Code for our paper "Domain adaptive transfer learning for fault diagnosis." 2019 Prognostics and System Health Management Conference (PHM-Paris). IEEE, 2019.
CWRU: Source is recorded under load 3; Target is recorded under load 1
The code is not identical to the implementation we used in the paper as we updated the code from tf1.x to tensorflow2/keras. The provided notebook was also used as part of the tutorial session for the European conference of the prognosticas and health management society (PHME21).
Please cite our work if you use this code:
@inproceedings{wang2019domain,
title={Domain adaptive transfer learning for fault diagnosis},
author={Wang, Qin and Michau, Gabriel and Fink, Olga},
booktitle={2019 Prognostics and System Health Management Conference (PHM-Paris)},
pages={279--285},
year={2019},
organization={IEEE}
}
@article{wang2020missing,
title={Missing-class-robust domain adaptation by unilateral alignment},
author={Wang, Qin and Michau, Gabriel and Fink, Olga},
journal={IEEE Transactions on Industrial Electronics},
volume={68},
number={1},
pages={663--671},
year={2020},
publisher={IEEE}
}
Unsupervised domain adaptation by backpropagation Ganin, Yaroslav, and Victor Lempitsky | ICML, 2015