Contrastive Adversarial Domain Adaptation for Machine Remaining Useful Life Predictionn (CADA) [Paper]
- Python3.x
- Pytorch==1.7
- Numpy
- Sklearn
- Pandas
- mat4py (for Fault diagnosis preprocessing)
We used NASA turbofan engines dataset
- run_the data/data_preprocessing.py to apply the preprocessings.
- Output the data form each domain in tuple format train_x, train_y, test_x, test_y
- Put the data in the data folder
- run python main_cross_domains.py
@article{CADA,
author={M. {Ragab} and Z. {Chen} and M. {Wu} and C. S. {Foo} and K. C. {Keong} and R. {Yan} and X. -L. {Li}},
journal={IEEE Transactions on Industrial Informatics},
title={Contrastive Adversarial Domain Adaptation for Machine Remaining Useful Life Prediction},
year={2020},
volume={},
number={},
pages={1-1},
doi={10.1109/TII.2020.3032690}}
For any issues/questions regarding the paper or reproducing the results, please contact me.
Mohamed Ragab
School of Computer Science and Engineering (SCSE),
Nanyang Technological University (NTU), Singapore.
Email: mohamedr002{at}e.ntu.edu.sg