Overhang structures are essential geometries in metal additive manufacturing for realizing complex shapes. However, achieving stable, support-free overhang structures requires precise control of process parameters, and securing shape fidelity becomes particularly challenging as overhang length increases due to thermal deformation. To address this challenge, this study proposed a Bayesian optimization framework for efficiently identifying optimal process parameters to fabricate high-difficulty overhang structures. An image-based scoring method was developed to quantitatively evaluate shape defects. Experimental data were collected by fabricating 3, 6, and 9 mm overhang structures with various process parameters. Based on collected data, Gaussian Process Regression (GPR) models were trained. A physics-informed soft penalty term based on energy density was incorporated to construct a surrogate model capable of making physically plausible predictions even in extrapolated regions. Using this model, Bayesian optimization was applied to overhang lengths of 12, 15, and 18 mm, for which no prior experimental data existed. Recommended parameters enabled stable, support-free fabrication of overhang structures. This study demonstrates that reliable optimization of process parameters for complex geometries can be achieved by combining minimal experimental data with physics-informed modeling, highlighting the framework’s potential extension to a wider range of geometries and processes

In the selective laser melting (SLM) process, a three-dimensional part is manufactured based on the formation of numerous molten tracks. Consequently, the generated melt pool in the scanning process of each track exhibits close relation to the internal defect formation and the quality of the fabricated part. In this study, a numerical model of single-track scanning of the SLM process is presented to analyze the melt pool characteristics for various process conditions. The presented model considers the thermal behavior of the powder material including the phase change and densification during the SLM process. The temperature-dependent energy absorption and the increase in effective energy absorptivity due to the keyhole mode melting are also incorporated in the heat flux model to evaluate the process conditions in the presence of high energy density. Moreover, the single-track specimens were manufactured under various process conditions for validation of the proposed model. The predicted melt pool dimensions, as well as the melting modes (Conduction/Keyhole), demonstrated good agreement with the experimental measurements. Based on the analysis results, the process boundaries (Keyhole/Lack-of-Fusion) for the SLM process of AlSi10Mg are provided and the potential application of the proposed model for exploring the process window is discussed.