Semi-supervised CAPP Transformer Learning via Pseudo-labeling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917239773462528 |
|---|---|
| author | Gross, Dennis Spieker, Helge Gotlieb, Arnaud Stathatos, Emmanuel Benardos, Panorios Vosniakos, George-Christopher |
| author_facet | Gross, Dennis Spieker, Helge Gotlieb, Arnaud Stathatos, Emmanuel Benardos, Panorios Vosniakos, George-Christopher |
| contents | High-level Computer-Aided Process Planning (CAPP) generates manufacturing process plans from part specifications. It suffers from limited dataset availability in industry, reducing model generalization. We propose a semi-supervised learning approach to improve transformer-based CAPP transformer models without manual labeling. An oracle, trained on available transformer behaviour data, filters correct predictions from unseen parts, which are then used for one-shot retraining. Experiments on small-scale datasets with simulated ground truth across the full data distribution show consistent accuracy gains over baselines, demonstrating the method's effectiveness in data-scarce manufacturing environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01419 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Semi-supervised CAPP Transformer Learning via Pseudo-labeling Gross, Dennis Spieker, Helge Gotlieb, Arnaud Stathatos, Emmanuel Benardos, Panorios Vosniakos, George-Christopher Machine Learning Artificial Intelligence High-level Computer-Aided Process Planning (CAPP) generates manufacturing process plans from part specifications. It suffers from limited dataset availability in industry, reducing model generalization. We propose a semi-supervised learning approach to improve transformer-based CAPP transformer models without manual labeling. An oracle, trained on available transformer behaviour data, filters correct predictions from unseen parts, which are then used for one-shot retraining. Experiments on small-scale datasets with simulated ground truth across the full data distribution show consistent accuracy gains over baselines, demonstrating the method's effectiveness in data-scarce manufacturing environments. |
| title | Semi-supervised CAPP Transformer Learning via Pseudo-labeling |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2602.01419 |