Fast fault diagnosis algorithm for rolling bearing based on transfer learning and deep residual network

被引：0

作者：

Liu F. ^{[1
]}

Chen R. ^{[1
]}

Xing K. ^{[2
]}

Ding S. ^{[1
]}

Zhang M. ^{[1
]}

机构：

[1] State Key Laboratory of Mechanics and Control of Mechanical Structures, Nanjing University of Aeronautics and Astronautics, Nanjing

[2] College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing

来源：

Zhendong yu Chongji/Journal of Vibration and Shock | 2022年 / 41卷 / 03期

关键词：

Deep learning; Deep residual network (ResNet); Rolling bearing fault diagnosis; Short-time Fourier transform (STFT); Transfer learning (TL);

D O I：

10.13465/j.cnki.jvs.2022.03.019

中图分类号：

学科分类号：

摘要：

Here, aiming at shortcomings of the existing rolling bearing fault diagnosis algorithm based on deep learning, such as, large amount of training parameters, long training time and a large number of training samples, a fast fault diagnosis algorithm (TL-ResNet) based on the transfer learning (TL) and the deep residual network (ResNet) was proposed. Firstly, a method of converting a vibration signal into 3-channel image data by combining short-time Fourier transform (STFT) and pseudo-color processing was developed. Then, ResNet 18 model trained on ImageNet data set was taken as the pre-training model, and it was applied in the field of rolling bearing fault diagnosis with TL method. Finally, a small sample transfer method was proposed to do fault diagnosis of rolling bearing under different working conditions. Tests were conducted on Case Western Reserve University (CWRU) and Padborn University (PU) data sets. Test results showed that diagnostic accuracies using TL-ResNet are 99.8% and 95.2%, respectively; the training time of TL-ResNet on CWRU data set is only 1.5 s; the proposed algorithm is superior to other fault diagnosis algorithms based on deep learning and classical algorithms, and it can be used for rapid fault diagnosis in practical industrial environment. © 2022, Editorial Office of Journal of Vibration and Shock. All right reserved.

引用

页码：154 / 164

页数：10

共 24 条

[1] BONNETT A H, YUNG C., Increased efficiency versus increased reliability[J], IEEE Industry Applications Magazine, 14, 1, pp. 29-36, (2008)
[2] ZHOU Xiaolong, LIU Weina, JIAN Zhenhai, Et al., Gear fault diagnosis based on improved HHT and Mahalanobis distance, Journal of Vibration and Shock, 36, 22, pp. 218-224, (2017)
[3] CHEN Junxun, CHENG Longsheng, HU Shaolin, Et al., Fault diagnosis of rolling bearings using modified Mahalanobis-Taguchi system based on EMD, Journal of Vibration and Shock, 36, 5, pp. 151-156, (2017)
[4] XIA M, LI T, XU L, Et al., Fault diagnosis for rotating machinery using multiple sensors and convolutional neural networks[J], IEEE/ASME Transactions on Mechatronics, 23, 1, pp. 101-110, (2017)
[5] ZHANG Long, MAO Zhide, YANG Shixi, Et al., An improved Kurtogram based on band-pass envelope spectral kurtosis with its application in bearing fault diagnosis, Journal of Vibration and Shock, 37, 23, pp. 171-179, (2018)
[6] JIANG Jingsheng, WANG Huaqing, KE Yanliang, Et al., Fault diagnosis based on LTSA and K-nearest neighbor classifier, Journal of Vibration and Shock, 36, 11, pp. 134-139, (2017)
[7] HE Dawei, PENG Jingbo, HU Jinhai, Et al., Bearing fault diagnosis based on a modified CS-SVM model optimized by an improved FOA algorithm, Journal of Vibration and Shock, 37, 18, pp. 108-114, (2018)
[8] LI Feng, TANG Baoping, GUO Yin, Early fault diagnosis using Laplacian twin least squares support vector machine, Journal of Vibration and Shock, 36, 16, pp. 85-92, (2017)
[9] HAIDONG S, HONGKAI J, YING L, Et al., A novel method for intelligent fault diagnosis of rolling bearings using ensemble deep auto-encoders[J], Mechanical Systems and Signal Processing, 102, pp. 278-297, (2018)
[10] SUN W J, SHAO S Y, ZHAO R, Et al., A sparse auto-encoder-based deep neural network approach for induction motor faults classification[J], Measurement, 89, pp. 171-178, (2016)

← 1 2 3 →