Neural networks analysis of compressive strength of lightweight concrete after high temperatures

Autor:	Ahmet Tortum, Rüstem Gül, A. Ferhat Bingöl
Rok vydání:	2013
Předmět:	Structural material Compressive strength Aggregate (composite) Materials science Artificial neural network Pumice Geotechnical engineering Strength loss Composite material
Zdroj:	Materials & Design (1980-2015). 52:258-264
ISSN:	0261-3069
DOI:	10.1016/j.matdes.2013.05.022
Popis:	When concrete, one of the most important structural materials, is exposed to elevated temperatures generally strength loss is observed. Decrease ratio in the compressive strength depends on many materials and experimental factors. An artificial neural network (ANN) approach was used to model the compressive strength of lightweight and semi lightweight concretes with pumice aggregate subjected to high temperatures. Model inputs were the target temperature, pumice aggregate ratio and heating duration and the output was the compressive strength of pumice aggregate concrete. Data on the compressive strength of pumice aggregate concrete after the effects of high temperatures was obtained from a previous experimental study. The predicted values of the ANN are in accordance with the experimental data. The results indicate that the model can predict the compressive strength with adequate accuracy.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::8a41b719503d5725cb8809fa207620e5 https://doi.org/10.1016/j.matdes.2013.05.022 Zobrazit plný text záznamu Full Text from ScienceDirect