Que Hongbo, Liu Xuyan, Jin Siqin, Huo Yaoyan, Wu Chengpan, Ding Chuancang, Zhu Zhongkui
School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing 100044, China.
CRRC Qishuyan Locomotive and Rolling Stock Technology Research Institute Co., Ltd., Changzhou 213003, China.
Sensors (Basel). 2024 Aug 10;24(16):5165. doi: 10.3390/s24165165.
Rolling bearing fault diagnosis methods based on transfer learning always assume that the sample classes in the target domain are consistent with those in the source domain during the training phase. However, it is difficult to collect all fault classes in the early stage of mechanical application. The more likely situation is that the training data in the target domain only contain a subset of the entire health state, which will lead to the problem of label imbalance compared with the source domain. The outlier classes in the source domain that do not have corresponding target domain samples for feature alignment will interfere with the feature transfer of other classes. To address this specific challenge, this study introduces an innovative inter-class feature transfer fault diagnosis approach. By leveraging label information, the method distinctively computes the distribution discrepancies among shared classes, thereby circumventing the deleterious influence of outlier classes on the transfer procedure. Empirical evaluations on two rolling bearing datasets, encompassing multiple partial transfer tasks, substantiate that the proposed method surpasses other approaches, offering a novel and efficacious solution for the realm of intelligent bearing fault diagnosis.
基于迁移学习的滚动轴承故障诊断方法总是假定在训练阶段目标域中的样本类别与源域中的样本类别一致。然而，在机械应用的早期阶段，很难收集到所有的故障类别。更有可能出现的情况是，目标域中的训练数据仅包含整个健康状态的一个子集，与源域相比，这将导致标签不平衡问题。源域中没有用于特征对齐的相应目标域样本的离群类别会干扰其他类别的特征迁移。为了应对这一特殊挑战，本研究引入了一种创新的类间特征迁移故障诊断方法。该方法通过利用标签信息，独特地计算共享类之间的分布差异，从而规避离群类别对迁移过程的有害影响。在包含多个部分迁移任务的两个滚动轴承数据集上的实证评估证实，所提出的方法优于其他方法，为智能轴承故障诊断领域提供了一种新颖且有效的解决方案。
