Machine Learning-Guided Optimization of Defects in In-Situ Alloyed Additively Manufactured Parts
| dc.contributor.author | Shelesh Nezhad, Shaaf | |
| dc.date.accessioned | 2025-12-15T06:26:31Z | |
| dc.date.available | 2025-12-15T06:26:31Z | |
| dc.date.issued | 2025 | |
| dc.description.abstract | In-situ alloying during laser powder bed fusion (LPBF) offers great compositional flexibility but is prone to process-induced defects such as lack of fusion, porosity, unmelted particles, etc. To address this problem, we developed a machine learning framework to predict and minimize major defects such as porosity (originating from lack of fusion or keyholing) and unmelted Nb particles in LPBF-fabricated in-situ alloyed Ti-45Nb. For this purpose, two least-squares boosting (LSBoost) ensemble regressors were trained using five process parameters (part shape, laser power, scan speed, hatch spacing, and scan rotation), along with their polynomial and interaction terms, to capture nonlinear relationships. These models achieved high accuracy, with R² values over 0.98 in both models. The grouped permutation importance revealed that porosity is primarily governed by hatch spacing and laser power, whereas unmelted Nb particles are primarily governed by laser power and scan speed. The models were implemented in two graphical interfaces: a forward predictor for real-time defect estimation and an inverse optimizer for identifying low-defect parameter sets. Together, they establish a unified, data-driven approach for defect-aware process optimization in in-situ alloyed systems, offering a pathway towards reproducible, low-defect additive manufacturing. | |
| dc.description.scholarlevel | Graduate | |
| dc.identifier.uri | https://hdl.handle.net/1828/22987 | |
| dc.language.iso | en | |
| dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 International | en |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | |
| dc.subject | Additive Manufacturing | |
| dc.subject | Laser Powder Bed Fusion (LPBF) | |
| dc.subject | In-Situ Alloying | |
| dc.subject | Titanium-Niobium Alloy | |
| dc.subject | Machine Learning | |
| dc.subject | Defect prediction | |
| dc.subject.department | Department of Mechanical Engineering | |
| dc.title | Machine Learning-Guided Optimization of Defects in In-Situ Alloyed Additively Manufactured Parts | |
| dc.type | Technical Report |