A Robust Method for Bearing Performance Degradation Assessment Based on Cyclostationary-Support Vector Data Description

摘要：

Bearing performance degradation assessment is one of the most important techniques in proactive maintenance aiming to realize equipment’s near-zero downtime and maximum productivity. In this paper, we propose a new robust method for it based on Cyclostationary analysis and support vector data description (SVDD). A health index is designed based on general distance. Combined spectral correlation density ccumulation energy is defined and used as feature vectors. Using feature vectors extracted from normal signals to train a SVDD model fitting a tight hypersphere around them, the general distance of test data to this hypersphere is used as the health index. Research results of its application in a bearing accelerated life test show that this health index can easier detect early degradation and better reflect degradation’s development than many other parameters.

关键词： Performance degradation assessment Cyclostationary analysis Support vector data description Bearing accelerated life test

作者: Yuna Pan Jin Chen

作者单位: State Key Laboratory of Mechanical System and Vibration,Shanghai Jiao Tong University,Shanghai 200240,China

会议类型: 国际会议

会议名称: 第六届国际振动工程会议(The 6th International Conference on Vibration Engineering)(ICVE’ 2008)

会议地点: 大连

会议语种:英文

在线出版日期: 2008-06-04（万方平台首次上网日期，不代表论文的发表时间）