Fault diagnosis of ORC expanders using a multiscale residual network with convolutional block attention
Jing Li, Zexu Gao · 2026
Read Fault diagnosis of ORC expanders using a multiscale residual network with convolutional block attention by Jing Li, Zexu Gao (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/pmc-13324522.txt.
Description
Jing Li and Zexu Gao build a smarter fault finder for heat recovery machines. Their paper, from twenty twenty-six, targets expanders in organic Rankine cycle systems. These parts turn waste heat into power. Faults like worn bearings, off-balance rotors, and cracked blades threaten their safe running.
Old check methods falter on shaky signals, rare fault types, and noise. Their deep network reads signals at several time scales at once. Attention blocks then boost the traits that mark a fault and mute the noise. A training plan with a special loss and data boosts handles rare classes. The system aims for fast, sure warnings in harsh plant settings.
Catalog record
| CREATOR | Jing Li, Zexu Gao |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 66 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |