A novel method of health indicator construction and remaining useful life prediction based on deep learning

• Autorzy: Zhan Xianbiao , Liu Zixuan , Yan Hao , Wu Zhenghao , Guo Chiming , Jia Xisheng

Identyfikatory

DOI

10.17531/ein/171374

• Języki publikacji: EN

Abstrakty

EN

The construction of health indicators (HI) for traditional deep learning requires human training labels and poor interpretability. This paper proposes an HI construction method based on Stacked Sparse Autoencoder (SSAE) and combines SSAE with Long short-term memory (LSTM) network to predict the remaining useful life (RUL). Extracting features from a single domain may result in insufficient feature extraction and cannot comprehensively reflect the degradation status information of mechanical equipment. In order to solve the problem, this article extracts features from time domain, frequency domain, and time-frequency domain to construct a comprehensive original feature set. Based on monotonicity, trendiness, and robustness, the most sensitive features from the original feature set are selected and put into the SSAE network to construct HI for state partitioning, and then LSTM is used for RUL prediction. By comparing with the existing methods, it is proved that the prediction effect of the proposed method in this paper is satisfied.

Słowa kluczowe

EN

stacked sparse autoencoder; health indicator; long short-term memory network; remaining useful life prediction

• Wydawca: Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne
• Czasopismo: Eksploatacja i Niezawodność
• Rocznik: 2023
• Tom: Vol. 25, no. 4
• Strony: art. no. 171374
• Opis fizyczny: Bibliogr. 41 poz., rys., tab., wykr.

Twórcy

autor

Zhan Xianbiao

• Army Engineering University of PLA, China
• Hebei Key Laboratory of Condition Monitoring and Assessment of Mechanical Equipment, China

• https://orcid.org/0000-0001-6775-9589

autor

Liu Zixuan

• North China Institute of Aerospace Engineering, China

autor

Yan Hao

• Army Engineering University of PLA, China

autor

Wu Zhenghao

• Army Engineering University of PLA, China

autor

Guo Chiming

• Army Engineering University of PLA, China

autor

Jia Xisheng

• Army Engineering University of PLA, China

• https://orcid.org/0009-0009-6766-6601

Bibliografia

• 1. Anowar F, Sadaoui S, Selim B. Conceptual and empirical comparison of dimensionality reduction algorithms (pca, kpca, lda, mds, svd, lle, isomap, le, ica, t-sne). Computer Science Review 2021; 40: 100378. doi: 10.1016/j.cosrev.2021.100378
• 2. Antoni J. Fast computation of the kurtogram for the detection of transient faults. Mechanical Systems and Signal Processing 2007; 21(1): 108-124.https://doi.org/10.1016/j.ymssp.2005.12.002
• 3. Ali J B, Saidi L, Harrath S, Bechhoefer E, Benbouzid M. Online automatic diagnosis of wind turbine bearings progressive degradations under real experimental conditions based on unsupervised machine learning. Applied Acoustics 2018; 132: 167-181.https://doi.org/10.1016/j.apacoust.2017.11.021
• 4. Bai H, Zhan X, Yan H, WuZ, WenL, Jia X. Combination of Optimized Variational Mode Decomposition and Deep Transfer Learning: A Better Fault Diagnosis Approach for Diesel Engines. Electronics, 2022, 11(13): 1969. doi: 10.3390/electronics11131969.
• 5. Chen Y, Rao M, Feng K, Niu G. Modified Varying Index Coefficient Autoregression Model for Representation of the Nonstationary Vibration From a Planetary Gearbox. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-12. doi: 10.1109/tim.2023.3259048.
• 6. Chen D, Qin Y, Qian Q, Wang Y, Liu F. Transfer life prediction of gears by cross-domain health indicator construction and multi-hierarchical long-term memory augmented network. Reliability Engineering & System Safety, 2022: 108916. doi:10.1016/j.ress.2022.108916.
• 7. Chen X, Shen Z, He Z, Sun C, Liu Z. Remaining life prognostics of rolling bearing based on relative features and multivariable support vector machine. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science 2013; 227(12): 2849-2860.https://doi.org/10.1177/0954406212474395
• 8. Chen J, Jing H, Chang Y, Qian L. Gated recurrent unit based recurrent neural network for remaining useful life prediction of nonlinear deterioration process. Reliab Eng Syst Saf 2019; 185: 372-382. https://doi.org/10.1016/j.ress.2019.01.006
• 9. Cao Y, Ding Y, Jia M, Tian R. A novel temporal convolutional network with residual self-attention mechanism for remaining useful life prediction of rolling bearings. Reliab Eng Syst Saf 2021; 215: 107813.
• 10. Cheng C, Ma G, Zhang Y, Sun M, Teng F, Ding H, et al. A deep learning-based remaining useful life prediction approach for bearings. IEEE/ASME transactions on mechatronics 2020; 25(3): 1243-1254.https://doi.org/10.1109/TMECH.2020.2971503
• 11. Chen W, Wang Z, Xie H, Yu W. Characterization of surface EMG signal based on fuzzy entropy.IEEE Transactions on neural systems and rehabilitation engineering 2007; 15(2): 266-272.https://doi.org/10.1109/TNSRE.2007.897025
• 12. Chen D, Qin Y, Wang Y, Zhou J. Health indicator construction by quadratic function-based deep convolutional auto-encoder and its application into bearing RUL prediction. ISA transactions 2021; 114: 44-56. https://doi.org/10.1016/j.isatra.2020.12.052
• 13. Dragomiretskiy K, Zosso D. Variational mode decomposition. IEEE transactions on signal processing 2013; 62(3): 531-544.https://doi.org/10.1109/TSP.2013.2288675
• 14. Fei Z, Yang F, Tsui K L, Li L, Zhang Z. Early prediction of battery lifetime via a machine learning based framework. Energy 2021; 225: 120205.https://doi.org/10.1016/j.energy.2021.120205
• 15. He Z, Shi T, Xuan J. Milling tool wear prediction using multi-sensor feature fusion based on stacked sparse autoencoders. Measurement 2022; 190: 110719.https://doi.org/10.1016/j.measurement.2022.110719
• 16. Igba J, Alemzadeh K, Durugbo C, Eiriksson E. Analyzing RMS and peak values of vibration signals for condition monitoring of wind turbine gearboxes. Renewable Energy 2016; 91: 90-106. DOI: 10.1016/j.renene.2016.01.006
• 17. Javed K, Gouriveau R, Zerhouni N, Nectoux P. Enabling health monitoring approach based on vibration data for accurate prognostics. IEEE Transactions on industrial electronics 2014; 62(1): 647-656. DOI: 10.1109/tie.2014.2327917
• 18. Liu Y, Hu X, Zhang W. Remaining useful life prediction based on health index similarity[J]. Reliab Eng Syst Saf 2019;185: 502-510. DOI: 10.1016/j.ress.2019.02.002
• 19. Luo J, Zhang X. Convolutional neural network based on attention mechanism and Bi-LSTM for bearing remaining life prediction. Applied Intelligence 2022; 52(1): 1076-1091. DOI: 10.1007/s10489-021-02503-2
• 20. Lin H,Lei Z, Wen G, Tian X, Huang X, Liu J, Zhou H, et al. A Novel Approach of Label Construction for Predicting Remaining Useful Life of Machinery. Shock and Vibration 2021; 2021. DOI: 10.1155/2021/6806319
• 21. Liu J, Pan C, Lei F, Hu D, Zuo H. Fault prediction of bearings based on LSTM and statistical process analysis. Reliab Eng Syst Saf 2021; 214: 107646. doi:10.1016/j.ress.2021.107646.
• 22. Li J, Wang Z, Liu X, Feng Z. Remaining Useful Life Prediction of Rolling Bearings Using GRU-DeepAR with Adaptive Failure Threshold. Sensors, 2023, 23(3): 1144. doi: 10.3390/s23031144.
• 23. Malhi A, Yan R, Gao R X. Prognosis of defect propagation based on recurrent neural networks. IEEE Transactions on Instrumentation and Measurement 2011; 60(3): 703-711. DOI: 10.1109/tim.2010.2078296
• 24. Qin Y, Yang J, Zhou J, Pu H, Mao Y. A new supervised multi-head self-attention autoencoder for health indicator construction and similarity-based machinery RUL prediction. Advanced Engineering Informatics, 2023, 56: 101973. doi: 10.1016/j.aei.2023.101973.
• 25. Qin Y, Zhou J, Chen D. Unsupervised health indicator construction by a novel degradation-trend-constrained variational autoencoder and its applications. IEEE/ASME Transactions on Mechatronics, 2021, 27(3): 1447-1456. doi: 10.1109/tmech.2021.3098737.
• 26. Skrimpas G A, Ursin T, Sweeney C, Marhadi K, Mijatovic N, Holboell J. Residual signal feature extraction for gearbox planetary stage fault detection. Wind Energy 2017; 20(8): 1389-1404. doi: 10.1002/we.2099.
• 27. Saidi L, Ali J B, Bechhoefer E, Benbouzid M. Wind turbine high-speed shaft bearings health prognosis through a spectral Kurtosis-derived indices and SVR. Applied Acoustics 2017; 120: 1-8. doi: 10.1016/j.apacoust.2017.01.005.
• 28. Shi H, Guo J, Bai X, Guo L, Liu Z, Sun J. Gearbox incipient fault detection based on deep recursive dynamic principal component analysis. IEEE Access 2020; 8: 57646-57660. doi: 10.1109/access.2020.2982213.
• 29. She D, Jia M, Pecht M G. Sparse auto-encoder with regularization method for health indicator construction and remaining useful life prediction of rolling bearing. Measurement Science and Technology 2020; 31(10): 105005.https://doi.org/10.1088/1361-6501/ab8c0f
• 30. Wang D. Some further thoughts about spectral kurtosis, spectral L2/L1 norm, spectral smoothness index and spectral Gini index for characterizing repetitive transients. Mechanical Systems and Signal Processing 2018; 108: 360-368. DOI: 10.1016/j.ymssp.2018.02.034
• 31. Widodo A, Yang B S. Application of relevance vector machine and survival probability to machine degradation assessment. Expert Systems with Applications 2011; 38(3): 2592-2599. DOI: 10.1016/j.eswa.2010.08.049
• 32. Wang H, Liao H, Ma X, Bao R. Remaining useful life prediction and optimal maintenance time determination for a single unit using isotonic regression and gamma process model. Reliability Engineering & System Safety, 2021, 210: 107504. doi:10.1016/j.ress.2021.107504.
• 33. Yoo Y, Baek J G. A novel image feature for the remaining useful lifetime prediction of bearings based on continuous wavelet transform and convolutional neural network. Applied Sciences 2018; 8(7): 1102. DOI: 10.3390/app8071102
• 34. Yu W, Kim I I Y, Mechefske C. An improved similarity-based prognostic algorithm for RULestimation using an RNN autoencoder scheme. Reliab Eng Syst Saf 2020; 199: 106926. DOI: 10.1016/j.ress.2020.106926
• 35. Yin J, Yan X. Mutual information–dynamic stacked sparse autoencoders for fault detection. Industrial & Engineering Chemistry Research 2019; 58(47): 21614-21624. DOI: 10.1021/acs.iecr.9b04389
• 36. Zhou H, Huang X, Wen G, Lei Z, Dong S, Zhang P, et al. Construction of Health Indicators for Condition Monitoring of RotatingMachinery: A Review of the Research. Expert Systems with Applications 2022; 117297. DOI: 10.1016/j.eswa.2022.117297.
• 37. Zhou J, Qin Y, Luo J, Zhu T. Remaining useful life prediction by distribution contact ratio health indicator and consolidatedmemory GRU. IEEE Transactions on Industrial Informatics, 2022. doi: 10.1109/TII.2022.3218665.
• 38. Zhang Y, Xie M, He Y, Han X. Capability-based remaining useful life prediction of machining tools considering non-geometry and tolerancing features with a hybrid model. International Journal of Production Research, 2022: 1-17. doi: 10.1080/00207543.2022.2152126.
• 39. Zhou Y, Kumar A, Parkash C, Vashishtha G, Tang H, Xiang J. A novel entropy-based sparsity measure for prognosis of bearing defects and development of a sparsogram to select sensitive filtering band of an axial piston pump. Measurement, 2022, 203: 111997. doi: 10.1016/j.measurement.2022.111997.
• 40. Zhou Y, Kumar A, Gandhi C P, Vashishtha G, Tang H, Kundu P, Singh M, Xiang J. Discrete entropy-based health indicator and LSTM for the forecasting of bearing health. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2023, 45(2): 120. doi: 10.1007/s40430-023-04042-y.
• 41. Zhan X, Bai H, Yan H, Wang R, Guo C, Jia X. Diesel engine fault diagnosis method based on optimized VMD and improved CNN. Processes, 2022, 10(11): 2162. doi: 10.3390/pr10112162.