Papers
6
Total Citations
77
H-Index
4
About
Guojin Feng is a researcher whose work sits at the intersection of intelligent fault diagnosis, condition monitoring, and robotics-based inspection systems for industrial applications. His research addresses one of manufacturing's most pressing challenges: reliably detecting and diagnosing mechanical faults in complex, safety-critical equipment while minimizing human intervention and labeled data requirements. Feng's most influential contribution to date is his comprehensive review of few-shot learning approaches for vibration-based fault diagnosis (2023, 35 citations), which has quickly become a key reference for researchers navigating the challenge of limited labeled fault data in industrial settings. His work on Modulation Signal Bispectrum Enhanced Squared Envelope analysis (2022, 22 citations) demonstrates particular expertise in epicyclic gearbox diagnostics, offering refined signal processing tools for compound fault detection in aerospace, automotive, and wind turbine systems. More recently, Feng has pioneered an emerging field combining acoustic sensing with mobile robotics for autonomous condition monitoring. His investigations into sound source localization using robotic platforms — optimizing measurement strategies for complex indoor acoustic environments — represent forward-thinking solutions for large-scale industrial inspections where manual checking proves inefficient. With a growing and diverse citation record, Feng's work is gaining meaningful traction across the fault diagnostics and intelligent maintenance communities.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6