BETON DAYANIM ÖZELLİKLERİNİN YÜZEY TEPKİ YÖNTEMİ, GENETİK ALGORİTMA VE YAPAY SİNİR AĞLARI İLE TAHMİNİ
Loading...
Date
2022
Journal Title
Journal ISSN
Volume Title
Publisher
Süleyman Demirel Üniversitesi
Abstract
Bu çalışmada, beton dayanım özellikleri yüzey tepki yöntemi, genetik algoritma ve
yapay sinir ağları yöntemleri ile tahmin edilmiştir. Altı farklı beton agregası
kullanılarak küp (10x10x10 cm) ve prizmatik (15x15x60 cm) beton numuneleri
hazırlanmış ve beton tek eksenli basınç dayanımı (UCSc) ve eğilme dayanımının
(FSc) tahmin edilmesi için bazı modeller geliştirilmiştir. Geliştirilen modellerde
beton yoğunluğu (ρc), beton agregalarının Los Angeles aşınma kaybı (LAA) ve
betonlara ait P dalgası hızı (Vpc) gibi parametreler kullanılmıştır. Elde edilen
modellerin performansları bazı istatistiksel göstergeler ışığında değerlendirilmiş
olup genetik algoritma ve yapay sinir ağlarını temel alan yöntemlerin beton
dayanım özelliklerini tahmininde başarılı bir şekilde kullanılabileceği
belirlenmiştir.
In this study, concrete strength properties were estimated by surface response method, genetic algorithm, and artificial neural network methods. Cubic (10x10x10 cm) and prismatic (15x15x60 cm) concrete samples were prepared using six different concrete aggregates, and some models were developed to estimate the uniaxial compressive strength (UCSc) and flexural strength (FSc) of concrete. In the developed models, parameters such as concrete density (ρc), Los Angeles abrasion loss of concrete aggregates (LAA), and P wave velocity (Vpc) of concretes were used. The performances of the models obtained were evaluated in the light of some statistical indicators, and it was determined that methods based on genetic algorithms and artificial neural networks could be successfully used to estimate the concrete strength properties.
In this study, concrete strength properties were estimated by surface response method, genetic algorithm, and artificial neural network methods. Cubic (10x10x10 cm) and prismatic (15x15x60 cm) concrete samples were prepared using six different concrete aggregates, and some models were developed to estimate the uniaxial compressive strength (UCSc) and flexural strength (FSc) of concrete. In the developed models, parameters such as concrete density (ρc), Los Angeles abrasion loss of concrete aggregates (LAA), and P wave velocity (Vpc) of concretes were used. The performances of the models obtained were evaluated in the light of some statistical indicators, and it was determined that methods based on genetic algorithms and artificial neural networks could be successfully used to estimate the concrete strength properties.
Description
Keywords
Beton Dayanımı, Agrega, Yüzey Tepki Yöntemi, Genetik Algoritma, Yapay Sinir Ağları, Concrete Strength, Aggregate, Response Surface Methodology, Genetic Algorithm, Artificial Neural Networks
Turkish CoHE Thesis Center URL
Citation
WoS Q
Scopus Q
Source
Volume
10
Issue
2
Start Page
429
End Page
441