基于多层域适应的无标签数据故障诊断方法  

Unlabeled data fault diagnosis method based on multi-domain adaptation

作　　者：王进花[1] 刘瑞 曹洁[1,2] WANG Jinhua;LIU Rui;CAO Jie(College of Electrical and Information Engineering,Lanzhou University of Technology,Lanzhou 730050,China;Gansu Manufacturing Information Engineering Research Center,Lanzhou 730050,China)

机构地区：[1]兰州理工大学电气工程与信息工程学院,兰州730050 [2]甘肃省制造信息工程研究中心,兰州730050

出　　处：《北京航空航天大学学报》2025年第4期1185-1194,共10页Journal of Beijing University of Aeronautics and Astronautics

基　　金：国家重点研发计划(2020YFB1713600);国家自然科学基金(62063020);甘肃省自然科学基金(20JR5RA463)。

摘　　要：在工业生产中,由于源域数据和目标域数据分布有差异且有标签的故障数据量较少,以至于现有的域适应轴承故障诊断方法大多精度不高。基于此,提出多层域适应神经网络(MDANN)故障诊断方法,用于无标签数据的滚动轴承故障诊断。使用小波包分解与重构(WPT)对原始振动信号进行处理,以降低信号冗余并避免关键信号特征遗失;利用多核最大均值差异(MKMMD)算法对输入特征值进行差异计算,并通过反向传播更新多层域适应神经网络的参数,使其能够提取域不变特征;为保证无标签目标域数据可以正常参与网络训练,使用最大概率标签作为真实标签的伪标签策略,解决目标域无标签数据无法训练问题,增强模型可靠诊断知识的获取。采用2个公开数据集CWRU和PU进行验证。实验结果表明:所提方法与常见的域适应方法对比具有更高的诊断精度,说明该方法能够有效地学习可迁移特征,拟合2个数据集之间的数据分布差异。in industrial production,due to the difference in the distribution of source domain data and target domain data and the small amount of labeled fault data,the accuracy of domain adaptation-based bearing fault diagnosis algorithms proposed in the past is generally not high.In view of this,the multi-domain adaptation neural network(MDANN)fault diagnosis method was proposed in this paper,which was used for rolling bearing fault diagnosis without labeled data.Firstly,the original vibration signal was processed by using wavelet packet transformation(WPT)to reduce signal redundancy and avoid the loss of key signal features.Secondly,the multikernel maximum mean discrepancy(MK-MMD)algorithm was used to calculate the difference of input eigenvalues,and the network parameters of MDANN were updated by backpropagation so that the network can extract domain invariant features.Finally,in order to ensure that unlabeled target domain data can participate in network training normally,the maximum probability label was used as a pseudo-label strategy of the real label to solve the problem that unlabeled target domain data cannot be trained and enhance the acquisition of reliable diagnosis knowledge of the model.Two publicly available datasets,CWRU and PU,were used for validation.The experimental results show that the proposed method has higher diagnosis accuracy compared with common domain adaptation methods,which further shows that the method can effectively learn the transferable features and fit the discrepancy in data distribution between the two datasets.

关 键 词：滚动轴承 故障诊断 迁移学习 多层域适应 伪标签策略 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置] TD453[自动化与计算机技术—控制科学与工程]