arXiv:2509.03070v5 Announce Type: replace-cross Abstract: This letter presents a CWT-enhanced vibration sensing framework for bearing fault monitoring through localized time-frequency region detection on continuous wavelet transform (CWT) spectrograms. Vibration signals are transformed into CWT spectrograms to improve the observability of weak and non-stationary fault signatures, and YOLOv9, YOLOv10, and YOLOv11 are employed to detect and identify localized fault-related energy regions in the time-frequency domain. Experiments on the CWRU, PU, and IMS datasets show that the proposed framework
The continuous evolution of AI models like YOLO and advancements in signal processing techniques make enhanced fault detection in critical machinery increasingly feasible.
This development improves predictive maintenance capabilities, potentially reducing downtime and operational costs for industrial assets, which is critical for industrial productivity and safety.
The ability to accurately detect weak and non-stationary fault signatures through AI-enhanced vibration analysis allows for earlier intervention and more reliable asset management.
- · Industrial manufacturers
- · Maintenance service providers
- · AI/ML developers
- · Sensor manufacturers
- · Traditional preventative maintenance methods
Improved reliability and lifespan of industrial machinery across various sectors.
Reduced operational expenditures and increased efficiency in manufacturing and energy industries due to fewer unexpected breakdowns.
Enhanced automation in monitoring and maintenance, potentially enabling more lights-out operations in factories and critical infrastructure.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG