Denoising Diffusion Implicit Model Combined with TransNet for Rolling Bearing Fault Diagnosis Under Imbalanced Data
Chaobing Wang, Cong Huang, Long Zhang, Zhibin Xiang, Yiwen Xiao, Tongshuai Qian, Jiayang Liu, Steven Chatterton · 2024
Read Denoising Diffusion Implicit Model Combined with TransNet for Rolling Bearing Fault Diagnosis Under Imbalanced Data by Chaobing Wang, Cong Huang, Long Zhang, Zhibin Xiang, Yiwen Xiao, Tongshuai Qian, Jiayang Liu, Steven Chatterton (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11678951.txt.
Description
Wang and co-authors tackle fault checks for rolling bearings when fault cases are rare in the data. Rare cases can cut test scores and put plant gear at risk. Their fix pairs a diffusion model called DDIM with a new net named TransNet. Signal traces first become flat images through a Gramian field step. DDIM then makes more training images to balance the set.
TransNet mixes shared-weight filters with the self-focus steps used in Transformer nets. The team tests the full method on the CWRU bearing set and a rail set from Nanchang. Scores pass 99 percent on both sets. The authors report better spread to new data than past fault methods.
Catalog record
| CREATOR | Chaobing Wang, Cong Huang, Long Zhang, Zhibin Xiang, Yiwen Xiao, Tongshuai Qian, Jiayang Liu, Steven Chatterton |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 37 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |