Data-driven fault diagnosis framework of taper roller bearings using statistically ranked feature sets and machine learning algorithms
A. Anwarsha, T. Narendiranath Babu · 2026
Read Data-driven fault diagnosis framework of taper roller bearings using statistically ranked feature sets and machine learning algorithms by A. Anwarsha, T. Narendiranath Babu (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/PMC13562557.txt.
Description
A. Anwarsha and T. Narendiranath Babu present a fast vibration-based method for spotting faults in taper roller bearings before machines break down. Bearings support much of industry, and early damage to a race, roller, or cage can end in costly stoppages. The 2026 study recorded shaking signals from a test bearing in five states: healthy, plus faults in the inner race, outer race, roller, and cage. Signals were gathered across speeds and loads, then reduced to time-based and frequency-based features.
Two statistical tests ranked the features by how well they separated the states, and the top set held 18 entries. Six classifier types were trained on different feature sets. A linear support vector machine on the Kruskal-Wallis-ranked set classified faults with 99 percent accuracy and trained fastest. The authors propose the pairing as a dependable, light method for automated bearing checks on the factory floor.
Catalog record
| CREATOR | A. Anwarsha, T. Narendiranath Babu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 76495 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |