CASSAD: Chroma-Augmented Semi-Supervised Anomaly Detection for Conveyor Belt Idlers
Fahad Alharbi, Suhuai Luo, Abdullah Alsaedi, Sipei Zhao, Guang Yang, Yongbo Li, Bing Li, Khandaker Noman, Teng Wang · 2024
Read CASSAD: Chroma-Augmented Semi-Supervised Anomaly Detection for Conveyor Belt Idlers by Fahad Alharbi, Suhuai Luo, Abdullah Alsaedi, Sipei Zhao, Guang Yang, Yongbo Li, Bing Li, Khandaker Noman, Teng Wang (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-11644144.txt.
Description
Fahad Alharbi and co-authors present a sound-based fault finder for conveyor parts in this 2024 paper. Rollers that support and guide belts are key to output, but faults are rare and labeling fault sounds takes much labor. That makes fully trained methods hard to build for this task.
Their method, called CASSAD, learns mostly from normal sounds and a few labeled cases. It adds features drawn from the pitch pattern of the sound, boosted by filtering, and adds noise to grow the data. On an industrial sound set, the method reached high scores that beat a baseline. It also beat two other common fault finders in the comparison.
Catalog record
| CREATOR | Fahad Alharbi, Suhuai Luo, Abdullah Alsaedi, Sipei Zhao, Guang Yang, Yongbo Li, Bing Li, Khandaker Noman, Teng Wang |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 68 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |