Condition monitoring of rolling element bearing based on Phase-PCA

As the key component of many rotating machineries, running condition of rolling element bearings must be monitored for guaranteeing production efficiency and safety. In this paper, a new method of condition monitoring for rolling element bearing, Phase-PCA, is proposed based on Principal Component Analysis (PCA) and Phase Space Reconstruction (PSR). Firstly, the phase space of the one dimension vibration signals is gained via using C-C method. Then, PCA is applied in this space. The proposed method is tested with experimental data collected from drive end ball bearing of a 2 hp Reliance Electric motor driven mechanical system. The simulation results show not only SPE statistic but also T² statistic can effectively identify different conditions of rolling element bearings and the degree of confidence is further improved.