[PDF][PDF] Deep unsupervised domain adaptation: A review of recent advances and perspectives

X Liu, C Yoo, F **ng, H Oh, G El Fakhri… - … on Signal and …, 2022 - nowpublishers.com
Deep learning has become the method of choice to tackle real-world problems in different
domains, partly because of its ability to learn from data and achieve impressive performance …

Data-driven remaining useful life estimation for milling process: sensors, algorithms, datasets, and future directions

S Sayyad, S Kumar, A Bongale, P Kamat, S Patil… - IEEE …, 2021 - ieeexplore.ieee.org
An increase in unplanned downtime of machines disrupts and degrades the industrial
business, which results in substantial credibility damage and monetary loss. The cutting tool …

A survey of transfer learning for machinery diagnostics and prognostics

S Yao, Q Kang, MC Zhou, MJ Rawa… - Artificial Intelligence …, 2023 - Springer
In industrial manufacturing systems, failures of machines caused by faults in their key
components greatly influence operational safety and system reliability. Many data-driven …

Bayesian transfer learning with active querying for intelligent cross-machine fault prognosis under limited data

R Zhu, W Peng, D Wang, CG Huang - Mechanical Systems and Signal …, 2023 - Elsevier
Most existing deep learning (DL)-based health prognostic methods assume that the training
and testing datasets are from identical machines operating under similar conditions …

Bi-LSTM-based two-stream network for machine remaining useful life prediction

R **, Z Chen, K Wu, M Wu, X Li… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
In industry, prognostics and health management (PHM) is used to improve the system
reliability and efficiency. In PHM, remaining useful life (RUL) prediction plays a key role in …

A new supervised multi-head self-attention autoencoder for health indicator construction and similarity-based machinery RUL prediction

Y Qin, J Yang, J Zhou, H Pu, Y Mao - Advanced Engineering Informatics, 2023 - Elsevier
Remaining useful life (RUL) prediction plays a significant role in the prognostic and health
management (PHM) of rotating machineries. A good health indicator (HI) can ensure the …

Remaining useful life prediction of bearings under different working conditions using a deep feature disentanglement based transfer learning method

T Hu, Y Guo, L Gu, Y Zhou, Z Zhang, Z Zhou - Reliability Engineering & …, 2022 - Elsevier
The data distribution discrepancy between the training and test samples makes it
challenging for the remaining useful life (RUL) prediction under different working conditions …

Dynamic model-assisted bearing remaining useful life prediction using the cross-domain transformer network

Y Zhang, K Feng, JC Ji, K Yu, Z Ren… - … /ASME Transactions on …, 2022 - ieeexplore.ieee.org
Remaining useful life (RUL) prediction of rolling bearings is of paramount importance to
various industrial applications. Recently, intelligent data-driven RUL prediction methods …

The two-stage RUL prediction across operation conditions using deep transfer learning and insufficient degradation data

H Cheng, X Kong, Q Wang, H Ma, S Yang - Reliability Engineering & …, 2022 - Elsevier
The remaining useful life (RUL) prediction provides an essential basis for improving
mechanical equipment reliability. In practical application, the variant of working conditions …

Domain generalization via adversarial out-domain augmentation for remaining useful life prediction of bearings under unseen conditions

Y Ding, M Jia, Y Cao, P Ding, X Zhao… - Knowledge-Based Systems, 2023 - Elsevier
Since classical deep learning (DL) techniques are hungry for massive data and suffer from
domain shift, domain adaptation (DA) methods are broadly adopted in prognostics and …