Document Type : p
Authors
1
Department of Civil Engineering, Faculty of Engineering, Islamic Azad University, Shabestar Branch, Shabestar, Iran
2
Master of Earthquake Engineering,Department of Civil Engineering, Shabestar Branch, Islamic Azad University,Shabesta, Iran.
10.22124/jcr.2021.18016.1465
Abstract
Nowadays, intelligent methods inspired from nature are implemented to resolve complex problems, there are very popular too. The most common one is artificial neural network; they are capable to collect huge amount of complex information through experiments and tests. With increasing population and a rise in construction and also due to limited resources and consumable materials, demand for hot rolled earthquake-resistant materials in the construction industry has increased. The purpose of this research, by considering concrete mix design parameters as input, the Static neural network and Time-series modeling to predict the compressive strength of concrete will be used. Mixing fly ash and silica fume various designs with different percentages (1%, 5%, 7%, 10%, 12%, 15%, 18%) and mixed with silica fume, fly ashes identical percentages (% 1% 1% 3 and 3%, 5% and 5%, 7% and 7%, 9% and 9%, 10% and 10%) as a percentage of the weight of cement, to evaluate the performance of the models in question were applied. It turned out that neural network models for predicting time series with 5 neurons performance concrete compressive strength is accurate and reliable.
Keywords
Main Subjects
)