Citas bibligráficas
Castillo, M., Huaman, M. (2023). Propuesta de un modelo de red neuronal artificial para la predicción de desplazamiento máximo en columnas de grava en base a ensayos de carga estática [Tesis, Universidad Peruana de Ciencias Aplicadas (UPC)]. http://hdl.handle.net/10757/669247
Castillo, M., Huaman, M. Propuesta de un modelo de red neuronal artificial para la predicción de desplazamiento máximo en columnas de grava en base a ensayos de carga estática [Tesis]. PE: Universidad Peruana de Ciencias Aplicadas (UPC); 2023. http://hdl.handle.net/10757/669247
@misc{renati/407844,
title = "Propuesta de un modelo de red neuronal artificial para la predicción de desplazamiento máximo en columnas de grava en base a ensayos de carga estática",
author = "Huaman Valderrama, Mayra Alejandra",
publisher = "Universidad Peruana de Ciencias Aplicadas (UPC)",
year = "2023"
}
Artificial Neural Networks (ANN) have been developed in different fields of engineering, because they simulate the behavior of biological neurons, which allows them to adapt to any environment and solve different types of problems. In this thesis, the results of the static load test are used, which aims to test the design hypothesis and to know the real behavior of the stone column, obtaining a stress-strain graph of the behavior of the element. The resulting value of the static load test is the maximum displacement, which consists of applying the ultimate load to the stone column to produce the maximum displacement. The application of ANN in this field allows us to save time and costs. In the present thesis, a neural network model is applied to predict the maximum displacements that stone columns can have based on the static load tests that contain the geotechnical characteristics of the soil, characteristics of the stone columns and the resulting values of the same. For this purpose, information was requested from various projects where static load tests were performed to obtain real data and, subsequently, to train the ANN model correctly. In this way, to be able to predict the maximum displacement in stone columns using ANN with a difference of less than or equal to 20% with respect to the results of conventional static load tests, thus demonstrating an acceptable margin of error.
Este ítem está sujeto a una licencia Creative Commons Licencia Creative Commons