0584910 - FZÚ 2025 RIV GB eng J - Journal Article
Stránský, O. - Tarant, Ivan - Beránek, L. - Holešovský, F. - Pathak, Sunil - Brajer, Jan - Mocek, Tomáš - Denk, Ondřej
Machine learning approach towards laser powder bed fusion manufactured AlSi10Mg thin tubes in laser shock peening.
Surface Engineering. Roč. 40, č. 1 (2024), s. 66-72. ISSN 0267-0844. E-ISSN 1743-2944
Institutional support: RVO:68378271
Keywords : laser powder bed fusion * laser shock peening * porosity * residual stresses * aluminium * machine learning * optimisation
OECD category: Optics (including laser optics and quantum optics)
Impact factor: 2.4, year: 2023 ; AIS: 0.298, rok: 2023
Method of publishing: Open access
DOI: https://doi.org/10.1177/02670844231221974

The industry’s demand for intricate geometries has spurred research into additive manufacturing (AM). Customising material properties, including surface roughness, integrity and porosity reduction, are the key industrial goals. This neces- sitates a holistic approach integrating AM, laser shock peening (LSP) and non-planar geometr y considerations. In this study, machine learning and neural networks offer a novel way to create intricate, abstract models capable of discerning complex process relationships. Our focus is on leveraging the certain range of laser parameters (energy, spot area, over- lap) to identify optimal residual stress, average surface roughness, and porosity values. Confirmatory experiments dem- onstrate close agreement, with an 8% discrepancy between modelled and actual residual stress values. This approach’s viability is evident even with limited datasets, provided proper precautions are taken.
Permanent Link: https://hdl.handle.net/11104/0352720