Unsupervised Learning for Machinery Adaptive Fault Detection Using Wide-Deep Convolutional Autoencoder with Kernelized Attention Mechanism
Hao Yan, Xiangfeng Si, Jianqiang Liang, Jian Duan, Tielin Shi, Pavlos Lazaridis · 2024
Read Unsupervised Learning for Machinery Adaptive Fault Detection Using Wide-Deep Convolutional Autoencoder with Kernelized Attention Mechanism by Hao Yan, Xiangfeng Si, Jianqiang Liang, Jian Duan, Tielin Shi, Pavlos Lazaridis (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-11679117.txt.
Description
Hao Yan and co-authors present an unsupervised method for spotting machine faults without labeled examples, in work from 2024. Labels for bearing faults are costly to gather, yet factories need early warning of wear. Their model learns the shape of normal signals and flags departures from it.
The design joins a wide-filter autoencoder with a large-kernel attention step that weighs the most telling signal parts. A small learned module sets the alarm threshold on its own, which helps when fault cases are rare. On two data sets, the model beat classic and recent rivals in accuracy, and did so with shorter training. Gains held up when fault cases were scarce.
Catalog record
| CREATOR | Hao Yan, Xiangfeng Si, Jianqiang Liang, Jian Duan, Tielin Shi, Pavlos Lazaridis |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |