A novel bearing fault diagnosis method using deep residual learning network

Bearing fault diagnosis is a serious problem on which researchers have focused to ensure the reliability and availability of rotating machinery. Knowledge-based methods are capable of providing promising solution to bearing diagnosis problem with high accuracy performance thanks to effectively processing collected sensor and actuator data. Deep learning (DL) has the advantage of ignoring feature extraction and providing accurate diagnosis among the machine learning algorithms. In order to address this issue, in this paper, a novel DL based model is presented for fault detection and classification of motor bearing. In this work, first, time domain signals are converted to images by a proposed signal-toimage conversion approach. Then, the converted gray-scale images are fed into a novel deep residual learning (DRL) network structured to learn end-to-end mapping between images and health condition of the motor bearing. The performance of the proposed DRL network is evaluated on a commonly used real vibration dataset provided by Case Western Reserve University (CWRU). Experimental results obtained for 10 different health condition demonstrate encouraging and outperforming performance with an average accuracy of 99.98% compared to the state-of-art knowledge-based bearing fault diagnosis methods.

Automated summary

This paper presents a novel deep learning-based model for fault detection and classification of motor bearing. Time domain signals are converted to grayscale images using a proposed signal-to-image conversion method, and a deep residual learning network is utilized to learn the mapping between images and the health condition of the motor bearing. Experimental results on a commonly used vibration dataset show that the proposed model outperforms knowledge-based methods with an average accuracy of 99.98%.