A Deep-Learning Method for Remaining Useful Life Prediction of Power Machinery via Dual-Attention Mechanism
Remaining useful life (RUL) prediction is a cornerstone of Prognostic and Health Management (PHM) for power machinery, playing a crucial role in ensuring the reliability and safety of these critical systems. In recent years, deep learning techniques have shown great promise in RUL prediction, provid...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/2/497 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587490917089280 |
|---|---|
| author | Fan Wang Aihua Liu Chunyang Qu Ruolan Xiong Lu Chen |
| author_facet | Fan Wang Aihua Liu Chunyang Qu Ruolan Xiong Lu Chen |
| author_sort | Fan Wang |
| collection | DOAJ |
| description | Remaining useful life (RUL) prediction is a cornerstone of Prognostic and Health Management (PHM) for power machinery, playing a crucial role in ensuring the reliability and safety of these critical systems. In recent years, deep learning techniques have shown great promise in RUL prediction, providing more reliable and accurate outcomes. However, existing models often struggle with comprehensive feature extraction, especially in capturing the complex behavior of power machinery, where non-linear degradation patterns arise under varying operational conditions. To tackle this limitation, we propose a multi-feature fusion model leveraging a dual-attention mechanism. Initially, convolutional neural networks (CNNs) and channel attention mechanisms are employed to preliminarily extract spatial features. Subsequently, a layer combining a Gate Recurrent Unit (GRU) and self-attention mechanisms is used to further extract and integrate temporal features. Finally, RUL values are predicted via regression. The effectiveness of the proposed method was validated on C-MAPSS datasets, and its superior performance in RUL prediction was demonstrated through comparative analysis with other methods. |
| format | Article |
| id | doaj-art-445f7ac1ece046d59fba2e2dc4b79e05 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-445f7ac1ece046d59fba2e2dc4b79e052025-01-24T13:49:08ZengMDPI AGSensors1424-82202025-01-0125249710.3390/s25020497A Deep-Learning Method for Remaining Useful Life Prediction of Power Machinery via Dual-Attention MechanismFan Wang0Aihua Liu1Chunyang Qu2Ruolan Xiong3Lu Chen4School of Naval Architecture, Ocean and Energy Power Engineering, Wuhan University of Technology, Wuhan 430070, ChinaSchool of Naval Architecture, Ocean and Energy Power Engineering, Wuhan University of Technology, Wuhan 430070, ChinaSchool of Naval Architecture, Ocean and Energy Power Engineering, Wuhan University of Technology, Wuhan 430070, ChinaSchool of Naval Architecture, Ocean and Energy Power Engineering, Wuhan University of Technology, Wuhan 430070, ChinaSchool of Naval Architecture, Ocean and Energy Power Engineering, Wuhan University of Technology, Wuhan 430070, ChinaRemaining useful life (RUL) prediction is a cornerstone of Prognostic and Health Management (PHM) for power machinery, playing a crucial role in ensuring the reliability and safety of these critical systems. In recent years, deep learning techniques have shown great promise in RUL prediction, providing more reliable and accurate outcomes. However, existing models often struggle with comprehensive feature extraction, especially in capturing the complex behavior of power machinery, where non-linear degradation patterns arise under varying operational conditions. To tackle this limitation, we propose a multi-feature fusion model leveraging a dual-attention mechanism. Initially, convolutional neural networks (CNNs) and channel attention mechanisms are employed to preliminarily extract spatial features. Subsequently, a layer combining a Gate Recurrent Unit (GRU) and self-attention mechanisms is used to further extract and integrate temporal features. Finally, RUL values are predicted via regression. The effectiveness of the proposed method was validated on C-MAPSS datasets, and its superior performance in RUL prediction was demonstrated through comparative analysis with other methods.https://www.mdpi.com/1424-8220/25/2/497remaining useful life predictionGRUmulti-feature fusiondual-attention mechanismpower machinery |
| spellingShingle | Fan Wang Aihua Liu Chunyang Qu Ruolan Xiong Lu Chen A Deep-Learning Method for Remaining Useful Life Prediction of Power Machinery via Dual-Attention Mechanism Sensors remaining useful life prediction GRU multi-feature fusion dual-attention mechanism power machinery |
| title | A Deep-Learning Method for Remaining Useful Life Prediction of Power Machinery via Dual-Attention Mechanism |
| title_full | A Deep-Learning Method for Remaining Useful Life Prediction of Power Machinery via Dual-Attention Mechanism |
| title_fullStr | A Deep-Learning Method for Remaining Useful Life Prediction of Power Machinery via Dual-Attention Mechanism |
| title_full_unstemmed | A Deep-Learning Method for Remaining Useful Life Prediction of Power Machinery via Dual-Attention Mechanism |
| title_short | A Deep-Learning Method for Remaining Useful Life Prediction of Power Machinery via Dual-Attention Mechanism |
| title_sort | deep learning method for remaining useful life prediction of power machinery via dual attention mechanism |
| topic | remaining useful life prediction GRU multi-feature fusion dual-attention mechanism power machinery |
| url | https://www.mdpi.com/1424-8220/25/2/497 |
| work_keys_str_mv | AT fanwang adeeplearningmethodforremainingusefullifepredictionofpowermachineryviadualattentionmechanism AT aihualiu adeeplearningmethodforremainingusefullifepredictionofpowermachineryviadualattentionmechanism AT chunyangqu adeeplearningmethodforremainingusefullifepredictionofpowermachineryviadualattentionmechanism AT ruolanxiong adeeplearningmethodforremainingusefullifepredictionofpowermachineryviadualattentionmechanism AT luchen adeeplearningmethodforremainingusefullifepredictionofpowermachineryviadualattentionmechanism AT fanwang deeplearningmethodforremainingusefullifepredictionofpowermachineryviadualattentionmechanism AT aihualiu deeplearningmethodforremainingusefullifepredictionofpowermachineryviadualattentionmechanism AT chunyangqu deeplearningmethodforremainingusefullifepredictionofpowermachineryviadualattentionmechanism AT ruolanxiong deeplearningmethodforremainingusefullifepredictionofpowermachineryviadualattentionmechanism AT luchen deeplearningmethodforremainingusefullifepredictionofpowermachineryviadualattentionmechanism |