基于GADF与引入迁移学习的ResNet34对变速轴承的故障诊断

doi:10.12068/j.issn.1005-3026.2022.03.011

东北大学学报（自然科学版） ›› 2022, Vol. 43 ›› Issue (3): 383-389.DOI: 10.12068/j.issn.1005-3026.2022.03.011

基于GADF与引入迁移学习的ResNet34对变速轴承的故障诊断

侯东晓¹，穆金涛¹，方成¹，时培明²

(1. 东北大学秦皇岛分校控制工程学院，河北秦皇岛066004; 2. 燕山大学电气工程学院，河北秦皇岛066004)

修回日期:2021-05-17 接受日期:2021-05-17 发布日期:2022-05-18
通讯作者: 侯东晓
作者简介:侯东晓(1982-)，男，山西平遥人，东北大学秦皇岛分校副教授；时培明(1979-)，男，黑龙江延寿人，燕山大学教授，博士生导师.
基金资助:
国家自然科学基金资助项目 (61973262)；河北省自然科学基金资助项目(E2019203146， E2020501013).

Fault Diagnosis of Variable Speed Bearings Based on GADF and ResNet34 Introduced Transfer Learning

HOU Dong-xiao¹， MU Jin-tao¹， FANG Cheng¹， SHI Pei-ming²

1. School of Control Engineering， Northeastern University at Qinhuangdao， Qinhuangdao 066004， China; 2. School of Electrical Engineering， Yanshan University， Qinhuangdao 066004， China.

Revised:2021-05-17 Accepted:2021-05-17 Published:2022-05-18
Contact: MU Jin-tao
About author:-
Supported by:
-

摘要/Abstract

摘要： 针对传统分析方法对于轴承在变速情况下的故障诊断较为困难的问题，提出一种基于格拉姆角差场(Gramian angular difference field，GADF)与引入迁移学习的ResNet34模型对变速轴承的故障诊断方法.首先利用GADF对一维时序振动信号进行编码，转换成二维图像，产生相应的故障图，再将这些故障图输入引用迁移学习的残差网络(ResNet)自动进行故障特征提取及分类.为了验证该方法的有效性，综合对比其他方法，本文方法在西储大学轴承数据集上表现更好.最后对加拿大渥太华大学的变速轴承数据集进行诊断，检验其在变速情况下的分类性能.结果表明，在变速情况下，所提方法可达到较高的诊断精度.

关键词: 故障诊断;变速轴承;格拉姆角域;残差网络;迁移学习

Abstract: Aiming at the problem that traditional analysis methods are difficult for fault diagnosis of bearings under variable speeds， a fault diagnosis method was proposed for variable speed bearings based on GADF(Gramian angular difference field) and ResNet34 model introduced transfer learning. Firstly， a one-dimensional time-series vibration signal was encoded by using GADF and converted into a two-dimensional image to generate the corresponding fault maps， which were then input into a residual network (ResNet) using transfer learning to automatically extract and classify fault features. To verify the effectiveness of the method， the results of comprehensive comparison with other methods showed that the proposed method performs better on the Western Reserve University bearing dataset. Finally， the variable speed bearing dataset from the University of Ottawa in Canada was diagnosed to examine its classification performance in the variable speed case. The results showed that a high diagnostic accuracy can be achieved in the variable speed case.

Key words: fault diagnosis; variable speed bearing; Gramian angular field; residual network(ResNet); transfer learning

中图分类号:

TH165⁺. 3

侯东晓，穆金涛，方成，时培明. 基于GADF与引入迁移学习的ResNet34对变速轴承的故障诊断[J]. 东北大学学报（自然科学版）, 2022, 43(3): 383-389.

HOU Dong-xiao， MU Jin-tao， FANG Cheng， SHI Pei-ming. Fault Diagnosis of Variable Speed Bearings Based on GADF and ResNet34 Introduced Transfer Learning[J]. Journal of Northeastern University(Natural Science), 2022, 43(3): 383-389.

参考文献

[1]Tang G，Wang Y，Huang Y，et al.Multiple time-frequency curve classification for tacho-less and resampling-less compound bearing fault detection under time-varying speed conditions［J］.IEEE Sensors Journal，2021，21(4):5091-5101.
[2]Tra V，Kim J，Khan S A，et al.Incipient fault diagnosis in bearings under variable speed conditions using multiresolution analysis and a weighted committee machine［J］.The Journal of the Acoustical Society of America，2017，142(1):35-41.
[3]Niu J，Lu S，Liu Y，et al.Bearing fault diagnosis of BLDC motor using Vold-Kalman order tracking filter under variable speed condition［C］//IEEE Conference on Industrial Electronics and Applications(ICIEA).Xian，2019:2379-2383.
[4]He K M，Zhang X，Ren S，et al.Deep residual learning for image recognition［C］//IEEE Conference on Computer Vision and Pattern Recognition.Seattle，2016:770-778.
[5]Chen X H，Zhang B K，Gao D.Bearing fault diagnosis base on multi-scale CNN and LSTM model［J］.Journal of Intelligent Manufacturing，2021，32(1):971-987.
[6]Eren L，Ince T，Kiranyaz S.A generic intelligent bearing fault diagnosis system using compact adaptive 1D CNN classifier［J］.Journal of Signal Processing Systems for Signal Image and Video Technology，2019，91(2):179-189.
[7]张立智，徐卫晓，井陆阳，等.基于EMD-SVD和CNN的旋转机械故障诊断［J］.振动，测试与诊断，2020，40(6):1063-1070，1228.(Zhang Li-zhi，Xu Wei-xiao，Jing Lu-yang，et al.Fault diagnosis of rotating machinery based on EMD-SVD and CNN［J］.Vibration，Test and Diagnosis，2020，40(6):1063-1070，1228.)
[8]Zhang W，Li C H，Peng G L，et al.A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load［J］.Mechanical Systems and Signal Processing，2018，100(1):439-453.
[9]Wang Z，Oates T.Imaging time-series to improve classification and imputation［C］//The 24th International Joint Conference on Artificial Intelligence(IJCAI).Buenos Aires，Argentina，2015:3939-3945.
[10]Hoang D T，Kang H J.Rolling element bearing fault diagnosis using convolutional neural network and vibration image［J］.Cognitive Systems Research，2018，53:42-50.
[11]万齐杨，熊邦书，李新民，等.基于DCAE-CNN的自动倾斜器滚动轴承故障诊断［J］.振动与冲击，2020，39(11):273-279.(Wan Qi-yang，Xiong Bang-shu，Li Xin-min，et al.Automatic tilter rolling bearing fault diagnosis based on DCAE-CNN ［J］.Vibration and Shock，2020，39(11):273-279.)
[12]Yuan Z，Zhang L，Duan L，et al.Intelligent fault diagnosis of rolling element bearings based on HHT and CNN［C］//Prognostics and System Health Management Conference(PHM-Chongqing).Chongqing，2018:292-296.
[13]Case Western Reserve University Bearing Data Center.Data file［EB/OL］.(2018-06-10)［2021-03-10］.https://cse groups. case. edu/bearing datacenter/pages/download-data-file.
[14]仝钰，庞新宇，魏子涵.基于GADF-CNN的滚动轴承故障诊断方法［J］.振动与冲击，2021，40(5):247-253，260.(Tong Yu，Pang Xin-Yu，Wei Zi-Han.A GADF-CNN based rolling bearing fault diagnosis method［J］.Vibration and Shock，2021，40(5):247-253，260.)
[15]Huang H，Baddour N.Bearing vibration data under time-varying rotational speed conditions［J］.Data in Brief，2018，21:1745-1749.

基于GADF与引入迁移学习的ResNet34对变速轴承的故障诊断

Fault Diagnosis of Variable Speed Bearings Based on GADF and ResNet34 Introduced Transfer Learning

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价