基于域适应与分类器差异的滚动轴承跨域故障诊断

doi:10.12068/j.issn.1005-3026.2021.03.010

东北大学学报（自然科学版） ›› 2021, Vol. 42 ›› Issue (3): 367-372.DOI: 10.12068/j.issn.1005-3026.2021.03.010

基于域适应与分类器差异的滚动轴承跨域故障诊断

张永超，李琦，任朝晖，周世华

(东北大学机械工程与自动化学院，辽宁沈阳110819)

收稿日期:2020-08-11 修回日期:2020-08-11 接受日期:2020-08-11 发布日期:2021-03-12
通讯作者: 张永超
作者简介:张永超(1993-)，男，辽宁朝阳人，东北大学博士研究生；任朝晖(1968-)，男，辽宁沈阳人，东北大学教授，博士生导师.
基金资助:
中央高校基本科研业务费专项资金资助项目(N180304018).

Cross-Domain Fault Diagnosis of Rolling Bearings Using Domain Adaptation with Classifier Discrepancy

ZHANG Yong-chao， LI Qi， REN Zhao-hui， ZHOU Shi-hua

School of Mechanical Engineering & Automation， Northeastern University， Shenyang 110819， China.

Received:2020-08-11 Revised:2020-08-11 Accepted:2020-08-11 Published:2021-03-12
Contact: REN Zhao-hui
About author:-
Supported by:
-

摘要/Abstract

摘要： 基于数据驱动方法诊断滚动轴承故障时，不同工况下的数据特征分布差异会导致模型诊断性能严重下降.针对这一问题，提出了基于域适应与分类器差异的滚动轴承跨域故障诊断方法.首先利用卷积神经网络对带标记的源域样本和无标记的目标域样本进行特征提取;然后通过2个全连接分类器进行故障分类;最后通过分步优化分类损失、域最大平均差异损失和分类器差异损失，实现源域和目标域之间的域分布对齐，从而实现无标记目标域样本的故障诊断.实验结果表明，所提方法与主流的域适应方法相比具有更高故障诊断准确率，验证了该方法的合理性和可行性.

关键词: 故障诊断;域适应;卷积神经网络;最大平均差异;滚动轴承

Abstract: When diagnosing rolling bearing faults based on data-driven methods， the discrepancy in data distribution under different operating conditions may result in severe degradation of model diagnosis performance.To handle this issue， a cross-domain fault diagnosis method of rolling bearing based on domain adaptation with classifier discrepancy was proposed.Firstly， the convolutional neural network was used to extract the features of the labeled source domain samples and the unlabeled target domain samples.Then， the features were classified by two fully connected classifiers.Finally， the classification loss， the maximum mean discrepancy loss and the classifier discrepancy loss were optimized step by step to align the domain distribution discrepancy between the source domain and the target domain so as to implement the fault diagnosis of unlabeled target domain samples.The experimental results showed that the proposed method has a higher fault diagnosis accuracy rate than the mainstream domain adaptation methods， which verifies its rationality and feasibility.

Key words: fault diagnosis;domain adaptation;convolutional neural network;maximum mean discrepancy; rolling bearing

中图分类号:

TH17

张永超，李琦，任朝晖，周世华. 基于域适应与分类器差异的滚动轴承跨域故障诊断[J]. 东北大学学报（自然科学版）, 2021, 42(3): 367-372.

ZHANG Yong-chao， LI Qi， REN Zhao-hui， ZHOU Shi-hua. Cross-Domain Fault Diagnosis of Rolling Bearings Using Domain Adaptation with Classifier Discrepancy[J]. Journal of Northeastern University(Natural Science), 2021, 42(3): 367-372.

参考文献

[1]Li X，Jia X D，Zhang W，et al.Intelligent cross-machine fault diagnosis approach with deep auto-encoder and domain adaptation［J］.Neurocomputing，2020，383:235-247.
[2]Yang B，Lei Y G，Jia F，et al.An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings［J］.Mechanical Systems and Signal Processing，2019，122:692-706.
[3]袁壮，董瑞，张来斌，等.深度领域自适应及其在跨工况故障诊断中的应用［J］.振动与冲击，2020，39(12):281-288.(Yuan Zhuang，Dong Rui，Zhang Lai-bin，et al.Deep domain adaptation and its application in fault diagnosis across working conditions［J］.Journal of Vibration and Shock，2020，39(12):281-288.)
[4]赵小强，张青青.改进Alexnet的滚动轴承变工况故障诊断方法［J］.振动，测试与诊断，2020，40(3):472-480.(Zhao Xiao-qiang，Zhang Qing-qing.Improved Alexnet based fault diagnosis method for rolling bearing under variable conditions［J］.Journal of Vibration，Measurement & Diagnosis，2020，40(3):472-480.)
[5]Shao H D，Jiang H K，Lin Y，et al.A novel method for intelligent fault diagnosis of rolling bearings using ensemble deep auto-encoders ［J］.Mechanical Systems and Signal Processing，2018，102:278-297.
[6]李嘉琳，何巍华，曲永志.PSO优化深度神经网络诊断齿轮早期点蚀故障［J］.东北大学学报(自然科学版)，2019，40(7):974-979.(Li Jia-lin，He Wei-hua，Qu Yong-zhi.Diagnosis of gear early pitting faults using PSO optimized deep neural network［J］.Journal of Northeastern University (Natural Science)，2019，40(7):974-979.)
[7]Glowacz A，Glowacz W，Glowacz Z，et al.Early fault diagnosis of bearing and stator faults of the single-phase induction motor using acoustic signals［J］.Measurement，2018，113:1-9.
[8]Han T，Liu C，Yang W G，et al.Learning transferable features in deep convolutional neural networks for diagnosing unseen machine conditions［J］.ISA Transactions，2019，93:341-353.
[9]Lu W N，Liang B，Cheng Y，et al.Deep model based domain adaptation for fault diagnosis［J］.IEEE Transactions on Industrial Electronics，2016，64:2296-2305.
[10]Li X，Zhang W，Ding Q S，et al.Multi-layer domain adaptation method for rolling bearing fault diagnosis［J］.Signal Process，2019，157:180-197.
[11]Han T，Liu C，Yang W G，et al.A novel adversarial learning framework in deep convolutional neural network for intelligent diagnosis of mechanical faults［J］.Knowledge-Based Systems，2019，165:474-487.
[12]Ma P，Zhang H L，Fan W H，et al.A diagnosis framework based on domain adaptation for bearing fault diagnosis across diverse domains［J］.ISA Transactions，2020，99:465-478.
[13]Zhang Y C，Ren Z H，Zhou S H.A new deep convolutional domain adaptation network for bearing fault diagnosis under different working conditions［J］.Shock and Vibration，2020，2020:1-14.
[14]Ganin Y，Lempitsky V.Unsupervised domain adaptation by backpropagation ［C］//International Conference on Machine Learning.New York，2015:1180-1189.
[15]Maaten L，Hinton G.Visualizing data using t-SNE［J］.Journal of Machine Learning Research，2008，9:2579-2605.

基于域适应与分类器差异的滚动轴承跨域故障诊断

Cross-Domain Fault Diagnosis of Rolling Bearings Using Domain Adaptation with Classifier Discrepancy

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 7

编辑推荐

Metrics

本文评价

[1]	宋博学，于天彪，姜兴宇，郗文超. 激光熔覆产生的熔池温度与对流分析[J]. 东北大学学报:自然科学版, 2020, 41(10): 1427-1431.
[2]	于天彪，宋博学，郗文超，马哲伦. 激光熔覆工艺参数对熔覆层形貌的影响及优化[J]. 东北大学学报:自然科学版, 2019, 40(4): 537-542.
[3]	刘长福，朱立达，仇健，李明. 基于VMD和FFT的变切深侧铣颤振特征提取方法[J]. 东北大学学报:自然科学版, 2018, 39(8): 1153-1157.
[4]	刘宇，王迁，刘阔，张义民. 基于小波奇异性和支持向量机微铣刀破损检测[J]. 东北大学学报:自然科学版, 2017, 38(10): 1426-1430.
[5]	李常有，杨勇，郭耸，张义民. 应用量纲分析与热图像的板缺陷深度检测[J]. 东北大学学报:自然科学版, 2017, 38(5): 680-684.
[6]	张天瑞，于天彪，赵海峰，王宛山. 数据挖掘技术在全断面掘进机故障诊断中的应用[J]. 东北大学学报:自然科学版, 2015, 36(4): 527-532.
[7]	郗文超，宋博学，梁赢东，于天彪. 原位生成NbC增强YCF102熔覆层热力学与耐磨性研究[J]. 东北大学学报（自然科学版）, 2021, 42(4): 538-543.