Fault prognosis using deep convolutional neural network and bootstrap-based method

Abstract

This article develops a generalized deep convolutional neural network (DCNN)-Bootstrap-based prognostic approach for remaining useful life (RUL) prediction of rolling bearing. The proposed architecture includes two main parts: first, a hybrid DCNN model is utilized to simultaneously extract informative representations hidden in both time series-based and image-based features and predict RUL of bearing; second, the proposed hybrid DCNN model is embedded into the Bootstrap-based implementation framework for quantification of RUL prediction interval. Unlike other deep learning (DL)-based prognostic approaches, the proposed DCNN-Bootstrap method has two innovative features: first, both time series-based and image-based features of bearings, which can multi-dimensionally characterize the degradation of bearing, are comprehensively leveraged by the proposed hybrid DCNN model; second, the RUL prediction interval can be effectively quantified without relying on any bearing's physical and statistical prior information recurring to Bootstrap implementation paradigm. Moreover, the proposed approach is experimentally validated with a case study on rolling element bearings, and comparisons with other popular techniques widely employed in this field are also presented.