传感技术学报2026，Vol.39Issue(7)：1489-1497,9.DOI:10.3969/j.issn.1004-1699.2026.07.010
基于动态残差收缩网络的滚动轴承故障诊断
Fault Diagnosis of Rolling Bearing Based on Dynamic Residual Shrinkage Network
摘要
Abstract
In recent years,rotating machinery and equipment has been widely used in the field of modern industrial production.As one of the key parts of rotating machinery,the rolling bearing is easy to wear and lead to mechanical failure due to the long time working in changeable and noisy harsh environment.To solve this problem,an intelligent fault diagnosis method based on dynamic residual shrink-age network(DyRSN)is proposed.The dynamic features,according to different input vibration data,can be adaptively captured by this method,thereby breaking through the limitation of the traditional static feature extraction method on the fixed network structure and pa-rameters.Secondly,the noise can be adaptively eliminated by utilizing the automatic soft thresholding module,so as to address the issue of noise interference in the actual application scene and improve the anti-noise capability of the model.Finally,the real vibration data of motor bearing bench is obtained by the vibration signal acquisition system of motor bearing based on wireless network to verify the effec-tiveness of the proposed method.The experimental results validate the good robustness of the proposed method and the feasibility of ac-curate rolling bearing diagnostics.关键词
故障诊断/深度学习/软阈值模块/旋转机械/滚动轴承Key words
fault diagnosis/deep learning/soft threshold module/rotating machinery/rolling bearing分类
机械制造引用本文复制引用
陈昊杰,陈永毅,张丹..基于动态残差收缩网络的滚动轴承故障诊断[J].传感技术学报,2026,39(7):1489-1497,9.基金项目
国家自然科学基金优秀青年项目(62322315) （62322315）
