Multiple manifolds analysis and its application to fault diagnosis

作者：Li Min^*; Xu Jinwu; Yang Jianhong; Yang Debin; Wang Dadong

来源：Mechanical Systems and Signal Processing, 2009, 23(8): 2500-2509.

DOI：10.1016/j.ymssp.2009.05.001

• Multiple manifolds analysis
• Fault clustering
• Trend analysis
• Roller bearing
• Fault diagnosis

A novel approach to fault diagnosis is proposed using multiple manifolds analysis (MMA) to extract manifold information from the vibration signals collected from a mechanical system. The basic idea of MMA is to reconstruct a manifold by embedding time series into a high-dimensional phase space. The tangent direction of the neighborhood for each point is then used to approximate its local geometry. The variation of the multiple manifolds representing different states of the mechanical system can be revealed by performing multi-way principal component analysis. The vibration signals acquired from roller bearings are employed to validate the proposed algorithms. Test results show that the proposed MMA-based approach can interpret different machine conditions and is effective to the fault diagnosis, and the MMA-based fault clustering and trend analysis algorithms have outperformed the conventional fault diagnosis methods.

• 出版日期2009-11
• 单位CSIRO; 北京科技大学