An Image Processing System for Char Combustion Reactivity Characterisation

Deisy Chaves, Emanuele Trucco, Juan Barraza, Maria P. Trujillo

Research output: Contribution to journalArticle

Abstract

Coal is the most used fuel source to generate electricity by pulverised coal combustion. During this process, volatile compounds are liberated giving rise to the formation of a variety of char particles. Char particles morphology can be classified into groups reflecting different coal reactivity levels which may be used to evaluate the effect of coal on the performance of burner. Char particles morphological classification may be automatically done with benefits in terms of speed, consistency and accuracy. However, the classification performance relies on correct identification of char particles. Moreover, broken walls, created during char generation process, blurriness and low contrast are factors that make the classification task a challenging problem. In this paper, we propose a system for particle detection and particle classification into two reactive groups. Initially, a set of candidate regions, that may contain particles, is selected by combining regions and edges. Then, regions containing particles are detected using texture features and a Support Vector Machine classifier. The particle classification is done based on the International Commission for Coal Petrology criteria. Experiments using coals from two Colombian regions —Valle and Antioquia— showed that the proposed system, in most cases, correctly detect char particles. Regarding the classification of detected particles, analysed char samples were automatically classified similarly as manual classification did. Consequently, the system is found to be a successful first approach for char combustion reactivity characterisation.
Original languageEnglish
Pages (from-to)60-70
Number of pages11
JournalComputers in Industry
Volume106
Early online date3 Jan 2019
DOIs
Publication statusPublished - Apr 2019

Fingerprint

Image processing
Coal
Petrology
Coal combustion
Fuel burners
Support vector machines
Classifiers
Electricity
Textures
Experiments

Keywords

  • Candidate regions
  • Char coal morphology
  • Image processing
  • Machine learning
  • Particle classification
  • Particle detection

Cite this

Chaves, Deisy ; Trucco, Emanuele ; Barraza, Juan ; Trujillo, Maria P. / An Image Processing System for Char Combustion Reactivity Characterisation. In: Computers in Industry. 2019 ; Vol. 106. pp. 60-70.
@article{2b87e1fe837b42c68d1ad371cf8f11dc,
title = "An Image Processing System for Char Combustion Reactivity Characterisation",
abstract = "Coal is the most used fuel source to generate electricity by pulverised coal combustion. During this process, volatile compounds are liberated giving rise to the formation of a variety of char particles. Char particles morphology can be classified into groups reflecting different coal reactivity levels which may be used to evaluate the effect of coal on the performance of burner. Char particles morphological classification may be automatically done with benefits in terms of speed, consistency and accuracy. However, the classification performance relies on correct identification of char particles. Moreover, broken walls, created during char generation process, blurriness and low contrast are factors that make the classification task a challenging problem. In this paper, we propose a system for particle detection and particle classification into two reactive groups. Initially, a set of candidate regions, that may contain particles, is selected by combining regions and edges. Then, regions containing particles are detected using texture features and a Support Vector Machine classifier. The particle classification is done based on the International Commission for Coal Petrology criteria. Experiments using coals from two Colombian regions —Valle and Antioquia— showed that the proposed system, in most cases, correctly detect char particles. Regarding the classification of detected particles, analysed char samples were automatically classified similarly as manual classification did. Consequently, the system is found to be a successful first approach for char combustion reactivity characterisation.",
keywords = "Candidate regions, Char coal morphology, Image processing, Machine learning, Particle classification, Particle detection",
author = "Deisy Chaves and Emanuele Trucco and Juan Barraza and Trujillo, {Maria P.}",
note = "The scientific work was supported by COLCIENCIAS, Scholarship “Estudios de Doctorado en Colombia 2013 (Doctoral Studies in Colombia 2013)”. Also we would like to thank to “Carvajal Pulpa y Papel SAS” for providing the coal samples, and Edward Garcia and Victor Sanabria for preparing char-blocks and acquiring images.",
year = "2019",
month = "4",
doi = "10.1016/j.compind.2018.12.014",
language = "English",
volume = "106",
pages = "60--70",
journal = "Computers in Industry",
issn = "0166-3615",
publisher = "Elsevier BV",

}

An Image Processing System for Char Combustion Reactivity Characterisation. / Chaves, Deisy ; Trucco, Emanuele; Barraza, Juan ; Trujillo, Maria P.

In: Computers in Industry, Vol. 106, 04.2019, p. 60-70.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An Image Processing System for Char Combustion Reactivity Characterisation

AU - Chaves, Deisy

AU - Trucco, Emanuele

AU - Barraza, Juan

AU - Trujillo, Maria P.

N1 - The scientific work was supported by COLCIENCIAS, Scholarship “Estudios de Doctorado en Colombia 2013 (Doctoral Studies in Colombia 2013)”. Also we would like to thank to “Carvajal Pulpa y Papel SAS” for providing the coal samples, and Edward Garcia and Victor Sanabria for preparing char-blocks and acquiring images.

PY - 2019/4

Y1 - 2019/4

N2 - Coal is the most used fuel source to generate electricity by pulverised coal combustion. During this process, volatile compounds are liberated giving rise to the formation of a variety of char particles. Char particles morphology can be classified into groups reflecting different coal reactivity levels which may be used to evaluate the effect of coal on the performance of burner. Char particles morphological classification may be automatically done with benefits in terms of speed, consistency and accuracy. However, the classification performance relies on correct identification of char particles. Moreover, broken walls, created during char generation process, blurriness and low contrast are factors that make the classification task a challenging problem. In this paper, we propose a system for particle detection and particle classification into two reactive groups. Initially, a set of candidate regions, that may contain particles, is selected by combining regions and edges. Then, regions containing particles are detected using texture features and a Support Vector Machine classifier. The particle classification is done based on the International Commission for Coal Petrology criteria. Experiments using coals from two Colombian regions —Valle and Antioquia— showed that the proposed system, in most cases, correctly detect char particles. Regarding the classification of detected particles, analysed char samples were automatically classified similarly as manual classification did. Consequently, the system is found to be a successful first approach for char combustion reactivity characterisation.

AB - Coal is the most used fuel source to generate electricity by pulverised coal combustion. During this process, volatile compounds are liberated giving rise to the formation of a variety of char particles. Char particles morphology can be classified into groups reflecting different coal reactivity levels which may be used to evaluate the effect of coal on the performance of burner. Char particles morphological classification may be automatically done with benefits in terms of speed, consistency and accuracy. However, the classification performance relies on correct identification of char particles. Moreover, broken walls, created during char generation process, blurriness and low contrast are factors that make the classification task a challenging problem. In this paper, we propose a system for particle detection and particle classification into two reactive groups. Initially, a set of candidate regions, that may contain particles, is selected by combining regions and edges. Then, regions containing particles are detected using texture features and a Support Vector Machine classifier. The particle classification is done based on the International Commission for Coal Petrology criteria. Experiments using coals from two Colombian regions —Valle and Antioquia— showed that the proposed system, in most cases, correctly detect char particles. Regarding the classification of detected particles, analysed char samples were automatically classified similarly as manual classification did. Consequently, the system is found to be a successful first approach for char combustion reactivity characterisation.

KW - Candidate regions

KW - Char coal morphology

KW - Image processing

KW - Machine learning

KW - Particle classification

KW - Particle detection

UR - http://www.scopus.com/inward/record.url?scp=85059350896&partnerID=8YFLogxK

U2 - 10.1016/j.compind.2018.12.014

DO - 10.1016/j.compind.2018.12.014

M3 - Article

VL - 106

SP - 60

EP - 70

JO - Computers in Industry

JF - Computers in Industry

SN - 0166-3615

ER -