计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (6A): 230700196-6.doi: 10.11896/jsjkx.230700196

• 交叉&应用 • 上一篇    下一篇

基于域对抗统计特性增强的跨域故障诊断方法

朱俞豪1, 张淞钊1, 张永1,2   

  1. 1 湖州师范学院信息工程学院 浙江 湖州 313000
    2 辽宁师范大学计算机与信息技术学院 辽宁 大连 116081
  • 发布日期:2024-06-06
  • 通讯作者: 张永(zhyong@zjhu.edu.cn)
  • 作者简介:(zyhff20160919@163.com)
  • 基金资助:
    辽宁省教育厅科学研究经费项目(LJKZ0965);湖州科技计划项目(2022GZ08,2023ZD2004)

Domain-adversarial Statistical Enhancement for Cross-domain Fault Diagnosis

ZHU Yuhao1, ZHANG Songzhao1, ZHANG Yong1,2   

  1. 1 School of Information Engineering,Huzhou University,Huzhou,Zhejiang 313000,China
    2 School of Computer & Information Technology,Liaoning Normal University,Dalian,Liaoning 116081,China
  • Published:2024-06-06
  • About author:ZHU Yuhao,born in 1997,postgraduate.His main research interests include fault diagnosis and machine learning.
    ZHANG Yong,born in 1975,Ph.D,professor,Ph.D supervisor,is a member of CCF(No.12677S).His main research interests include machine learning and data mining.
  • Supported by:
    Scientific Research Foundation of the Education Department of Liaoning Province(LJKZ0965) and Huzhou Science and Technology Plan Project(2022GZ08,2023ZD2004).

PDF (PC)

305

摘要： 故障诊断对于保障大型机械设备安全稳定运行具有十分重要的意义,但获得的数据存在严重标签缺失或缺少的问题,且不同工况下的数据特征分布显著不同。传统机器学习或微调的方法存在特征提取模式单一、视角固定的局限性,使得同类不同域的特征难以对齐。针对以上问题,文中提出了一种基于域对抗统计特性增强的跨域故障诊断方法DASEM(Domain-Adversarial Statistical Enhancement Model)。该方法采用直推式深度迁移学习技术,在域对抗框架下增强全局统计特性的表示,并与局部结构模式融合,构建双路径特征提取器。同时,利用域标签和数据结构之间的平衡关系来描述域对抗的表现形式,并通过类标签输出故障诊断结果。在西储大学轴承数据集和江南大学轴承数据集上的实验结果显示,DASEM在各个跨域任务上的平均精度分别达到了94.90%和93.15%,证明了该方法的有效性。

关键词: 故障诊断, 特征分布对齐, 域对抗, 全局统计特性

Abstract: Fault diagnosis is of great importance in ensuring the safe and stable operation of large-scale mechanical equipment.However,the obtained data often suffer from severe label shortages or lack of labels,and the data distribution varies significantly at different operating conditions.Traditional machine learning or fine-tuning methods have limitations in feature extraction,with a single pattern and fixed perspective,making it difficult to align features of the same class but different domains.To address these issues,this paper proposes a domain-adversarial statistical enhancement-based cross-domain fault diagnosis method called DASEM.This method utilizes direct transfer deep learning techniques to enhance the representation of global statistical characteristics within the framework of domain adversarial learning.It also integrates these characteristics with local structural patterns by constructing a dual-path feature extractor.The balance between domain labels and data structures is utilized to describe the manifestation of domain adversarial learning,and the fault diagnosis results are outputted based on class labels.Experimental results on the bearing datasets from Western Reserve University and Jiangnan University demonstrate the effectiveness of DASEM,achieving an average accuracy of 94.90% and 93.15%,respectively,for various cross-domain tasks.

Key words: Fault diagnosis, Feature distribution alignment, Domain adversarial, Global statistical characteristics

中图分类号: 

  • TP181
[1]PEI S C,YEH M H,LUO T L.Fractional Fourier series expansion for finite signals and dual extension to discrete-time fractional Fourier transform[J].IEEE Transactions on Signal Processing,1999,47(10):2883-2888.
[2]KUMAR R,VERMA P K.Signal Space Estimation:Application to Subspace Spectrum Analysis[C]//Proceedings of the Am-bient Communications and Computer Systems.Springer,2018.
[3]PALUPI I R,RAHARJO W.The utilization of signal analysis by using short time Fourier transform[C]//Proceedings of the RSF Conference Series:Engineering and Technology.2021.
[4]PENG Z,PETER W T,CHU F.A comparison study of im-proved Hilbert-Huang transform and wavelet transform:Application to fault diagnosis for rolling bearing[J].Mechanical Systems and Signal Processing,2005,19(5):974-988.
[5]OSADCHIY A,KAMENEV A,SAHAROV V,et al.Signal processing algorithm based on discrete wavelet transform[J].Designs,2021,5(3):41.
[6]ZAMAN S,ISLAM R.Classification of FNIRS using Wigner-ville distribution and CNN[J].International Journal of Image,Graphics and Signal Processing,2021,13(5):1-13.
[7]LU N,YIN T.Transferable common feature space mining for fault diagnosis with imbalanced data[J].Mechanical Systems and Signal Processing,2021,156:107645.
[8]XIAO Y,WANG J,HE Z,et al.Deep transfer learning with metric structure for fault diagnosis[J].Knowledge-Based Systems,2022,256:109826.
[9]GOLDT S,MÉZARD M,KRZAKALA F,et al.Modeling the influence of data structure on learning in neural networks:The hidden manifold model[J].Physical Review X,2020,10(4):041044.
[10]ZHENG H,YANG Y,YIN J,et al.Deep domain generalization combining a priori diagnosis knowledge toward cross-domain fault diagnosis of rolling bearing[J].IEEE Transactions on Instrumentation and Measurement,2020,70:3501311.
[11]ZHANG B,LI W,LI X L,et al.Intelligent fault diagnosis under varying working conditions based on domain adaptive convolutional neural networks[J].IEEE Access,2018,6:66367-66384.
[12]SHAO S,MCALEER S,YAN R,et al.Highly accurate machine fault diagnosis using deep transfer learning[J].IEEE Transactions on Industrial Informatics,2018,15(4):2446-2455.
[13]CAO P,ZHANG S,TANG J.Preprocessing-free gear fault diagnosis using small datasets with deep convolutional neural network-based transfer learning[J].IEEE Access,2018,6:26241-26253.
[14]JIANG G,HE H,YAN J,et al.Multiscale convolutional neural networks for fault diagnosis of wind turbine gearbox[J].IEEE Transactions on Industrial Electronics,2018,66(4):3196-3207.
[15]ZHU L,JI D,ZHU S,et al.Learning statistical texture for semantic segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021.
[16]WEN L,LI X,GAO L.A transfer convolutional neural network for fault diagnosis based on ResNet-50[J].Neural Computing and Applications,2020,32:6111-6124.
[17]SHI J,PENG D,PENG Z,et al.Planetary gearbox fault diagno-sis using bidirectional-convolutional LSTM networks[J].Mechanical Systems and Signal Processing,2022,162:107996.
[18]LI T,ZHAO Z,SUN C,et al.Domain adversarial graph convolutional network for fault diagnosis under variable working conditions[J].IEEE Transactions on Instrumentation and Measurement,2021,70:3515010.
[19]LI X,ZHANG Z,GAO L,et al.A new semi-supervised faultdiagnosis method via deep CORAL and transfer componentana-lysis[J].IEEE Transactions on Emerging Topics in Computational Intelligence,2021,6(3):690-699.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发