|About this Abstract
||2022 TMS Annual Meeting & Exhibition
||Advances in Surface Engineering IV
||Multi-objective Machine Learning Assisted Optimization of Multi-layered PVD Coatings
||Aida Amroussia, Andrew Detor, Scott Weaver, Patrick Shower, Anteneh Kebbede, Andrew Hoffman, Raul Rebak
|On-Site Speaker (Planned)
To increase the reliability and safety of existing fossil, biomass, and nuclear power plants, it is necessary to develop cost-effective coatings that provide improved wear and corrosion resistance in high temperature water and steam environments. Physical vapor deposition (PVD) coatings are widely used in different industries due to their scalability and good performance.
A large number of intertwined processing parameters such as voltage, pressure, carrier gas flow and target composition influence the resulting PVD coating microstructure, thickness, and performance. In this study, we leverage advances in machine learning to optimize the deposition parameters of our novel multi-layered PVD coatings (based on high-strength ceramics and metals). The results of our multi-objective optimization approach (microstructural features, solid particle erosion and steam oxidation resistance) will be presented and discussed in the context of improving overall system performance.
||Surface Modification and Coatings, Machine Learning,