ANN Based Modeling of Performance and Emission Characteristics of Diesel Engine Fuelled with Polanga Biodiesel at Different Injection Pressures

Abstract

The present work predicts the performance and exhaust parameters of a single cylinder 4-stroke diesel engine at different injection pressures using blended mixture of Polanga biodiesel and diesel by artificial neural network (ANN). Experimental data for training and testing in the proposed ANN was obtained at a constant speed and full load condition. An ANN model was developed based on standard Back- Propagation algorithm for the engine. Multi layer perception network (MLP) was used for non-linear mapping between the 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 ANN model can predict the engine performance and exhaust emissions quite well with correlation coefficient (R) 0.99998, 0.9999, 0.99998, 0.9999, 0.9958, 0.9993, 0.9999 for the brake specific fuel consumption, brake thermal efficiency, exhaust gas temperature, NOx, CO, smoke and UBHC emissions, respectively.