基于TTUR的C-DCGAN机械故障诊断模型稳定训练方法
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

TH17;TP183

基金项目:

山西省青年科技研究基金资助项目(201901D211202);山西省重点研发计划资助项目(201903D421008)


Stability Training Method of C‑DCGAN in Mechanical Fault Diagnosis Based on TTUR
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对条件深度卷积生成式对抗网络(conditional deep convolutional generative adversarial network ,简称C-DCGAN)在训练过程中出现的不稳定性问题,提出具有随机梯度下降的双时间尺度更新规则(two time-scale update rule,简称TTUR)用于C-DCGAN机械故障诊断模型训练中,在判别器和生成器具有单独学习速率的情况下提高模型的稳定性。首先,给出了TTUR在C?DCGAN模型中收敛性证明;其次,在西储大学轴承数据集(Case Western Reserve University,简称CWUR)和实验室行星齿轮箱数据集上验证其有效性;最后,引入Jensen-Shannon 散度(Jensen-Shannon divergence,简称JSD)指标评估模型捕获到的真实数据和生成数据之间的相似度。实验结果表明,TTUR提高了C-DCGAN的学习能力,优于传统的C-DCGAN。

    Abstract:

    To solve the instability of conditional deep convolutional generative adversarial network (C-DCGAN) in training process, we propose a two time-scale update rule (TTUR) for C-DCGAN with stochastic gradient descent in model training for mechanical fault diagnosis. The model stability is improved when the discriminator and generator have learning rates for their own. Firstly, the convergence of TTUR in C-DCGAN model is proved. Secondly, the validity of the method is verified on the bearing data set of Case Western Reserve University (CWUR) and planetary gearbox data set of laboratories. Finally, the Jensen-Shannon divergence (JSD) is introduced to capture the similarity of generated data to real ones. Experiments suggest that TTUR improves the learning for C-DCGAN and outperforms conventional C-DCGAN.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2022-08-27
  • 出版日期:
您是第位访问者
振动、测试与诊断 ® 2024 版权所有
技术支持:北京勤云科技发展有限公司