Application of Genetic programming to predict an SI engine brake power and torque using ethanol- gasoline fuel blends

Abstract

The main objective of this study is to predict the performance of a commercial spark ignition (SI) engine using multigene genetic
programming (GP). To acquire data for training and testing of the proposed GP, a four-cylinder, four-stroke test engine was fueled with ethanolgasoline fuel blends. The fuels were blended with various percentages of ethanol (0, 5, 10, 15 and 20%), and the engine was operated at different
engine speeds and loads. The experimental results showed that using ethanol–gasoline blend fuels increased the brake power and torque of the
engine. Numerous runs were performed with model of GP and the performance of developed equations was evaluated. The optimum models were
selected according to statistical criteria of root mean square error (RMSE) and coefficient of determination (R2). The values of RMSE and R2 for
brake power were found to be 0.388 and 0.998. It was observed that the GP model can predict engine torque with correlation coefficient (R2) in
the range of 0.99–1 and RMSE was found to be 0.731. The simulation results demonstrated that GP model is a good tool to predict the engine
brake power and torque under test.