AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Chinese Journal of Aeronautics Article
Article Link
Cite
EndNote(RIS) BibTeX
Collect
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Full Length Article | Open Access

Source free unsupervised domain adaptation for electro-mechanical actuator fault diagnosis

Jianyu WANG, Heng ZHANG, Qiang MIAO,( )
College of Electrical Engineering, Sichuan University, Chengdu 610065, China

Peer review under responsibility of Editorial Committee of CJA.

Show Author Information

Abstract

A common necessity for prior unsupervised domain adaptation methods that can improve the domain adaptation in unlabeled target domain dataset is access to source domain dataset and target domain dataset simultaneously. However, data privacy makes it not always possible to access source domain dataset and target domain dataset in actual industrial equipment simultaneously, especially for aviation component like Electro-Mechanical Actuator (EMA) whose dataset are often not shareable due to the data copyright and confidentiality. To address this problem, this paper proposes a source free unsupervised domain adaptation framework for EMA fault diagnosis. The proposed framework is a combination of feature network and classifier. Firstly, source domain datasets are only applied to train a source model. Secondly, the well-trained source model is transferred to target domain and classifier is frozen based on source domain hypothesis. Thirdly, nearest centroid filtering is introduced to filter the reliable pseudo labels for unlabeled target domain dataset, and finally, supervised learning and pseudo label clustering are applied to fine-tune the transferred model. In comparison with several traditional unsupervised domain adaptation methods, case studies based on low- and high-frequency monitoring signals on EMA indicate the effectiveness of the proposed method.

Keywords

Data privacyUnsupervised domain adaptationElectro-mechanical actuatorPseudo-label clusteringNearest centroid filtering

References

1
Balaban E, Bansal P, Stoelting P, et al. A diagnostic approach for electro-mechanical actuators in aerospace systems. 2009 IEEE Aerospace conference. March 7-14, 2009; Big Sky, USA.Piscataway: IEEE Press, 2009:1–13.
Crossref
2

Mazzoleni M, Previdi F, Scandella M, et al. Experimental development of a health monitoring method for electro-mechanical actuators of flight control primary surfaces in more electric aircrafts. IEEE Access 2019;7:153618–34.
Crossref Google Scholar
3

Liu CQ, Luo GZ, Chen Z, et al. A linear ADRC-based robust high-dynamic double-loop servo system for aircraft electro-mechanical actuators. Chin J Aeronaut 2019;32(9):2174–87.
Crossref Google Scholar
4

Kumar M. A survey on electro hydrostatic actuator: Architecture and way ahead. Mater Today Proc 2021;45:6057–63.
Crossref Google Scholar
5

Fu J, Maré JC, Fu YL. Modelling and simulation of flight control electromechanical actuators with special focus on model architecting, multidisciplinary effects and power flows. Chin J Aeronaut 2017;30(1):47–65.
Crossref Google Scholar
6

Liu KJ, Feng YW, Xue XF. Fault diagnosis of hydraulic retraction system based on multi-source signals feature fusion and health assessment for the actuator. J Intell Fuzzy Syst 2018;34(6):3635–49.
Crossref Google Scholar
7

Wang JY, Miao JG, Wang JL, et al. Fault diagnosis of electrohydraulic actuator based on multiple source signals: an experimental investigation. Neurocomputing 2020;417:224–38.
Crossref Google Scholar
8

Yang J, Guo YQ, Zhao WL. Long short-term memory neural network based fault detection and isolation for electro-mechanical actuators. Neurocomputing 2019;360:85–96.
Crossref Google Scholar
9

Hussain YM, Burrow SG, Henson L, et al. A review of techniques to mitigate jamming in electromechanical actuators for safety critical applications. Int J Progn Health Manag 2018;9(Special):1–12.
Google Scholar
10

Li WH, Huang RY, Li JP, et al. A perspective survey on deep transfer learning for fault diagnosis in industrial scenarios: theories, applications and challenges. Mech Syst Signal Process 2022;167:108487.
Crossref Google Scholar
11

Pan SJ, Yang Q. A survey on transfer learning. IEEE Trans Knowl Data Eng 2010;22(10):1345–59.
Crossref Google Scholar
12

Li C, Zhang SH, Qin Y, et al. A systematic review of deep transfer learning for machinery fault diagnosis. Neurocomputing 2020;407:121–35.
Crossref Google Scholar
13

Xiao DY, Huang YX, Qin CJ, et al. Transfer learning with convolutional neural networks for small sample size problem in machinery fault diagnosis. Proc Inst Mech Eng C J Mech Eng Sci 2019;233(14):1–12.
Google Scholar
14

Wang JY, Mo ZL, Zhang H, et al. A deep learning method for bearing fault diagnosis based on time-frequency image. IEEE Access 2019;7:42373–83.
Crossref Google Scholar
15

Zhao ZB, Zhang QY, Yu XL, et al. Applications of unsupervised deep transfer learning to intelligent fault diagnosis: a survey and comparative study. IEEE Trans Instrum Meas 2021;70:1–28.
Crossref Google Scholar
16

Lu WN, Liang B, Cheng Y, et al. Deep model based domain adaptation for fault diagnosis. IEEE Trans Ind Electron 2017;64(3):2296–305.
Crossref Google Scholar
17

Si J, Shi HM, Chen JC, et al. Unsupervised deep transfer learning with moment matching: a new intelligent fault diagnosis approach for bearings. Measurement 2021;172:108827.
Crossref Google Scholar
18

Wang JY, Zhang YJ, Luo C, et al. Deep learning domain adaptation for electro-mechanical actuator fault diagnosis under variable driving waveforms. IEEE Sens J 2022;22(11):10783–93.
Crossref Google Scholar
19

Shen CQ, Wang X, Wang D, et al. Dynamic joint distribution alignment network for bearing fault diagnosis under variable working conditions. IEEE Trans Instrum Meas 2021;70:1–13.
Crossref Google Scholar
20
Zhang B, Li W, Hao J, et al. Adversarial adaptive 1-D convolutional neural networks for bearing fault diagnosis under varying working condition. arXiv preprint: 1805.00778,2018.
Crossref
21

Chen ZY, He GL, Li JP, et al. Domain adversarial transfer network for cross-domain fault diagnosis of rotary machinery. IEEE Trans Instrum Meas 2020;69(11):8702–12.
Crossref Google Scholar
22

Han T, Li YF, Qian M. A hybrid generalization network for intelligent fault diagnosis of rotating machinery under unseen working conditions. IEEE Trans Instrum Meas 2021;70:1–11.
Google Scholar
23

Guo L, Lei YG, Xing SB, et al. Deep convolutional transfer learning network: a new method for intelligent fault diagnosis of machines with unlabeled data. IEEE Trans Ind Electron 2019;66(9):7316–25.
Crossref Google Scholar
24

Wang XD, Liu F. Triplet loss guided adversarial domain adaptation for bearing fault diagnosis. Sensors (Basel) 2020;20(1):320.
Crossref Google Scholar
25
Jin C, Ragab M, Aung KMM. Secure transfer learning for machine fault diagnosis under different operating conditions. Cham: Springer International Publishing; 2020. p. 278–97.
Crossref
26

Zhang ZH, Xu XB, Gong WF, et al. Efficient federated convolutional neural network with information fusion for rolling bearing fault diagnosis. Control Eng Pract 2021;116 104913.
Crossref Google Scholar
27
Liu YA, Zhang W, Wang J, et al. Data-free knowledge transfer: a survey. arXiv preprint: 2112.15278,2021.
Crossref
28

Wang D, Chen YK, Shen CQ, et al. Fully interpretable neural network for locating resonance frequency bands for machine condition monitoring. Mech Syst Signal Process 2022;168 108673.
Crossref Google Scholar
29
Liu Y, Zhang W, Wang J. Source-free domain adaptation for semantic segmentation. IEEE/CVF conference on computer vision and pattern recognition. 20-25 June 2021; Nashville, USA.Piscataway: IEEE Press;2021:1215–24.
30
Li XF, Chen WJ, Xie D, et al. A free lunch for unsupervised domain adaptive object detection without source data. arXiv preprint: 2012.05400,2020.
Crossref
31
Liang J, He R, Sun ZN, et al. Distant supervised centroid shift: A simple and efficient approach to visual domain adaptation. 2019 IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR). 15-20 June 2019; Long Beach, USA.Piscataway: IEEE Press; 2020:2970–9.
32
Liang J, Hu DP, Feng JS. Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. Proceedings of the 37th international conference on machine learning. New York: ACM; 2020:6028–39.
Crossref
33
Kim Y, Cho D, Han K, et al. Domain adaptation without source data. arXiv preprint: 2007.01524,2020.
34
Huang JX, Guan DY, Xiao AR, et al. Model adaptation: Historical contrastive learning for unsupervised domain adaptation without source data. arXiv preprint: 2110.03374,2021.
35
Tzeng E, Hoffman J, Saenko K, et al. Adversarial discriminative domain adaptation. Proceedings of the IEEE conference on computer vision and pattern recognition. 2017:7167-76.
36

Wang JY, Mo ZL, Zhang H, et al. Ensemble diagnosis method based on transfer learning and incremental learning towards mechanical big data. Measurement 2020;155:107517.
Crossref Google Scholar
37
Müller R, Kornblith S, Hinton G. When does label smoothing help? arXiv preprint: 1906.02629,2019.
Crossref
38
Bridle JS, Heading AJR, MacKay DJC. Unsupervised classifiers, mutual information and ‘phantom targets’. Proceedings of the 4th international conference on neural information processing systems. 2 - 5 December 1991; Denver, USA. New York: ACM; 1991:1096–101.
39
Caron M, Bojanowski P, Joulin A, et al. Deep clustering for unsupervised learning of visual features.arXiv preprint: 1807.05520,2018.
40
Lee DH. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. Workshop on challenges in representation learning (ICML) 2013; 3(2):1-6.
Crossref
41
Balaban E, Saxena A, Narasimhan S, et al. Experimental validation of a prognostic health management system for electro-mechanical actuators. Reston: AIAA; 2011. Report No.: AIAA-2011-1518.
Chinese Journal of Aeronautics
Volume 36 Issue 4,
April 2023
Pages 252-267
DOI: 10.1016/j.cja.2023.02.028
Cite this article:
WANG J, ZHANG H, MIAO Q. Source free unsupervised domain adaptation for electro-mechanical actuator fault diagnosis. Chinese Journal of Aeronautics, 2023, 36(4): 252-267. https://doi.org/10.1016/j.cja.2023.02.028

27

Views

7

Crossref

7

Web of Science

7

Scopus

Altmetrics
Received: 25 April 2022
Revised: 25 May 2022
Accepted: 20 June 2022
Published: 24 February 2023
© 2023 Chinese Society of Aeronautics and Astronautics.

This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Return