Defects analysis in LPBF printing based on up-skin and down-skin angles using machine learning
Bibliographic record
Abstract
In laser powder bed fusion (LPBF) additive manufacturing, geometric features of parts have a significant impact on their printability and quality. Special attention in the literature has been given to the characteristic feature of distinction between up-skin and down-skin surface properties, where up-skin and down-skin surfaces have different orientation angles with respect to the build plate during part fabrication. We focus on slice-level, surface-connected defect analysis relative to up- and down-skin orientation using a YOLO→U-Net pipeline, followed by clustering and statistical morphology. We use a dataset acquired by X-ray CT scanning of LPBF-manufactured Ti–6Al–4V (Ti64) parts and 3D lattice structures with segmented regions of the top and bottom skins. This design allows slice-level analysis of defect geometry with respect to surface-normal direction. Lattice architectures with strut-based and surface-based features with a cell size of 2 mm and strut/wall thickness between 0.25-0.55 mm were utilized in this study. Machine learning and deep learning techniques such as YOLO and U-Net have significantly contributed to the precision and effectiveness of defect and pore detection and classification in 3D-printed components. Outcomes are expected to enhance the defect formation mechanism knowledge and allow optimization of print and design parameters toward improved quality and reliability of key application 3D printed parts.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.003 | 0.004 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".