Specific Soft Computing Strategies for Evaluating the Performance and Emissions of an SI Engine Using Alcohol-Gasoline Blended Fuels-A Comprehensive Analysis

The huge fossil fuel consumption has created an unprecedented situation and, with the accompanying rise in car numbers, pollution levels have been well beyond human control. This is alarming enough to note that the level of pollution has surpassed all levels and the need for the hour is to find an alternative fuel that can really be of great help in reducing exhaust emissions and that efficiency. Experiments performed on S.I engine are considered to be time-consuming and the expenses met to perform these experiments are too costly, so the need of soft computing techniques involved in this area. Soft computing has shown a great deal of potential in providing researchers with the exact solution that could be used to validate or predict performance and emission parameters. The different software computing methods are widely used, includes the Adaptive Neuro Fuzzy Inference System (ANFIS), the Artificial Neural Network (ANN), the Fuzzy Expert System (FES), Response Surface Methodology (RSM) and Support Vector Machine (SVM). The one and only objective of this effort is to bring out the comprehensive review of various researchers who have carried out the work on soft computing techniques on S.I engines with a variety of alternative fuels.