Aero-Engine Remaining Useful Life Estimation Based on CAE-TCN Neural Networks
With the rapid growth of the aviation fields, the remaining useful life (RUL) estimation of aero-engine has become the focus of the industry. Due to the shortage of existing prediction methods, life prediction is stuck in a bottleneck. Aiming at the low efficiency of traditional estimation algorithm...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/1/17 |
| _version_ | 1797626330085326848 |
|---|---|
| author | Guanghao Ren Yun Wang Zhenyun Shi Guigang Zhang Feng Jin Jian Wang |
| author_facet | Guanghao Ren Yun Wang Zhenyun Shi Guigang Zhang Feng Jin Jian Wang |
| author_sort | Guanghao Ren |
| collection | DOAJ |
| description | With the rapid growth of the aviation fields, the remaining useful life (RUL) estimation of aero-engine has become the focus of the industry. Due to the shortage of existing prediction methods, life prediction is stuck in a bottleneck. Aiming at the low efficiency of traditional estimation algorithms, a more efficient neural network is proposed by using Convolutional Neural Networks (CNN) to replace Long-Short Term Memory (LSTM). Firstly, multi-sensor degenerate information fusion coding is realized with the convolutional autoencoder (CAE). Then, the temporal convolutional network (TCN) is applied to achieve efficient prediction with the obtained degradation code. It does not depend on the iteration along time, but learning the causality through a mask. Moreover, the data processing is improved to further improve the application efficiency of the algorithm. ExtraTreesClassifier is applied to recognize when the failure first develops. This step can not only assist labelling, but also realize feature filtering combined with tree model interpretation. For multiple operation conditions, new features are clustered by K-means++ to encode historical condition information. Finally, an experiment is carried out to evaluate the effectiveness on the Commercial Modular Aero-Propulsion System Simulation (CMAPSS) datasets provided by the National Aeronautics and Space Administration (NASA). The results show that the proposed algorithm can ensure high-precision prediction and effectively improve the efficiency. |
| first_indexed | 2024-03-11T10:08:52Z |
| format | Article |
| id | doaj.art-6b7ff0d3967a4032ba1666cac763490e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T10:08:52Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-6b7ff0d3967a4032ba1666cac763490e2023-11-16T14:49:30ZengMDPI AGApplied Sciences2076-34172022-12-011311710.3390/app13010017Aero-Engine Remaining Useful Life Estimation Based on CAE-TCN Neural NetworksGuanghao Ren0Yun Wang1Zhenyun Shi2Guigang Zhang3Feng Jin4Jian Wang5Institute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaInstitute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaSchool of Mechanical Engineering & Automation, Beihang University, Beijing 100191, ChinaInstitute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaSchool of Automation, Beijing Institute of Technology, Beijing 100081, ChinaInstitute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaWith the rapid growth of the aviation fields, the remaining useful life (RUL) estimation of aero-engine has become the focus of the industry. Due to the shortage of existing prediction methods, life prediction is stuck in a bottleneck. Aiming at the low efficiency of traditional estimation algorithms, a more efficient neural network is proposed by using Convolutional Neural Networks (CNN) to replace Long-Short Term Memory (LSTM). Firstly, multi-sensor degenerate information fusion coding is realized with the convolutional autoencoder (CAE). Then, the temporal convolutional network (TCN) is applied to achieve efficient prediction with the obtained degradation code. It does not depend on the iteration along time, but learning the causality through a mask. Moreover, the data processing is improved to further improve the application efficiency of the algorithm. ExtraTreesClassifier is applied to recognize when the failure first develops. This step can not only assist labelling, but also realize feature filtering combined with tree model interpretation. For multiple operation conditions, new features are clustered by K-means++ to encode historical condition information. Finally, an experiment is carried out to evaluate the effectiveness on the Commercial Modular Aero-Propulsion System Simulation (CMAPSS) datasets provided by the National Aeronautics and Space Administration (NASA). The results show that the proposed algorithm can ensure high-precision prediction and effectively improve the efficiency.https://www.mdpi.com/2076-3417/13/1/17remaining useful life estimationaero-engineconvolutional autoencodertemporal convolutional network |
| spellingShingle | Guanghao Ren Yun Wang Zhenyun Shi Guigang Zhang Feng Jin Jian Wang Aero-Engine Remaining Useful Life Estimation Based on CAE-TCN Neural Networks Applied Sciences remaining useful life estimation aero-engine convolutional autoencoder temporal convolutional network |
| title | Aero-Engine Remaining Useful Life Estimation Based on CAE-TCN Neural Networks |
| title_full | Aero-Engine Remaining Useful Life Estimation Based on CAE-TCN Neural Networks |
| title_fullStr | Aero-Engine Remaining Useful Life Estimation Based on CAE-TCN Neural Networks |
| title_full_unstemmed | Aero-Engine Remaining Useful Life Estimation Based on CAE-TCN Neural Networks |
| title_short | Aero-Engine Remaining Useful Life Estimation Based on CAE-TCN Neural Networks |
| title_sort | aero engine remaining useful life estimation based on cae tcn neural networks |
| topic | remaining useful life estimation aero-engine convolutional autoencoder temporal convolutional network |
| url | https://www.mdpi.com/2076-3417/13/1/17 |
| work_keys_str_mv | AT guanghaoren aeroengineremainingusefullifeestimationbasedoncaetcnneuralnetworks AT yunwang aeroengineremainingusefullifeestimationbasedoncaetcnneuralnetworks AT zhenyunshi aeroengineremainingusefullifeestimationbasedoncaetcnneuralnetworks AT guigangzhang aeroengineremainingusefullifeestimationbasedoncaetcnneuralnetworks AT fengjin aeroengineremainingusefullifeestimationbasedoncaetcnneuralnetworks AT jianwang aeroengineremainingusefullifeestimationbasedoncaetcnneuralnetworks |