This repository is the official implementation of DDDAN: Deep discriminative domain adaptation network considering sampling frequency for cross-domain mechanical fault diagnosis (ESWA 2025).
- Python 3.9
- Numpy 1.16.2
- Pandas 0.24.2
- tqdm 4.31.1
- sklearn 0.21.3
- Scipy 1.2.1
- pytorch >= 1.2
- torchvision >= 0.40
- use the
train.pyto train - for example, use the following commands to test JDA_W for PHM with the transfer_task 0-->3
python train.py --data_name PHM --data_dir D:/Data/PHM --transfer_task [0],[3] --last_batch True --distance_metric True --distance_loss JDA_W
Part of the code refers to the following open source code:
- SWK.py from the paper "Interpretable Physics-informed Domain Adaptation Paradigm for Cross-machine Transfer Diagnosis" proposed by He et al.
@article{chen2025deep,
title={Deep discriminative domain adaptation network considering sampling frequency for cross-domain mechanical fault diagnosis},
author={Chen, Guiping and Xiang, Dong and Liu, Tingting and Xu, Feng and Fang, Ke},
journal={Expert Systems with Applications},
pages={127296},
year={2025},
publisher={Elsevier}
}