Bibliographic citations
Villegas, M., (2019). Aplicación de redes neuronales para la predicción de la resistencia a la compresión del concreto según el ensayo de esclerometría [Tesis, Universidad Peruana de Ciencias Aplicadas (UPC)]. http://hdl.handle.net/10757/626504
Villegas, M., Aplicación de redes neuronales para la predicción de la resistencia a la compresión del concreto según el ensayo de esclerometría [Tesis]. PE: Universidad Peruana de Ciencias Aplicadas (UPC); 2019. http://hdl.handle.net/10757/626504
@misc{renati/369087,
title = "Aplicación de redes neuronales para la predicción de la resistencia a la compresión del concreto según el ensayo de esclerometría",
author = "Villegas Effio, Marcelo Alonso",
publisher = "Universidad Peruana de Ciencias Aplicadas (UPC)",
year = "2019"
}
The rebound number index is a result value of surface hardness´s test. This method is based on obtain concrete particular’s level. This characteristic has a direct relationship with the development of compressive strength, called f’c. So, if concrete particulars are more compact, it will increase mechanic strength and rebound number index´s value. The relationships between these tests have been studied over the years and it has been estimated high values of correlation, although without quantifying the influence of additional parameters that are not indifferent to the sclerometer test. In this research are analyzed the principal factors which affect surface hardness´s value and influent in the determination of mechanic strength of concrete. The factors studied are the water-cement ratio, humidity condition, age of concrete and maximum size of aggregate. These factors are analyzed in standardized concrete samples and the results obtained were processed statistically by artificial neuronal network’s methodology (RNA), this tool will predict results of compressive strength when other factors, which were explained, have been determinate. The results of this research show that the result of resistance to compression can be predicted with acceptable margin of error and that considering the influence factors in the prediction generates better accuracy in the results and reduction in the Pearson correlation index studied between the test of surface hardness and compressive strength.
This item is licensed under a Creative Commons License