Uncertain RUL prediction for aircraft engines: an attention-based ensemble method with partial-transfer Bayesian deep learning.
Saved in:
| Title: | Uncertain RUL prediction for aircraft engines: an attention-based ensemble method with partial-transfer Bayesian deep learning. |
|---|---|
| Authors: | Zeng, Jiyan1,2 zengjy97@buaa.edu.cn, Tong, Yaohua3 TongYaohua@buaa.edu.cn, Cheng, Yujie1,2,4 chengyujie@buaa.edu.cn, Lu, Chen1,2,4 luchen@buaa.edu.cn |
| Source: | Journal of Vibroengineering. Jun2026, Vol. 28 Issue 4, p922-939. 18p. |
| Subjects: | Remaining useful life, Bayesian analysis, Ensemble learning, Knowledge transfer, Measurement uncertainty (Statistics), Condition-based maintenance, Airplane motors |
| Abstract: | Accurate prediction of the remaining useful life (RUL) of aircraft engines is crucial for ensuring flight safety and optimizing maintenance strategies. However, traditional data-driven methods typically yield point estimation, failing to quantify uncertainties arising from data noise and model limitations. This study proposes an attention-based ensemble method with partial-transfer Bayesian deep learning (Att-ensembled PT-BDL) for uncertainty quantification in aircraft engine RUL prediction. The proposed method transfers weights and biases from existing point estimation deep learning models as prior knowledge to the mean values of weights and biases in Bayesian deep learning models, freezing these parameters during training to reduce trainable parameters and enhance computational efficiency. An ensemble framework, enhanced by an attention mechanism, integrates multiple models to improve prediction accuracy and uncertainty quantification performance. A case study is conducted to demonstrate the effectiveness of the proposed method with a dataset of the PHM data challenge. The experiment results show that the proposed Att-ensembled PT-BDL method can achieve a better prediction accuracy and uncertainty quantification performance in terms of root mean square error (RMSE), prediction interval coverage probability (PICP) and prediction interval normalized average width (PINAW). [ABSTRACT FROM AUTHOR] |
| Copyright of Journal of Vibroengineering is the property of Extrica and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 195026781 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Uncertain RUL prediction for aircraft engines: an attention-based ensemble method with partial-transfer Bayesian deep learning. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Zeng%2C+Jiyan%22">Zeng, Jiyan</searchLink><relatesTo>1,2</relatesTo><i> zengjy97@buaa.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Tong%2C+Yaohua%22">Tong, Yaohua</searchLink><relatesTo>3</relatesTo><i> TongYaohua@buaa.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Cheng%2C+Yujie%22">Cheng, Yujie</searchLink><relatesTo>1,2,4</relatesTo><i> chengyujie@buaa.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Lu%2C+Chen%22">Lu, Chen</searchLink><relatesTo>1,2,4</relatesTo><i> luchen@buaa.edu.cn</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Journal+of+Vibroengineering%22">Journal of Vibroengineering</searchLink>. Jun2026, Vol. 28 Issue 4, p922-939. 18p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Remaining+useful+life%22">Remaining useful life</searchLink><br /><searchLink fieldCode="DE" term="%22Bayesian+analysis%22">Bayesian analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Ensemble+learning%22">Ensemble learning</searchLink><br /><searchLink fieldCode="DE" term="%22Knowledge+transfer%22">Knowledge transfer</searchLink><br /><searchLink fieldCode="DE" term="%22Measurement+uncertainty+%28Statistics%29%22">Measurement uncertainty (Statistics)</searchLink><br /><searchLink fieldCode="DE" term="%22Condition-based+maintenance%22">Condition-based maintenance</searchLink><br /><searchLink fieldCode="DE" term="%22Airplane+motors%22">Airplane motors</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Accurate prediction of the remaining useful life (RUL) of aircraft engines is crucial for ensuring flight safety and optimizing maintenance strategies. However, traditional data-driven methods typically yield point estimation, failing to quantify uncertainties arising from data noise and model limitations. This study proposes an attention-based ensemble method with partial-transfer Bayesian deep learning (Att-ensembled PT-BDL) for uncertainty quantification in aircraft engine RUL prediction. The proposed method transfers weights and biases from existing point estimation deep learning models as prior knowledge to the mean values of weights and biases in Bayesian deep learning models, freezing these parameters during training to reduce trainable parameters and enhance computational efficiency. An ensemble framework, enhanced by an attention mechanism, integrates multiple models to improve prediction accuracy and uncertainty quantification performance. A case study is conducted to demonstrate the effectiveness of the proposed method with a dataset of the PHM data challenge. The experiment results show that the proposed Att-ensembled PT-BDL method can achieve a better prediction accuracy and uncertainty quantification performance in terms of root mean square error (RMSE), prediction interval coverage probability (PICP) and prediction interval normalized average width (PINAW). [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Journal of Vibroengineering is the property of Extrica and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=195026781 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.21595/jve.2026.26015 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 18 StartPage: 922 Subjects: – SubjectFull: Remaining useful life Type: general – SubjectFull: Bayesian analysis Type: general – SubjectFull: Ensemble learning Type: general – SubjectFull: Knowledge transfer Type: general – SubjectFull: Measurement uncertainty (Statistics) Type: general – SubjectFull: Condition-based maintenance Type: general – SubjectFull: Airplane motors Type: general Titles: – TitleFull: Uncertain RUL prediction for aircraft engines: an attention-based ensemble method with partial-transfer Bayesian deep learning. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Zeng, Jiyan – PersonEntity: Name: NameFull: Tong, Yaohua – PersonEntity: Name: NameFull: Cheng, Yujie – PersonEntity: Name: NameFull: Lu, Chen IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 06 Text: Jun2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 13928716 Numbering: – Type: volume Value: 28 – Type: issue Value: 4 Titles: – TitleFull: Journal of Vibroengineering Type: main |
| ResultId | 1 |
