To promote relevant researches on domain adaptive RUL prediction in the community, we provide the N-CMAPSS dataset used in this paper, with 7 domains readily available. Download here.
Pytorch implementation for Domain Adaptive Remaining Useful Life Prediction with Transformer, https://doi.org/10.1109/TIM.2022.3200667
- Prognostic health management (PHM) has become a crucial part in building highly automated systems, whose primary task
is to precisely predict the remaining useful life (RUL) of the system. In this paper, we leverage domain adaptation for RUL prediction and propose a novel method by
aligning distributions at both the feature level and the semantic level. The proposed method facilitates a large improvement of model
performance as well as faster convergence. Besides, we propose to use Transformer as backbone, which can capture long-term
dependency more efficiently. We test our model on CMAPSS dataset and its newly published variant N-CMAPSS provided by NASA, achieving
state-of-the-art results on both source-only RUL prediction and domain adaptive RUL prediction tasks.
This is a strict constraint!
- pytorch==1.10
- torchvision==0.11.0
- Unzip
CMAPSS.zipintoCMAPSSfolder, which contains processed CMAPSS dataset used in this code.
- train on CMAPSS
python train_cmapss.py --source $S --target $T
where$Sis source domain,$Tis target domain. Domains include "FD001,FD002,FD003,FD004". Trained models are saved to/online. - evaluate on CMAPSS
You can evaluate our best performing models saved in foldersave/finalby running:
python validation_cmapss.py --source $S --target $T
where$Sis source domain,$Tis target domain. Domains include "FD001,FD002,FD003,FD004".
@article{li2022domain,
title={Domain Adaptive Remaining Useful Life Prediction With Transformer},
author={Li, Xinyao and Li, Jingjing and Zuo, Lin and Zhu, Lei and Shen, Heng Tao},
journal={IEEE Transactions on Instrumentation and Measurement},
volume={71},
pages={1--13},
year={2022},
publisher={IEEE}
}