DCAGGCN: A novel method for remaining useful life prediction of bearings

Reliability Engineering & System Safety, Год журнала: 2025, Номер unknown, С. 110978 - 110978

Опубликована: Март 1, 2025

Язык: Английский

---

Rolling bearing remaining useful life prediction using deep learning based on high-quality representation

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 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.

Язык: Английский

---

Digital twin-inspired methods for rotating machinery intelligent fault diagnosis and remain useful life prediction: A state-of-the-art review and future challenges

Mechanical Systems and Signal Processing, Год журнала: 2025, Номер 232, С. 112770 - 112770

Опубликована: Апрель 21, 2025

Язык: Английский

---

Heterogeneous graph representation-driven multiplex aggregation graph neural network for remaining useful life prediction of bearings

Mechanical Systems and Signal Processing, Год журнала: 2024, Номер 220, С. 111679 - 111679

Опубликована: Июль 2, 2024

Язык: Английский

---

A novel weighted sparse classification framework with extended discriminative dictionary for data-driven bearing fault diagnosis

Mechanical Systems and Signal Processing, Год журнала: 2024, Номер 222, С. 111777 - 111777

Опубликована: Июль 27, 2024

Язык: Английский

---

A digital twin system for centrifugal pump fault diagnosis driven by transfer learning based on graph convolutional neural networks

Computers in Industry, Год журнала: 2024, Номер 163, С. 104155 - 104155

Опубликована: Авг. 30, 2024

Язык: Английский

---

An Adaptive Sparse Graph Learning Method Based on Digital Twin Dictionary for Remaining Useful Life Prediction of Rolling Element Bearings

IEEE Transactions on Industrial Informatics, Год журнала: 2024, Номер 20(9), С. 10892 - 10900

Опубликована: Май 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.

Язык: Английский

---

Domain generalization for rotating machinery real-time remaining useful life prediction via multi-domain orthogonal degradation feature exploration

Mechanical Systems and Signal Processing, Год журнала: 2024, Номер 223, С. 111924 - 111924

Опубликована: Сен. 16, 2024

Язык: Английский

---

UBO-EREX: Uncertainty Bayesian-Optimized Extreme Recurrent EXpansion for Degradation Assessment of Wind Turbine Bearings

Electronics, Год журнала: 2024, Номер 13(12), С. 2419 - 2419

Опубликована: Июнь 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

Язык: Английский

---

Attention guided partial domain adaptation for interpretable transfer diagnosis of rotating machinery

Advanced Engineering Informatics, Год журнала: 2024, Номер 62, С. 102708 - 102708

Опубликована: Июль 29, 2024

Язык: Английский

---