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 this paper, the reliability-based parameter study is carried out for the stamping process of a front rail roof member with the ultra high strength steel, considering the scatters of the material properties and the process parameters. With the reliability-based design optimization (RBDO) scheme, the springback tendency is investigated from the perturbation of the process parameters such as the sheet thickness, ultimate tensile strength, yield strength, Coulomb friction coefficient, and applied padding force. The amount of the elastic recovery along the height direction is quantified to describe the springback tendency from the analysis. The analysis shows the springback-amount scattering is not ignorable when the yield stress scatters within the similar range of the ultimate tensile strength. The analysis results fully explain the importance of controlling the scatters as well as the average yield-strength amount in the mass production of the stamped products.