Examinando por Autor "Balladares, Eduardo"

Mostrando 1 - 2 de 2
  • Miniatura
    Ítem
    Kinetic aspects on ferric arsenate formation in a fix bed gas-solid reaction system
    (Universidad Nacional de Colombia, 2015) Balladares, Eduardo; Parra, Roberto; Sánchez, Mario
    The fixation of arsenic contained in gases produced during pyrometallurgical processes by using solid ferric oxide was studied in the range 873-1073 K under different oxygen potential and solid aggregates porosities. Arsenic fixation on solid iron oxides is described by the pore blocking model under the studied conditions. The solid product of the reaction has a molar volume 3 times larger than the solid reactant causing fast decreasing of the inter-granular spacing. The activation energies of arsenic fixation reaction are 34.96 and 35.46 kJ/mol for porosities of 0.88 and 0.74 respectively, and for porosity of 0.55 the activation energy was 26.88 kJ/mol. These values of activation energy show that intra-pellets diffusion has an effect only in samples with 0.55 porosity. Minor sintering of particles was detected. Industrial application of the concept demands a reaction system, which in is required better gas-solid contact for attaining larger conversions. © The author; licensee Universidad Nacional de Colombia.
  • No hay miniatura disponible
    Ítem
    Machine Learning-Based Classification of Sulfide Mineral Spectral Emission in High Temperature Processes
    (Multidisciplinary Digital Publishing Institute (MDPI), 0025) Toro, Carlos; Díaz, Walter; Reyes, Gonzalo; Peña, Miguel; Caselli, Nicolás; Taramasco, Carla; Ormeño-Arriagada, Pablo; Balladares, Eduardo
    Accurate classification of sulfide minerals during combustion is essential for optimizing pyrometallurgical processes such as flash smelting, where efficient combustion impacts resource utilization, energy efficiency, and emission control. This study presents a deep learning-based approach for classifying visible and near-infrared (VIS-NIR) emission spectra from the combustion of high-grade sulfide minerals. A one-dimensional convolutional neural network (1D-CNN) was developed and trained on experimentally acquired spectral data, achieving a balanced accuracy score of 99.0% in a test set. The optimized deep learning model outperformed conventional machine learning methods, highlighting the effectiveness of deep learning for spectral analysis in high-temperature environments. In addition, Gradient-weighted Class Activation Mapping (Grad-CAM) was applied to enhance model interpretability and identify key spectral regions contributing to classification decisions. The results demonstrated that the model successfully distinguished spectral features associated with different mineral species, offering insights into combustion dynamics. These findings support the potential integration of deep learning for real-time spectral monitoring in industrial flash smelting operations, thereby enabling more precise process control and decision-making. © 2025 by the authors.