Internal Modifications to Optimize Pollution and Emissions of Internal Combustion Engines through Multiple-Criteria Decision-Making and Artificial Neural Networks

The present work proposes several modifications to optimize both emissions and consumption in a commercial marine diesel engine. A numerical model was carried out to characterize the emissions and consumption of the engine under several performance parameters. Particularly, five internal modificatio...

Full description

Saved in:
Bibliographic Details
Published in:International journal of environmental research and public health 2021-12, Vol.18 (23), p.12823
Main Authors: Galdo, María Isabel Lamas, Miranda, Javier Telmo, Lorenzo, José Manuel Rebollido, Caccia, Claudio Giovanni
Format: Article
Language:English
Subjects:
Air pollution
Cooling
Cooling water
Decision making
Diesel engines
Emissions
Engine valves
Environmental Pollution
Exhaust gases
Gasoline
Industrial plant emissions
Internal combustion engines
Marine engines
Mathematical models
Multiple criterion
Neural networks
Neural Networks, Computer
Numerical models
Parameter modification
Temperature
Vehicle Emissions
Water temperature
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The present work proposes several modifications to optimize both emissions and consumption in a commercial marine diesel engine. A numerical model was carried out to characterize the emissions and consumption of the engine under several performance parameters. Particularly, five internal modifications were analyzed: water addition; exhaust gas recirculation; and modification of the intake valve closing, overlap timing, and cooling water temperature. It was found that the result on the emissions and consumption presents conflicting criteria, and thus, a multiple-criteria decision-making model was carried out to characterize the most appropriate parameters. In order to analyze a high number of possibilities in a reasonable time, an artificial neural network was developed.
ISSN:1660-4601
1661-7827
1660-4601
DOI:10.3390/ijerph182312823