中国舰船研究2025，Vol.20Issue(2)：3-19,17.DOI:10.19693/j.issn.1673-3185.04175
基于深度学习的旋转机械小样本故障诊断方法研究综述
A review of deep learning-based few sample fault diagnosis method for rotating machinery
摘要
Abstract
[Objectives]Deep learning has shown great potential in the field of rotating machinery fault dia-gnosis.Its excellent performance heavily relies on sufficient training samples.However,in practical engineer-ing applications,acquiring sufficient training data is particularly difficult,resulting in poor generalization cap-ability and low diagnostic accuracy.Therefore,few-sample fault diagnosis methods,which can effectively ex-tract fault-related information from limited data,have gradually become a research focus in both academic and engineering circles.[Method]In this paper,the latest achievements in few-sample fault diagnosis of rotat-ing machinery are reviewed and summarized.This paper describes the definition and learning methods for few-sample fault diagnosis.Few-sample fault diagnosis methods aim to effectively develop fault diagnosis models with strong generalization capability under limited training data conditions.Currently,according to different technical principles,existing few-sample fault diagnosis methods can be classified into five categor-ies:meta-learning,transfer learning,domain generalization,data augmentation,and self-supervised learning.Subsequently,this paper elaborates on the applications of these five methods in rotating machinery fault dia-gnosis.Meta-learning-based fault diagnosis methods improve the ability of models to rapidly learn and adapt to new tasks by acquiring common knowledge from multiple related tasks.The transfer learning-based fault diagnosis methods achieve knowledge migration from the source domain to the target domain using unsuper-vised domain adaptation techniques.The domain generalization-based fault diagnosis methods train models us-ing single or multiple source domains and enable the model to learn features that are common across those do-mains.The data augmentation-based fault diagnosis methods expand the original dataset by generating models.The self-supervised learning-based fault diagnosis methods exploit the structural information of data to con-struct pseudo-labels.[Results]The paper summarizes the core ideas,advantages,and limitations of these five methods.Meta-learning can improve the model's generalization capability but may require significant computational resources.Transfer learning can improve learning efficiency but is limited by domain similarity.Domain generalization can enhance the model performance in unknown domains but may suffer from overfit-ting issues.Data augmentation can increase dataset diversity but may generate inconsistent samples.Self-supervised learning can utilize unlabeled data but faces challenges such as complex task design and potential overfitting.[Conclusions]In the future,data governance,multimodal learning,federated learning,and mechanism-data hybrid-driven methods should be further explored in the field of few-sample fault diagnosis.It will overcome the limitations of existing methods and further improve the reliability of few-sample fault dia-gnosis.关键词
旋转机械/故障分析/故障诊断/小样本/元学习/迁移学习/领域泛化/数据增强/自监督学习Key words
rotating machinery/failure analysis/fault diagnosis/few sample/meta-learning/transfer learning/domain generalization/data augmentation/self-supervised learning分类
交通工程引用本文复制引用
吴轲,吴军,舒启明,沈卫明,宋文斌..基于深度学习的旋转机械小样本故障诊断方法研究综述[J].中国舰船研究,2025,20(2):3-19,17.基金项目
国家自然科学基金项目(523B2100) （523B2100）
华中科技大学交叉研究支持计划项目(2024JCYJ028) （2024JCYJ028）
