Comparative analysis of various modelling techniques for emission prediction of diesel engine fueled by diesel fuel with nanoparticle additives

Abstract

In this study, emissions of compression ignition engine fueled by diesel fuel with nanoparticle  additives  was  modeled  by  regression  analysis,  artificial  neural  network  (ANN)  and  adaptive  neuro  fuzzy  inference  system  (ANFIS)  methods.  Cetane  number  (CN)  and  engine  speed  (rpm) were selected as input parameters for estimation of carbon monoxide (CO), oxides of  nitrogen (NOx), and carbon dioxide (CO2) emissions. The results of estimation techniques were  compared with each other and they showed that regression analysis was not accurate enough  for prediction. On the other hand, ANN and ANFIS modelling techniques gave more accurate  results with respect to regression analysis; linear and non-linear. Especially ANFIS models can  be suggested as estimation method with minimum error compared to experimental results.