Transformer based spatially resolved prediction of mechanical properties in wire arc additive manufacturing
Bibliographic record
Abstract
Metal additive manufacturing (MAM) provides remarkable design and component geometry freedom over various materials. One of the most recent MAM methods is the wire-arc additive manufacturing (WAAM) technique, which provides a higher deposition rate than other methods. This method also suffered from heterogeneity in location-based thermal profiles, leading to spatial variation in the properties of as-built mechanical properties, which become more complicated in the manufacturing design and process of large parts. To address this, we developed a data-driven spatio-temporal model based on transformer architecture to predict the location-dependent mechanical properties based on the thermal history of fabricated parts with multiple contours. The framework enables the dynamic emissivity calculation of the part for various temperatures and layer ranges to reduce the error of thermal history acquisition. We systematically compared the proposed approach's performance with other machine learning methods. The results demonstrate that the framework achieves good prediction capabilities using a small dataset. It provides a state-of-the-art methodology for predicting the spatial and temporal evolution of mechanical properties leveraging the transformer architecture. Finally, for model prediction interpretation, we investigated the location-aware morphology with various thermal profiles and mechanical properties, which allowed us to explain the reason behind each prediction.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".