Title: A review on the artificial neural network approach to analysis and prediction of seismic damage in infrastructure

Authors: Manouchehr Shokri; Kian Tavakoli

Addresses: Faculty of Civil engineering, Department of Transportation and Highway, University Teknologi Malaysia, Johor, Malaysia ' Faculty of Computer Science Information Technology, Asia Pacific University, Kuala Lumpur, Malaysia

Abstract: Machine learning has been the focus of attention in recent decades, and the influence of the artificial neural networks (ANN) is notable as the most extensively used models of machine learning in the assessment of infrastructures. This paper presents the state of the art of analysis and prediction of seismic damage in infrastructure. The survey demonstrates that ANNs are the essential tools for predicting damage detection of seismic performances of RC bridges. It was also shown that efficiency stresses of the reinforcements are one of the important sources of uncertainty in fragility analysis of RC bridges. It is evident from this evaluation that ANNs have been successfully applied to many infrastructure engineering areas like prediction, risk analysis, decision-making, resources optimisation, classification, and selection.

Keywords: seismic evaluation; dynamic analysis; RC bridge; artificial neural network; ANN; finite element model; FEM; deep learning; damage detection.

DOI: 10.1504/IJHM.2019.104386

International Journal of Hydromechatronics, 2019 Vol.2 No.4, pp.178 - 196

Received: 30 Jul 2019
Accepted: 24 Sep 2019

Published online: 06 Jan 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article