Novel Transfer Learning Based on Support Vector Data Description for Aeroengine Fault Detection
Publication: Journal of Aerospace Engineering
Volume 37, Issue 3
Abstract
Fault detection is an important part of aeroengine health management. Intelligent fault detection methods represented by machine learning have been widely studied. However, most studies assume that training and test data follow the same distribution, which is unrealistic. Due to the degradation of engine performance or change of engine operating environment, the historical operation data of aeroengines are different from the current operation data of the engine. If the engine history operation data are directly used to train a fault detection model, the fault detection of the current engine may lead to low efficiency and affect the reliability of fault detection. In order to overcome this problem, transfer learning is introduced into aircraft engine fault detection in this paper. This paper combines transfer learning with support vector data description (SVDD), a common fault detection algorithm, and proposes SVDD-based transfer learning (SVDD-TL). This algorithm takes the spherical center of the SVDD as the knowledge structure to transfer from the source domain to the target domain, which can improve the detection accuracy of the model in the target domain. A fault detection experiment for an aeroengine was designed. Single and mixed fault data were used in the experiment, and the variation of fault data quantity was considered. Experimental results showed that the proposed method can improve the fault detection accuracy of the model in the target domain and still have good detection performance when the amount of fault data changes.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or codes generated or used during the study are proprietary or confidential in nature and may only be provided with restrictions. The aeroengine model cannot be provided because it is proprietary, and it is a part of an ongoing project. Some algorithm codes can be provided upon reasonable request.
Acknowledgments
This research was supported in part by the National Science and Technology Major Project (J2019-I-0010-0010), in part by the Fundamental Research Funds for the Central Universities (NS2022027), and in part by the Science Center for Gas Turbine Project (P2022-B-V-002-001).
References
Camerini, V., G. Coppotelli, and S. Bendisch. 2018. “Fault detection in operating helicopter drivetrain components based on support vector data description.” Aerosp. Sci. Technol. 73 (Feb): 48–60. https://doi.org/10.1016/j.ast.2017.11.043.
Cui, J., Y. Tian, X. Cui, J. Wang, L. Jiang, and M. Yu. 2020. “A method for fault diagnosis of aviation engine gas system.” In Proc., 39th Chinese Control Conf., 4244–4248. Beijing: Systems Engineering Society of China. https://doi.org/10.23919/CCC50068.2020.9189544.
DeCastro, J. A., J. S. Litt, and D. K. Frederick. 2008. “A modular aero-propulsion system simulation of a large commercial aircraft engine.” In Proc., 44th AIAA/ASME/SAE/ASEE Joint Propulsion Conf. and Exhibit, 2008–4579. Reston, VA: American Institute of Aeronautics and Astronautics.
Fan, Y. P., J. Luo, and M. C. Ren. 2006. “Aero-engine fault diagnosis based on one-class classification of SVM.” [In Chinese.] Gas Turbine Exp. Res. 3 (4): 22–28.
Ganin, Y., E. Ustinova, H. Ajakan, P. Germain, H. Larochelle, F. Laviolette, M. Marchand, and V. Lempitsky. 2016. “Domain-adversarial training of neural networks.” J. Mach. Learn. Res. 17 (59): 1–35.
Jin, H.-J., Y.-P. Zhao, and Z.-Q. Wang. 2023. “A rotating stall warning method for aero-engine compressor based on DeepESVDD-CNN.” Aerosp. Sci. Technol. 139 (Aug): 108411. https://doi.org/10.1016/j.ast.2023.108411.
Leng, Q., H. G. Qi, J. Miao, W. T. Zhu, and G. P. Su. 2015. “One-class classification with extreme learning machine.” Math. Probl. Eng. 2015 (May): 412957. https://doi.org/10.1155/2015/412957.
Li, B., Y.-P. Zhao, and Y.-B. Chen. 2021. “Unilateral alignment transfer neural network for fault diagnosis of aircraft engine.” Aerosp. Sci. Technol. 118 (Nov): 107031. https://doi.org/10.1016/j.ast.2021.107031.
Lin, T., G. Chen, W. Ouyang, Q. Zhang, H. Wang, and L. Chen. 2018. “Hyper-spherical distance discrimination: A novel data description method for aero-engine rolling bearing fault detection.” Mech. Syst. Signal Process. 109 (Sep): 330–351. https://doi.org/10.1016/j.ymssp.2018.01.009.
Long, M., Y. Cao, J. Wang, and M. I. Jordan. 2015. “Learning transferable features with deep adaptation networks.” In Vol. 1 of Proc., 32nd Int. Conf. on Machine Learning, 97–105. New York: IEEE Computer Society.
Long, M., J. Wang, G. Ding, J. Sun, and P. S. Yu. 2013. “Transfer feature learning with joint distribution adaptation.” In Proc., IEEE Int. Conf. on Computer Vision, 2200–2207. New York: IEEE.
Pan, S. J., I. W. Tsang, J. T. Kwok, and Q. Yang. 2011. “Domain adaptation via transfer component analysis.” IEEE Trans. Neural Networks 22 (2): 199–210. https://doi.org/10.1109/TNN.2010.2091281.
Pan, S. J., and Q. Yang. 2010. “A survey on transfer learning.” IEEE Trans. Knowl. Data Eng. 22 (10): 1345–1359. https://doi.org/10.1109/TKDE.2009.191.
Peng, P., and Y.-P. Zhao. 2023. “Robust semi-supervised discriminant embedding method with soft label in kernel space.” Neural Comput. Appl. 35 (11): 8601–8623. https://doi.org/10.1007/s00521-022-08134-z.
Perhinschi, M. G., J. Porter, H. Moncayo, J. Davis, and W. S. Wayne. 2010. “Development of a detection scheme for aircraft engine failures based on the artificial immune system paradigm.” In Proc., AIAA Guidance, Navigation, and Control Conf., 2010–7740. Reston, VA: American Institute of Aeronautics and Astronautics.
Schölkopf, B., R. Williamson, A. J. Smola, and J. C. Shawe-Taylor. 2000. “Support vector method for novelty detection.” In Advances in neural information processing systems, 582–588. Cambridge, MA: MIT Press.
Schwendemann, S., Z. Amjad, and A. Sikora. 2021. “Bearing fault diagnosis with intermediate domain based layered maximum mean discrepancy: A new transfer learning approach.” Eng. Appl. Artif. Intell. 105 (Oct): 104415. https://doi.org/10.1016/j.engappai.2021.104415.
Tax, D. M. J., and R. P. W. Duin. 1999. “Support vector data description.” Pattern Recognit. Lett. 20 (11–13): 1191–1199. https://doi.org/10.1016/S0167-8655(99)00087-2.
Tax, D. M. J., A. Ypma, and R. P. W. Duin. 1999. “Pump failure detection using support vector data descriptions.” Lect. Notes Comput. Sci. 1642 (Mar): 415–425. https://doi.org/10.1007/3-540-48412-4_35.
Tayarani-Bathaie, S. S., and K. Khorasani. 2015. “Fault detection and isolation of gas turbine engines using a bank of neural networks.” J. Process Control 36 (Dec): 22–41. https://doi.org/10.1016/j.jprocont.2015.08.007.
Wang, J., W. Liu, K. Qiu, H. Xiong, and L. Zhao. 2019. “Dynamic hypersphere SVDD without describing boundary for one-class classification.” Neural Comput. Appl. 31 (8): 3295–3305. https://doi.org/10.1007/s00521-017-3277-0.
Wang, Z., J.-L. Zarader, and S. Argentieri. 2012. “A novel aircraft engine fault diagnostic and prognostic system based on SVM.” In Proc., 2012 IEEE Int. Conf. on Condition Monitoring and Diagnosis, 723–728. New York: IEEE.
Wu, T., Y. Liang, R. Varela, C. Wu, G. Zhao, and X. Han. 2016. “Self-adaptive SVDD integrated with AP clustering for one-class classification.” Pattern Recognit. Lett. 84 (Mar): 232–238. https://doi.org/10.1016/j.patrec.2016.10.009.
Xie, J., L. Zhang, L. Duan, and J. Wang. 2016. “On cross-domain feature fusion in gearbox fault diagnosis under various operating conditions based on transfer component analysis.” In Proc., 2016 IEEE Int. Conf. on Prognostics and Health Management, 7542845. New York: IEEE.
Yin, S., X. Zhu, and C. Jing. 2014. “Fault detection based on a robust one class support vector machine.” Neurocomputing 145 (Dec): 263–268. https://doi.org/10.1016/j.neucom.2014.05.035.
Zhao, L., C. Mo, T. Sun, and W. Huang. 2020a. “Aero engine gas-path fault diagnose based on multimodal deep neural networks.” Wireless Commun. Mobile Comput. 2020 (Oct): 1–10. https://doi.org/10.1155/2020/8891595.
Zhao, Y.-P., G. Huang, Q.-K. Hu, and B. Li. 2020b. “An improved weighted one class support vector machine for turboshaft engine fault detection.” Eng. Appl. Artif. Intell. 94 (Sep): 103796. https://doi.org/10.1016/j.engappai.2020.103796.
Zhao, Y.-P., Y.-L. Xie, and Z.-F. Ye. 2021. “A new dynamic radius SVDD for fault detection of aircraft engine.” Eng. Appl. Artif. Intell. 100 (Apr): 104177. https://doi.org/10.1016/j.engappai.2021.104177.
Zhong, S.-S., S. Fu, and L. Lin. 2019. “A novel gas turbine fault diagnosis method based on transfer learning with CNN.” Measurement 137 (Mar): 435–453. https://doi.org/10.1016/j.measurement.2019.01.022.
Zhou, Y., K. Wu, Z. Meng, and M. Tian. 2017. “Fault detection of aircraft based on support vector domain description.” Comput. Electr. Eng. 61 (Mar): 80–94. https://doi.org/10.1016/j.compeleceng.2017.06.016.
Zhu, F., J. Yang, C. Gao, S. Xu, N. Ye, and T. Yin. 2016. “A weighted one-class support vector machine.” Neurocomputing 189 (May): 1–10. https://doi.org/10.1016/j.neucom.2015.10.097.
Zhuang, F. Z., Z. Qi, K. Duan, D. Xi, Y. Zhu, H. Zhu, H. Xiong, and Q. He. 2021. “A comprehensive survey on transfer learning.” Proc. IEEE 109 (1): 43–76. https://doi.org/10.1109/JPROC.2020.3004555.
Information & Authors
Information
Published In
Journal of Aerospace Engineering
Volume 37 • Issue 3 • May 2024
Copyright
© 2024 American Society of Civil Engineers.
History
Received: Jun 13, 2022
Accepted: Nov 29, 2023
Published online: Feb 9, 2024
Published in print: May 1, 2024
Discussion open until: Jul 9, 2024
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.