Residual Life Prediction of Rolling Bearings Driven by Digital Twins DOI Open Access

Jiayi Fan,

Lijuan Zhao, Minghao Li

et al.

Symmetry, Journal Year: 2025, Volume and Issue: 17(3), P. 406 - 406

Published: March 8, 2025

To enhance the maintenance efficiency and operational stability of rolling bearings, this work establishes a methodology for bearing life prediction, employing digital twin systems to evaluate remaining useful bearings. A comprehensive twin-integrated model entire lifecycle bearings is constructed using Modelica language. This generates sufficient reliable data Due symmetrical physical structure generated also have symmetry. Based on characteristic (RUL) prediction algorithm developed recurrent neural network (RNN), specifically an improved gated unit (GRU) model. An optimization employed adjust hyperparameters determine initial fault point bearing. multi-feature dataset constructed, effectively enhancing precision reliability lifespan estimation. existing measured bearing’s lifecycle, parameters are updated. Through parameter degradation component twin, generated. By combining with actual measurement data, method addresses limitations traditional approaches in situations where complete scarce, providing technical support intelligent

Language: Английский

DCAGGCN: A novel method for remaining useful life prediction of bearings DOI
Deqiang He, Jiayang Zhao, Zhenzhen Jin

et al.

Reliability Engineering & System Safety, Journal Year: 2025, Volume and Issue: unknown, P. 110978 - 110978

Published: March 1, 2025

Language: Английский

Citations

1
Rolling bearing remaining useful life prediction using deep learning based on high-quality representation DOI Creative Commons
Chenyang Wang, Wanlu Jiang, Lei Shi

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 10, 2025

In the realm of intelligent manufacturing, accurately predicting remaining useful life (RUL) rolling bearings is essential for maintaining high reliability and optimized performance rotating machinery. To address challenges associated with efficiently representing degradation states capturing temporal dependencies in RUL prediction, this paper proposes a deep learning-based approach. The proposed method integrates one-dimensional convolutional autoencoder (1D-DCAE) high-quality feature extraction multilevel bidirectional long short-term memory (Bi-LSTM) network pattern attention (TPA) mechanism to capture dependencies. 1D-DCAE extracts health indicators (HIs) from vibration signals, which serve as representations state. These HIs, along self-labelled data, are fed inputs into Bi-LSTM + TPA model, enhancing quality data used prediction network. Experimental results on PHM2012 bearing dataset demonstrate that effectively signal features outperforms traditional labelling methods, achieving higher accuracy robustness. Furthermore, model exhibits strong generalizability transferability across diverse operating conditions, underscoring its potential real-world applications.

Language: Английский

Citations

1
Digital twin-inspired methods for rotating machinery intelligent fault diagnosis and remain useful life prediction: A state-of-the-art review and future challenges DOI
Kun Yu, Caizi Fan, Yongchao Zhang

et al.

Mechanical Systems and Signal Processing, Journal Year: 2025, Volume and Issue: 232, P. 112770 - 112770

Published: April 21, 2025

Language: Английский

Citations

1
Heterogeneous graph representation-driven multiplex aggregation graph neural network for remaining useful life prediction of bearings DOI
Yongchang Xiao, Dongdong Liu, Lingli Cui

et al.

Mechanical Systems and Signal Processing, Journal Year: 2024, Volume and Issue: 220, P. 111679 - 111679

Published: July 2, 2024

Language: Английский

Citations

7
A novel weighted sparse classification framework with extended discriminative dictionary for data-driven bearing fault diagnosis DOI
Lingli Cui, Zhichao Jiang, Dongdong Liu

et al.

Mechanical Systems and Signal Processing, Journal Year: 2024, Volume and Issue: 222, P. 111777 - 111777

Published: July 27, 2024

Language: Английский

Citations

7
A digital twin system for centrifugal pump fault diagnosis driven by transfer learning based on graph convolutional neural networks DOI
Zifeng Xu, Zhe Wang,

Chaojia Gao

et al.

Computers in Industry, Journal Year: 2024, Volume and Issue: 163, P. 104155 - 104155

Published: Aug. 30, 2024

Language: Английский

Citations

7
An Adaptive Sparse Graph Learning Method Based on Digital Twin Dictionary for Remaining Useful Life Prediction of Rolling Element Bearings DOI
Lingli Cui, Xin Wang, Dongdong Liu

et al.

IEEE Transactions on Industrial Informatics, Journal Year: 2024, Volume and Issue: 20(9), P. 10892 - 10900

Published: May 20, 2024

The remaining useful life (RUL) prediction of rolling element bearings is usually subject to the following limitations. First, it difficult obtain massive performance degradation data, which resulting in insufficient learning historical law. Second, parameters most existing models depend heavily on manual selection, leads poor generalization performance. To address these problems, a novel adaptive sparse graph (ASGL) method based digital twin dictionary (DTD) proposed this article. facilitate when data are insufficient, extended exponential and linear piecewise first established, then DTD that covers various behaviors constructed. Besides, new objective function designed regularization introduced adaptively topology data. Therefore, avoids wrong adjacency relationship caused by inappropriate parameters. simulation experimental results show has higher accuracy than samples, ASGL easy implement lower dependence parameter selections. In addition, compared with some state-of-the-art methods, can better RUL results.

Language: Английский

Citations

5
Domain generalization for rotating machinery real-time remaining useful life prediction via multi-domain orthogonal degradation feature exploration DOI
Jie Shang,

Danyang Xu,

Haobo Qiu

et al.

Mechanical Systems and Signal Processing, Journal Year: 2024, Volume and Issue: 223, P. 111924 - 111924

Published: Sept. 16, 2024

Language: Английский

Citations

5
UBO-EREX: Uncertainty Bayesian-Optimized Extreme Recurrent EXpansion for Degradation Assessment of Wind Turbine Bearings DOI Open Access
Tarek Berghout, Mohamed Benbouzid

Electronics, Journal Year: 2024, Volume and Issue: 13(12), P. 2419 - 2419

Published: June 20, 2024

Maintenance planning is crucial for efficient operation of wind turbines, particularly in harsh conditions where degradation critical components, such as bearings, can lead to costly downtimes and safety threats. In this context, prognostics play a vital role, enabling timely interventions prevent failures optimize maintenance schedules. Learning systems-based vibration analysis bearings stands out one the primary methods assessing turbine health. However, data complexity challenging pose significant challenges accurate assessment. This paper proposes novel approach, Uncertainty Bayesian-Optimized Extreme Recurrent EXpansion (UBO-EREX), which combines Machines (ELM), lightweight neural network, with Expansion algorithms, recently advanced representation learning technique. The UBO-EREX algorithm leverages Bayesian optimization its parameters, targeting uncertainty an objective function be minimized. We conducted comprehensive study comparing basic ELM set time-series adaptive deep learners, all optimized using prediction errors main objective. Our results demonstrate superior performance terms approximation generalization. Specifically, shows improvements approximately 5.1460 ± 2.1338% coefficient determination generalization over learners 5.7056% ELM, respectively. Moreover, search time significantly reduced 99.7884 0.2404% highlighting effectiveness real-time assessment bearings. Overall, our findings underscore significance incorporating uncertainty-aware predictive strategies offering enhanced accuracy, efficiency, robustness

Language: Английский

Citations

4
Attention guided partial domain adaptation for interpretable transfer diagnosis of rotating machinery DOI
Gang Wang, Dongdong Liu, Jiawei Xiang

et al.

Advanced Engineering Informatics, Journal Year: 2024, Volume and Issue: 62, P. 102708 - 102708

Published: July 29, 2024

Language: Английский

Citations

4