SEFormer: A Lightweight CNN-Transformer Based on Separable Multiscale Depthwise Convolution and Efficient Self-Attention for Rotating Machinery Fault Diagnosis
Source abstract
Abstract
Traditional data-driven fault diagnosis methods depend on expert experience to manually extract effective fault features of signals, which has certain limitations. Conversely, deep learning techniques have gained prominence a... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Machine Fault Diagnosis Techniques · Non-Destructive Testing Techniques · Ultrasonics and Acoustic Wave Propagation
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (39)
Show source-provided references
1. Fault diagnosis of mechanical equipment in high energy consumption industries in China: A review10.1016/j.ymssp.2022.109833 ↗
2. A comprehensive survey on applications of AI technologies to failure analysis of industrial systems10.1016/j.engfailanal.2023.107172 ↗
3. Recent deep learning models for diagnosis and health monitoring: A review of research works and future challenges
4. A review of the application of deep learning in intelligent fault diagnosis of rotating machinery
5. Applications of machine learning to machine fault diagnosis: A review and roadmap10.1016/j.ymssp.2019.106587 ↗
6. Deep learning algorithms for rotating machinery intelligent diagnosis: An open source benchmark study10.1016/j.isatra.2020.08.010 ↗
7. Ensemble transfer CNNs driven by multi-channel signals for fault diagnosis of rotating machinery cross working conditions
8. A fault diagnosis method for rotating machinery based on CNN with mixed information10.1109/TII.2022.3224979 ↗
9. Multi-scale convolutional network with channel attention mechanism for rolling bearing fault diagnosis
10. Convolutional transformer: An enhanced attention mechanism architecture for remaining useful life estimation of bearings
11. A comprehensive survey on applications of transformers for deep learning tasks10.1016/j.eswa.2023.122666 ↗
12. A survey of techniques for optimizing transformer inference
13. Signal-transformer: A robust and interpretable method for rotating machinery intelligent fault diagnosis under variable operating conditions10.1109/TIM.2022.3217869 ↗
14. Variational attention-based interpretable transformer network for rotary machine fault diagnosis10.1109/TNNLS.2022.3202234 ↗
15. A novel time-frequency Transformer based on self-attention mechanism and its application in fault diagnosis of rolling bearings10.1016/j.ymssp.2021.108616 ↗
16. CoAtNet: Marrying convolution and attention for all data sizes
17. Recent advances in the application of deep learning for fault diagnosis of rotating machinery using vibration signals10.1007/s10462-022-10293-3 ↗
18. CLFormer: A lightweight transformer based on convolutional embedding and linear self-attention with strong robustness for bearing fault diagnosis under limited sample conditions
19. Convformer-NSE: A novel end-to-end gearbox fault diagnosis framework under heavy noise using joint global and local information10.1109/TMECH.2022.3199985 ↗
20. LiConvFormer: A lightweight fault diagnosis framework using separable multiscale convolution and broadcast self-attention10.1016/j.eswa.2023.121338 ↗
21. A. G. Howard et al., “MobileNets: Efficient convolutional neural networks for mobile vision applications,” 2017. doi: 10.48550/arXiv.1704.04861.
22. Xception: Deep learning with depthwise separable convolutions
23. MobileNetV2: Inverted residuals and linear bottlenecks
24. Depthwise convolution is all you need for learning multiple visual domains
25. Attention is all you need
26. Attention mechanism in intelligent fault diagnosis of machinery: A review of technique and application10.1016/j.measurement.2022.111594 ↗
27. Efficient Attention: Attention with linear complexities
28. HS-KDNet: A lightweight network based on hierarchical-split block and knowledge distillation for fault diagnosis with extremely imbalanced data
29. S. Mehta and M. Rastegari, “Separable self-attention for mobile vision transformers,” 2022. doi: 10.48550/arXiv.2206.02680.
30. I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” 2019. doi: 10.48550/arXiv.1711.05101.
31. The emerging graph neural networks for intelligent fault diagnostics and prognostics: A guideline and a benchmark study10.1016/j.ymssp.2021.108653 ↗
32. Multiscale kernel based residual convolutional neural network for motor fault diagnosis under nonstationary conditions10.1109/TII.2019.2941868 ↗
33. Deep residual learning for image recognition
34. Convolutional neural networks at constrained time cost
35. Approximated and user steerable tSNE for progressive visual analytics10.1109/TVCG.2016.2570755 ↗
36. Sequential fuzzy diagnosis method for motor roller bearing in variable operating conditions based on vibration analysis10.3390/s130608013 ↗
37. Intelligent fault diagnosis of gearbox under variable working conditions with adaptive intraclass and interclass convolutional neural network10.1109/TNNLS.2021.3135877 ↗
38. A multi-source domain information fusion network for rotating machinery fault diagnosis under variable operating conditions10.1016/j.inffus.2024.102278 ↗
39. A domain feature decoupling network for rotating machinery fault diagnosis under unseen operating conditions10.1016/j.ress.2024.110449 ↗