Aircraft Engines Remaining Useful Life Prediction with an Improved Online Sequential Extreme Learning Machine
The efficient data investigation for fast and accurate remaining useful life prediction of aircraft engines can be considered as a very important task for maintenance operations. In this context, the key issue is how an appropriate investigation can be conducted for the extraction of important infor...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/3/1062 |
| _version_ | 1818128168036335616 |
|---|---|
| author | Tarek Berghout Leïla-Hayet Mouss Ouahab Kadri Lotfi Saïdi Mohamed Benbouzid |
| author_facet | Tarek Berghout Leïla-Hayet Mouss Ouahab Kadri Lotfi Saïdi Mohamed Benbouzid |
| author_sort | Tarek Berghout |
| collection | DOAJ |
| description | The efficient data investigation for fast and accurate remaining useful life prediction of aircraft engines can be considered as a very important task for maintenance operations. In this context, the key issue is how an appropriate investigation can be conducted for the extraction of important information from data-driven sequences in high dimensional space in order to guarantee a reliable conclusion. In this paper, a new data-driven learning scheme based on an online sequential extreme learning machine algorithm is proposed for remaining useful life prediction. Firstly, a new feature mapping technique based on stacked autoencoders is proposed to enhance features representations through an accurate reconstruction. In addition, to attempt into addressing dynamic programming based on environmental feedback, a new dynamic forgetting function based on the temporal difference of recursive learning is introduced to enhance dynamic tracking ability of newly coming data. Moreover, a new updated selection strategy was developed in order to discard the unwanted data sequences and to ensure the convergence of the training model parameters to their appropriate values. The proposed approach is validated on the C-MAPSS dataset where experimental results confirm that it yields satisfactory accuracy and efficiency of the prediction model compared to other existing methods. |
| first_indexed | 2024-12-11T07:28:57Z |
| format | Article |
| id | doaj.art-6a35e44fff6c4b40bdd52c887aebb4e8 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-11T07:28:57Z |
| publishDate | 2020-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-6a35e44fff6c4b40bdd52c887aebb4e82022-12-22T01:15:53ZengMDPI AGApplied Sciences2076-34172020-02-01103106210.3390/app10031062app10031062Aircraft Engines Remaining Useful Life Prediction with an Improved Online Sequential Extreme Learning MachineTarek Berghout0Leïla-Hayet Mouss1Ouahab Kadri2Lotfi Saïdi3Mohamed Benbouzid4Laboratory of Automation and Manufacturing Engineering, University of Batna 2, Batna 05000, AlgeriaLaboratory of Automation and Manufacturing Engineering, University of Batna 2, Batna 05000, AlgeriaDepartment of Computer Science, University of Batna 2, Batna 05078, AlgeriaSIME_Lab (LR 13ES03), University of Sousse–ESSTHS, Sousse 4011, TunisiaInstitut de Recherche Dupuy de Lôme (UMR CNRS 6027), University of Brest, 29238 Brest, FranceThe efficient data investigation for fast and accurate remaining useful life prediction of aircraft engines can be considered as a very important task for maintenance operations. In this context, the key issue is how an appropriate investigation can be conducted for the extraction of important information from data-driven sequences in high dimensional space in order to guarantee a reliable conclusion. In this paper, a new data-driven learning scheme based on an online sequential extreme learning machine algorithm is proposed for remaining useful life prediction. Firstly, a new feature mapping technique based on stacked autoencoders is proposed to enhance features representations through an accurate reconstruction. In addition, to attempt into addressing dynamic programming based on environmental feedback, a new dynamic forgetting function based on the temporal difference of recursive learning is introduced to enhance dynamic tracking ability of newly coming data. Moreover, a new updated selection strategy was developed in order to discard the unwanted data sequences and to ensure the convergence of the training model parameters to their appropriate values. The proposed approach is validated on the C-MAPSS dataset where experimental results confirm that it yields satisfactory accuracy and efficiency of the prediction model compared to other existing methods.https://www.mdpi.com/2076-3417/10/3/1062c-mapssdynamic forgetting factorelmos-elmremaining useful lifestacked elmtemporal difference |
| spellingShingle | Tarek Berghout Leïla-Hayet Mouss Ouahab Kadri Lotfi Saïdi Mohamed Benbouzid Aircraft Engines Remaining Useful Life Prediction with an Improved Online Sequential Extreme Learning Machine Applied Sciences c-mapss dynamic forgetting factor elm os-elm remaining useful life stacked elm temporal difference |
| title | Aircraft Engines Remaining Useful Life Prediction with an Improved Online Sequential Extreme Learning Machine |
| title_full | Aircraft Engines Remaining Useful Life Prediction with an Improved Online Sequential Extreme Learning Machine |
| title_fullStr | Aircraft Engines Remaining Useful Life Prediction with an Improved Online Sequential Extreme Learning Machine |
| title_full_unstemmed | Aircraft Engines Remaining Useful Life Prediction with an Improved Online Sequential Extreme Learning Machine |
| title_short | Aircraft Engines Remaining Useful Life Prediction with an Improved Online Sequential Extreme Learning Machine |
| title_sort | aircraft engines remaining useful life prediction with an improved online sequential extreme learning machine |
| topic | c-mapss dynamic forgetting factor elm os-elm remaining useful life stacked elm temporal difference |
| url | https://www.mdpi.com/2076-3417/10/3/1062 |
| work_keys_str_mv | AT tarekberghout aircraftenginesremainingusefullifepredictionwithanimprovedonlinesequentialextremelearningmachine AT leilahayetmouss aircraftenginesremainingusefullifepredictionwithanimprovedonlinesequentialextremelearningmachine AT ouahabkadri aircraftenginesremainingusefullifepredictionwithanimprovedonlinesequentialextremelearningmachine AT lotfisaidi aircraftenginesremainingusefullifepredictionwithanimprovedonlinesequentialextremelearningmachine AT mohamedbenbouzid aircraftenginesremainingusefullifepredictionwithanimprovedonlinesequentialextremelearningmachine |