Title: Performance prediction of a CI engine using artificial neural network for various SME and diesel fuel blends

Authors: Burak Gokalp, H. Metin Ertunc, Murat Hosoz, H. Ibrahim Sarac

Addresses: Department of Mechanical Engineering, Kocaeli University, 41040 Kocaeli, Turkey. ' Department of Mechanical Engineering, Kocaeli University, 41040 Kocaeli, Turkey. ' Department of Mechanical Engineering, Kocaeli University, 41040 Kocaeli, Turkey. ' Department of Mechanical Engineering, Kocaeli University, 41040 Kocaeli, Turkey

Abstract: This study deals with predicting performance parameters and exhaust emissions of a four-stroke, four-cylinder, direct injection diesel engine fuelled with soybean oil methyl ester and its blends with jet fuel, marine fuel and No. 2 diesel fuel using Artificial Neural Network (ANN) approach. For this aim, an ANN model for the engine was developed using experimental data, and the performance of the ANN predictions was measured by comparing them with the experimental results. It was revealed that the ANN approach can accurately predict the performance parameters and exhaust emissions of the diesel engine using various diesel and biodiesel fuels.

Keywords: marine fuel; jet fuel; SME; soybean methyl ester; ANN; artificial neural networks; performance prediction; exhaust emissions; direct injection diesel engines; vehicle emissions; diesel fuel blends; biofuels; biodiesel.

DOI: 10.1504/IJVD.2010.035357

International Journal of Vehicle Design, 2010 Vol.54 No.2, pp.156 - 176

Received: 11 Sep 2009
Accepted: 08 Apr 2010
Published online: 26 Sep 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article