Spatiotemporal non-negative projected convolutional network with bidirectional NMF and 3DCNN for remaining useful life estimation of bearings

•A novel SNPCN prognostics framework for RUL estimation of bearings is proposed, which surpasses some state-of-the-art models in accuracy.•The proposed BiNMF algorithm can strongly support the efficient operation of the TFR-based prognostics models.•The superiority of 3D convolution kernels is prove...

Full description

Saved in:

Bibliographic Details
Published in:	Neurocomputing (Amsterdam) Vol. 450; pp. 294 - 310
Main Authors:	Wang, Xu, Wang, Tianyang, Ming, Anbo, Zhang, Wei, Li, Aihua, Chu, Fulei
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 25.08.2021
Subjects:	Bearing Convolutional neural network Non-negative matrix factorization Remaining useful life Time–frequency representation Time–frequency representation Non-negative matrix factorization Remaining useful life Convolutional neural network Bearing
ISSN:	0925-2312, 1872-8286
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	•A novel SNPCN prognostics framework for RUL estimation of bearings is proposed, which surpasses some state-of-the-art models in accuracy.•The proposed BiNMF algorithm can strongly support the efficient operation of the TFR-based prognostics models.•The superiority of 3D convolution kernels is proved in learning the bearing degradation knowledge from TFRs.•The spatiotemporal information in vibration signals is proved to be quite suitable for the RUL estimation of bearings. Remaining useful life (RUL) estimation for bearings is crucial in guaranteeing the reliability of rotating machinery. With the rapid development of information science, deep-learning-based RUL estimation has become more appealing as it can automatically establish the mapping relationship between the monitored data and the degradation states through feature learning. Vibration analysis via time–frequency representation (TFR) has shown great advantages for the detection of bearing damage in deep-learning-based prognostics. However, the following two problems remain: 1) insufficient or ineffective utilization of the data feature information, and 2) the requirement for huge computational resources, which still present challenges for the accuracy and efficiency of TFR-based prognostics. A novel RUL estimation approach called spatiotemporal non-negative projected convolutional network (SNPCN) is hence proposed. The approach can fully learn the spatiotemporal degradation features of bearing TFRs with high computational efficiency. In detail, the continuous wavelet transform (CWT) was applied as a TFR analysis method to reveal the nonstationary properties of the bearing degradation signals. Then, a newly proposed bidirectional non-negative matrix factorization (BiNMF) method was used to obtain the low-rank eigenmatrices of the TFRs and greatly compress the calculations in TFR-based prognostics. A three-dimensional convolutional neural network (3DCNN) was next constructed to learn the spatiotemporal degradation features in adjacent BiNMF eigenmatrices and construct the mapping relationship between the bearing RUL and current monitored data. Experiments on the PRONOSTIA platform demonstrate the feasibility and superiority of the proposed SNPCN-based bearing RUL estimation approach.
ISSN:	0925-2312 1872-8286
DOI:	10.1016/j.neucom.2021.04.048