Spacecraft Intelligent Fault Diagnosis under Variable Working Conditions via Wasserstein Distance-Based Deep Adversarial Transfer Learning

In recent years, deep learning methods which promote the accuracy and efficiency of fault diagnosis task without any extra requirement of artificial feature extraction have elicited the attention of researchers in the field of manufacturing industry as well as aerospace. However, the problems that d...

Full description

Saved in:
Bibliographic Details
Main Authors: Gang Xiang, Kun Tian
Format: Article
Language:English
Published: Wiley 2021-01-01
Series:International Journal of Aerospace Engineering
Online Access:http://dx.doi.org/10.1155/2021/6099818
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850213741572915200
author Gang Xiang
Kun Tian
author_facet Gang Xiang
Kun Tian
author_sort Gang Xiang
collection DOAJ
description In recent years, deep learning methods which promote the accuracy and efficiency of fault diagnosis task without any extra requirement of artificial feature extraction have elicited the attention of researchers in the field of manufacturing industry as well as aerospace. However, the problems that data in source and target domains usually have different probability distributions because of different working conditions and there are insufficient labeled or even unlabeled data in target domain significantly deteriorate the performance and generalization of deep fault diagnosis models. To address these problems, we propose a novel Wasserstein Generative Adversarial Network with Gradient Penalty- (WGAN-GP-) based deep adversarial transfer learning (WDATL) model in this study, which exploits a domain critic to learn domain invariant feature representations by minimizing the Wasserstein distance between the source and target feature distributions through adversarial training. Moreover, an improved one-dimensional convolutional neural network- (CNN-) based feature extractor which utilizes exponential linear units (ELU) as activation functions and wide kernels is designed to automatically extract the latent features of raw time-series input data. Then, the fault model classifier trained in one working condition (source domain) with sufficient labeled samples could be generalized to diagnose data in other working conditions (target domain) with insufficient labeled samples. Experiments on two open datasets demonstrate that our proposed WDATL model outperforms most of the state-of-the-art approaches on transfer diagnosis tasks under diverse working circumstances.
format Article
id doaj-art-81c72049b24a47f3bb7ea265b1b4adb6
institution OA Journals
issn 1687-5966
1687-5974
language English
publishDate 2021-01-01
publisher Wiley
record_format Article
series International Journal of Aerospace Engineering
spelling doaj-art-81c72049b24a47f3bb7ea265b1b4adb62025-08-20T02:09:05ZengWileyInternational Journal of Aerospace Engineering1687-59661687-59742021-01-01202110.1155/2021/60998186099818Spacecraft Intelligent Fault Diagnosis under Variable Working Conditions via Wasserstein Distance-Based Deep Adversarial Transfer LearningGang Xiang0Kun Tian1School of Automation and Electrical Engineering, Beihang University, Beijing 100191, ChinaBeijing Aerospace Automatic Control Institute, Beijing 100854, ChinaIn recent years, deep learning methods which promote the accuracy and efficiency of fault diagnosis task without any extra requirement of artificial feature extraction have elicited the attention of researchers in the field of manufacturing industry as well as aerospace. However, the problems that data in source and target domains usually have different probability distributions because of different working conditions and there are insufficient labeled or even unlabeled data in target domain significantly deteriorate the performance and generalization of deep fault diagnosis models. To address these problems, we propose a novel Wasserstein Generative Adversarial Network with Gradient Penalty- (WGAN-GP-) based deep adversarial transfer learning (WDATL) model in this study, which exploits a domain critic to learn domain invariant feature representations by minimizing the Wasserstein distance between the source and target feature distributions through adversarial training. Moreover, an improved one-dimensional convolutional neural network- (CNN-) based feature extractor which utilizes exponential linear units (ELU) as activation functions and wide kernels is designed to automatically extract the latent features of raw time-series input data. Then, the fault model classifier trained in one working condition (source domain) with sufficient labeled samples could be generalized to diagnose data in other working conditions (target domain) with insufficient labeled samples. Experiments on two open datasets demonstrate that our proposed WDATL model outperforms most of the state-of-the-art approaches on transfer diagnosis tasks under diverse working circumstances.http://dx.doi.org/10.1155/2021/6099818
spellingShingle Gang Xiang
Kun Tian
Spacecraft Intelligent Fault Diagnosis under Variable Working Conditions via Wasserstein Distance-Based Deep Adversarial Transfer Learning
International Journal of Aerospace Engineering
title Spacecraft Intelligent Fault Diagnosis under Variable Working Conditions via Wasserstein Distance-Based Deep Adversarial Transfer Learning
title_full Spacecraft Intelligent Fault Diagnosis under Variable Working Conditions via Wasserstein Distance-Based Deep Adversarial Transfer Learning
title_fullStr Spacecraft Intelligent Fault Diagnosis under Variable Working Conditions via Wasserstein Distance-Based Deep Adversarial Transfer Learning
title_full_unstemmed Spacecraft Intelligent Fault Diagnosis under Variable Working Conditions via Wasserstein Distance-Based Deep Adversarial Transfer Learning
title_short Spacecraft Intelligent Fault Diagnosis under Variable Working Conditions via Wasserstein Distance-Based Deep Adversarial Transfer Learning
title_sort spacecraft intelligent fault diagnosis under variable working conditions via wasserstein distance based deep adversarial transfer learning
url http://dx.doi.org/10.1155/2021/6099818
work_keys_str_mv AT gangxiang spacecraftintelligentfaultdiagnosisundervariableworkingconditionsviawassersteindistancebaseddeepadversarialtransferlearning
AT kuntian spacecraftintelligentfaultdiagnosisundervariableworkingconditionsviawassersteindistancebaseddeepadversarialtransferlearning