Earthquake Hazard Safety Assessment of Existing Buildings Using Optimized Multi-Layer Perceptron Neural Network

Ehsan Harirchian,Shahla Rasulzade,Tom Lahmer

doi:10.3390/en13082060

Ehsan Harirchian, Shahla Rasulzade + Show 1 more

Open Access

https://doi.org/10.3390/en13082060

Copy DOI

Journal: Energies	Publication Date: Apr 20, 2020
Citations: 32	License type: CC BY 4.0

Affiliation: Bauhaus-Universität Weimar, University of Kassel

Abstract

The latest earthquakes have proven that several existing buildings, particularly in developing countries, are not secured from damages of earthquake. A variety of statistical and machine-learning approaches have been proposed to identify vulnerable buildings for the prioritization of retrofitting. The present work aims to investigate earthquake susceptibility through the combination of six building performance variables that can be used to obtain an optimal prediction of the damage state of reinforced concrete buildings using artificial neural network (ANN). In this regard, a multi-layer perceptron network is trained and optimized using a database of 484 damaged buildings from the Düzce earthquake in Turkey. The results demonstrate the feasibility and effectiveness of the selected ANN approach to classify concrete structural damage that can be used as a preliminary assessment technique to identify vulnerable buildings in disaster risk-management programs.

Highlights

In civil engineering, reinforced concrete (RC) is considered to be one of the most frequently used building components that has a significant character in building structure
Six input variables considered in this dataset, which are Minimum Normalized Lateral Strength Index (MNLSI), Minimum Normalized Lateral Stiffness Index (MNLSTFI), OVR, RNS, Soft Story Index (SSI), and Number of Stories, as described beforehand
Though most of the fast-growing city expenditures were typically situated in seismic-prone areas throughout recent decades, seismic threat-sensitive urban planning and seismic-resistant building was not the maximum priority during this evolution stage

Summary

Introduction

In civil engineering, reinforced concrete (RC) is considered to be one of the most frequently used building components that has a significant character in building structure. The majority of existing buildings in seismic regions do not satisfy modern design code requirements and need to be upgraded to an appropriate level. There are many methods available for seismic assessment of structures, which involve detailed structural analysis and design [2,3]. These detailed assessment methods consume more time when the assessment must be performed for many buildings [4]. Seismic vulnerability assessment of reinforced concrete buildings using hierarchical fuzzy rule base modeling. Rapid visual earthquake hazard evaluation of existing buildings by fuzzy logic modeling.

Methods

Results

Conclusion