Intelligent Health Assessment of Aviation Bearing Based on Deep Transfer Graph Convolutional Networks under Large Speed Fluctuations
As a critical support and fixed component of aero engines, electro-hydrostatic actuators, and other equipment, the operation of aviation bearings is often subject to high speed, high-temperature rise, large load, and other continuous complex fluctuation conditions, which makes their health assessmen...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-04-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/9/4379 |
_version_ | 1797601707698421760 |
---|---|
author | Xiaoli Zhao Xingjun Zhu Jianyong Yao Wenxiang Deng Yudong Cao Peng Ding Minping Jia Haidong Shao |
author_facet | Xiaoli Zhao Xingjun Zhu Jianyong Yao Wenxiang Deng Yudong Cao Peng Ding Minping Jia Haidong Shao |
author_sort | Xiaoli Zhao |
collection | DOAJ |
description | As a critical support and fixed component of aero engines, electro-hydrostatic actuators, and other equipment, the operation of aviation bearings is often subject to high speed, high-temperature rise, large load, and other continuous complex fluctuation conditions, which makes their health assessment tasks more difficult. To solve this problem, an intelligent health assessment method based on a new Deep Transfer Graph Convolutional Network (DTGCN) is proposed for aviation bearings under large speed fluctuation conditions. First, a new DTGCN algorithm is designed, which mainly uses the domain adaptation mechanism to enhance the performance of Graph Convolutional Network (GCN) and the generalization performance of transfer properties. Specifically, order spectrum analysis is employed to resample the vibration signals of aviation bearings and transform them into order spectral signals. Then, the trained 1dGCN is used as the feature extractor, and the designed Dynamic Multiple Kernel Maximum Mean Discrepancy (DMKMMD) is calculated to match the difference in edge distribution. Finally, the aligned features are fed into the softmax classifier for intelligent health assessment. The effectiveness of the proposed diagnostic algorithm and method are validated by using aviation bearing fault data set under large speed fluctuation conditions. |
first_indexed | 2024-03-11T04:07:29Z |
format | Article |
id | doaj.art-f86086ebb446467e8f47b06fee906f66 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-11T04:07:29Z |
publishDate | 2023-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-f86086ebb446467e8f47b06fee906f662023-11-17T23:43:34ZengMDPI AGSensors1424-82202023-04-01239437910.3390/s23094379Intelligent Health Assessment of Aviation Bearing Based on Deep Transfer Graph Convolutional Networks under Large Speed FluctuationsXiaoli Zhao0Xingjun Zhu1Jianyong Yao2Wenxiang Deng3Yudong Cao4Peng Ding5Minping Jia6Haidong Shao7School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Mechanical Engineering, Southeast University, Nanjing 211189, ChinaSchool of Mechanical Engineering, Southeast University, Nanjing 211189, ChinaSchool of Mechanical Engineering, Southeast University, Nanjing 211189, ChinaCollege of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082, ChinaAs a critical support and fixed component of aero engines, electro-hydrostatic actuators, and other equipment, the operation of aviation bearings is often subject to high speed, high-temperature rise, large load, and other continuous complex fluctuation conditions, which makes their health assessment tasks more difficult. To solve this problem, an intelligent health assessment method based on a new Deep Transfer Graph Convolutional Network (DTGCN) is proposed for aviation bearings under large speed fluctuation conditions. First, a new DTGCN algorithm is designed, which mainly uses the domain adaptation mechanism to enhance the performance of Graph Convolutional Network (GCN) and the generalization performance of transfer properties. Specifically, order spectrum analysis is employed to resample the vibration signals of aviation bearings and transform them into order spectral signals. Then, the trained 1dGCN is used as the feature extractor, and the designed Dynamic Multiple Kernel Maximum Mean Discrepancy (DMKMMD) is calculated to match the difference in edge distribution. Finally, the aligned features are fed into the softmax classifier for intelligent health assessment. The effectiveness of the proposed diagnostic algorithm and method are validated by using aviation bearing fault data set under large speed fluctuation conditions.https://www.mdpi.com/1424-8220/23/9/4379aviation bearingsintelligent health assessmentlarge speed fluctuationsgraph convolutional network (GCN)transfer learning |
spellingShingle | Xiaoli Zhao Xingjun Zhu Jianyong Yao Wenxiang Deng Yudong Cao Peng Ding Minping Jia Haidong Shao Intelligent Health Assessment of Aviation Bearing Based on Deep Transfer Graph Convolutional Networks under Large Speed Fluctuations Sensors aviation bearings intelligent health assessment large speed fluctuations graph convolutional network (GCN) transfer learning |
title | Intelligent Health Assessment of Aviation Bearing Based on Deep Transfer Graph Convolutional Networks under Large Speed Fluctuations |
title_full | Intelligent Health Assessment of Aviation Bearing Based on Deep Transfer Graph Convolutional Networks under Large Speed Fluctuations |
title_fullStr | Intelligent Health Assessment of Aviation Bearing Based on Deep Transfer Graph Convolutional Networks under Large Speed Fluctuations |
title_full_unstemmed | Intelligent Health Assessment of Aviation Bearing Based on Deep Transfer Graph Convolutional Networks under Large Speed Fluctuations |
title_short | Intelligent Health Assessment of Aviation Bearing Based on Deep Transfer Graph Convolutional Networks under Large Speed Fluctuations |
title_sort | intelligent health assessment of aviation bearing based on deep transfer graph convolutional networks under large speed fluctuations |
topic | aviation bearings intelligent health assessment large speed fluctuations graph convolutional network (GCN) transfer learning |
url | https://www.mdpi.com/1424-8220/23/9/4379 |
work_keys_str_mv | AT xiaolizhao intelligenthealthassessmentofaviationbearingbasedondeeptransfergraphconvolutionalnetworksunderlargespeedfluctuations AT xingjunzhu intelligenthealthassessmentofaviationbearingbasedondeeptransfergraphconvolutionalnetworksunderlargespeedfluctuations AT jianyongyao intelligenthealthassessmentofaviationbearingbasedondeeptransfergraphconvolutionalnetworksunderlargespeedfluctuations AT wenxiangdeng intelligenthealthassessmentofaviationbearingbasedondeeptransfergraphconvolutionalnetworksunderlargespeedfluctuations AT yudongcao intelligenthealthassessmentofaviationbearingbasedondeeptransfergraphconvolutionalnetworksunderlargespeedfluctuations AT pengding intelligenthealthassessmentofaviationbearingbasedondeeptransfergraphconvolutionalnetworksunderlargespeedfluctuations AT minpingjia intelligenthealthassessmentofaviationbearingbasedondeeptransfergraphconvolutionalnetworksunderlargespeedfluctuations AT haidongshao intelligenthealthassessmentofaviationbearingbasedondeeptransfergraphconvolutionalnetworksunderlargespeedfluctuations |