Acoustic deep learning for defect detection in aluminium wheel rims
Arkadiusz Rychlik · 2026
Read Acoustic deep learning for defect detection in aluminium wheel rims by Arkadiusz Rychlik (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/PMC13534414.txt.
Description
Arkadiusz Rychlik presents in 2026 RimNet, a sound-based deep learning tool for finding defects in aluminium wheel rims. Workshop checks today rely mostly on eyes and touch, so hidden flaws can be missed. The method strikes each rim once, turns the sound into time-frequency images, and lets a network judge condition.
Training used 930 labelled examples spanning shape faults, material defects, and sound rims. File-level accuracy reached high levels, and no wheel was misjudged under the test protocol. Wrong calls carried wider uncertainty, and a companion app gives live results with confidence scores for each rim.
Catalog record
| CREATOR | Arkadiusz Rychlik |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 125028 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |