Prediction of CO and HC emissions in Otto motors through neural networks

Ingenius. Revista de Ciencia y Tecnología

View Publication Info
 
 
Field Value
 
Title Prediction of CO and HC emissions in Otto motors through neural networks
Predicción de emisiones de CO y HC en motores Otto mediante redes neuronales
 
Creator León Japa, Rogelio Santiago
Maldonado Ortega, José Luis
Contreras Urgiles, Rafael Wilmer
 
Subject prediction, pollutant emissions, carbon monoxide (CO), non-combustion hydrocarbons (HC), diagnostics, neural networks
prediction
pollutant emissions
carbon monoxide (CO)
non-combustion hydrocarbons (HC)
diagnostics
neural networks
 
Description This paper explains the application of RNA (Artificial Neural Networks) for the prediction of pollutant emissions generated by mechanical failures in ignition engines, from which the percentage of CO (% Carbon Monoxide) and the particulate can be quantified. per million HC (ppm Unburned Hydrocarbons), through the study of the Otto cycle admission phase, which is recorded through the physical implementation of a MAP sensor (Manifold Absolute Pressure). A rigorous sampling protocol and consequent statistical analysis is applied. The selection and reduction of attributes of the MAP sensor signal is made based on the greater contribution of information and significant difference with the application of 3 statistical methods (ANOVA, correlation matrix and Random Forest), from which a base of data that allows the training of two neural networks feed-forward backpropagation, with which we obtain a classification error of 5.4061e-09 and 9.7587e-05  for the neural network of CO and HC respectively.
En el presente trabajo se explica la aplicación de RNA (redes neuronales artificiales) para la predicción de emisiones contaminantes generadas por fallas mecánicas en motores de encendido provocado, de la cual se puede cuantificar el porcentaje de CO (% monóxido de carbono) y el particulado por millón HC (ppm hidrocarburos sin quemar), a través del estudio de la fase de admisión del ciclo Otto, la cual es registrada por medio de la implementación física de un sensor MAP (Manifold Absolute Pressure). Se aplica un riguroso protocolo de muestreo y consecuente análisis estadístico. La selección y reducción de atributos de la señal del sensor MAP se realiza en función del mayor aporte de información y diferencia significativa con la aplicación de tres métodos estadísticos (ANOVA, matriz de correlación y Random Forest), de la cual se obtiene una base de datos que permite el entrenamiento de dos redes neuronales feed-forward backpropagation, con las cuales se obtiene un error de clasificación de 5.4061e-9 y de 9.7587e-5 para la red neuronal de CO y HC respectivamente.
 
Publisher Universidad Politécnica Salesiana
 
Date 2019-12-27
 
Type info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
 
Format application/pdf
application/pdf
 
Identifier https://ingenius.ups.edu.ec/index.php/ingenius/article/view/23.2020.03
10.17163/ings.n23.2020.03
 
Source Ingenius; Núm. 23 (2020): enero-junio; 30-39
Ingenius; No 23 (2020): january-june; 30-39
Ingenius; n. 23 (2020): enero-junio; 30-39
1390-860X
1390-650X
10.17163/ings.n23
 
Language spa
eng
 
Relation https://ingenius.ups.edu.ec/index.php/ingenius/article/view/23.2020.03/3552
https://ingenius.ups.edu.ec/index.php/ingenius/article/view/23.2020.03/3559
 
Rights Derechos de autor 2020 Universidad Politécnica Salesiana
http://creativecommons.org/licenses/by-nc-sa/4.0
 

Contact Us

The PKP Index is an initiative of the Public Knowledge Project.

For PKP Publishing Services please use the PKP|PS contact form.

For support with PKP software we encourage users to consult our wiki for documentation and search our support forums.

For any other correspondence feel free to contact us using the PKP contact form.

Find Us

Twitter

Copyright © 2015-2018 Simon Fraser University Library