Contrastive Adversarial Domain Adaptation for Machine Remaining Useful Life Prediction


Journal article


Mohamed Ragab, Zhenghua Chen, Min Wu, Chuan Sheng Foo, Kwoh Chee Keong, Ruqiang Yan, Xiao-Li Li
IEEE Transactions on Industrial Informatics, 2020, pp. 1--1

View PDF
Cite

Cite

APA   Click to copy
Ragab, M., Chen, Z., Wu, M., Foo, C. S., Keong, K. C., Yan, R., & Li, X.-L. (2020). Contrastive Adversarial Domain Adaptation for Machine Remaining Useful Life Prediction. IEEE Transactions on Industrial Informatics, 1–1.


Chicago/Turabian   Click to copy
Ragab, Mohamed, Zhenghua Chen, Min Wu, Chuan Sheng Foo, Kwoh Chee Keong, Ruqiang Yan, and Xiao-Li Li. “Contrastive Adversarial Domain Adaptation for Machine Remaining Useful Life Prediction.” IEEE Transactions on Industrial Informatics (2020): 1–1.


MLA   Click to copy
Ragab, Mohamed, et al. “Contrastive Adversarial Domain Adaptation for Machine Remaining Useful Life Prediction.” IEEE Transactions on Industrial Informatics, 2020, pp. 1–1.


BibTeX   Click to copy

@article{ragab2020a,
  title = {Contrastive Adversarial Domain Adaptation for Machine Remaining Useful Life Prediction},
  year = {2020},
  journal = {IEEE Transactions on Industrial Informatics},
  pages = {1--1},
  author = {Ragab, Mohamed and Chen, Zhenghua and Wu, Min and Foo, Chuan Sheng and Keong, Kwoh Chee and Yan, Ruqiang and Li, Xiao-Li}
}

In this paper, we develop a novel contrastive adversarial domain adaptation (CADA) approach for machine RUL prediction. Specifically, it is able to transfer the knowledge learned from the data under one condition (labeled source domain) to the data from another condition (unlabeled target domain). The proposed CADA can find domain invariant representations of the target domain data while preserving their intrinsic structure which is crucial to achieve satisfactory performance in the target domain.

Share


Follow this website


You need to create an Owlstown account to follow this website.


Sign up

Already an Owlstown member?

Log in