预览加载中,请您耐心等待几秒...
1/3
2/3
3/3

在线预览结束,喜欢就下载吧,查找使用更方便

如果您无法下载资料,请参考说明:

1、部分资料下载需要金币,请确保您的账户上有足够的金币

2、已购买过的文档,再次下载不重复扣费

3、资料包下载后请先用软件解压,在使用对应软件打开

基于GA-BP神经网络的结构损伤位置识别 Abstract StructuredamagedetectionusingGA-BPneuralnetworkisapromisingapproachforidentifyingthelocationofstructuraldamage.Inthispaper,weproposeanovelapproachthatcombinesgeneticalgorithmandbackpropagationneuralnetworktoeffectivelyidentifythestructuraldamagelocation.Theproposedapproachistestedonareal-worldstructurewithsimulateddamage,andtheresultsdemonstratetheeffectivenessoftheproposedapproachindetectingthedamagelocation. Introduction Structuredamagecanhavesignificantimpactsonthesafetyandfunctionalityofcivilstructures.Therefore,itiscrucialtoidentifythelocationofstructuraldamagetopreventfailuresandensurethesafetyandreliabilityofstructures.Structuredamagedetectionmethodscanbebroadlycategorizedintotwogroups:model-basedanddata-drivenapproaches.Model-basedmethodsrelyonanalyticalmodelsofthestructure,whiledata-drivenmethodsusemeasuredresponsedatatoidentifythedamagelocation. Amongthedata-drivenmethods,neuralnetworkshavebeenwidelyusedtodetectstructuraldamage.Backpropagation(BP)neuralnetworkisoneofthemostpopularneuralnetworkalgorithmsbecauseofitssimplicityandeffectiveness.However,BPneuralnetworkhassomedisadvantages,suchasgettingtrappedinlocalminima,slowconvergence,anddifficultyindeterminingoptimalparameters.Toovercometheseproblems,geneticalgorithm(GA)techniquecanbeusedtooptimizetheparametersoftheBPneuralnetwork. Inthispaper,weproposeaGA-BPneuralnetworkapproachtodetectthelocationofstructuraldamage.TheGA-BPneuralnetworkcombinesGAandBPneuralnetworktooptimizetheparametersoftheneuralnetworkforbetterperformanceindamagedetection. Methodology TheGA-BPneuralnetworkapproachconsistsofthreemainsteps:preparingthedata,trainingtheneuralnetwork,andidentifyingthedamagelocation.Thedetailsofeachstepareasfollows: Preparingthedata:Thefirststepistocollectresponsedatafromthestructurebeforeandafterdamage.Inthisstudy,afiniteelementmodeliscreatedtosimulatethestructure,anddamageissimulatedbyreducingthestiffnessofcertainelementsinthestructure.Theresponsedataisobtainedbyperformingdynami