Prediction of CI engine performance, emission and combustion characteristics using fish oil as a biodiesel at different injection timing using fuzzy logic

The present study investigates the potential of Fuzzy Inference System (FIS) to predict the performance, combustion and exhaust emissions of the Compression Ignition (CI) engine at different injection timings (21 degrees, 24 degrees, 27 degrees bTDC) using fish oil biodiesel. The experimental investigations are carried out on a single cylinder constant speed direct injection diesel engine under variable load conditions. Here Multi Input Multi Output (MIMO) fuzzy models are developed, trained and validated to predict the parameters like Brake Thermal Efficiency (BTE), Hydrocarbon (HC), Exhaust Gas Temperature (EGT), Oxides of Nitrogen (NOx), Carbon monoxide (CO), Smoke, Carbon dioxide (CO2), Ignition Delay (ID), Combustion Delay (CD) and Maximum Rate of Pressure Rise (MRPR) with the experimental performance data sets using Trapezoidal membership function. The developed MIMO fuzzy model is capable of predicting the performance, emissions and combustion parameters of the engine with better correlation coefficients in the range of 0.946-0.999, mean absolute percentage error in the range of 0.06-4.5% with noticeably low root mean square errors. The validation results confirm the applicability of the developed FIS models with high degree of accuracy and minimum time demand that can effectively replace the costly and time consuming real life experiments and trails. (C) 2016 Elsevier Ltd. All rights reserved.