8 April 2010 Ultrasonic acoustic health monitoring of ball bearings using neural network pattern classification of power spectral density
Author Affiliations +
Abstract
This paper presents a generic passive non-contact based approach using ultrasonic acoustic emissions (UAE) to facilitate the neural network classification of bearing health, and more specifically the bearing operating condition. The acoustic emission signals used in this study are in the ultrasonic range (20-120 kHz). A direct benefit of microphones capable of measurements in this frequency range is their inherent directionality. Using selected bands from the UAE power spectrum signature, it is possible to pose the health monitoring problem as a multi-class classification problem, and make use of a single neural network to classify the ultrasonic acoustic emission signatures. Artificial training data, based on statistical properties of a significantly smaller experimental data set is used to train the neural network. This specific approach is generic enough to suggest that it is applicable to a variety of systems and components where periodic acoustic emissions exist.
© (2010) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
William Kirchner, Steve Southward, Mehdi Ahmadian, "Ultrasonic acoustic health monitoring of ball bearings using neural network pattern classification of power spectral density", Proc. SPIE 7650, Health Monitoring of Structural and Biological Systems 2010, 765024 (8 April 2010); doi: 10.1117/12.847105; https://doi.org/10.1117/12.847105
PROCEEDINGS
10 PAGES


SHARE
Back to Top