Fault Diagnosis of Ship Chilled Water Units Based on a Hybrid Attention Domain-Adaptive Network
Qiaolian Feng, Yanfei Li, Yongbao Liu, Xiao Liang, Mingyang Liu, Duo Qu, Yue Cen · 2026
Read Fault Diagnosis of Ship Chilled Water Units Based on a Hybrid Attention Domain-Adaptive Network by Qiaolian Feng, Yanfei Li, Yongbao Liu, Xiao Liang, Mingyang Liu, Duo Qu, Yue Cen (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/PMC13511930.txt.
Description
Qiaolian Feng, Yanfei Li, Yongbao Liu, Xiao Liang, Mingyang Liu, Duo Qu, and Yue Cen build a learning system that spots faults in ship chilled water units, in 2026 work. It works across different machines and conditions. Ship chillers face shifting sea conditions, few labeled fault examples for the target machine, and noisy vibration in sensor signals. The design improves an earlier domain adaptation network with a doubled attention setup.
Two encoder branches handle the differing sensor sets of two chiller types. Attention modules boost fault-sensitive parts of the signal and damp noise, while shortcut links keep deep training stable. A two-layer alignment scheme, mixing an adversarial game with a distance measure, pulls the two machines' signal patterns together so fault knowledge transfers. The authors report the system can flag subtle faults of varying severity under few-example conditions, a setting where plain models often fail.
Catalog record
| CREATOR | Qiaolian Feng, Yanfei Li, Yongbao Liu, Xiao Liang, Mingyang Liu, Duo Qu, Yue Cen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 104 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |