M Saidi Neicharan - Ph.D. student Tarbiat Modares University(TMU)
Barat Ghobadian - Associated professor-TMU
T Tavakoli - professor-TMU
R Khoshbakhtisarayi - Sahand Technical University

Ignition delay in diesel engines is a very complex phenomenon that depends on various diesel engine parameters. One of these parameters is the diesel engine fuel source. On the other hand alternative fuels for diesel engines are becoming increasingly important due to diminishing petroleum reserves and the environmental consequences of exhaust gases from petroleum fuelled engines. In this regard, biodiesel fuel is an environmentally friendly alternative to petro diesel fuel. The objective of this research paper was therefore to investigate the ignition delay of a diesel engine using different blends of biodiesel fuel obtained from WVO and traditional petro diesel fuel in the form of blend ratios from B0 to B100. To carry this research work, Cetane number of blended fuels was measured based on ASTM-D613 standard method. The experimentalresults revealed that increasing biodiesel percentage, cetane number of blended fuel was also increased and consequently resulting in the decrease of ignition delay. In contrast, with increasing engine load, ignition delay was decreased. Using some of the experimental data fortraining, an ANN model was developed based on standard Back-Propagation algorithm for the test engine. Multi layer perception network (MLP) was used for nonlinear mapping between the input and the output parameters. The ANN model was developed to predict a correlation between ignition delay using different diesel-biodiesel blended fuels, engine load and different cetane numbers as input data. Different activation functions and several rules were used to assess the percentage error between the desired and the predicted values. It was observed that the ANN model can predict the ignition delay with correlation coefficient (R) of 0.999. Mean relative errors (MRE) value was 0.74, while root mean square errors (RMSE) were found to be very low. This study determinates that ANN approach can be used to predict the ignition delay of CI engine accurately.

Biodiesel, Petro diesel fuel, Diesel engine, Ignition delay, ANN