Physics guided semantic consistency learning for bearing fault diagnosis in agricultural machinery under operating condition shifts
Zhenlong Li, Shanyu Piao, Haowei Li · 2026
Read Physics guided semantic consistency learning for bearing fault diagnosis in agricultural machinery under operating condition shifts by Zhenlong Li, Shanyu Piao, Haowei Li (2026) 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/PMC13572434.txt.
Description
Zhenlong Li, with two colleagues, presents a 2026 method for spotting bearing faults in farm machines when work conditions shift. Bearings face swings in speed and load plus dirt and noise, so a model trained in one setting often fails in the next. The team trained on source data only, with no peek at the target setting.
Two paths read each signal. One path is physics-based and hunts the ring band tied to impacts, while the other learns patterns from the raw wave shape. A gate blends the two views for each sample, and a loss term keeps the views in agreement. On three data sets, accuracy in the home setting ran from 97.53 to 99.48 percent. Cross-speed tests on a farm rig stayed near 98 percent both ways. Swapping the physics path for plain features hurt results, which backs its role.
Catalog record
| CREATOR | Zhenlong Li, Shanyu Piao, Haowei Li |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 103022 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |