Detection of slight variations in combustion conditions with machine learning and computer vision

Compais, Pedro ; Arroyo, Jorge ; Castán-Lascorz, Miguel Ángel ; Barrio, Jorge ; Gil, Antonia (Universidad de Zaragoza)

Resumen: When monitoring combustion conditions, detecting minor variations, which may be complex even for the human eye, is critical for providing a fast response and correcting deviations. The aim of this study is to detect slight variations in combustion conditions by developing a flame monitoring system using machine learning and computer vision techniques applied to color images. Predictive models are developed for fuel blends with different heating values. The predictive models classify the combustion equivalence ratio based on multiple conditions, using a mean step size of 0.10 between states, a lower value than previously reported in related studies. Three machine learning algorithms are used for each fuel blend: logistic regression, support vector machine, and artificial neural network (multilayer perceptron). These models are fed the statistical, geometrical, and textural features extracted from the color images of the flames. The classification achieves accuracies from 0.78 to 0.97 in the detection of slight variations in the combustion conditions for all heating values. Thus, the monitoring system developed in this study is a promising alternative for implementation on an industrial scale and quick detection of changes in combustion conditions.

Idioma: Inglés

DOI: 10.1016/j.engappai.2023.106772

Año: 2023

Publicado en: ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 126 , Part A (2023), 106772 [11 pp.]
ISSN: 0952-1976

Factor impacto JCR: 7.5 (2023)

Categ. JCR: AUTOMATION & CONTROL SYSTEMS rank: 6 / 84 = 0.071 (2023) - Q1 - T1
Categ. JCR: ENGINEERING, MULTIDISCIPLINARY rank: 5 / 181 = 0.028 (2023) - Q1 - T1
Categ. JCR: ENGINEERING, ELECTRICAL & ELECTRONIC rank: 25 / 353 = 0.071 (2023) - Q1 - T1
Categ. JCR: COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE rank: 24 / 197 = 0.122 (2023) - Q1 - T1

Factor impacto CITESCORE: 9.6 - Control and Systems Engineering (Q1) - Electrical and Electronic Engineering (Q1) - Artificial Intelligence (Q1)

Factor impacto SCIMAGO: 1.749 - Artificial Intelligence (Q1) - Control and Systems Engineering (Q1) - Electrical and Electronic Engineering (Q1)

Financiación: info:eu-repo/grantAgreement/EC/H2020/820771/EU/ Boosting new Approaches for flexibility Management By Optimizing process Off-gas and waste use/BAMBOO
Financiación: info:eu-repo/grantAgreement/EC/H2020/869939/EU/Implementation of a smart RETROfitting framework in the process industry towards its operation with variable, biobased and circular FEEDstock/RETROFEED

Tipo y forma: Artículo (Versión definitiva)

Área (Departamento): Área Máquinas y Motores Térmi. (Dpto. Ingeniería Mecánica)