Data-Driven Deep Learning-Based Attention Mechanism for Remaining Useful Life Prediction: Case Study Application to Turbofan Engine Analysis
Accurately predicting the remaining useful life (RUL) of the turbofan engine is of great significance for improving the reliability and safety of the engine system. Due to the high dimension and complex features of sensor data in RUL prediction, this paper proposes four data-driven prognostic models...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/10/20/2453 |
| _version_ | 1797514788254777344 |
|---|---|
| author | Amgad Muneer Shakirah Mohd Taib Sheraz Naseer Rao Faizan Ali Izzatdin Abdul Aziz |
| author_facet | Amgad Muneer Shakirah Mohd Taib Sheraz Naseer Rao Faizan Ali Izzatdin Abdul Aziz |
| author_sort | Amgad Muneer |
| collection | DOAJ |
| description | Accurately predicting the remaining useful life (RUL) of the turbofan engine is of great significance for improving the reliability and safety of the engine system. Due to the high dimension and complex features of sensor data in RUL prediction, this paper proposes four data-driven prognostic models based on deep neural networks (DNNs) with an attention mechanism. To improve DNN feature extraction, data are prepared using a sliding time window technique. The raw data collected after normalizing is simply fed into the suggested network, requiring no prior knowledge of prognostics or signal processing and simplifying the proposed method’s applicability. In order to verify the RUL prediction ability of the proposed DNN techniques, the C-MAPSS benchmark dataset of the turbofan engine system is validated. The experimental results showed that the developed long short-term memory (LSTM) model with attention mechanism achieved accurate RUL prediction in both scenarios with a high degree of robustness and generalization ability. Furthermore, the proposed model performance outperforms several state-of-the-art prognosis methods, where the LSTM-based model with attention mechanism achieved an RMSE of 12.87 and 11.23 for FD002 and FD003 subset of data, respectively. |
| first_indexed | 2024-03-10T06:36:32Z |
| format | Article |
| id | doaj.art-59365ffa5ae0456cba9899a78ef73db7 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T06:36:32Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-59365ffa5ae0456cba9899a78ef73db72023-11-22T18:01:27ZengMDPI AGElectronics2079-92922021-10-011020245310.3390/electronics10202453Data-Driven Deep Learning-Based Attention Mechanism for Remaining Useful Life Prediction: Case Study Application to Turbofan Engine AnalysisAmgad Muneer0Shakirah Mohd Taib1Sheraz Naseer2Rao Faizan Ali3Izzatdin Abdul Aziz4Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, Seri Iskandar 32160, MalaysiaDepartment of Computer and Information Sciences, Universiti Teknologi PETRONAS, Seri Iskandar 32160, MalaysiaDepartment of Computer Science, University of Management and Technology, Lahore 54728, PakistanDepartment of Computer Science, University of Management and Technology, Lahore 54728, PakistanDepartment of Computer and Information Sciences, Universiti Teknologi PETRONAS, Seri Iskandar 32160, MalaysiaAccurately predicting the remaining useful life (RUL) of the turbofan engine is of great significance for improving the reliability and safety of the engine system. Due to the high dimension and complex features of sensor data in RUL prediction, this paper proposes four data-driven prognostic models based on deep neural networks (DNNs) with an attention mechanism. To improve DNN feature extraction, data are prepared using a sliding time window technique. The raw data collected after normalizing is simply fed into the suggested network, requiring no prior knowledge of prognostics or signal processing and simplifying the proposed method’s applicability. In order to verify the RUL prediction ability of the proposed DNN techniques, the C-MAPSS benchmark dataset of the turbofan engine system is validated. The experimental results showed that the developed long short-term memory (LSTM) model with attention mechanism achieved accurate RUL prediction in both scenarios with a high degree of robustness and generalization ability. Furthermore, the proposed model performance outperforms several state-of-the-art prognosis methods, where the LSTM-based model with attention mechanism achieved an RMSE of 12.87 and 11.23 for FD002 and FD003 subset of data, respectively.https://www.mdpi.com/2079-9292/10/20/2453turbofan engine degradationdata-driven prognosticdeep neural network (DNN)prognostics and health management (PHM)remaining useful life (RUL)uncertainty |
| spellingShingle | Amgad Muneer Shakirah Mohd Taib Sheraz Naseer Rao Faizan Ali Izzatdin Abdul Aziz Data-Driven Deep Learning-Based Attention Mechanism for Remaining Useful Life Prediction: Case Study Application to Turbofan Engine Analysis Electronics turbofan engine degradation data-driven prognostic deep neural network (DNN) prognostics and health management (PHM) remaining useful life (RUL) uncertainty |
| title | Data-Driven Deep Learning-Based Attention Mechanism for Remaining Useful Life Prediction: Case Study Application to Turbofan Engine Analysis |
| title_full | Data-Driven Deep Learning-Based Attention Mechanism for Remaining Useful Life Prediction: Case Study Application to Turbofan Engine Analysis |
| title_fullStr | Data-Driven Deep Learning-Based Attention Mechanism for Remaining Useful Life Prediction: Case Study Application to Turbofan Engine Analysis |
| title_full_unstemmed | Data-Driven Deep Learning-Based Attention Mechanism for Remaining Useful Life Prediction: Case Study Application to Turbofan Engine Analysis |
| title_short | Data-Driven Deep Learning-Based Attention Mechanism for Remaining Useful Life Prediction: Case Study Application to Turbofan Engine Analysis |
| title_sort | data driven deep learning based attention mechanism for remaining useful life prediction case study application to turbofan engine analysis |
| topic | turbofan engine degradation data-driven prognostic deep neural network (DNN) prognostics and health management (PHM) remaining useful life (RUL) uncertainty |
| url | https://www.mdpi.com/2079-9292/10/20/2453 |
| work_keys_str_mv | AT amgadmuneer datadrivendeeplearningbasedattentionmechanismforremainingusefullifepredictioncasestudyapplicationtoturbofanengineanalysis AT shakirahmohdtaib datadrivendeeplearningbasedattentionmechanismforremainingusefullifepredictioncasestudyapplicationtoturbofanengineanalysis AT sheraznaseer datadrivendeeplearningbasedattentionmechanismforremainingusefullifepredictioncasestudyapplicationtoturbofanengineanalysis AT raofaizanali datadrivendeeplearningbasedattentionmechanismforremainingusefullifepredictioncasestudyapplicationtoturbofanengineanalysis AT izzatdinabdulaziz datadrivendeeplearningbasedattentionmechanismforremainingusefullifepredictioncasestudyapplicationtoturbofanengineanalysis |