Summary of Thermopore: Predicting Part Porosity Based on Thermal Images Using Deep Learning, by Peter Myung-won Pak et al.
ThermoPore: Predicting Part Porosity Based on Thermal Images Using Deep Learning
by Peter Myung-Won Pak, Francis Ogoke, Andrew Polonsky, Anthony Garland, Dan S. Bolintineanu, Dan R. Moser, Michael J. Heiden, Amir Barati Farimani
First submitted to arxiv on: 23 Apr 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed deep learning approach uses thermal image monitoring data to quantify and localize porosity within Laser Powder Bed Fusion fabricated samples. The model combines Convolutional Neural Network architecture for pore count prediction with Video Vision Transformer’s spatial and temporal attention mechanisms for area localization. The porosity quantification achieved an R2 score of 0.57, while the localization produced average IoU scores of 0.32 and a maximum of 1.0. This work establishes foundations for part porosity “Digital Twins” based on additive manufacturing monitoring data, reducing post-inspection testing activities. Additionally, machine learning analysis accelerates acquisition of crucial insights typically available through ex-situ part evaluation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research creates a way to use thermal images taken during the 3D printing process to measure and locate porosity in the final product. The model is like a digital twin that can help reduce testing time and costs by providing real-time information about porosity. This can be very useful for making sure parts meet quality standards and for understanding how different printing settings affect the final product. |
Keywords
» Artificial intelligence » Attention » Deep learning » Machine learning » Neural network » Vision transformer
