Pioneering ML-driven framework for in-situ vertical surface roughness prediction in LPBF
Bibliographic record
Abstract
Real-time prediction of vertical surface roughness in laser powder bed fusion (LPBF) is essential for process control and quality assurance, yet it remains largely unexplored due to view-blocking by loose powder in the machine bed. This study introduces the first integrated framework that combines in-situ photodiode monitoring with machine learning (ML) to predict sidewall roughness during fabrication. A high-speed photodiode sensor captures melt pool intensity signals near vertical surfaces, which are processed into time- and frequency-domain features. These features, together with process parameters, serve as inputs to ML models, while post-process surface roughness measurements (Sa), obtained via laser scanning confocal microscopy, are used as outputs during training. Once trained, the model can then be applied in real-time to predict roughness directly from photodiode signals acquired during printing, enabling side-specific monitoring without additional measurement steps. Among the five models evaluated, Random Forest (RF) and eXtreme Gradient Boosting (XGB) achieved the highest predictive accuracy, with RF improving from R2 = 0.35 (parameters only) to R2 = 0.78 when in-situ features were included. This framework demonstrates that photodiode-based monitoring, coupled with ML, enables reliable, side-specific, real-time prediction of vertical surface roughness in LPBF, offering a pathway towards adaptive quality control and reduced post-processing.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".