YOLO models enhance bearing fault detection using CWT spectrograms

Researchers have developed a new vibration sensing framework for bearing fault monitoring that utilizes continuous wavelet transform (CWT) spectrograms and object detection models like YOLOv9, YOLOv10, and YOLOv11. This approach enhances the detection of weak and non-stationary fault signatures by localizing energy regions in the time-frequency domain. Experiments on benchmark datasets demonstrated improved detectability and robustness compared to traditional methods, achieving high mean average precision (mAP) scores. AI

IMPACT This research demonstrates a novel application of object detection models for industrial diagnostics, potentially improving predictive maintenance and operational efficiency.

RANK_REASON The cluster contains an academic paper detailing a new methodology for vibration sensing using AI models. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• CWRU dataset
• IMS dataset
• Po-Heng Chou
• PU dataset
• YOLOv10
• YOLOv11
• YOLOv9

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →