Self-Attention Metric Learning Based on Multiscale Feature Fusion for Few-Shot Fault Diagnosis

Xie, Jingsong; Liu, Jie; Ding, Tianqi; Wang, Tiantian; Yu, Tianjian

doi:10.1109/jsen.2023.3296750

Cited by 13 publications

(1 citation statement)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Few-shot learning and transfer learning can reduce the requirement for training samples. Xie et al [10] proposed a few-shot intelligent diagnosis model based on self-attention metric learning to classify bearing faults. Zhang et al [11] proposed a fewshot learning framework for bearing fault diagnosis based on model-agnostic meta-learning.…”

Section: Introductionmentioning

confidence: 99%

Rapid learning of bearing signal pattern using CfCs promoted by a self-attention mechanism

Yang,

Pan,

Zhou

2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Deep learning is helpful for improving the fault recognition ability of bearings, but this kind of model relies on a large number of training samples and computing resources. In this paper, an algorithm termed a closed-form continuous-depth neural network (CfC) assisted by an information compression-interaction (ICI) module and spatial conjunction attention (SCA) module (CfC-ISCA) is proposed. The ICI module extracts the main features of input signals, the SCA module is designed for positioning target features and capturing more useful features, and the CfC module is used to further fuse features and achieve rapid learning of samples. This algorithm can learn bearing fault signal patterns rapidly and has excellent fault identification ability under small sample conditions. Some public datasets are used to validate the model performance. The test results show that the proposed CfC-ISCA algorithm has comprehensive advantages in fault signal recognition, consumption of computing resources and fast learning compared to comparative methods.

show abstract

Section: Introductionmentioning

confidence: 99%