一種用于機(jī)器聲音異常檢測的ARViTrans方法

打開文本圖片集

doi：10.19734/j.issn.1001-3695.2024.10.0365

ARViTrans method for machine sound anomaly detection

ChenLonga，b，Guo Fabina，bt，Huang Xiaoweia，b，Lu Yashia，b （a.Schoolofifcaellgee&igtdslqpntStatesEaoFultredico&tee University，Hefei ，China）

Abstract：Inordertosolvetheproblems thattheexisting machine soundanomalydetection methodsonly focus onthe single featuresof the time，frequencyorchanneldimensions，ignoringthemutualconnectionbetweenthespectralfeaturesandthe timeseriesinformation，andtheinitial featurelossleads toinaccurate fitingof thesampledatadistribution，thuscausing a highanomaly mised detectionrateandfalse alarmrate，this paper proposedARViTrans，amachine sound anomalydetection methodthatintegratedatentionmechanismsandskipconnections.Firstlythispaperproposedathree-dimensionalicient coordinateatentionmechanismstocollaborativelycapturethetimedomain，frequencydomainandchanneldimensionfeatures through thedecouplingoperationofthefeaturespace.Secondly，itusedMobileViTasthebackbonenetworkanddesignedthe RES-MoViT module toreplacethe original MobileViT module.Skipconnections captured the information between the input andoutputand beterfitthesampledata distribution.Thegradientrefluxreduced therepeatedlearningof similarfeatureparametersandimprovedtheparameterutilizationeficiency.Finally，itcomparedtheexperimentalresultsontheMMdataset with the AE and MobileNetV2 of the DCASE Task2 baseline system. The AUC improves by 10.14% and 10.26% ，respectively.The pAUC improves by 13.40% and 6.50% ，respectively. The experimental results indicate that the proposed method caneffectivelycapturethemutualconnectionbetween featuresofdiferent dimensions while maintainingalowmodelcomplexity，improve the accuracy of anomaly detection and reduce the false alarm rate.

Key words：anomaly detection；MobileViT；attention mechanism；residual connection；unsupervise

0 引言

近年來，工業(yè)機(jī)器設(shè)備的狀態(tài)監(jiān)測在工廠自動化領(lǐng)域中發(fā)揮著至關(guān)重要的作用[1]。（剩余21819字）