基于软联合最大均值差异的域自适应齿轮箱故障诊断  

Domain Adaptive Gearbox Fault Diagnosis Based on Soft Joint Maximum Mean Difference

作　　者：张彦民 ZHANG Yan-min(Jilin Agricultural Science and Technology University,School of Mechanical and Civil Engineering,Jilin Jilin 132101,China)

机构地区：[1]吉林农业科技学院机械与土木工程学院,吉林吉林132101

出　　处：《机械设计与制造》2023年第10期50-58,64,共10页Machinery Design & Manufacture

基　　金：吉林省教育厅“十二五”科学技术研究项目(2015-384)。

摘　　要：为了解决源域和目标域之间存在联合分布差异,提出了一种基于软连接最大均值差异的域自适应齿轮箱故障诊断方法。首先提出了一种域自适应Y网模型,用于提取跨源域和目标域的域不变深度特征,解决域自适应问题。然后通过软联合最大均值差异来驱动传输过程,从而模拟源域和目标域之间的分布差异。进一步引入SE-RES模块,增强了稀疏特征提取的双连接卷积流水线,并提出了一种考虑类权重偏差的软联合最大均值差异度量。最后通过两个行星齿轮箱数据集进行实验验证,结果证明提出的方法实现了不同行星齿轮箱在不同工况下的域自适应故障诊断。In order to solve the joint distribution difference between the source domain and the target domain,a domain adaptive gearbox fault diagnosis method based on the maximum mean difference of soft connection is proposed.Firstly,a domain adaptive Y-net model is proposed to extract domain invariant depth features across the source domain and the target domain to solve the domain adaptive problem.Then,the transmission process is driven by the soft joint maximum mean difference to simulate the dis-tribution difference between the source domain and the target domain.Furthermore,SE-RES module is introduced to enhance the dual connection convolution pipeline of sparse feature extraction,and a soft joint maximum mean difference measure consider-ing class weight deviation is proposed.Finally,two planetary gearbox data sets are used to verify the proposed method.The re-sults show that the proposed method can realize the domain adaptive fault diagnosis of different planetary gearbox under different working conditions.

关 键 词：行星齿轮箱 域自适应 软联合最大均值差异 故障诊断 

分 类 号：TH16[机械工程—机械制造及自动化] TP273[自动化与计算机技术—检测技术与自动化装置]