Imbalanced Fault Classification of Bearing via Wasserstein Generative Adversarial Networks with Gradient Penalty

Recently, generative adversarial networks (GANs) are widely applied to increase the amounts of imbalanced input samples in fault diagnosis. However, the existing GAN-based methods have convergence difficulties and training instability, which affect the fault diagnosis efficiency. This paper develops...

Full description

Saved in:
Bibliographic Details
Main Authors: Baokun Han, Sixiang Jia, Guifang Liu, Jinrui Wang
Format: Article
Language:English
Published: Wiley 2020-01-01
Series:Shock and Vibration
Online Access:http://dx.doi.org/10.1155/2020/8836477
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832566162217500672
author Baokun Han
Sixiang Jia
Guifang Liu
Jinrui Wang
author_facet Baokun Han
Sixiang Jia
Guifang Liu
Jinrui Wang
author_sort Baokun Han
collection DOAJ
description Recently, generative adversarial networks (GANs) are widely applied to increase the amounts of imbalanced input samples in fault diagnosis. However, the existing GAN-based methods have convergence difficulties and training instability, which affect the fault diagnosis efficiency. This paper develops a novel framework for imbalanced fault classification based on Wasserstein generative adversarial networks with gradient penalty (WGAN-GP), which interpolates randomly between the true and generated samples to ensure that the transition region between the true and false samples satisfies the Lipschitz constraint. The process of feature learning is visualized to show the feature extraction process of WGAN-GP. To verify the availability of the generated samples, a stacked autoencoder (SAE) is set to classify the enhanced dataset composed of the generated samples and original samples. Furthermore, the exhibition of the loss curve indicates that WGAN-GP has better convergence and faster training speed due to the introduction of the gradient penalty. Three bearing datasets are employed to verify the effectiveness of the developed framework, and the results show that the proposed framework has an excellent performance in mechanical fault diagnosis under the imbalanced training dataset.
format Article
id doaj-art-d1700f36aa9e4d89bd3772d0fe16c151
institution Kabale University
issn 1070-9622
1875-9203
language English
publishDate 2020-01-01
publisher Wiley
record_format Article
series Shock and Vibration
spelling doaj-art-d1700f36aa9e4d89bd3772d0fe16c1512025-02-03T01:04:59ZengWileyShock and Vibration1070-96221875-92032020-01-01202010.1155/2020/88364778836477Imbalanced Fault Classification of Bearing via Wasserstein Generative Adversarial Networks with Gradient PenaltyBaokun Han0Sixiang Jia1Guifang Liu2Jinrui Wang3College of Mechanical and Electrical Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Mechanical and Electrical Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Mechanical and Electrical Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Mechanical and Electrical Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaRecently, generative adversarial networks (GANs) are widely applied to increase the amounts of imbalanced input samples in fault diagnosis. However, the existing GAN-based methods have convergence difficulties and training instability, which affect the fault diagnosis efficiency. This paper develops a novel framework for imbalanced fault classification based on Wasserstein generative adversarial networks with gradient penalty (WGAN-GP), which interpolates randomly between the true and generated samples to ensure that the transition region between the true and false samples satisfies the Lipschitz constraint. The process of feature learning is visualized to show the feature extraction process of WGAN-GP. To verify the availability of the generated samples, a stacked autoencoder (SAE) is set to classify the enhanced dataset composed of the generated samples and original samples. Furthermore, the exhibition of the loss curve indicates that WGAN-GP has better convergence and faster training speed due to the introduction of the gradient penalty. Three bearing datasets are employed to verify the effectiveness of the developed framework, and the results show that the proposed framework has an excellent performance in mechanical fault diagnosis under the imbalanced training dataset.http://dx.doi.org/10.1155/2020/8836477
spellingShingle Baokun Han
Sixiang Jia
Guifang Liu
Jinrui Wang
Imbalanced Fault Classification of Bearing via Wasserstein Generative Adversarial Networks with Gradient Penalty
Shock and Vibration
title Imbalanced Fault Classification of Bearing via Wasserstein Generative Adversarial Networks with Gradient Penalty
title_full Imbalanced Fault Classification of Bearing via Wasserstein Generative Adversarial Networks with Gradient Penalty
title_fullStr Imbalanced Fault Classification of Bearing via Wasserstein Generative Adversarial Networks with Gradient Penalty
title_full_unstemmed Imbalanced Fault Classification of Bearing via Wasserstein Generative Adversarial Networks with Gradient Penalty
title_short Imbalanced Fault Classification of Bearing via Wasserstein Generative Adversarial Networks with Gradient Penalty
title_sort imbalanced fault classification of bearing via wasserstein generative adversarial networks with gradient penalty
url http://dx.doi.org/10.1155/2020/8836477
work_keys_str_mv AT baokunhan imbalancedfaultclassificationofbearingviawassersteingenerativeadversarialnetworkswithgradientpenalty
AT sixiangjia imbalancedfaultclassificationofbearingviawassersteingenerativeadversarialnetworkswithgradientpenalty
AT guifangliu imbalancedfaultclassificationofbearingviawassersteingenerativeadversarialnetworkswithgradientpenalty
AT jinruiwang imbalancedfaultclassificationofbearingviawassersteingenerativeadversarialnetworkswithgradientpenalty