Time Shifting Data Augmentation to Alleviate Class-Imbalance Problem for Cross-Domain Bearing Fault Diagnosis



Published Sep 4, 2023
Donghwi Yoo Minseok Choi Hyunseok Oh


This paper presents a new cross-domain fault diagnostic method for rolling element bearings with class-imbalanced datasets. The key idea to alleviate the class imbalance problem is the incorporation of the data augmentation strategy. This study proposes a new data augmentation technique, namely, time shifting data augmentation (TS- DA). Synthetic data is generated to balance the number of normal and fault data. The validity of the proposed method is evaluated using a dataset from the bearing testbed. The results show that the proposed method augments different types of bearing fault data effectively and outperforms existing methods under the class imbalance problem.  

Abstract 173 | PDF Downloads 140



Bearing fault diagnosis, Data augmentation, Artificial intelligence

Long, M., Cao, Y., Wang, J., & Jordan, M. (2015). Learning transferable features with deep adaptation networks. International Conference on Machine Learning, pp. 97-105.

Ganin, Y., & Lempitsky, V. (2015). Unsupervised domain adaptation by backpropagation. International Conference on Machine Learning, pp. 1180-1189.
Special Session Papers