用户名 密 码 登 录 忘记密码 免费注册

网站会员中心 | 设为首页 | 加入收藏

 您好，欢迎光临中国轴承行业网         退出登陆

会员中心 | 设为首页 | 加入收藏

协会

统计

国外文献 > 1.轴承 > 7. 智能方法与计算 > 机器学习

关键词搜索：

标 题： A class-level matching unsupervised transfer learning network for rolling bearing fault diagnosis under various working conditions
一种适用于不同工况下滚动轴承故障诊断的类级匹配无监督迁移学习网络
作 者： Chunran Huo
Quansheng Jiang
Yehu Shen
Xiaoshan Lin
Qixin Zhu
Qingkui Zhang
关键词： Transfer learning  [迁移学习]
Fault diagnosis  [ 故障诊断]
Maximum classifier discrepancy  [ 最大分类器差异]
Rolling bearing  [ 滚动轴承]
出版年： 2023
期刊名： Applied Soft Computing
应用软计算
年卷期： 2023, vol.146
摘 要： As an effective method, deep transfer learning is used to solve the problem of unsupervised fault diagnosis of rolling bearings. In the process of obtaining domain invariant features, the feature matching at the domain-level does not consider the distribution of each category in matching the global distribution of source domain features and target domain features. To solve this problem, a class-level matching transfer learning network is proposed. In this method, source domain data and target domain data from different categories are matched first. Meanwhile, domain-level matching and class-level matching are combined based on the maximum classifier discrepancy structure. Then the transfer training process is divided into three stages: domain-level matching, class-level matching, and target domain pseudo-label direct guidance network training. The proposed method utilizes the target domain pseudo-label output by the network to extract the features of the target data by self-directing. Compared with the improved maximum classifier discrepancy on the Paderborn University dataset, the proposed method improves the fault diagnosis average accuracy by 12.95% on the six transfer tasks. It significantly improves the diagnostic accuracy of unsupervised bearing fault diagnosis under various working conditions.

作为一种有效方法，深度迁移学习被用于解决滚动轴承无监督故障诊断问题。在获取域不变特征的过程中，域级特征匹配未考虑各类别在匹配源域特征与目标域特征全局分布时的分布情况。为解决这一问题，提出了一种类级匹配迁移学习网络。该方法首先对不同类别的源域数据和目标域数据进行匹配，同时基于最大分类器差异结构将域级匹配与类级匹配相结合。随后，迁移训练过程分为三个阶段：域级匹配、类级匹配以及目标域伪标签直接引导网络训练。所提方法利用网络输出的目标域伪标签，通过自主导向方式提取目标数据的特征。与在帕德博恩大学数据集上改进的最大分类器差异方法相比，该方法在六个迁移任务上提升了故障诊断平均准确率12.95%。它显著提高了在各种工作条件下无监督轴承故障诊断的诊断准确性。
中文内容为网络AI翻译，专业术语未必准确，仅供参考。

VIP网员

联系我们 | 登录注册 | 会员管理 | 网员服务 | 服务信息 | 广告服务 | 高薪聘请 | 法律声明 | 关于我们

京公网安备 11010202009788    京ICP备2021015424号