Deep Learning for Melt Pool Depth Contour Prediction From Surface Thermal Images via Vision Transformers
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911880858042368 |
|---|---|
| author | Ogoke, Francis Pak, Peter Myung-Won Myers, Alexander Quirarte, Guadalupe Beuth, Jack Malen, Jonathan Farimani, Amir Barati |
| author_facet | Ogoke, Francis Pak, Peter Myung-Won Myers, Alexander Quirarte, Guadalupe Beuth, Jack Malen, Jonathan Farimani, Amir Barati |
| contents | Insufficient overlap between the melt pools produced during Laser Powder Bed Fusion (L-PBF) can lead to lack-of-fusion defects and deteriorated mechanical and fatigue performance. In-situ monitoring of the melt pool subsurface morphology requires specialized equipment that may not be readily accessible or scalable. Therefore, we introduce a machine learning framework to correlate in-situ two-color thermal images observed via high-speed color imaging to the two-dimensional profile of the melt pool cross-section. Specifically, we employ a hybrid CNN-Transformer architecture to establish a correlation between single bead off-axis thermal image sequences and melt pool cross-section contours measured via optical microscopy. In this architecture, a ResNet model embeds the spatial information contained within the thermal images to a latent vector, while a Transformer model correlates the sequence of embedded vectors to extract temporal information. Our framework is able to model the curvature of the subsurface melt pool structure, with improved performance in high energy density regimes compared to analytical melt pool models. The performance of this model is evaluated through dimensional and geometric comparisons to the corresponding experimental melt pool observations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_17699 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Deep Learning for Melt Pool Depth Contour Prediction From Surface Thermal Images via Vision Transformers Ogoke, Francis Pak, Peter Myung-Won Myers, Alexander Quirarte, Guadalupe Beuth, Jack Malen, Jonathan Farimani, Amir Barati Machine Learning Computer Vision and Pattern Recognition Insufficient overlap between the melt pools produced during Laser Powder Bed Fusion (L-PBF) can lead to lack-of-fusion defects and deteriorated mechanical and fatigue performance. In-situ monitoring of the melt pool subsurface morphology requires specialized equipment that may not be readily accessible or scalable. Therefore, we introduce a machine learning framework to correlate in-situ two-color thermal images observed via high-speed color imaging to the two-dimensional profile of the melt pool cross-section. Specifically, we employ a hybrid CNN-Transformer architecture to establish a correlation between single bead off-axis thermal image sequences and melt pool cross-section contours measured via optical microscopy. In this architecture, a ResNet model embeds the spatial information contained within the thermal images to a latent vector, while a Transformer model correlates the sequence of embedded vectors to extract temporal information. Our framework is able to model the curvature of the subsurface melt pool structure, with improved performance in high energy density regimes compared to analytical melt pool models. The performance of this model is evaluated through dimensional and geometric comparisons to the corresponding experimental melt pool observations. |
| title | Deep Learning for Melt Pool Depth Contour Prediction From Surface Thermal Images via Vision Transformers |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.17699 |