Artificial Neural Networks Approach for the Prediction of Thermal Balance of SI Engine Using Ethanol-Gasoline Blends - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Artificial Neural Networks Approach for the Prediction of Thermal Balance of SI Engine Using Ethanol-Gasoline Blends

Résumé

This study deals with artificial neural network (ANN) modeling of a spark ignition engine to predict engine thermal balance. To acquire data for training and testing of ANN, a four-cylinder, four-stroke test engine was fuelled with ethanol-gasoline blended fuels with various percentages of ethanol and operated at different engine speeds and loads. The performance of the ANN was validated by comparing the prediction data set with the experimental results. Results showed that the ANN provided the best accuracy in modeling the thermal balance with correlation coefficient equal to 0.997, 0.998, 0.996 and 0.992 for useful work, heat lost through exhaust, heat lost to the cooling water and unaccounted losses respectively. The experimental results showed as the percentage of ethanol in the ethanol-gasoline blends is increased, the percentage of useful work is increased, while the heat lost to cooling water and exhaust are decreased compared to neat gasoline fuel operation.
Fichier principal
Vignette du fichier
978-3-642-32498-7_3_Chapter.pdf (142.49 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01542472 , version 1 (19-06-2017)

Licence

Paternité

Identifiants

Citer

Mostafa Kiani Deh Kiani, Barat Ghobadian, Fathollah Ommi, Gholamhassan Najafi, Talal Yusaf. Artificial Neural Networks Approach for the Prediction of Thermal Balance of SI Engine Using Ethanol-Gasoline Blends. International Cross-Domain Conference and Workshop on Availability, Reliability, and Security (CD-ARES), Aug 2012, Prague, Czech Republic. pp.31-43, ⟨10.1007/978-3-642-32498-7_3⟩. ⟨hal-01542472⟩
125 Consultations
195 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More