Compound Fault Diagnosis of Rotating Machinery under Different Conditions Based on Subspace Embedded Feature Distribution Alignment

doi:10.3901/JME.2021.02.021

Abstract

Abstract: Aiming at the problem of cross domain feature alignment and distribution difference self-adaptive adjustment in different working conditions of composite fault diagnosis, a method of composite fault diagnosis for rotating machinery under different working conditions of subspace embedded feature distribution alignment(SEDA) is proposed. Using correlation alignment(CORAL) effectively suppressed the domain shift by aligning the corresponding features of the source domain and the target domain in the target domain subspace; In this space, the training base classifier is used to predict the pseudo label of the target domain, which has been used to quantitatively estimate the weights of the edge distribution and the conditional distribution of the two domains, so as to adapt to the differences of the feature distribution of the two domains; Through the structural risk minimization framework(SRM) constructed a kernel function, establish a classifier to transfer the above two-step learning rules, and obtain the optimal coefficient matrix through iterative updating to complete the composite fault diagnosis task. The feasibility and effectiveness of the proposed method are proved by two groups of multi-class composite fault diagnosis experiments.

Key words: different working conditions, compound fault, subspace embedded, feature alignment, adaptive adjustment of distribution difference

CLC Number:

TH17

CHEN Renxiang, WU Haonian, ZHANG Xia, TANG Baoping, HU Xiaolin, CAI Dongyin. Compound Fault Diagnosis of Rotating Machinery under Different Conditions Based on Subspace Embedded Feature Distribution Alignment[J]. Journal of Mechanical Engineering, 2021, 57(2): 21-29.

References

[1] WANG Xiaodong,ZI Yanyang,HE Zhengjia. Multiwavelet construction via an adaptive symmetric lifting scheme and its applications for rotating machinery fault diagnosis[J]. Measurementence & Technology,2009,20(4):045103.
[2] 明安波,褚福磊,张炜. 滚动轴承复合故障特征分离的小波-频谱自相关方法[J]. 机械工程学报,2013,49(3):80-87. MING Anbo,CHU Fulei,ZHANG Wei. Wavelet-spectrum autocorrelation method for feature separation of rolling bearing composite faults[J]. Journal of Mechanical Engineering,2013,49(3):80-87.
[3] PANG Haiyang,YANG Yu,LI Xin,et al. Symplectic geometry mode decomposition and its application to rotating machinery compound fault diagnosis[J]. Mechanical Systems and Signal Processing,2019,114:189-211.
[4] 陈小旺,冯志鹏,MING L. 基于迭代广义同步压缩变换的时变工况行星齿轮箱故障诊断[J]. 机械工程学报,2015,51(1):131-137. CHEN Xiaowang,FENG Zhipeng,MING L. Fault diagnosis of planetary gearbox under time-varying working conditions based on iterative generalized synchronous compression transform[J]. Journal of Mechanical Engineering,2015,51(1):131-137.
[5] 沈飞,陈超,严如强. 奇异值分解与迁移学习在电机故障诊断中的应用[J]. 振动工程学报,2017,30(1):118-126. SHEN Fei,CHEN Chao,YAN Ruqiang. Application of singular value decomposition and transfer learning in motor fault diagnosis[J]. Journal of Vibration Engineering,2017,30(1):118-126.
[6] 段礼祥,谢骏遥,王凯,等. 基于不同工况下辅助数据集的齿轮箱故障诊断[J]. 振动与冲击,2017,36(10):104-108. DUAN Lixiang,XIE Junyao,WANG Kai,et al. Gearbox fault diagnosis based on auxiliary data sets under different working conditions[J]. Vibration and Shock,2017,36(10):104-108.
[7] 康守强,胡明武,王玉静,等. 基于特征迁移学习的变工况下滚动轴承故障诊断方法[J]. 中国电机工程学报,2019(3):764-772. KANG Shouqiang,HU Mingwu,WANG Yujing,et al. Fault diagnosis method of rolling bearing under variable conditions based on feature transfer learning[J]. Proceedings of the CSEE,2019(3):764-772.
[8] WANG Jindong,FENG Wenjie,CHEN Yiqiang,et al. Visual domain adaptation with manifold embedded distribution alignment[C]//2018 ACM Multimedia Conference in Seoul,July,Korea,2018. ACM,2018:402-410.
[9] SUN Baochen,FENG Jiashi,SAENKO K. Return of frustratingly easy domain adaptation[C]//The Thirtieth AAAI Conference on Artificial Intelligence in Phoenix,Arizona,USA,February 12-17,2016. NewYork:AAAI,2016,6-8.
[10] LONG Mingsheng,WANG Jianmin,DING Guiguang,et al. Adaptation regularization:A general framework for transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering,2014,26(5):1076-1089.
[11] GONG Boqing,SHI Yuan,SHA Fei,et al. Geodesic flow kernel for unsupervised domain adaptation[C]//The 25TH IEEE Conference on Computer Vision and Pattern Recognition in Providence,Rhode Island,June 16-21,2012. NewYork:IEEE,2012:2066-2073.
[12] PAN S J,TSANG W I,KWOK T J,et al. Domain adaptation via transfer component analysis[J]. IEEE Transactions on Neural Etworks,2011,22(2):199-210.
[13] LONG Mingsheng,WANG Jianmin,DING Guiguang,et al. Transfer feature learning with joint distribution adaptation[C]//2013 IEEE International Conference on Computer Vision in Sydney,Australia,December 1-8,2013. NewYork:IEEE,2013:2200-2207.
[14] WANG Jindong,CHEN Yiqiang,HAO Shuji,et al. Balanced distribution adaptation for transfer learning[C]//IEEE International Conference on Data Mining 2017 in New Orleans,USA,November 18-21,2017. NewYork:IEEE,2017:1129-1134.
[15] LONG Mingsheng,WANG Jianmin,DING Guiguang,et al. Transfer joint matching for unsupervised domain adaptation[C]//2013 IEEE International Conference on Computer Vision in Sydney,Australia,December 1-8,2013. New York:IEEE,2013:2200-2207.
[16] ZHANG Jing,LI Wanqing,OGUNBONA P. Joint geometrical and statistical alignment for visual domain adaptation[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition in Honolulu,HI,USA,July 21-26,2017. New York:IEEE,2017:5150-5158.
[17] JIA Feng. LEI Yaguo,LIN Jing,et al. Deep neural networks:A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data[J]. Mechanical Systems and Signal Processing,2016,72-73:303-315.