Answers are grounded in this paper and cite their sources.
Review highlights machine learning's role in optimizing quality and stability in high-reflectivity metal laser fusion, suggesting improvements.
High-reflectivity metals (HRMs) have low absorption of near-infrared laser radiation and are prone to defects such as lack of fusion, balling, and pores during laser powder bed fusion (LPBF), making process stability and quality consistency difficult to ensure. Traditional trial-and-error experiments and purely numerical simulations involve long development cycles, high costs, and delayed feedback in process development, whereas machine learning provides new data-driven tools for parameter screening, process monitoring, and performance prediction. With the low absorptivity and high thermal conductivity of HRMs as the underlying physical basis, this review systematically summarizes the application progress of machine learning in process parameter optimization, process monitoring and quality assessment, and performance prediction. It further discusses the limitations of current studies in terms of data scale, cross-material generalization, physical consistency, and engineering validation, and proposes constructing standardized multimodal datasets, developing small-sample and transfer-learning strategies, and integrating physical information with interpretable models to support quality control and process optimization in HRMs-LPBF.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: