基于ResNet50-CBAM模型的滾動(dòng)軸承故障診斷研究

打開文本圖片集

中圖分類號(hào)：TP18 文獻(xiàn)標(biāo)志碼：A 文章編號(hào)：2095-2945（2025）19-0001-04

Abstract：Aimingattheshortcomingsintraditionalrollingbearingfaultsignalfeatureextraction，arollingbearingfault diagnosismethodbasedonConvolutionalBlockAtentionModule（CBAM）andresidualnetwork（ResNet5O）isproposed.Thefault signalsintheCaseWesternReserveUniversitydatasetwererandomlyandlocalloverlappedsampled，andthebearingfault signalswereconvertedintotwo-dimensionaltime-frequencydomainimagesusingICEEMDANandHilbert.Thetime-frequency domainimagesweretheninputintotheResNet5O-CBAMnetworkmodel.，trainingandtestingtheaccuracyofthemodel. Convolutionalneuralnetworksandtransferlearningareaddedtothenetworkmodeltosolvetheproblemsofdificultyindata acquisitionandlongtraining time.ExperimentshaveprovedthatResNet5O-CBAMhasstrong faultfeatureextractioncapablities. Compared with other network models，the accuracy rate is 8%～15% higher. Finally，rolling bearing signals are collected on a servosystemexperimentalsimulationplatform，andtheimprovednetworkmodelisusedfordiagnosis.Theresultsprovethatthis diagnosis method has high accuracy in rolling bearing fault diagnosis.

Keywords： rolling bearing; fault diagnosis; ResNet5O-CBAM; network model; data

滾動(dòng)軸承作為設(shè)備隨動(dòng)系統(tǒng)中重要的組件，主要承擔(dān)支撐和旋轉(zhuǎn)的功能，可降低設(shè)備傳動(dòng)軸與支撐部位的摩擦力，同時(shí)為傳動(dòng)軸的軸承提供支撐。（剩余4739字）