自适应正则化迁移学习的不同工况下滚动轴承故障诊断
DOI:
CSTR:
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

TH165 + . 3 TP18

基金项目:

国家自然科学基金(51975079)、国家重点研发项目(2018YFB1306601)、内燃机可靠性国家重点实验室开放基金( SKLER- 201912)、重庆市研究生导师团队项目(JDDSTD2018006)、重庆市北碚区科学技术局技术创新与应用示范项目(2020- 6)资助。


Fault diagnosis of rolling bearing under different working conditions using adaptation regularization based transfer learning
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:

    针对不同工况下存在两域分布差异复杂的问题,提出自适应正则化迁移学习的不同工况下滚动轴承故障诊断方法。 首 先,训练基分类器为目标域预测伪标签,利用联合分布适配对齐两域分布,以减小分布差异;其次,通过流形正则化对目标域数 据进一步利用,挖掘数据的潜在分布几何结构,学习目标域数据分布信息;最后,利用在结构风险最小化框架下建立的分类器结 合上述两步学习策略,迭代更新伪标签获得最优系数矩阵完成不同工况下滚动轴承故障诊断。 在两组滚动轴承数据集上进行 实验验证,实验结果显示所提方法识别准确率分别达到了 96. 38% ,94. 18% 。 证明该方法能够有效应对多种工况导致的复杂分 布差异,同时具有较好的有效性和可行性。

    Abstract:

    Aiming at the complex distribution difference caused by two domains under different working conditions, an adaptation regularization based transfer learning method for rolling bearing fault diagnosis under different working conditions is proposed. Firstly, the training base classifier predicts the pseudo label for the target domain, and the joint distribution is used to align two domain distributions to reduce the distribution difference. Secondly, the target domain data are further utilized through the manifold regularization to mine the potential distribution geometry of the data and learn the target domain data distribution information. Finally, the classifier is established under the framework of structural risk minimization combined with the above two-step learning principle. The optimal coefficient matrix is obtained by iteratively updating pseudo labels to complete the fault diagnosis of rolling bearing under different working conditions. The experimental validation is implemented on two rolling bearing datasets. Results show that the identification accuracy values of the proposed method are 96. 38% and 94. 18% , respectively. It shows that the method can effectively deal with the complex distribution differences caused by multiple working conditions, and has good effectiveness and feasibility.

    参考文献
    相似文献
    引证文献
引用本文

陈仁祥,朱玉清,胡小林,赵树恩,张 晓.自适应正则化迁移学习的不同工况下滚动轴承故障诊断[J].仪器仪表学报,2021,(8):95-103

复制
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: 2023-06-28
  • 出版日期:
文章二维码