Abstract
We present a novel method for roller bearing fault diagnosis based on Locality Preserving Projection (LPP) and adaptive boosting algorithm (Adaboost). Firstly, we obtained several parameters from vibration signals and set up the original dataset, including time domain parameters, frequency domain parameters, and time-frequency domain parameters. Successively, we extract dimension reduced features from the original dataset using LPP. And finally, we use the adaptive boosting algorithm for training and classification. In this paper, we analyze on normal condition, inner race defect, outer race defect, and ball defect of roller bearing. To verify its advantage, we make some comparative trails, and simulation result shows its effectiveness and superiority.
Key words
Roller bearing /
Locality preserving projection /
Eigenvalue /
Eigenvector /
Adaboost
{{custom_keyword}} /
Cite this article
Download Citations
YAO pei;WANG Zhong-sheng;JIANGH Hong-kai;LIU Zhen-bao;BU Shu-hui.
Roller bearing fault diagnosis based on locality preserving projection[J]. Journal of Vibration and Shock, 2013, 32(5): 144-148
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
{{custom_fnGroup.title_en}}
Footnotes
{{custom_fn.content}}