An Improved Scheme for Vibration-Based Rolling Bearing Fault Diagnosis Using Feature Integration and AdaBoost Tree-Based Ensemble Classifier

Abstract

Bearings are key components in modern power machines. Effective diagnosis of bearing faults is crucial for normal operation. Recently, the deep convolutional neural network (DCNN) with 2D visualization technology has shown great potential in bearing fault diagnosis. Traditional DCNN-based fault diagnosis mostly adopts a single learner with one input and is time-consuming in sample and network construction to obtain a satisfied performance. In this paper, a scheme combining diverse DCNN learners and an AdaBoost tree-based ensemble classifier is proposed to improve the diagnosis performance and reduce the requirement of sample and network construction simultaneously. In this scheme, multiple types of samples can be constructed independently and employed for diagnosis simultaneously; next, the same number of DCNN learners are built for underlying features extraction and the obtained results are integrated and finally fed into the ensemble classifier for fault diagnosis. An illustration based on the Case Western Reserve University datasets is given, which proves the superiority of the proposed scheme in both accuracy and robustness. Herein, we present a universal scheme to improve the diagnosis performance, and give an example for practical application, where the signal preprocessing and image sample construction methods can also be applied in other vibration-based analysis.