From Envelope Spectra to Bearing Remaining Useful Life: An Intelligent Vibration-Based Prediction Model with Quantified Uncertainty

被引:0
作者
Wen, Haobin [1 ]
Zhang, Long [2 ]
Sinha, Jyoti K. [1 ]
机构
[1] Univ Manchester, Dept Mech & Aerosp Engn, Dynam Lab, Manchester M13 9PL, England
[2] Univ Manchester, Dept Elect & Elect Engn, Manchester M13 9PL, England
关键词
bearings; remaining useful life; vibration; prognostics and health management; variational autoencoder; uncertainty quantification; physical interpretation;
D O I
10.3390/s24227257
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Bearings are pivotal components of rotating machines where any defects could propagate and trigger systematic failures. Once faults are detected, accurately predicting remaining useful life (RUL) is essential for optimizing predictive maintenance. Although data-driven methods demonstrate promising performance in direct RUL prediction, their robustness and practicability need further improvement regarding physical interpretation and uncertainty quantification. This work leverages variational neural networks to model bearing degradation behind envelope spectra. A convolutional variational autoencoder for regression (CVAER) is developed to probabilistically predict RUL distributions with confidence measures. Enhanced average envelope spectra (AES) are used as network input for its physical robustness in bearing condition assessment and fault detection. The use of the envelope spectrum ensures that it contains only bearing-related information by removing other rotor-related frequencies, hence it improves the RUL prediction. Unlike traditional variational autoencoders, the probabilistic regressor and latent generator are formulated to quantify uncertainty in RUL estimates and learn meaningful latent representations conditioned on specific RUL. Experimental validations are conducted on vibration data collected using multiple accelerometers whose natural frequencies cover bearing resonance ranges to ensure fault detection reliability. Beyond conventional bearing diagnosis, envelope spectra are extended for statistical RUL prediction integrating physical knowledge of actual defect conditions. Comparative and ablation studies are conducted against benchmark models to demonstrate their effectiveness.
引用
收藏
页数:26
相关论文
共 39 条
[1]  
Ba J, 2014, ACS SYM SER
[2]   De-noising of Contrast-Enhanced MRI Sequences by an Ensemble of Expert Deep Neural Networks [J].
Benou, Ariel ;
Veksler, Ronel ;
Friedman, Alon ;
Raviv, Tammy Riklin .
DEEP LEARNING AND DATA LABELING FOR MEDICAL APPLICATIONS, 2016, 10008 :95-110
[3]   Prognostics and Health Management of Industrial Assets: Current Progress and Road Ahead [J].
Biggio, Luca ;
Kastanis, Iason .
FRONTIERS IN ARTIFICIAL INTELLIGENCE, 2020, 3
[4]   Variational Autoencoder for Classification and Regression for Out-of-Distribution Detection in Learning-Enabled Cyber-Physical Systems [J].
Cai, Feiyang ;
Ozdagli, Ali, I ;
Koutsoukos, Xenofon .
APPLIED ARTIFICIAL INTELLIGENCE, 2022, 36 (01)
[5]   Bearing Remaining Useful Life Prediction Using Federated Learning With Taylor-Expansion Network Pruning [J].
Chen, Xi ;
Wang, Hui ;
Lu, Siliang ;
Yan, Ruqiang .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2023, 72
[6]   Deep transfer learning based on Bi-LSTM and attention for remaining useful life prediction of rolling bearing [J].
Dong, Shaojiang ;
Xiao, Jiafeng ;
Hu, Xiaolin ;
Fang, Nengwei ;
Liu, Lanhui ;
Yao, Jinbao .
RELIABILITY ENGINEERING & SYSTEM SAFETY, 2023, 230
[7]   Potential, challenges and future directions for deep learning in prognostics and health management applications [J].
Fink, Olga ;
Wang, Qin ;
Svensen, Markus ;
Dersin, Pierre ;
Lee, Wan-Jui ;
Ducoffe, Melanie .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2020, 92
[8]  
Heimes FO, 2008, 2008 INTERNATIONAL CONFERENCE ON PROGNOSTICS AND HEALTH MANAGEMENT (PHM), P59
[9]  
Higgins I., 2017, ICLR (Poster), P1
[10]   Feature Extraction Using Weighted Training Samples [J].
Imani, Maryam ;
Ghassemian, Hassan .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2015, 12 (07) :1387-1391