Affiliations: School of Mechanical Engineering, Southeast University, Nanjing, China
Correspondence:
[*]
Corresponding author. Zhisheng Zhang, Associate professor, School of Mechanical Engineering, Southeast University, Nanjing, China. E-mail: oldbc@seu.edu.cn.
Abstract: The rolling bearing is the crucial component in the rotating machinery. The degradation process monitoring and remaining useful life prediction of the bearing are necessary for the condition-based maintenance. The commonly used deep learning methods use the raw or processed time domain data as the input. However, the feature extracted by these approaches is insufficient and incomprehensive. To tackle this problem, this paper proposed an improved Deep Convolution Neural Network with the dual-channel input from the time and frequency domain in parallel. The proposed methodology consists of two stages: the incipient failure identification and the degradation process fitting. To verify the effectiveness of the method, the IEEE PHM 2012 dataset is adopted to compare the proposed method and other commonly used approaches. The results show that the improved Deep Convolution Neural Network can effectively describe the degradation process for the rolling bearing.
Keywords: Rolling bearing, Deep Convolution Neural Network, remaining useful life prediction, dual-channel input
