Predicting the Remaining Useful Life of an Aircraft Engine Using a Stacked Sparse Autoencoder with Multilayer Self-Learning
Because they are key components of aircraft, improving the safety, reliability and economy of engines is crucial. To ensure flight safety and reduce the cost of maintenance during aircraft engine operation, a prognostics and health management system that focuses on fault diagnosis, health assessment...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2018-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2018/3813029 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849401041211097088 |
|---|---|
| author | Jian Ma Hua Su Wan-lin Zhao Bin Liu |
| author_facet | Jian Ma Hua Su Wan-lin Zhao Bin Liu |
| author_sort | Jian Ma |
| collection | DOAJ |
| description | Because they are key components of aircraft, improving the safety, reliability and economy of engines is crucial. To ensure flight safety and reduce the cost of maintenance during aircraft engine operation, a prognostics and health management system that focuses on fault diagnosis, health assessment, and life prediction is introduced to solve the problems. Predicting the remaining useful life (RUL) is the most important information for making decisions about aircraft engine operation and maintenance, and it relies largely on the selection of performance degradation features. The choice of such features is highly significant, but there are some weaknesses in the current algorithm for RUL prediction, notably, the inability to obtain tendencies from the data. Especially with aircraft engines, extracting useful degradation features from multisensor data with complex correlations is a key technical problem that has hindered the implementation of degradation assessment. To solve these problems, deep learning has been proposed in recent years to exploit multiple layers of nonlinear information processing for unsupervised self-learning of features. This paper presents a deep learning approach to predict the RUL of an aircraft engine based on a stacked sparse autoencoder and logistic regression. The stacked sparse autoencoder is used to automatically extract performance degradation features from multiple sensors on the aircraft engine and to fuse multiple features through multilayer self-learning. Logistic regression is used to predict the remaining useful life. However, the hyperparameters of the deep learning, which significantly impact the feature extraction and prediction performance, are determined based on expert experience in most cases. The grid search method is introduced in this paper to optimize the hyperparameters of the proposed aircraft engine RUL prediction model. An application of this method of predicting the RUL of an aircraft engine with a benchmark dataset is employed to demonstrate the effectiveness of the proposed approach. |
| format | Article |
| id | doaj-art-8a88ded2f02c48c497d55dd9604f8aae |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2018-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-8a88ded2f02c48c497d55dd9604f8aae2025-08-20T03:37:51ZengWileyComplexity1076-27871099-05262018-01-01201810.1155/2018/38130293813029Predicting the Remaining Useful Life of an Aircraft Engine Using a Stacked Sparse Autoencoder with Multilayer Self-LearningJian Ma0Hua Su1Wan-lin Zhao2Bin Liu3School of Reliability and Systems Engineering, Beihang University, Beijing, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing, ChinaBecause they are key components of aircraft, improving the safety, reliability and economy of engines is crucial. To ensure flight safety and reduce the cost of maintenance during aircraft engine operation, a prognostics and health management system that focuses on fault diagnosis, health assessment, and life prediction is introduced to solve the problems. Predicting the remaining useful life (RUL) is the most important information for making decisions about aircraft engine operation and maintenance, and it relies largely on the selection of performance degradation features. The choice of such features is highly significant, but there are some weaknesses in the current algorithm for RUL prediction, notably, the inability to obtain tendencies from the data. Especially with aircraft engines, extracting useful degradation features from multisensor data with complex correlations is a key technical problem that has hindered the implementation of degradation assessment. To solve these problems, deep learning has been proposed in recent years to exploit multiple layers of nonlinear information processing for unsupervised self-learning of features. This paper presents a deep learning approach to predict the RUL of an aircraft engine based on a stacked sparse autoencoder and logistic regression. The stacked sparse autoencoder is used to automatically extract performance degradation features from multiple sensors on the aircraft engine and to fuse multiple features through multilayer self-learning. Logistic regression is used to predict the remaining useful life. However, the hyperparameters of the deep learning, which significantly impact the feature extraction and prediction performance, are determined based on expert experience in most cases. The grid search method is introduced in this paper to optimize the hyperparameters of the proposed aircraft engine RUL prediction model. An application of this method of predicting the RUL of an aircraft engine with a benchmark dataset is employed to demonstrate the effectiveness of the proposed approach.http://dx.doi.org/10.1155/2018/3813029 |
| spellingShingle | Jian Ma Hua Su Wan-lin Zhao Bin Liu Predicting the Remaining Useful Life of an Aircraft Engine Using a Stacked Sparse Autoencoder with Multilayer Self-Learning Complexity |
| title | Predicting the Remaining Useful Life of an Aircraft Engine Using a Stacked Sparse Autoencoder with Multilayer Self-Learning |
| title_full | Predicting the Remaining Useful Life of an Aircraft Engine Using a Stacked Sparse Autoencoder with Multilayer Self-Learning |
| title_fullStr | Predicting the Remaining Useful Life of an Aircraft Engine Using a Stacked Sparse Autoencoder with Multilayer Self-Learning |
| title_full_unstemmed | Predicting the Remaining Useful Life of an Aircraft Engine Using a Stacked Sparse Autoencoder with Multilayer Self-Learning |
| title_short | Predicting the Remaining Useful Life of an Aircraft Engine Using a Stacked Sparse Autoencoder with Multilayer Self-Learning |
| title_sort | predicting the remaining useful life of an aircraft engine using a stacked sparse autoencoder with multilayer self learning |
| url | http://dx.doi.org/10.1155/2018/3813029 |
| work_keys_str_mv | AT jianma predictingtheremainingusefullifeofanaircraftengineusingastackedsparseautoencoderwithmultilayerselflearning AT huasu predictingtheremainingusefullifeofanaircraftengineusingastackedsparseautoencoderwithmultilayerselflearning AT wanlinzhao predictingtheremainingusefullifeofanaircraftengineusingastackedsparseautoencoderwithmultilayerselflearning AT binliu predictingtheremainingusefullifeofanaircraftengineusingastackedsparseautoencoderwithmultilayerselflearning |