Hasan Özkaynak

In performance-based earthquake engineering (PBEE), fragility curves hold significant importance for a reliable risk assessment of the existing reinforced concrete (RC) structures. Fragility curves require numerous incremental nonlinear dynamic analyses, which are highly time-consuming and computationally intensive. However, predicting the fragility curve parameters of RC structures by a machine learning algorithm could effectively reduce this cost. In this study, machine learning (ML)-based numerical analyses were performed in order to predict the fragility curve parameters of the existing RC structures, considering rapidly observable structural parameters by street survey. The construction date, story number, plan irregularities, soft story, and damage states are the main variables that are considered in this study. Hence, a dataset comprising the results of 620 structural fragility analyses was compiled from the existing literature. Key fragility parameters, namely the median and standard deviation, are predicted using several machine learning algorithms, including Random Forest (RF), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), and Artificial Neural Networks (ANNs). The performance of the proposed models is evaluated using R², RMSE, and MAE metrics under a five-fold cross-validation scheme. Furthermore, nonlinear dynamic analyses are conducted on a representative set of structural models to validate the machine learning predictions. The results indicate that the ANN model achieves the highest predictive accuracy, followed by ensemble tree-based methods, demonstrating the capability of machine learning approaches to effectively capture complex nonlinear relationships between seismic input parameters and structural response. The proposed framework significantly reduces computational effort while maintaining reliable prediction accuracy, offering an efficient tool for seismic risk assessment and fragility estimation of existing structures.

Proportion and detailing reinforcement for all structural members to resist internal forces occurring during strong ground motion are among the main seismic design criteria for reinforced concrete (RC) frame systems. Preliminary design is a crucial step in order to reach a proper final design. However, this stage mainly depends on the experience and intuition of the practitioner. The main aim of this study is to apply a multicriteria decision-making tool, namely Analytical Hierarchy Process (AHP) in selecting the optimal design candidate. A total of 76 optimal designed models out of 3,074 code-compiled buildings were selected based on the considered criteria via AHP procedure. During the analysis, the influence of selected design parameters such as site conditions, strength, ductility, and construction material on the optimal seismic design of these structures are investigated. Findings contribute to the optimization of structural design for both performance and monetary efficiency, while reducing the negative environmental effects.

Ülkemiz sığ deprem etkilerinin yoğun olarak hissedildiği ve sismik aktivitenin yüksek olduğu bir coğrafyada yer almaktadır. Mevcut yapılarımızın azımsanmayacak bir bölümünün mühendislik hizmeti görmeden imal edilmiş olması nedeniyle geçmişte yaşadığımız depremler, büyük can ve mal kayıplarına sebep olmuştur. Şehirlerimizin deprem direncinin artırılması için etkili önlemler alınmadığı sürece ileriki yıllarda meydana gelebilecek muhtemel depremlerin de büyük zararlar vereceği ortadadır. Bu nedenle deprem güvenliği bilinmeyen yapılarımızın mevcut yapı stokundan ayıklanarak güncel durumlarının belirlenmesi ve deprem riskinin azaltılması için ivedilikle harekete geçilmesi gerekmektedir. Özellikle beklenen İstanbul depremi açısından 2000 yılı öncesi yapılmış yapıların deprem güvenliklerinin sorgulanması ve bu yapıların güçlendirilerek İstanbul’un deprem direncinin artırılması hususu ülkemiz geleceği açısından da büyük önem taşımaktadır. Geçtiğimiz yıllarda yaşadığımız acı tecrübelerden; 17 Ağustos 1999 Düzce depremi, 26 Eylül 2019 Silivri Depremi ve 06 Şubat 2023 Kahramanmaraş depremleri yakın tarihin en belirgin örnekleridir. Bu yazıda muhtemel İstanbul depremine hazırlık açısından önemli olan farklı güçlendirme teknikleri sunulmuştur. Söz konusu yöntemler insanların tahliyesine gerek kalmaması nedeniyle son derece rasyonel ve uygulanabilir nitelikte olduğu düşünülmektedir.

This paper presents the effects of fundamental member and loading parameters on total dissipated energy capacity of RC columns in quantitative way by using an experimental database. Specifically, concrete compressive strength, yield strength of reinforcing bars; shear span-to-depth ratio, reinforcement ratios; peak drift ratio, and axial load ratio, are considered as influencing factors. Pearson’s correlation coefficients are utilized as dependency indicators to construct a correlation matrix where the effect of each factor on dissipated energy level is quantified. Results show that the effective factors among selected features are peak drift ratio, transverse reinforcement volumetric ratios of a member, and yield strength of rebars whereas the most influencing factors are the first two.