A multi-step progressive fault diagnosis method for rolling element bearing based on energy entropy theory and hybrid ensemble auto-encoder. (April 2019)

• Record Type: Journal Article
• Authors: Jiang, Wei; Zhou, Jianzhong; Liu, Han; Shan, Yahui
• Is Part Of: ISA transactions. Volume 87(2019)
• Page Start: 235
• Page End: 250
• Publication Date: 2019-04
• Subjects: Rolling element bearing -- Multi-step progressive fault diagnosis -- Statistical analysis -- Energy entropy -- Hybrid ensemble auto-encoder -- Modified t-SNE; Engineering instruments -- Periodicals; Engineering instruments; Periodicals; Electronic journals; 629.805
• DOI: 10.1016/j.isatra.2018.11.044
• Languages: English
• ISSNs: 0019-0578

Abstract

Abstract: It is meaningful to efficiently identify the health status of bearing and automatically learn the effective features from the original vibration signals. In this paper, a multi-step progressive method based on energy entropy (EE) theory and hybrid ensemble auto-encoder (HEAE), systematically blending the statistical analysis approach with the deep learning technology, is proposed for rolling element bearing (REB) fault diagnosis. Firstly, a preliminary detection about the REB health status is performed by the statistical analysis technique integrated with the EE theory. Secondly, if fault exists in REB, a new HEAE is constructed based on denoising auto-encoder and contractive auto-encoder to strengthen the feature learning ability and automatically extract the deep state features from the raw data. Subsequently, a modified t-distributed stochastic neighbor embedding (M-tSNE) algorithm is developed to achieve the features reduction to further improve the diagnosis efficiency. Finally, the low-dimensional representations after features reduction are as the inputs of softmax classifier to recognize the fault conditions. The proposed method is applied to the fault diagnosis of REB. The results confirm the effectiveness and superiority of the proposed method, and it is more suitable for the actual engineering applications compared with other existing methods. Highlights: A multi-step progressive method based on energy entropy theory and hybrid ensemble auto-encoder is proposed for rolling element bearing fault diagnosis. An online preliminary detection strategy about bearing health status is developed based on the statistical analysis technique integrated with the FEEMD energy entropy theory. A hybrid ensemble auto-encoder is constructed to further enhance the feature learning ability. A modified t-SNE algorithm is developed for features reduction to improve the diagnosis efficiency. Experimental results demonstrate the superiority and practicality of the proposed multi-step diagnosis method.