Novel prediction approach for exhaust gases using Elman neural network combined with particle swarm optimization

Matheus H.R. Miranda, Fabrício L. Silva, Felipe S. Frutuoso, Jony J. Eckert, Mona Lisa M. Oliveira and Ludmila C.A. Silva

Energy, 2025, vol. 331, issue C

Abstract: The paper introduces a novel approach for predicting vehicle pollutant emissions using Elman artificial neural networks (ENN) trained by the Multi-Objective Particle Swarm Optimization (MOPSO) algorithm. Three training sets were conducted, including simulated data from the ADVISOR™ software and experimental data collected from a real-world driving cycle with a vehicle fueled with regular gasoline and hydrous ethanol. The main objective is to predict the emissions of hydrocarbons (HC), nitrogen oxides (NOx), and non-methane organic gases (NMOG), minimizing the root mean square error (RMSE) and maximizing the correlation coefficient between estimated and actual values. Results show that the ENN solution with the best trade-off exhibited a difference of less than 1% in emissions prediction during training with ADVISOR™ data. For experimental data, remarkable correlation indices were achieved, reaching up to 0.9932 for NMOG emissions, 0.9975 for NOx, and 0.9926 for HC in gasoline-fueled vehicle. Ethanol-fueled vehicles showed similarly high correlations.

Keywords: Elman neural network; Multi-objective optimization; Particle swarm optimization; Exhaust gases predictions; Simulation and experimental data (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225024119
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:331:y:2025:i:c:s0360544225024119

DOI: 10.1016/j.energy.2025.136769

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().