Deep Convolutional Neural Network for Structural Dynamic Response Estimation and System Identification

Abstract

This 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.