This repository contains the code for A deep learning framework for layer-wise porosity prediction in metal powder bed fusion using thermal signatures. The code provides the following functions:
- detection module to detect porosity using thermal signatures
- prediction module to predict future layer's porosity using previous layers' history information.
The basic requirement for using the files is a Python 3.8.19 environment with PyTorch 2.3.0
Here is a brief description of the files and folder content:
- detection_module.py: to detect porosity labels using thermal signatures.
- prediction_module.py: to predict future layer's porosity labels using previous layers' history information.
To generate the dataset, run detection_module.py file to detect porosity labels first. Next, run prediction_module.py to predict future layer's porosity labels using previous layers' history information.
The code was developed by Yuwei Mao from the CUCIS group at the Electrical and Computer Engineering Department at Northwestern University.
- Mao, Yuwei, Hui Lin, Christina Xuan Yu, Roger Frye, Darren Beckett, Kevin Anderson, Lars Jacquemetton et al. "A deep learning framework for layer-wise porosity prediction in metal powder bed fusion using thermal signatures." Journal of Intelligent Manufacturing 34, no. 1 (2023): 315-329. PDF
The research code shared in this repository is shared without any support or guarantee on its quality. However, please do raise an issue if you find anything wrong and I will try my best to address it.
email: yuweimao2019@u.northwestern.edu
Copyright (C) 2023, Northwestern University.
See COPYRIGHT notice in top-level directory.
This work was primarily supported by the following financial assistance award 70NANB19H005 from U.S. Department of Commerce, National Institute of Standards and Technology as part of the Center for Hierarchical Materials Design (CHiMaD). Partial support from Predictive Science and Engineering Design Cluster (PS &ED, Northwestern University); DOE awards DE-SC0019358, DE-SC0021399; and NSF award CMMI-2053929 is also acknowledged.