An artificial neural network developed for predicting of performance and emissions of a spark ignition engine fueled with butanol–gasoline blends

The engine experiments require multiple tests that are hard, time-consuming, and high cost. Therefore, an artificial neural network model was developed in this study to successfully predict the engine performance and exhaust emissions when a port fuel injection spark ignition engine fueled with n-butanol–gasoline blends (0–60 vol.% n-butanol blended with gasoline referred as G100-B60) under various equivalence ratio. In the artificial neural network model, compression ratio, equivalence ratio, blend percentage, and engine load were used as the input parameters, while engine performance and emissions like brake thermal efficiency, brake-specific fuel consumption, carbon monoxide, unburned hydrocarbons, and nitrogen oxides were used as the output parameters. In comparison between experimental data and predicted results, a correlation coefficient ranging from 0.9929 to 0.9996 and a mean relative error ranging from 0.1943% to 9.9528% were obtained. It is indicated that the developed artificial neural network model was capable of predicting the combustion of n-butanol–gasoline blends due to a commendable accuracy.

Abstract licence: CC BY

37 more references, whose wording the paper’s licence keeps private.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.