Proceedings of the
9th International Conference of Asian Society for Precision Engineering and Nanotechnology (ASPEN2022)
15 – 18 November 2022, Singapore
doi:10.3850/978-981-18-6021-8_OR-01-0297
Review on the Use of Machine Learning Techniques to Optimize the Processing of Copper Alloys in Additive Manufacturing
Department of Mechanical Engineering, College of Design and Engineering, National University of Singapore, 9 Engineering Drive 1, Block EA, 117575, Singapore
ABSTRACT
Additive manufacturing (AM) affords unprecedented opportunity to mix materials on the fly during a build. This has seen the emergence of in-situ alloying in metal AM, an exciting area of research exploring the potential to develop novel high-performance materials. However, the mixing of constituent elements during melting currently lacks control. Local variations in the elemental distribution can occur across the build area and the exact composition of manufactured parts is unknown. Optimizing process parameters to build defect-free material, an essential task in any alloy development process for AM, is also labour-intensive. Here, we propose the use of in-situ process monitoring to measure and track elemental composition in laser powder bed fusion builds and assess consolidation optimality. In-situ process monitoring methods are briefly reviewed, revealing promising technologies for application. Both fixed and moving frame of reference imaging systems were found to have potential uses. Lastly, potential stages of the novel material development pipeline to which in-situ monitoring could be beneficial were discussed and necessary research objectives for this to be realized were identified.
Keywords: Copper alloys, Machine learning, Additive manufacturing, 3D printing, Powder bed fusion.
Department of Mechanical Engineering, College of Design and Engineering, National University of Singapore, 9 Engineering Drive 1, Block EA, 117575, Singapore
ABSTRACT
Additive manufacturing (AM) affords unprecedented opportunity to mix materials on the fly during a build. This has seen the emergence of in-situ alloying in metal AM, an exciting area of research exploring the potential to develop novel high-performance materials. However, the mixing of constituent elements during melting currently lacks control. Local variations in the elemental distribution can occur across the build area and the exact composition of manufactured parts is unknown. Optimizing process parameters to build defect-free material, an essential task in any alloy development process for AM, is also labour-intensive. Here, we propose the use of in-situ process monitoring to measure and track elemental composition in laser powder bed fusion builds and assess consolidation optimality. In-situ process monitoring methods are briefly reviewed, revealing promising technologies for application. Both fixed and moving frame of reference imaging systems were found to have potential uses. Lastly, potential stages of the novel material development pipeline to which in-situ monitoring could be beneficial were discussed and necessary research objectives for this to be realized were identified.
Keywords: Copper alloys, Machine learning, Additive manufacturing, 3D printing, Powder bed fusion.
