"The study focuses on the design of an automatic evaluation of the parameters for aluminium-based diffusion coatings that are applied to steel to protect the material's surface. The aim is to prevent adverse environmental influences on the material by appropriate choice of coating layer. The parameters of the coating layers are evaluated using data from electron microscope images. Our method leverages machine learning, integrating real and synthetically generated data to accurately determine material parameters," explained Petr Strakos, one of the paper's authors.
According to Strakos, this new method will facilitate the effective optimization of coatings for high-temperature and corrosion resistance, thereby advancing the development of specialized materials suited for demanding environments. It will be particularly beneficial in the energy sector, such as in the design of a new generation of steam turbines that can operate at higher temperatures than currently possible.