ANFIS modelling of the performance and emissions of a diesel engine using diesel fuel and biodiesel blends

HOŞÖZ M., ERTUNÇ H. M., Karabektas M., Ergen G.

APPLIED THERMAL ENGINEERING, vol.60, pp.24-32, 2013 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 60
  • Publication Date: 2013
  • Doi Number: 10.1016/j.applthermaleng.2013.06.040
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.24-32
  • Keywords: Diesel engine, Biodiesel, Adaptive neuro-fuzzy inference system, ANFIS, Emissions, ARTIFICIAL NEURAL-NETWORK, OIL METHYL-ESTER, EXHAUST EMISSIONS, HEAT-TRANSFER, COMBUSTION, TEMPERATURE, PREDICT
  • Kocaeli University Affiliated: Yes


This study investigates the applicability of adaptive neuro-fuzzy inference system (ANFIS) approach for modelling the performance parameters and exhaust emissions of a diesel engine employing various fuels. In order to gather data for developing the proposed ANFIS model, a single-cylinder direct injection diesel engine was fuelled with diesel fuel, biodiesel and their blends, and steady-state tests were performed by varying the biodiesel content, engine speed and engine load. Then, using experimental data, engine performance parameters, namely engine power, brake specific fuel consumption, brake thermal efficiency, exhaust gas temperature, and emissions of HC, CO and NO were determined. After an ANFIS model for the prediction of the performance parameters and exhaust emissions of the engine was developed using some of the data acquired in the experiments, the model results were compared with experimental ones for determining the accuracy of the ANFIS predictions. It was determined that the predictions usually agreed well with the experimental results with correlation coefficients in the range of 0.940-1.000 and mean relative errors in the range of 1.40-27.40%. The results suggest that the ANFIS approach can be used successfully for predicting the performance and emissions of diesel engines using various fuels. (C) 2013 Elsevier Ltd. All rights reserved.