A motor bearing fault diagnosis model based on multi-adversarial domain adaptation
Xin-Ming Liu, Rui-Ming Zhang, Jin-Ping Li, Yu-Fei Xu, Kun Li · 2024
Read A motor bearing fault diagnosis model based on multi-adversarial domain adaptation by Xin-Ming Liu, Rui-Ming Zhang, Jin-Ping Li, Yu-Fei Xu, Kun Li (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-11585630.txt.
Description
Xin-Ming Liu and co-authors build a model that diagnoses motor bearing faults when the machine or conditions change, in a paper from 2024. A model trained on one device often fails on another because the data patterns shift. That shift weakens feature transfer between domains.
Their model adapts across domains with several rival discriminators at once. An improved residual network extracts features, sharpened by modules that weigh kernel sizes and global context. A multi-kernel distance measure tracks how far apart the domains sit, class by class. A dynamic factor balances the two kinds of distribution gap. Transfer tests across working conditions and devices gave excellent fault calls. The authors present the design as a fix for cross-device diagnosis.
Catalog record
| CREATOR | Xin-Ming Liu, Rui-Ming Zhang, Jin-Ping Li, Yu-Fei Xu, Kun Li |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 69 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |