A Hybrid Deep Learning Framework for Multi-Sensor PMSM Fault Diagnosis Based on SVMD Denoising and Spatiotemporal Feature Fusion

Mingdong Guan, Yiming Peng, Yingxi Xie · 2026

Read A Hybrid Deep Learning Framework for Multi-Sensor PMSM Fault Diagnosis Based on SVMD Denoising and Spatiotemporal Feature Fusion by Mingdong Guan, Yiming Peng, Yingxi Xie (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-13568371.txt.

Description

Mingdong Guan, Yiming Peng, and Yingxi Xie present a hybrid deep learning system for motor fault diagnosis in a 2026 paper. Permanent magnet synchronous motors power much of industry, and catching their faults early guards safety and uptime. Single sensors miss too much under noise, load swings, and partial information.

Their framework fuses several sensors at once. A signal method called SVMD first strips noise by discarding weak components, then rebuilds cleaner signals. Parallel temporal and spatial networks extract features over time and across channels, and a bidirectional memory network with attention sharpens the result. The system sorts motors into multiple fault classes, aiming for robust diagnosis under real factory conditions.

Catalog record

CREATORMingdong Guan, Yiming Peng, Yingxi Xie
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE49 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13568371

Browse the full library · About the Tower of Babel