Artificial neural network-based prediction of performance and emission characteristics of CI engine using polanga as a biodiesel

Abstract

The present work predicts the performance parameters, namely brake specific fuel consumption (BSFC), brake thermal efficiency (BTE), peak pressure, exhaust gas temperature and exhaust emissions of a single cylinder four-stroke diesel engine at different injection timings and engine load using blended mixture of polanga biodiesel by artificial neural network (ANN). The properties of biodiesel produced from polanga were measured based on ASTM standards. Using some of the experimental data for training, an ANN model was developed based on standard back-propagation algorithm for the engine. Multi-layer perception network was used for non-linear mapping between input and output parameters. Different activation functions and several rules were used to assess the percentage error between the desired and the predicted values. It was observed that the developed ANN model can predict the engine performance and exhaust emissions quite well with correlation coefficient (R) 0.99946, 0.99968, 0.99988, 0.99967, 0.99899, 0.99941 and 0.99991 for the BSFC, BTE, peak pressure, exhaust gas temperature, NOx, smoke and unburned hydrocarbon emissions, respectively. The experimental results revealed that the blended fuel provides better engine performance and improved emission characteristics.