Browsing by Autor "D. Sierra-Porta"

Now showing 1 - 3 of 3

Efficient improvement for the estimation of the surface of free energy asphalt binder using Machine Learning tools
(2021) D. Sierra-Porta
"The Surface Free Energy (SFE) of a material is defined as the energy needed to create a new surface unit under vacuum conditions. This property is directly related to the resistance to fracture and recovery of material and the ability to create strong adhesion with other materials. This value can be used as a complementary parameter for the selection and optimal combination of materials for asphalt mixtures, as well as in the micromechanical modeling of fracture and recovery processes of said mixtures. This document describes the results of the implementation of the use of machine learning and Random Forest prediction techniques for the estimation of surface free energy based on data from previous studies. The experimental samples were twenty-three asphalt binders used in a Strategic Highway Research Program (SHRP). A decrease of 54% and 82% in the mean absolute error (MAE) and the mean square error (MSE), respectively was found for the new model built. While the model fits better with a 12% improvement, according to the adjusted determination coefficient, the accuracy and the score of the model also increases notably in 2% and 55%, respectively."
Mejora eficiente para la estimación de la energía libre superficial del ligante asfáltico mediante herramientas de Machine Learning
(Industrial University of Santander, 2021) D. Sierra-Porta
The Surface Free Energy (SFE) of a material is defined as the energy needed to create a new surface unit under vacuum conditions. This property is directly related to the resistance to fracture and recovery of material and the ability to create strong adhesion with other materials. This value can be used as a complementary parameter for the selection and optimal combination of materials for asphalt mixtures, as well as in the micromechanical modelingof fracture and recovery processes of said mixtures. This document describes the results of the implementation of the use of machine learning and Random Forest prediction techniques for the estimation of surface free energy based on data from previous studies. The experimental samples were twenty-three asphalt binders used in a Strategic Highway Research Program (SHRP). A decrease of 54% and 82% in the mean absolute error (MAE) and the mean square error (MSE), respectively was found for the new model built. While the model fits better with a 12% improvement, according to the adjusted determination coefficient, the accuracy and the score of the model also increases notably in 2% and 55%, respectively.
Muography in Colombia: Simulation Framework, Instrumentation, and Data Analysis
(2022) J. Pe ̃na-Rodr ́ıguez; A. Vesga-Ram ́ırez; A. V ́asquez-Ram ́ırez; Ming An; R. de Le ́on-Barrios; D. Sierra-Porta; R. Calder ́on-Ardila; J. Pisco-Guavabe; H. Asorey; J. D. Sanabria-G ́omez
We present the Colombo-Argentinian Muography Program for studying inland Latin American volcanoes. It describes the implementation of a simulation framework covering various factors with different spatial and time scales: the geomagnetic effects at a particular geographic point, the development of extensive air showers in the atmosphere, the propagation through the scanned structure, and the detector response. Next, we sketch the criteria adopted for designing, building, and commissioning MuTe: a hybrid Muon Telescope based on a composite detection technique. It combines a hodoscope for particle tracking and a water Cherenkov detector to enhance the muon-to-background-signal separation due to extensive air showers' soft and multiple-particle components. MuTe also discriminates inverse-trajectory and lowmomentum muons by using a picosecond Time-of-Flight system. We also characterize the instrument's structural-mechanical and thermal-behavior, discussing preliminary results from the background composition and the telescope-health monitoring variables. Finally, we discuss the implementations of an optimization algorithm to improve the volcano internal density distribution estimation and machine learning techniques for background rejection.