditions by Image Data Augmentation. JOM (2020). https://doi.org/10.1007/s11837-020-04404-0 Journal