• CN:11-2187/TH
  • ISSN:0577-6686

机械工程学报 ›› 2024, Vol. 60 ›› Issue (18): 43-52.doi: 10.3901/JME.2024.18.043

• 仪器科学与技术 • 上一篇    下一篇

扫码分享

基于模糊域自适应的源自由域旋转机械故障诊断方法

赵轲1, 叶敏1, 王瑞欣1, 陆海2, 刘孟孟3, 邵海东4   

  1. 1. 长安大学工程机械学院 西安 710054;
    2. 国营长虹机械厂 桂林 541003;
    3. 西安现代控制研究所 西安 710061;
    4. 湖南大学机械与运载工程学院 长沙 410082
  • 收稿日期:2023-12-15 修回日期:2024-08-10 出版日期:2024-09-20 发布日期:2024-11-15
  • 作者简介:赵轲,男,1998年出生,博士,讲师。主要研究方向为故障诊断与寿命预测,数据挖掘与信息融合。E-mail:zhaoke@chd.edu.cn
    叶敏(通信作者),男,1978年出生,博士,教授,博士研究生导师。主要研究方向为工程机械故障诊断。E-mail:mingye@chd.edu.cn
  • 基金资助:
    国家自然科学基金(51905160,52275085)、长安大学青年学者学科交叉团队建设(300104240912)、湖南省自然科学基金优秀青年科学基金(2021JJ20017)和陕西省博士后科研(2023BSHEDZZ219)资助项目。

Fuzzy Domain Adaptation Approach for Source-free Domain Rotary Machinery Fault Diagnosis

ZHAO Ke1, YE Min1, WANG Ruixin1, LU Hai2, LIU Mengmeng3, SHAO Haidong4   

  1. 1. School of Construction and Machinery, Chang'an University, Xi'an 710054;
    2. State-owned Changhong Machinery Factory, Guilin 541003;
    3. Xi'an Modern Control Research Institute, Xi'an 710061;
    4. College of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082
  • Received:2023-12-15 Revised:2024-08-10 Online:2024-09-20 Published:2024-11-15

摘要: 现有的域自适应方法需要访问原始数据,因此存在潜在的数据隐私泄露风险。模糊域自适应通过生成模糊规则和关系,无需访问源数据,从而构建了域自适应模型。基于这一思想,提出一种基于模糊域自适应的源自由域旋转机械故障诊断方法。具体来说,在源域训练时,采用联合训练策略,通过共享模型参数同时训练所有源模型,显著提高每个私有源模型的多域性能。此外,提出的方法还建立一个融合模糊策略的模型,从源样本和各类别对应的锚点中获得模糊规则。在目标域自适应阶段,提出的方法首先使用目标数据重新训练源特征提取器,同时保持模糊规则不变。然后,引入锚点对齐策略,以传递诊断知识。最后,提出的方法设计过滤策略,获取高置信度的目标伪标签,并结合自监督学习策略对目标模型进行最终优化。经过滚动轴承跨域诊断案例和齿轮跨域诊断案例的验证,该框架是一种高效且安全的故障诊断解决方案。

关键词: 旋转机械故障诊断, 数据隐私泄露, 源自由域, 模糊域自适应, 自监督学习策略

Abstract: Existing domain adaptation methods require access to raw data, increasing the risk of data leakage. Fuzzy domain adaptation generates fuzzy rules and relationships without accessing source data. Leveraging knowledge from the source, this research proposes a novel method for source-free domain rotary machinery fault diagnosis using fuzzy domain adaptation. Specifically, during source domain training, a joint training strategy simultaneously trains all source models by sharing model parameters. This approach significantly enhances the multi-domain performance of each private source model. Additionally, a model with a fused fuzzy strategy is constructed to derive fuzzy rules from source samples and anchor points corresponding to various categories. In the target domain adaptation phase, the proposed method retrains the source feature extractor using target data while keeping the fuzzy rules fixed. Subsequently, an anchor point alignment strategy is introduced to transfer diagnostic knowledge. Finally, a filtering strategy is designed to obtain high-confidence target pseudo-labels, combining a self-supervised learning strategy for the ultimate optimization of the target model. After verification by rolling bearing cross-domain diagnosis cases and gear cross-domain diagnosis cases, the framework is an efficient and secure solution for fault diagnosis.

Key words: rotary machinery fault diagnosis, data privacy leakage, source-free domain, fuzzy domain adaptation, self-supervised learning strategy

中图分类号: