期刊
ADVANCED ENGINEERING INFORMATICS
卷 52, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.aei.2022.101552
关键词
Modified ACGAN; New framework; Multi-mode data augmentation; Rotating machinery fault diagnosis; Spectrum normalization
资金
- National Natural Science Foundation of China [51905160]
- Natural Science Fund for Excellent Young Scholars of Hunan Province [2021JJ20017]
- National Key Research and Development Program of China [2019YFE0105100]
- Fundamental Research Funds for the Central Universities [531118010335]
This study proposes a modified auxiliary classifier GAN (MACGAN) model to address the issue of insufficient samples in fault diagnosis. By improving the ACGAN framework and introducing techniques such as Wasserstein distance and spectral normalization, the proposed method can generate high-quality multi-mode fault samples more effectively, improving the accuracy and stability of fault diagnosis models.
As one of the representative unsupervised data augmentation methods, generative adversarial networks (GANs) have the potential to solve the problem of insufficient samples in fault diagnosis of rotating machinery. However, the existing unsupervised GANs are usually incapable of simultaneously generating multi-mode fault samples and have some shortcomings such as mode collapse and gradient vanishing. To overcome these deficiencies, a supervised model called modified auxiliary classifier GAN (MACGAN) designed with new framework is proposed in this paper. Firstly, a new ACGAN framework is developed by adding an independent classifier to improve the compatibility between the classification and discrimination. Secondly, the Wasserstein distance is introduced in the new loss functions to overcome mode collapse and gradient vanishing. Finally, to achieve stable training, a spectral normalization is used to replace the weight clipping to constrain the weight parameters of discriminator. The proposed method is applied to fault diagnosis of bearing and gear. Compared with the existing GANs, the proposed method can more efficiently generate multi-mode fault samples with higher qualities, which can be used to assist the training of deep learning-based fault diagnosis models with high accuracy and good stability.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据