Skip to main content
SpringerLink
Log in

Unsupervised construction of health indicator for rotating machinery via multi-criterion feature selection and attentive variational autoencoder

  • Article
  • Published:
Science China Technological Sciences Aims and scope Submit manuscript

Abstract

Health indicator (HI) construction is a crucial task in degradation evaluation and facilitates the prognostic and health management (PHM) of rotating machinery. Excluding interference from artificial labeling, the HI construction approaches in an unsupervised manner have attracted substantial attention. Nevertheless, current unsupervised methods generally struggle with two problems: (1) ignorance of both redundancy between features and global variability of features during the feature selection process; (2) inadequate utilization of information from different sampling moments. To tackle these problems, this work develops a novel unsupervised approach for HI construction that integrates multi-criterion feature selection and the Attentive Variational Autoencoder (Attentive VAE). Explicitly, a multi-criterion feature selection (McFS) algorithm together with an elaborately designed metric is proposed to determine a superior feature subset, considering the relevance, the redundancy, and the global variability of features simultaneously. Then, for the adequate utilization of the information from distinct sampling moments, a deep learning model named Attentive VAE is established. The Attentive VAE is solely fed with the selected features in the health state for model training and the HI is derived through the reconstruction error to reveal the degradation degree of machinery. Two case studies based on genuine experimental datasets are involved to quantitatively evaluate the superiority of the developed approach, demonstrating its superiority over other unsupervised methods for characterizing degradation processes. The effectiveness of both the McFS algorithm and the Attentive VAE is verified by ablation experiments, respectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Jin Y R, Qin C J, Zhang Z N, et al. A multi-scale convolutional neural network for bearing compound fault diagnosis under various noise conditions. Sci China Tech Sci, 2022, 65: 2551–2563

    Article  Google Scholar 

  2. Xu Y G, Wang L, Hu A J, et al. Time-extracting S-transform algorithm and its application in rolling bearing fault diagnosis. Sci China Tech Sci, 2022, 65: 932–942

    Article  Google Scholar 

  3. Wang T Y, Han Q K, Chu F L, et al. Vibration based condition monitoring and fault diagnosis of wind turbine planetary gearbox: A review. Mech Syst Signal Process, 2019, 126: 662–685

    Article  Google Scholar 

  4. Di Z Y, Shao H D, Xiang J W. Ensemble deep transfer learning driven by multisensor signals for the fault diagnosis of bevel-gear cross-operation conditions. Sci China Tech Sci, 2021, 64: 481–492

    Article  Google Scholar 

  5. Zhao D Z, Li J Y, Cheng W D, et al. Compound faults detection of rolling element bearing based on the generalized demodulation algorithm under time-varying rotational speed. J Sound Vib, 2016, 378: 109–123

    Article  Google Scholar 

  6. Lei Z H, Wen G R, Dong S Z, et al. An intelligent fault diagnosis method based on domain adaptation and its application for bearings under polytropic working conditions. IEEE Trans Instrum Meas, 2021, 70: 1–14

    Article  Google Scholar 

  7. Zhao B X, Cheng C M, Tu G W, et al. An interpretable denoising layer for neural networks based on reproducing kernel Hilbert space and its application in machine fault diagnosis. Chin J Mech Eng, 2021, 34: 1–11

    Article  Google Scholar 

  8. Li J, Zi Y, Wang Y, et al. Health indicator construction method of bearings based on Wasserstein dual-domain adversarial networks under normal data only. IEEE Trans Ind Electron, 2022, 69: 10615–10624

    Article  Google Scholar 

  9. He Y H, Zhao Y X, Han X, et al. Functional risk-oriented health prognosis approach for intelligent manufacturing systems. Reliab Eng Syst Saf, 2022, 203: 107090

    Article  Google Scholar 

  10. Lei Y G, Li N P, Guo L, et al. Machinery health prognostics: A systematic review from data acquisition to RUL prediction. Mech Syst Signal Process, 2018, 104: 799–834

    Article  Google Scholar 

  11. Qian Y N, Yan R Q, Hu S J. Bearing degradation evaluation using recurrence quantification analysis and Kalman filter. IEEE Trans Instrum Meas, 2014, 63: 2599–2610

    Article  Google Scholar 

  12. Rai A, Kim J M. A novel health indicator based on information theory features for assessing rotating machinery performance degradation. IEEE Trans Instrum Meas, 2020, 69: 6982–6994

    Article  Google Scholar 

  13. Wang Y, Peng Y, Zi Y, et al. A two-stage data-driven-based prognostic approach for bearing degradation problem. IEEE Trans Ind Inf, 2016, 12: 924–932

    Article  Google Scholar 

  14. Soualhi M, Nguyen K T P, Medjaher K. Pattern recognition method of fault diagnostics based on a new health indicator for smart manufacturing. Mech Syst Signal Process, 2020, 142: 106680

    Article  Google Scholar 

  15. Chang Y, Chen J, Lv H, et al. Heterogeneous bi-directional recurrent neural network combining fusion health indicator for predictive analytics of rotating machinery. ISA Trans, 2022, 122: 409–423

    Article  Google Scholar 

  16. Guo L, Li N, Jia F, et al. A recurrent neural network based health indicator for remaining useful life prediction of bearings. Neurocomputing, 2017, 240: 98–109

    Article  Google Scholar 

  17. Wang H, Peng M, Miao Z, et al. Remaining useful life prediction techniques for electric valves based on convolution auto encoder and long short term memory. ISA Trans, 2021, 108: 333–342

    Article  Google Scholar 

  18. Yang J L, Yin S Y, Chang Y Q, et al. An efficient method for monitoring degradation and predicting the remaining useful life of mechanical rotating components. IEEE Trans Instrum Meas, 2021, 70: 1–14

    Article  Google Scholar 

  19. She D M, Jia M P. Wear indicator construction of rolling bearings based on multi-channel deep convolutional neural network with exponentially decaying learning rate. Measurement, 2019, 135: 368–375

    Article  Google Scholar 

  20. Yang H B, Sun Z, Jiang G D, et al. Remaining useful life prediction for machinery by establishing scaled-corrected health indicators. Measurement, 2020, 163: 108035

    Article  Google Scholar 

  21. Xu F, Wang L. Constructing a health indicator for bearing degradation assessment via an unsupervised and enhanced stacked autoencoder. Adv Eng Inf, 2022, 53: 101708

    Article  Google Scholar 

  22. Dai J, Wang J, Huang W, et al. Machinery health monitoring based on unsupervised feature learning via generative adversarial networks. IEEE ASME Trans Mechatron, 2020, 25: 2252–2263

    Article  Google Scholar 

  23. Li X, Cheng C, Zhang G, et al. An unsupervised condition monitoring method for rolling bearings based on compound feature selection and multistep-aware BiGRU-VAE. IEEE Trans Instrum Meas, 2023, 72: 1–12

    Google Scholar 

  24. Xu Z, Bashir M, Liu Q, et al. A novel health indicator for intelligent prediction of rolling bearing remaining useful life based on unsupervised learning model. Comput Ind Eng, 2023, 176: 108999

    Article  Google Scholar 

  25. Luo M, Li C, Zhang X, et al. Compound feature selection and parameter optimization of ELM for fault diagnosis of rolling element bearings. ISA Trans, 2016, 65: 556–566

    Article  Google Scholar 

  26. Wei Z, Wang Y, He S, et al. A novel intelligent method for bearing fault diagnosis based on affinity propagation clustering and adaptive feature selection. Knowledge-Based Syst, 2017, 116: 1–12

    Article  Google Scholar 

  27. Li Y B, Yang Y T, Li G Y, et al. A fault diagnosis scheme for planetary gearboxes using modified multi-scale symbolic dynamic entropy and mRMR feature selection. Mech Syst Signal Process, 2017, 91: 295–312

    Article  Google Scholar 

  28. Hamaide V, Glineur F. Unsupervised minimum redundancy maximum relevance feature selection for predictive maintenance. Int J Prognost Health Manag, 2021, 12

  29. Zhang S, Liu Z, Chen Y, et al. Selective kernel convolution deep residual network based on channel-spatial attention mechanism and feature fusion for mechanical fault diagnosis. ISA Trans, 2023, 133: 369–383

    Article  Google Scholar 

  30. Yang Q, Tang B, Li Q, et al. Dual-frequency enhanced attention network for aircraft engine remaining useful life prediction. ISA Trans, 2023, 141: 167–183

    Article  Google Scholar 

  31. Ding Y, Jia M, Miao Q, et al. A novel time-frequency transformer based on self-attention mechanism and its application in fault diagnosis of rolling bearings. Mech Syst Signal Process, 2022, 168: 108616

    Article  Google Scholar 

  32. Li Z, Jiang W, Wu X, et al. Study on health indicator construction and health status evaluation of hydraulic pumps based on LSTM-VAE. Processes, 2022, 10: 1869

    Article  Google Scholar 

  33. Zhang L, Zhang H, Cai G. The multiclass fault diagnosis of wind turbine bearing based on multisource signal fusion and deep learning generative model. IEEE Trans Instrum Meas, 2022, 71: 1–12

    Google Scholar 

  34. Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. ArXiv: 1706.03762

  35. Kingma D P, Welling M. Auto-encoding variational bayes. ArXiv: 1312.6114

  36. Zhang B, Zhang L, Xu J. Degradation feature selection for remaining useful life prediction of rolling element bearings. Qual Reliab Engng Int, 2016, 32: 547–554

    Article  Google Scholar 

  37. Qin Y, Zhou J, Chen D. Unsupervised health indicator construction by a novel degradation-trend-constrained variational autoencoder and its applications. IEEE ASME Trans Mechatron, 2022, 27: 1447–1456

    Article  Google Scholar 

  38. Chen D, Qin Y, Wang Y, et al. Health indicator construction by quadratic function-based deep convolutional auto-encoder and its application into bearing RUL prediction. ISA Trans, 2021, 114: 44–56

    Article  Google Scholar 

  39. Székely G J, Rizzo M L, Bakirov N K. Measuring and testing dependence by correlation of distances. Ann Statist, 2007, 35

  40. Peng H C, Long F H, Ding C. Feature selection based on mutual information criteria of max-dependency, max-relevance, and minredundancy. IEEE Trans Pattern Anal Mach Intell, 2005, 27: 1226–1238

    Article  Google Scholar 

  41. Estevez P A, Tesmer M, Perez C A, et al. Normalized mutual information feature selection. IEEE Trans Neural Netw, 2009, 20: 189–201

    Article  Google Scholar 

  42. McHugh M L. The Chi-square test of independence. Biochem Med, 2013, 23: 143–149

    Article  Google Scholar 

  43. Pincus S M. Approximate entropy as a measure of system complexity. Proc Natl Acad Sci USA, 1991, 88: 2297–2301

    Article  MathSciNet  Google Scholar 

  44. Richman J S, Moorman J R. Physiological time-series analysis using approximate entropy and sample entropy. Am J Physiol-Heart Circ Physiol, 2000, 278: H2039–H2049

    Article  Google Scholar 

  45. Bandt C, Pompe B. Permutation entropy: A natural complexity measure for time series. Phys Rev Lett, 2002, 88: 17410

    Article  Google Scholar 

  46. Chen W, Wang Z, Xie H, et al. Characterization of surface EMG signal based on fuzzy entropy. IEEE Trans Neural Syst Rehabil Eng, 2007, 15: 266–272

    Article  Google Scholar 

  47. Guo L, Yu Y, Duan A, et al. An unsupervised feature learning based health indicator construction method for performance assessment of machines. Mech Syst Signal Process, 2022, 167: 108573

    Article  Google Scholar 

  48. Graves A, Mohamed A-R, Hinton G. Speech recognition with deep recurrent neural networks. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. Vancouver, 2013. 6645–6649

  49. Nectoux P, Gouriveau R, Medjaher K, et al. Pronostia: An experimental platform for bearings accelerated degradation tests. In: IEEE International Conference on Prognostics and Health Management. Denver, 2012. 1–8

  50. Wang B, Lei Y, Li N, et al. A hybrid prognostics approach for estimating remaining useful life of rolling element bearings. IEEE Trans Rel, 2020, 69: 401–412

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai, 200240, China

    XinYu Li, ChangMing Cheng & ZhiKe Peng

  2. School of Mechanical Engineering, Ningxia University, Yinchuan, 750021, China

    ZhiKe Peng

Authors
  1. XinYu Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. ChangMing Cheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. ZhiKe Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to ChangMing Cheng.

Additional information

This work was supported by the National Key Research and Development Program of China (Grant No. 2021YFB3400700), the China Academy of Railway Sciences Corporation Limited within the major issues of the fund (Grant No. 2021YJ212), the National Natural Science Foundation of China (Grant Nos. 12072188, 12121002), and the Natural Science Foundation of Shanghai (Grant No. 20ZR1425200).

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, X., Cheng, C. & Peng, Z. Unsupervised construction of health indicator for rotating machinery via multi-criterion feature selection and attentive variational autoencoder. Sci. China Technol. Sci. 67, 1524–1537 (2024). https://doi.org/10.1007/s11431-023-2610-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11431-023-2610-4

Search

Navigation