|
EMU I-REP >
02 Faculty of Engineering >
Department of Civil Engineering >
Theses (Master's and Ph.D) – Civil Engineering >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11129/6116
|
Title: | Seismic Performance Assessment of Reinforced Concrete Building Stock Using Artificial Neural Network and Linear Regression Analysis |
Authors: | Özay, Giray (Supervisor) Karayel, Oğuz Eastern Mediterranean University, Faculty of Engineering, Dept. of Civil Engineering |
Keywords: | Civil Engineering Department Earthquake resistant design Earthquake resistant design--Concrete construction--Reinforced concrete Buildings--Earthquake effects Reinforced concrete--Reinforced concrete construction ANN, TBEC2018, Pushover, Performance |
Issue Date: | Jan-2020 |
Publisher: | Eastern Mediterranean University (EMU) - Doğu Akdeniz Üniversitesi (DAÜ) |
Citation: | Karayel, Oğuz. (2020). Seismic Performance Assessment of Reinforced Concrete Building Stock Using Artificial Neural Network and Linear Regression Analysis. Thesis (M.S.), Eastern Mediterranean University, Institute of Graduate Studies and Research, Dept. of Civil Engineering, Famagusta: North Cyprus. |
Abstract: | Istanbul is located on extensive piece of land which is susceptible by seismic activity.
In the last half century, Turkish earthquake codes for designing building under
earthquake loads went through many modifications and editions (TEC1975, TEC1997,
TEC2007, and TBEC2018). Hence, there are many buildings existing that has been
built in accordance with old regulations since improvements in the recent earthquake
code. Therefore, the need of a quick assessment method to identify the building
seismic performance level in accordance with the latest seismic code is extremely vital.
For this purpose, this research is aiming to prepare a database for the quick estimation
on building seismic performance by constructing an artificial neural network model
that is capable of this, relating building material properties, geometry, designed
standard, site class, and peak ground acceleration to the building seismic performance
levels. In order to meet these objectives, 540 reinforced concrete building models with
various parameters are modeled with respect to TEC1975, TEC1997, TEC2007,
TBEC2018 and seismic performance obtained from the analysis in accordance with
TBEC2018. Data obtained are used to train and validate the constructed artificial
neural network (ANN) model. Also, several training algorithms performed with
various number of hidden layers and comparison between them is discussed in order
to figure out the optimum number of hidden layers and best train method which gives
the highest accuracy of prediction for the performance assessment of the buildings.
Since the artificial neural network model created for the performance level estimation
of the existing buildings, validity of the created model is checked by the application
through the existing buildings as a case study with various parameters within the range
of considerations according to the existing study. The data obtained from the analysis
is used to perform multiple linear regression analysis (MVLRA) as well. Results
indicate that ANN can be a very profound technique in predicting the seismic
performance levels with a determination coefficient (R2
) of 0.8786. Furthermore,
identification of the significance of the predictor variables according to their effect on
seismic assessment have been done with several methods which are widely used in
literature as well. ÖZ:
Istanbul deprem hareketleri ile kritik durumda bulunan büyük bir bölgedir. Bu
bağlamda son zamanlarda depreme dayanıklı yapı tasarımı konusunda birçok
araştırma ve geliştirmelerle birlikte Türk Deprem Yönetmelikleri tasarlanmıştır. Buna
rağmen, farklı tasarım ve yaklaşım öngörüleriyle önceden inşa edilmiş birçok mevcut
yapı bulunmaktadır. Bu doğrultuda, yapıların yeni deprem yönetmeliğine göre yapı
performans seviyesinin belirlenmesi adına hızlı değerlendirme yönteminin
geliştirilmesi hayati bir ihtiyaç haline gelmiştir. Bu çalışmanın amacı yapay sinir ağı
modeli ile binaların farklı malzeme özellikleri, geometrisi, tasarım yönetmeliği, zemin
çeşidi, yer ivmesine göre bina performans seviyesi hakkında hızlı değerlendime
metodu geliştirmektir. Bu bağlamda, TDY1975, TDY1997, TDY2007 ve TBDY2018
kullanılarak belirtilen farklı parametreler doğrultusunda 540 betonarme bina
modellenmiş ve TBDY2018 ile bina performans analizi yapılmıştır. Analizlerden elde
edilen veriler yapay sinir ağı modeli öğretiminde ve doğrulamasında kullanılmıştır.
Buna ek olarak, yapay sinir ağı farklı öğrenim algoritmaları ile modellenip en doğru
performans tahmini elde edilen öğrenim algoritması ile çalışan yapay sinir ağı modeli
belirlenmiştir. Analizden elde edilen veriler ile doğrusal regresyon analizi de
yapılmıştır. Sonuç olarak yapay sinir ağı modelinin doğruluk payı anlamında çok etkili
bir teknik olduğu ve modelin doğruluk oranı (R2
) 0.8786 olarak bulunmuştur. Buna ek
olarak, çalışmada kullanılan farklı parametrelerin performans seviyesinin
belirlenmesindeki etkisi bağlamında önem sırasına göre sıralanması adına literatür
araştırması ile yaygın olarak kullanıldığı belirlenen farklı metodlar uygulanılmıştır. |
Description: | Master of Science in Civil Engineering. Institute of Graduate Studies and Research. Thesis (M.S.) - Eastern Mediterranean University, Faculty of Engineering, Dept. of Civil Engineering, 2020. Supervisor: Assoc. Prof. Dr. Giray Özay. |
URI: | http://hdl.handle.net/11129/6116 |
Appears in Collections: | Theses (Master's and Ph.D) – Civil Engineering
|
This item is protected by original copyright
|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
|