中北大学学报（自然科学版）2025，Vol.46Issue(5)：632-640,9.DOI:10.62756/jnuc.issn.1673-3193.2025.04.0008
滚动轴承域适应迁移学习故障识别方法
Domain-Adaptive Transfer Learning Method for Rolling Bearing Fault Identification
摘要
Abstract
To address challenges in practical engineering where bearing data contains noise and labeled data is scarce,this study proposed a transfer learning method for fault identification using a wavelet packet 1D-CNN and compound domain adaptation loss.The developed wavelet packet branch attention CNN(WPBA-CNN)integrated wavelet packet analysis and attention mechanisms for noise-resistant feature extraction.A branch maximum mean discrepancy(BMMD)loss was designed for multi-scale branches,and combined cross-entropy loss with fast batch nuclear-norm maximization(FBNM)method to form the domain adaptation compound loss(DACL).Experimental results demonstrate that the accuracy of the WPBA-CNN-DACL method increases by 16 percentage points compared to the TICNN method,and the accuracy of the BMMD component increases by 3.3 percentage points compared to the traditional MMD.The average accuracy rate of the 20 migration tasks reaches 98.24%.These experimental results validate the synergistic advantages of our method in noise suppression and cross domain adaptation,and this method can serve as an effective solution for unlabeled bearing fault diagnosis.关键词
卷积神经网络/迁移学习/域适应/复合损失函数Key words
convolutional neural network/transfer learning/domain adaptation/composite loss function分类
机械制造引用本文复制引用
申炜,黄晋英,范振芳,王宇轩..滚动轴承域适应迁移学习故障识别方法[J].中北大学学报（自然科学版）,2025,46(5):632-640,9.基金项目
山西省基础研究计划资助项目(202203021211096) （202203021211096）
中国博士后科学基金面上资助项目(2024M752992) （2024M752992）
