基于改进EfficientNet模型的轻量化滚动轴承故障诊断方法  

A lightweight rolling bearing fault diagnosis method based on improved EfficientNet model

作　　者：戴莹钰 李靖超[1] 赵莹[1] 刘艳丽 王申华 张斌 DAI Yingyu;LI Jingchao;ZHAO Ying;LIU Yanli;WANG Shenhua;ZHANG Bin(School of Electronic and Information Engineering,Shanghai Dianji University,Shanghai 201306,CHN;Wuyi County Power Supply Company,State Grid Zhejiang Electric Power Co.,Ltd.,Jinhua 321200,CHN;Kanagawa University,Yokohama 2218686,JPN)

机构地区：[1]上海电机学院电子信息学院,上海201306 [2]国网浙江省电力有限公司武义县供电公司,浙江金华321200 [3]日本神奈川大学,横滨2218686

出　　处：《制造技术与机床》2024年第9期9-15,共7页Manufacturing Technology & Machine Tool

基　　金：国家自然科学基金面上基金项目(62076160);上海市自然科学基金面上项目(21ZR1424700);上海市青年科技启明星项目(23QA1403800)。

摘　　要：相比依赖于人工分析且无法充分提取信号中丰富信息的传统故障诊断方法,采用深度学习模型可以取得更理想的识别效果,但依然存在所使用的模型参数量大、计算成本高的问题。文章提出一种将格拉姆角场(gramian angular field,GAF)编码方式与改进的EfficientNet-B0模型相结合的方法进行轴承的故障诊断。首先,一维轴承信号经过格拉姆角场编码为二维时序图像;其次,将二维图像输入引入注意力机制CBAM模块的EfficientNet-B0模型中自动进行特征提取和分类识别;最后,在仿真试验环节使用凯斯西储大学与德国帕德博恩大学的轴承数据集,基于格拉姆角场与EfficientNet-B0-CBAM模型的诊断方法对轴承故障的识别准确率分别可达到99.90%和98.04%,可以得出所提出的方法在保持模型轻量化特点的基础上拥有更高的识别准确率和更好的泛化能力。Compared to traditional fault diagnosis methods that rely on manual analysis and cannot fully extract the rich information within signals,deep learning models can achieve more ideal recognition results.However,these models often suffer from large parameter sizes and high computational costs.This paper proposes a method combining the gramian angular field(GAF)encoding technique with an improved EfficientNet-B0 model for bearing fault diagnosis.Firstly,the one-dimensional bearing signal is encoded into a two-dimensional time-series image using the GAF method.Secondly,the twodimensional image is input into the EfficientNet-B0 model,which incorporates the CBAM attention mechanism,for automatic feature extraction and classification.Finally,in the simulation experiments,bearing datasets from Case Western Reserve University and Paderborn University in Germany were used.The diagnostic method based on the GAF and EfficientNet-B0-CBAM model achieved recognition accuracies of 99.90%and 98.04%for bearing faults,respectively.It can be concluded that the proposed method maintains the lightweight characteristics of the model while achieving higher recognition accuracy and better generalization capability.

关 键 词：智能故障诊断 格拉姆角场 轻量化卷积神经网络 EfficientNet-B0 注意力机制 CBAM 

分 类 号：TH133.33[机械工程—机械制造及自动化]