Experimental and theoretical investigation of oxygenated biomass fuelled CI engine

Abstract

Energy is essential to economic and social development and improved quality of life in all countries. Much of the worldand#8223;s energy, however, is currently produced and consumed in ways that could not be sustained if technology were to remain constant and if overall quantities were to increase substantially. When fossil fuels are burned, they emit greenhouse gases (GHGs) that are now recognized as being responsible for climate change. Detailed experiments were carried out on a Kirloskar make, four-stroke, single cylinder CI engine. A BENZ make eddy-current dynamometer and an online data acquisition system were used to load the engine. The observed smoke reduction for J20 and J100 is 4% and 16% at full load. JME has 6.5% lower heating value less than that of diesel fuel and causes power loss. External EGR has emerged as the preferred type of EGR for heavy duty diesel engines and was used in this study The higher NOx emissions produced with biodiesel can be reduced by adding 15% of either ethanol or methanol in JME-diesel fuel blends. To experimentally investigate the performance and emissions of an engine is complex, time consuming and costly, especially for studies which use many different engine operating conditions. Hence a new approach based on Artificial Neural Networks (ANNs) was developed to predict the engine performance and emission values by using the part of the experimental data obtained. The computer code solving the back-propagation algorithm and measuring the network performance was implemented under the MATLAB environment. Coefficient of efficiency (R2) values of the test data obtained for all output parameters were above 0.99. The predicted values of engine performance and emission parameters by ANN are with in ±5% of the observed values. Consequently, with the use of ANNs, engine performance and emissions can be determined by performing only a limited number of tests instead of a detailed experimental study, thus saving both engineering effort and money. newline newline newline