A parametric study for specific fuel consumption of an intercooled diesel engine using a neural network

Turbocharging is a process wherein the amount of oxygen used in a combustion reaction is increased to raise output and decrease specific fuel consumption. On account of this, fuel economy and thermal efficiency are more important for all engines. The use of an intercooler reduces the temperature of intake air to the engine, and this cooler and denser air increases thermal and volumetric efficiency. Most research projects on engineering problems usually take the form of experimental studies. However, experimental research is relatively expensive and time consuming. In recent years, Neural Networks (NNs) have increasingly been used in a diverse range of engineering applications. In this study, various parametric studies are executed to investigate the interrelationship between a single variable and two steadies and two constant parameters on the brake specific fuel consumption (BSFC, g/kW h). The variables selected are engine speed, load and Crankshaft Angel (CA). The data used in the present study were obtained from previous experimental research by the author. These data were used to enhance, train and test a NN model using a MATLAB-based program. The results of the NN based model were found to be convincing and were consistent with the experimental results. The trained NN based model was then used to perform the parametric studies. The performance of the NN based model and the results of parametric studies are presented in graphical form and evaluated. (C) 2011 Elsevier Ltd. All rights reserved.