An Intelligent Fault Diagnosis Method based on STFT and Convolutional Neural Network for Bearings Under Variable Working Conditions | IEEE Conference Publication | IEEE Xplore

An Intelligent Fault Diagnosis Method based on STFT and Convolutional Neural Network for Bearings Under Variable Working Conditions


Abstract:

The faults on rolling bearings, one of key components in various rotating machinery, are usually main source of many failures in these devices. It leads to many attention...Show More

Abstract:

The faults on rolling bearings, one of key components in various rotating machinery, are usually main source of many failures in these devices. It leads to many attentions by engineers and scholars who expect to accurately diagnosis their faults as early as possible to prevent chain accident. Many diagnosis methods are reported to process the cases under the constant speed or load, while the reality on this is often harsh and variable, which limits the accuracy of bearing diagnosis. To address this problem, an intelligent fault diagnosis model is put forward by combining the short-time Fourier transform (STFT) and the convolutional neural network (CNN), the former of which is used to transform the vibration signal in time domain to time-frequency domain and further forms inputs of the latter. Experimental data accumulated from six bearings under two conditions are applied to verify the effectiveness and accuracy of the diagnosis model. The damages on the bearing outer or inner race are actually generated during the accelerated life time tests and are still at the early stage, which are quite different from artificial damages and make the accurate diagnosis harder. Analyses and comparisons of the experiment results demonstrate the feasibility and higher diagnosis accuracy of the intelligent diagnosis model.
Date of Conference: 25-27 October 2019
Date Added to IEEE Xplore: 27 December 2019
ISBN Information:
Conference Location: Qingdao, China
School of Mechanical and Electronical Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China
School of Mechanical and Electronical Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China
School of Mechanical and Electronical Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China

I. Introduction

As an important component in manufacturing industry, bearings are widely used in various mechanical equipment, especially in the area of motor [1]-[3], urban rail train [4], gearbox [5]-[6] and so on. With the increasingly high-quality requirements for various types of mechanical equipment, condition monitoring for bearings plays an important role for their safety and reliability operation. It is reported that damages are easily existed in bearings under harsh working environment and further affect their service life [7]. Furthermore, their damage may cause their failure and chain reactions on adjacent machine components and the whole rotating machinery. Therefore, it is critical to put forward an effective and applicable method to identify bearing fault state so that it not only reduces the probability of accidents but also saves maintenance costs.

School of Mechanical and Electronical Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China
School of Mechanical and Electronical Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China
School of Mechanical and Electronical Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China

References

References is not available for this document.