Nitinol (NiTi) has gained popularity across various industries due to its shape memory and superelastic properties. Recently, additive manufacturing (AM) has been increasingly utilized to produce NiTi components. This study focuses on single‐track nitinol samples fabricated via powder bed fusion using laser beam (PBF‐LB). Investigating the effects of laser power and scanning speed on melt pool dimensions reveals that melt pool width increases linearly with laser power and decreases logarithmically with scanning speed. However, melt pool depth exhibits outliers that deviate from these trends. Three analytical models are evaluated to predict melt pool dimensions, generally aligning with experimental trends. Notably, the Eagar–Tsai model delivers the most accurate predictions for melt pool width, with a mean absolute error of less than 10%, while the Gladush–Smurov model is more reliable for melt pool depth predictions, showing a mean absolute error under 20%. In contrast, the Rosenthal equation yields less reliable results for both dimensions. This suggests that a combined approach utilizing the strengths of both the Eagar–Tsai and Gladush–Smurov models may provide the most accurate predictions for the melt pool profile of NiTi in PBF‐LB.

This study provides a comprehensive analysis of residual stress characteristics in nitinol parts fabricated via laser powder bed fusion (PBF-LB). Unlike previous works that primarily focus on qualitative assessments or single-measurement techniques, this research employs a multi-modal experimental approach, Electronic Speckle Pattern Interferometry-Hole Drilling (ESPI-HD) and X-ray Diffraction (XRD), to achieve a more precise and spatially resolved evaluation of residual stress distribution. Furthermore, the study establishes a direct correlation between residual stress evolution and in situ pyrometric melt pool temperature data, an aspect that has not been extensively explored in prior investigations. A key novel finding is the non-monotonic relationship between volumetric energy density (VED) and residual stress. In this work, laser power was kept constant, and VED was varied by adjusting scanning speed and hatch spacing. The results show that the average residual stress initially increases with decreasing scan speed and hatch spacing, plateaus at a critical threshold, and subsequently decreases. However, residual stress was also found to vary in the build direction, indicating the complex stress distributions and accommodation mechanisms within the material. Additionally, an inverse relationship was recorded between the thermal gradient and VED which challenges conventional assumptions about their relationship. These insights offer a new perspective on optimizing PBF-LB process parameters for enhanced structural performance and long-term reliability of additively manufactured nitinol.

Powder bed fusion–laser beam (PBF-LB) of nickel–titanium (NiTi) has attracted increasing interest in aerospace, biomedical, and energy applications owing to its shape memory and superelastic properties, combined with the capability to fabricate complex geometries. However, the strong sensitivity of NiTi to thermal history and process variability makes predictive modeling and process parameter selection challenging. In this work, a physics-guided decision-support framework is developed for melt pool prediction and stability assessment during the PBF-LB processing of NiTi. A high-fidelity thermal finite element model incorporating CALPHAD-derived, temperature-dependent material properties was calibrated using a subset of experimental measurements and independently validated against additional experimental melt pool data. The calibrated model demonstrated good agreement with experiments, yielding mean absolute percentage errors of 4.22% and 5.63% for melt pool width and depth, respectively, on the validation dataset. A multi-output random forest surrogate trained on the validated simulation dataset enabled rapid prediction of melt pool geometric features, achieving test-set $R^2$ values exceeding 0.95, together with low MAE and RMSE values, while five-fold cross-validation confirmed robust predictive performance. The proposed framework integrates surrogate predictions with physics-based melt pool stability criteria to rapidly identify physically feasible processing conditions, thereby providing a computationally efficient foundation for future supervisory process control strategies.