A hybrid VMD-CNN-autoencoder approach for speed-invariant fault detection of parallel and angular misalignment in rotating machinery
N Chandran, K Sathish Kumar · 2026
Read A hybrid VMD-CNN-autoencoder approach for speed-invariant fault detection of parallel and angular misalignment in rotating machinery by N Chandran, K Sathish Kumar (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-13342506.txt.
Description
Chandran and Sathish Kumar build a fault detector for rotating machines in a 2026 study. Shaft misalignment, parallel or angled, causes costly breakdowns if missed. A detector that works at any speed is the prize. Their rig was a custom fault simulator with multi-axis vibration sensors.
Signals were gathered at three shaft speeds in the lab. A decomposition step split them into clean mode pieces. An autoencoder and a neural network drew deep features, joined with classic stats. Two tree classifiers, guarded against overfitting, voted in an ensemble. The system sorted healthy and two fault states with high accuracy. Speed changes did not break the call.
Catalog record
| CREATOR | N Chandran, K Sathish Kumar |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 53 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |