Show simple item record

contributor authorRih-Teng Wu; Mohammad R. Jahanshahi
date accessioned2019-03-10T12:05:29Z
date available2019-03-10T12:05:29Z
date issued2019
identifier other%28ASCE%29EM.1943-7889.0001556.pdf
identifier urihttp://yetl.yabesh.ir/yetl1/handle/yetl/4254838
description abstractThis study presents a deep convolutional neural network (CNN)-based approach to estimate the dynamic response of a linear single-degree-of-freedom (SDOF) system, a nonlinear SDOF system, and a full-scale 3-story multidegree of freedom (MDOF) steel frame. In the MDOF system, roof acceleration is estimated through the input ground motion. Various cases of noise-contaminated signals are considered in this study, and the conventional multilayer perceptron (MLP) algorithm serves as a reference for the proposed CNN approach. According to the results from numerical simulations and experimental data, the proposed CNN approach is able to predict the structural responses accurately, and it is more robust against noisy data compared with the MLP algorithm. Moreover, the physical interpretation of CNN model is discussed in the context of structural dynamics. It is demonstrated that in some special cases, the convolution kernel has the capability of approximating the numerical integration operator, and the convolution layers attempt to extract the dominant frequency signature observed in the ideal target signal while eliminating irrelevant information during the training process.
publisherAmerican Society of Civil Engineers
titleDeep Convolutional Neural Network for Structural Dynamic Response Estimation and System Identification
typeJournal Paper
journal volume145
journal issue1
journal titleJournal of Engineering Mechanics
identifier doi10.1061/(ASCE)EM.1943-7889.0001556
page04018125
treeJournal of Engineering Mechanics:;2019:;Volume ( 145 ):;issue: 001
contenttypeFulltext


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record