A novel deep convolutional neural network-bootstrap integrated method for RUL prediction of rolling bearing. (October 2021)

• Record Type: Journal Article
• Authors: Huang, Cheng-Geng; Huang, Hong-Zhong; Li, Yan-Feng; Peng, Weiwen
• Is Part Of: Journal of manufacturing systems. Volume 61(2021)
• Page Start: 757
• Page End: 772
• Publication Date: 2021-10
• Subjects: Bearings -- Deep learning -- Bootstrap -- Remaining useful life prediction -- Deep convolutional neural network -- Prognostic and health management; Manufacturing processes -- Periodicals; Production engineering -- Data processing -- Periodicals; Robots, Industrial -- Periodicals; Production, Technique de la -- Informatique -- Périodiques; Robots industriels -- Périodiques; Electronic journals; 670.42
• DOI: 10.1016/j.jmsy.2021.03.012
• Languages: English
• ISSNs: 0278-6125

Abstract

Highlights: This manuscript develops a novel deep convolutional neural network (DCNN) and Multilayer perceptron (MLP) dual network-based prognostic model, which can simultaneously take both 1D time series data and 2D image data as inputs to further boost the RUL prediction performance. The developed dual network is embedded into the Bootstrap implementation framework, and the proposed DCNN-Bootstrap integrated method can quantify the corresponding RUL prediction interval without relying on any prior information related to degradation process, such as its degradation physical/statistical models and the corresponding parameters initial statistical distribution. Through two case studies of rolling bearings, the effectiveness and generalization capability of the proposed dual network and the DCNN-bootstrap integrated prognostic method was comprehensively demonstrated and validated. Additionally, the source codes of the proposed method and the comparative methods will be made available to all interested readers. Abstract: In this study, a novel deep convolutional neural network-bootstrap-based integrated prognostic approach for the remaining useful life (RUL) prediction of rolling bearing is developed. The proposed architecture includes two main parts: 1) a deep convolutional neural network–multilayer perceptron (i.e., DCNN–MLP) dual network is utilized to simultaneously extract informative representations hidden in both time series-based and image-based features and to predict the RUL of bearings, and 2) the proposed dual network is embedded into the bootstrap-based implementation framework to quantify the RUL prediction interval. Unlike other deep-learning-based prognostic approaches, the proposed DCNN-bootstrap integrated method has two innovative features: 1) both 1D time series-based and 2D image-based features of bearings, which can multi-dimensionally characterize the degradation of bearings, are comprehensively leveraged by the proposed dual network, and 2) the RUL prediction interval can be effectively quantified without relying on the bearing's physical or statistical prior information based on bootstrap implementation paradigm. The proposed approach is experimentally validated with two case studies on rolling element bearings, and comparisons with other state-of-the-art techniques are also presented. Subsequently, our code will be open sourced.