Vibration-Based Wear Condition Estimation of Journal Bearings Using Convolutional Autoencoders
Cihan Ates, Tobias Höfchen, Mario Witt, Rainer Koch, Hans-Jörg Bauer, Steven Chatterton · 2023
Read Vibration-Based Wear Condition Estimation of Journal Bearings Using Convolutional Autoencoders by Cihan Ates, Tobias Höfchen, Mario Witt, Rainer Koch, Hans-Jörg Bauer, Steven Chatterton (2023) 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-10675279.txt.
Description
Cihan Ates and co-authors estimate the wear of journal bearings from their vibration signals in a 2023 study. Bearings are central to rotating machinery, and knowing their wear without opening the machine saves cost and downtime. The team ran seventeen bearings through a procedure that speeds wear, recording vibration from several sensors and positions.
They compressed the sensor data with convolutional autoencoders, neural networks that squeeze signals into a compact code. That code tracked the true wear state closely, with an average correlation of ninety-one percent across four setups. The network learned from unlabeled data, so little hand-measured wear data was needed. The authors present the method as a practical route to predictive maintenance.
Catalog record
| CREATOR | Cihan Ates, Tobias Höfchen, Mario Witt, Rainer Koch, Hans-Jörg Bauer, Steven Chatterton |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 51 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |