Development of artificial neural network to predict the performance of spark ignition engine fuelled with waste pomegranate ethanol blends
Dinesh Y. Dhande, C. S. Choudhari, D. P. Gaikwad, Kiran B. Dahe
Abstract
In this study, an artificial neural network (ANN) is developed to predict the performance of a spark-ignition engine using waste pomegranate ethanol blends. A series of experiments on a single-cylinder, four-stroke spark-ignition engine yielded the data needed for neural network training and validation. 70 percent of the experimental data was used to train the network using the feed-forward back propagation (FFBP) algorithm. The developed network model's performance was evaluated by contrasting its output with experimental results. Input parameters included engine speed, ethanol blends, and output parameters included indicated and brake power, thermal, volumetric, and mechanical efficiencies. Training and testing data had regression coefficients that were almost identical to one. The research revealed that the ANN model can be a better option for predicting engine performance with a higher level of accuracy.