基于小波时频图与MobileViT的滚动轴承故障诊断方法  

A fault diagnosis method of rolling bearing based on wavelet time-frequency diagram and MobileViT

作　　者：马坤 刘广璞[1] 黄晋英[1] 强浩垚 Ma Kun;Liu Guangpu;Huang Jinying;Qiang Haoyao(School of Mechanical Engineering,North University of China,Shanxi Taiyuan,030051,China;Military Representative Office of Army Equipment Department,Beijing,100072,China)

机构地区：[1]中北大学机械工程学院,山西太原030051 [2]陆军装备部驻北京某军代室,北京100072

出　　处：《机械设计与制造工程》2025年第3期93-98,共6页Machine Design and Manufacturing Engineering

基　　金：山西省创新项目(2023KY600)。

摘　　要：为解决现有滚动轴承故障诊断方法无法兼顾高准确率与实时性的问题,提出了一种基于小波时频图与MobileViT的滚动轴承故障诊断方法。该方法通过连续小波变换将原始信号表示为小波时频图,然后将小波时频图作为特征图输入到MobileViT进行训练,实现滚动轴承故障状态识别。实验结果表明,与对比方法相比,该方法在公开数据集中的故障诊断率达到100%,且具有更少的参数量与计算量,具有工程应用价值。In order to solve the problem that the existing fault diagnosis methods of rolling bearings cannot take into account both high accuracy and real-time,a fault diagnosis method of rolling bearings based on wavelet time-frequency graph and MobileViT is proposed.In this method,the original signal is represented as a wavelet time-frequency graph by continuous wavelet transform,and then the wavelet time-frequency graph is input to MobileViT as a feature graph for training,and the fault state recognition of rolling bearings is realized.The experimental results show that,compared with the comparison method,the proposed method has a fault diagnosis rate of 100%in the open data set and less parameters and calculation,so it has engineering application value.

关 键 词：滚动轴承 故障诊断 连续小波变换 小波时频图 MobileViT 

分 类 号：TH133.33[机械工程—机械制造及自动化] TP18[自动化与计算机技术—控制理论与控制工程]