W Li, X Zhong, H Shao, B Cai, X Yang - Advanced Engineering Informatics, 2022 - Elsevier
… In order to validate the effectiveness of the proposed method, two multi-mode faultdata augmentation and intelligent diagnosis cases for bearings and gears are studied in this chapter. …
K Yu, TR Lin, H Ma, X Li, X Li - Mechanical Systems and Signal Processing, 2021 - Elsevier
… dataaugmentation (DA) and metric learning is proposed for an intelligent bearing faultdiagnosis under limited labeled data… on an experimental bearing fault dataset from our laboratory …
X Gao, F Deng, X Yue - Neurocomputing, 2020 - Elsevier
… eg, industrial process data, some more dataaugment methods are needed… dataaugmentation to increase the numbers of input data samples in low-data domain of the imbalanced data …
… on two rotating machinery datasets, the data-driven faultdiagnostic model can significantly … proposed dataaugmentation method is promising for faultdiagnostic tasks with imbalanced …
X Jiang, Z Ge - IEEE Transactions on Automation Science and …, 2020 - ieeexplore.ieee.org
… role in process monitoring and faultdiagnosis. While the online monitoring system uses sensors to obtain measurement data of mechanical equipment and industrial processes which …
… Deep learning algorithms for diagnosing machineryfaults have become prevalent owing to their robustness and capacity for adaptation. Deep architectures of computational layers and …
M Chen, H Shao, H Dou, W Li… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
… potential for dataaugmentation and intelligent faultdiagnosis of … Li, “Machineryfaultdiagnosis with imbalanced data using … framework for rotating machineryfaultdiagnosis under strong …
S Tang, S Yuan, Y Zhu - IEEE Access, 2020 - ieeexplore.ieee.org
… attention of researchers in machineryfaultdiagnosis. In the light … of final diagnosis accuracy, data preprocessing is necessary … dataaugmentation used in the CNN based intelligent fault …
T Zhang, J Chen, F Li, K Zhang, H Lv, S He, E Xu - ISA transactions, 2022 - Elsevier
… or feature adaptation without dataaugmentation. On the … machines can be classified directly by designing fault classifiers suitable for small & imbalanced data without dataaugmentation …