This paper presents a new approach for automatical classification of structural state through deep learning.In this work,a Convolutional Neural Network (CNN) was designed to fuse both the feature extraction and classification blocks into an intelligent and compact learning system and detect the structural state of a steel frame;the input was a series of vibration signals,and the output was a structural state.The digital image correlation (DIC)technology was utilized to collect vibration information of an actual steel frame,and subsequently,the raw signals,without further pre-processing,were directly utilized as the CNN samples.The results show that CNN can achieve 99％classification accuracy for the research model.Besides,compared with the backpropagation neural network (BPNN),the CNN had an accuracy similar to that of the BPNN,but it only consumes 19％ of the training time.The outputs of the convolution and pooling layers were visually displayed and discussed as well.It is demonstrated that:1) the CNN can extract the structural state information from the vibration signals and classify them;2) the detection and computational performance of the CNN for the incomplete data are better than that of the BPNN;3) the CNN has better anti-noise ability.

School of Civil and Transportation Engineering,Guangdong University of Technology,Guangzhou 510006,China;Earthquake Engineering Research & Test Center,Guangzhou University,Guangzhou 510405,China;Guangzhou Municipal Engineering Testing Co.,Ltd.,Guangzhou 510520,China

[1]Shuai TENG;Gongfa CHEN;Shaodi WANG;Jiqiao ZHANG;Xiaoli SUN-.Digital image correlation-based structural state detection through deep learning)[J].结构与土木工程前沿,2022(01):45-56

automatical

Digital,image,correlation,structural,state,detection,through,deep,learning,This,paper,presents,new,approach,classification,In,this,Convolutional,Neural,Network,was,designed,fuse,both,feature,extraction,blocks,into,intelligent,compact,system,steel,frame,input,series,vibration,signals,digital,DIC,technology,utilized,collect,information,actual,subsequently,raw,without,further,processing,were,directly,samples,results,show,that,can,achieve,accuracy,research,model,Besides,compared,backpropagation,neural,network,BPNN,had,similar,but,only,consumes,training,outputs,convolution,pooling,layers,visually,displayed,discussed,well,It,demonstrated,from,classify,them,computational,performance,incomplete,data,better,than,has,anti,noise,ability

0.552277