Publications
2018
1.
Chaves, Deisy; Robles, Laura Fernández; Bernal, Jose; Alegre, Enrique; Trujillo, Maria
Automatic characterisation of chars from the combustion of pulverised coals using machine vision Artículo de revista
En: Powder technology, vol. 338, pp. 110–118, 2018, (Publisher: Elsevier).
Resumen | Enlaces | BibTeX | Etiquetas: char morphology, coal combustion, machine vision, reactivity classification
@article{chaves_automatic_2018,
title = {Automatic characterisation of chars from the combustion of pulverised coals using machine vision},
author = {Deisy Chaves and Laura Fernández Robles and Jose Bernal and Enrique Alegre and Maria Trujillo},
url = {https://www.sciencedirect.com/science/article/pii/S0032591018304753},
year = {2018},
date = {2018-01-01},
journal = {Powder technology},
volume = {338},
pages = {110–118},
abstract = {This paper presents a method for automatically characterizing char particles produced during pulverized coal combustion using machine vision. The study combines two approaches: morphological analysis and intensity distribution through texture features. By using bit-plane slicing, the method captures both fine and rough details of the char particles. The particles are then classified based on their reactivity (high, medium, or low). Tested on char images from Colombian coal regions, the method achieves precision comparable to manual analysis, offering a more efficient, automated solution for evaluating coal reactivity.},
note = {Publisher: Elsevier},
keywords = {char morphology, coal combustion, machine vision, reactivity classification},
pubstate = {published},
tppubtype = {article}
}
This paper presents a method for automatically characterizing char particles produced during pulverized coal combustion using machine vision. The study combines two approaches: morphological analysis and intensity distribution through texture features. By using bit-plane slicing, the method captures both fine and rough details of the char particles. The particles are then classified based on their reactivity (high, medium, or low). Tested on char images from Colombian coal regions, the method achieves precision comparable to manual analysis, offering a more efficient, automated solution for evaluating coal reactivity.