Process screening in additive manufacturing: Detection of keyhole mode using surface topography and machine learning
Bibliographic record
Abstract
• Proposed a facile strategy to infer part microstructure using surface topography. • Achieved successful laser powder bed fusion of non-spherical Al7075 powders enhanced with nanoparticles. • Demonstrated the prediction of keyhole melting using surface topographical features and an interpretable machine learning model. Screening of defective additive manufactured (AM) parts is crucial for ensuring process consistency and part reliability, yet common microstructural inspection methods can be time-consuming or destructive. This study explores how surface analysis combined with machine learning (ML) algorithms can effectively infer the microstructure of laser powder bed fusion (LPBF) parts. As a case study, non-spherical ZrH₂ nanoparticle-enhanced AA7075 aluminum powders was fabricated using 60 different LPBF recipes. ML classification models were then employed to link side-surface topographical features to keyhole melting occurring within the parts. Among the tested ML models, random forest (RF) achieving a testing accuracy of 95 % and an F1-score of 0.98, outperforming both the neural network (NN) and support vector machine (SVM) models. To enhance the interpretability of the ML model, the RF model was leveraged to identify the hierarchical importance of surface features associated with keyhole melting mode. This resulted in the development of keyhole-probability maps based on superficial surface parameters, providing engineers with an effective and easy-to-use tool for screening keyhole mode parts. While further validation is needed, the proposed strategy lays a foundation for leveraging surface topography to infer microstructural features and adapting the method to different material systems.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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".