ANN Based Prediction of Engine Performance and Exhaust Emission Responses of a CI Engine Powered By Ternary Blends

Abstract

In this study, experimental data was gathered from a single cylinder diesel engine fuelled with pyrolytic oil, neat diesel and butanol fuel blends. The experiments were conducted at varying engine loads from 0.25 kW to 1 kW with the interval of 0.25 kW. The engine performance and emission data obtained were predicted using an artificial neural network (ANN) algorithm. Assessed responses are CO, NOx, BSFC, and BTE. The results were discussed in terms of R2, MBE, and RMSE metrics. The performance and emission responses were predicted with a good R2 value of 0.986, 0.963, 0.991, and 0967 for BTE, BSFC, NOx, and CO, respectively, and all MBE value is very close to zero and smaller than 1.14. In the conclusion, the present paper showed that the ternary form of n-butanol-pyrolytic fuel and diesel fuel can be used in a CI engine with no modification on the vehicular system and the emission and performance responses of ternary fuels can be accurately predicted using an artificial neural network.

Keywords

• artificial neural network,
• engine,
• n-butanol,
• waste tire pyrolysis oil,