Frequency-Aware Lightweight Convolutional Neural Network for Edge-Enabled Intelligent Bearing Fault Diagnosis and Health Management
Hao Tian, Shitong Hua, Wenbiao Gui, Sijie Zou, Chenglong Wang · 2026
Read Frequency-Aware Lightweight Convolutional Neural Network for Edge-Enabled Intelligent Bearing Fault Diagnosis and Health Management by Hao Tian, Shitong Hua, Wenbiao Gui, Sijie Zou, Chenglong Wang (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/pmc-13611102.txt.
Description
Factory bearings whisper their faults in vibration, but heavy neural nets cannot ride on cheap edge chips. Hao Tian, Shitong Hua, Wenbiao Gui, Sijie Zou, and Chenglong Wang slim the net down in a 2026 paper. Their design first turns each vibration burst into a compact spectrum, shrinking input eightfold. Three parallel filters match the shapes of single, paired, and family fault tones.
On a standard bearing test set, accuracy averaged above ninety-nine percent. The whole model holds about sixty-five thousand parameters and answers in well under a millisecond. Strict split rules guarded against leaked test data. Five random seeds checked stability. The authors aim at on-site health tracking for machines.
Catalog record
| CREATOR | Hao Tian, Shitong Hua, Wenbiao Gui, Sijie Zou, Chenglong Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 77 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |