Xiumei Li, Wu Deng, Huimin Zhao and Guanghai Zheng Pages 144 - 152 ( 9 )
It is important to diagnose the faults of rolling bearings, because they may lead to the failure of motor, and even the entire operating system-related disorders and failures. In order to diagnose the early faults of bearings, a novel method for early diagnosis of rolling bearing faults based on resonance-based sparse signal decomposition and principal component analysis was proposed in the present paper. Firstly, the vibration signals produced from a faulty rolling bearing were split into high and low resonance components using resonance-based sparse signal decomposition. Secondly, the principal components were extracted using principal component analysis, in order to transform the signals into frequency domain. Finally, the results were compared with the theoretical fault frequencies to locate the faulty elements. The proposed method was applied in the experimental data. The experimental results show that the proposed fault diagnosis method can quickly discern the faulty elements of rolling bearings, improve the diagnostic accuracy and provide an overview of the early fault diagnosis of rolling bearings. In this article, recent patents have been discussed.
Fast ICA algorithm, fault diagnosis, Hilbert transform, principal component analysis, resonance-based sparse decomposition, rolling bearing, vibration signal.
Software Institute, Dalian Jiaotong University, Huanghe Road, Shahekou District, Dalian, 116028, P.R. China.