Comparative Analysis of Deep Learning and Decision Tree Approaches for Predicting Aircraft Engine Remaining Useful Life
Accurate prediction of Remaining Useful Life (RUL) is crucial for Prognostics and Health Management (PHM), particularly in predictive maintenance strategies aimed at ensuring the reliability of industrial systems. This study compares two approaches for RUL prediction of aircraft engines: a deep lear...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2024-11-01
|
| Series: | Fatigue of Aircraft Structures |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/fas-2023-0012 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846143499630542848 |
|---|---|
| author | Madjour Hassina Zermane Hanane Rahmouni Djemaa Mouss Mohammed Djamel |
| author_facet | Madjour Hassina Zermane Hanane Rahmouni Djemaa Mouss Mohammed Djamel |
| author_sort | Madjour Hassina |
| collection | DOAJ |
| description | Accurate prediction of Remaining Useful Life (RUL) is crucial for Prognostics and Health Management (PHM), particularly in predictive maintenance strategies aimed at ensuring the reliability of industrial systems. This study compares two approaches for RUL prediction of aircraft engines: a deep learning-based one-dimensional Convolutional Neural Network (CNN-1D) and a traditional Decision Tree (DT) algorithm, using data from the C-MAPSS dataset. The results show that the CNN-1D model significantly outperforms the DT model, achieving a Root Mean Square Error (RMSE) of 21.44 on the training set and 27.12 on the test set, compared to the DT model’s RMSE of 23.83 and 28.93, respectively. These findings highlight the superior capability of deep learning techniques in RUL estimation, underscoring their importance in PHM and predictive maintenance applications. |
| format | Article |
| id | doaj-art-5c38220c679640f4b5f46b42e756bba3 |
| institution | Kabale University |
| issn | 2300-7591 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Fatigue of Aircraft Structures |
| spelling | doaj-art-5c38220c679640f4b5f46b42e756bba32024-12-02T12:05:37ZengSciendoFatigue of Aircraft Structures2300-75912024-11-0120231518320010.2478/fas-2023-0012Comparative Analysis of Deep Learning and Decision Tree Approaches for Predicting Aircraft Engine Remaining Useful LifeMadjour Hassina0Zermane Hanane1Rahmouni Djemaa2Mouss Mohammed Djamel3Laboratory of Automation and Manufacturing, Department of Industrial Engineering, University of Batna 2, Batna, AlgeriaLaboratory of Automation and Manufacturing, Department of Industrial Engineering, University of Batna 2, Batna, AlgeriaLaboratory of Automation and Manufacturing, Department of Industrial Engineering, University of Batna 2, Batna, AlgeriaLaboratory of Automation and Manufacturing, Department of Industrial Engineering, University of Batna 2, Batna, AlgeriaAccurate prediction of Remaining Useful Life (RUL) is crucial for Prognostics and Health Management (PHM), particularly in predictive maintenance strategies aimed at ensuring the reliability of industrial systems. This study compares two approaches for RUL prediction of aircraft engines: a deep learning-based one-dimensional Convolutional Neural Network (CNN-1D) and a traditional Decision Tree (DT) algorithm, using data from the C-MAPSS dataset. The results show that the CNN-1D model significantly outperforms the DT model, achieving a Root Mean Square Error (RMSE) of 21.44 on the training set and 27.12 on the test set, compared to the DT model’s RMSE of 23.83 and 28.93, respectively. These findings highlight the superior capability of deep learning techniques in RUL estimation, underscoring their importance in PHM and predictive maintenance applications.https://doi.org/10.2478/fas-2023-0012remaining useful lifedeep learningconvolution neural networkspredictive maintenanceprognostics and health management |
| spellingShingle | Madjour Hassina Zermane Hanane Rahmouni Djemaa Mouss Mohammed Djamel Comparative Analysis of Deep Learning and Decision Tree Approaches for Predicting Aircraft Engine Remaining Useful Life Fatigue of Aircraft Structures remaining useful life deep learning convolution neural networks predictive maintenance prognostics and health management |
| title | Comparative Analysis of Deep Learning and Decision Tree Approaches for Predicting Aircraft Engine Remaining Useful Life |
| title_full | Comparative Analysis of Deep Learning and Decision Tree Approaches for Predicting Aircraft Engine Remaining Useful Life |
| title_fullStr | Comparative Analysis of Deep Learning and Decision Tree Approaches for Predicting Aircraft Engine Remaining Useful Life |
| title_full_unstemmed | Comparative Analysis of Deep Learning and Decision Tree Approaches for Predicting Aircraft Engine Remaining Useful Life |
| title_short | Comparative Analysis of Deep Learning and Decision Tree Approaches for Predicting Aircraft Engine Remaining Useful Life |
| title_sort | comparative analysis of deep learning and decision tree approaches for predicting aircraft engine remaining useful life |
| topic | remaining useful life deep learning convolution neural networks predictive maintenance prognostics and health management |
| url | https://doi.org/10.2478/fas-2023-0012 |
| work_keys_str_mv | AT madjourhassina comparativeanalysisofdeeplearninganddecisiontreeapproachesforpredictingaircraftengineremainingusefullife AT zermanehanane comparativeanalysisofdeeplearninganddecisiontreeapproachesforpredictingaircraftengineremainingusefullife AT rahmounidjemaa comparativeanalysisofdeeplearninganddecisiontreeapproachesforpredictingaircraftengineremainingusefullife AT moussmohammeddjamel comparativeanalysisofdeeplearninganddecisiontreeapproachesforpredictingaircraftengineremainingusefullife |