Gramian angular field fusion with dual-branch ConvNeXt and channel-aware transformer for vibration sensor-based fault diagnosis

Pengjuan Liu, Jindou Ma · 2026

Read Gramian angular field fusion with dual-branch ConvNeXt and channel-aware transformer for vibration sensor-based fault diagnosis by Pengjuan Liu, Jindou Ma (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/plos-pone-0354912.txt.

Description

Pengjuan Liu and Jindou Ma published this 2026 engineering paper on spotting faults in rotating machines from vibration readings. A single chart type can miss parts of a fault's signature, so they turned vibration signals into two kinds of images, one stressing overall patterns and one stressing quick local changes.

Two linked neural networks read the image pair, and an attention module weighs which signal channels matter most. Tested on public bearing and gear data sets, the system named faults correctly about ninety-seven to ninety-eight times in a hundred. Reliable early warnings like this help factories fix machines before a breakdown stops production.

Catalog record

CREATORPengjuan Liu, Jindou Ma
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE50838
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0354912

Browse the full library · About the Tower of Babel