Learning to Imbalanced Open Set Generalize: A Meta-Learning Framework for Enhanced Mechanical Diagnosis

Authors:
Top Cited Papers
Publisher website
Google Scholar
Abstract
To alleviate data distribution under different operating conditions, domain generalization (DG) has been applied in mechanical diagnosis. Still, its effectiveness is limited when unknown fault states appear in the target domain. Consequently, open set DG (OSDG) has emerged to identify unknown classes in unknown domains. However, data collection costs and safety concerns have resulted in a significant class imbalance in OSDG. This imbalance causes the decision boundary to be skewed toward abundant positive classes, ultimately leading to misclassifying unknown states and increasing security risks. Currently, there is a lack of methods to simultaneously address domain shift and class shift in an imbalanced unknown domain. To tackle this issue, this article proposes a multisource domain-class gradient coordination meta-learning (MDGCML) framework, which can learn the generalized boundaries of all tasks by coordinating gradients between interdomains and interclasses. Based on the MDGCML, a joint learning paradigm involving the sharing of parameters between open-set classifiers and closed-set classifiers is constructed to enable quick adaption of the model to unknown domains. The superior performance of the proposed framework has been verified on two datasets.
Funding Information
  • China Technical Basic Research Plan (JSJT2022206A001)
  • Chinese Scholarships Council of China (202306120133)
  • China Association for Science and Technology Youth Talent Support Engineering Doctoral Program

This publication has 41 references indexed in Scilit: