Application of ANN to predict performance and emissions of SI engine using gasoline-methanol blends

The deployment of methanol like alternative fuels in engines is a necessity of the present time to comprehend power requirements and environmental pollution. Furthermore, a comprehensive prediction of the impact of the methanol-gasoline blend on engine characteristics is also required in the era of artificial intelligence. The current study analyzes and compares the experimental and Artificial Neural Network (ANN) aided performance and emissions of four-stroke, single-cylinder SI engine using methanol-gasoline blends of 0%, 3%, 6%, 9%, 12%, 15%, and 18%. The experiments were performed at engine speeds of 1300-3700 rpm with constant loads of 20 and 40 psi for seven different fractions of fuels. Further, an ANN model has developed setting fuel blends, speed and load as inputs, and exhaust emissions and performance parameters as the target. The dataset was randomly divided into three groups of training (70%), validation (15%), and testing (15%) using MATLAB. The feedforward algorithm was used with tangent sigmoid transfer active function (tansig) and gradient descent with an adaptive learning method. It was observed that the continuous addition of methanol up to 12% (M12) increased the performance of the engine. However, a reduction in emissions was observed except for NO_x emissions. The regression correlation coefficient (R) and the mean relative error (MRE) were in the range of 0.99100-0.99832 and 1.2%-2.4% respectively, while the values of root mean square error were extremely small. The findings depicted that M12 performed better than other fractions. ANN approach was found suitable for accurately predicting the performance and exhaust emissions of small-scaled SI engines.