《计算机应用研究》|Application Research of Computers

数据失衡下基于WGAN和GAPCNN的轴承故障诊断研究

Research on bearing fault diagnosis based on WGAN and GAPCNN under imbalance of data

免费全文下载 (已被下载 次)  
获取PDF全文
作者 薛振泽,满君丰,彭成,邓河
机构 1.湖南工业大学 计算机学院,湖南 株洲 412007;2.中南大学 自动化学院,长沙 410083;3.长沙民政职业技术学院,长沙 410004
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2020)12-032-3681-05
DOI 10.19734/j.issn.1001-3695.2019.07.0555
摘要 针对轴承故障数据严重失衡导致所训练的模型诊断能力和泛化能力较差等问题,提出基于Wasserstein距离的生成对抗网络来平衡数据集的方法。该方法首先将少量故障样本进行对抗训练,待网络达到纳什均衡时,再将生成的故障样本添加到原始少量故障样本中起到平衡数据集的作用;提出基于全局平均池化卷积神经网络的诊断模型,将平衡后的数据集输入到诊断模型中进行训练,通过模型自适应地逐层提取特征,实现故障的精确分类诊断。实验结果表明,所提诊断方法优于其他算法和模型,同时拥有较强的泛化能力和鲁棒性。
关键词 故障诊断; 深度学习; 滚动轴承; 生成对抗网络; 卷积神经网络
基金项目 国家自然科学基金项目(61871432,61702178,61702177)
湖南省自然科学基金项目(2018JJ4063,2019JJ60008,2017JJ3065)
湖南省教育厅科研项目(16A059,17A052,15C0081,15C0401)
湖南省研究生创新基金项目(CX2018B740)
本文URL http://www.arocmag.com/article/01-2020-12-032.html
英文标题 Research on bearing fault diagnosis based on WGAN and GAPCNN under imbalance of data
作者英文名 Xue Zhenze, Man Junfeng, Peng Cheng, Deng He
机构英文名 1.School of Computer Science,Hunan University of Technology,Zhuzhou Hunan 412007,China;2.School of Automation,Central South University,Changsha 410083,China;3.School of Changsha Social Work College,Changsha 410004,China
英文摘要 Aiming at the problem of poor diagnosis ability and generalization ability of the trained model caused by serious imbalance of bearing fault data, this paper proposed a method of generative adversarial networks based on Wasserstein distance to balance dataset. Firstly, it trained a small number of fault samples for adversarial training. Then when the network reached the Nash equilibrium, it added the generated fault samples to the original small number of fault samples to balance the dataset. This paper proposed a diagnostic model based on global average pooled convolutional neural network. The balanced data set was input into the diagnostic model for training. The model was adaptively extracted layer by layer to achieve accurate classification diagnosis of faults. The experimental results show that the proposed diagnostic method is superior to other algorithms and models, and has strong generalization ability and robustness.
英文关键词 fault diagnosis; deep learning; rolling bearing; generative adversarial networks; convolution neural network
参考文献 查看稿件参考文献
 
收稿日期 2019/7/19
修回日期 2019/9/9
页码 3681-3685
中图分类号 TP183
文献标志码 A