Paper
21 March 2006 An experimental system for vibration sources identification with independent component analysis
Hong-Xian Ye, Shi-Xi Yang, Jiang-Xin Yang, Xiao-Ping Hu
Author Affiliations +
Proceedings Volume 6040, ICMIT 2005: Mechatronics, MEMS, and Smart Materials; 604015 (2006) https://doi.org/10.1117/12.664187
Event: ICMIT 2005: Merchatronics, MEMS, and Smart Materials, 2005, Chongqing, China
Abstract
Independent Component Analysis (ICA) can recover the original sources in multichannel observations when the original sources and the mixing process are not known. An experiment system with three known sources as an analog of the real world to research the validity and feasibility of ICA in gearbox fault diagnosis was set up. A normal gearbox and an abnormal gearbox were the object, a small motor was used to simulate the effect of the environment, and single tooth failure and the misalignment fault were considered as the inner known sources. Eight selective places where accelerometers glued on presented the full information of gearbox. The experiment results show that when the signal frequency is less than 100hz, it is appropriate to consider the mixing model of vibration sources as instantaneous model. The separation results by mean of FastICA algorithm which obtained from instantaneous model can successfully separate the vibration of disturbing motor, the pulse of single tooth failure and the frequency of misalignment fault from the observation on gearbox with light load. The experiment results suggest that the setup of the experimental system provides us an efficient experimental environment for algorithm research of validity and its feasibility testing and verifying.
© (2006) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hong-Xian Ye, Shi-Xi Yang, Jiang-Xin Yang, and Xiao-Ping Hu "An experimental system for vibration sources identification with independent component analysis", Proc. SPIE 6040, ICMIT 2005: Mechatronics, MEMS, and Smart Materials, 604015 (21 March 2006); https://doi.org/10.1117/12.664187
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Independent component analysis

Sensors

Teeth

Convolution

Phase shifts

Signal processing

Vibrometry

Back to Top