Development of an ANN based system identification tool to estimate the performance-emission characteristics of a CRDI assisted CNG dual fuel diesel engine

In the present study the performance and emission parameters of a single cylinder four-stroke CRDI engine under CNG-diesel dual-fuel mode have been modeled by Artificial Neural Network. An ANN model was developed to predict BSFC, BTE, NOx, PM and HC based on the experimental data, with load, fuel injection pressure and CNG energy share as input parameters for the network. The developed ANN model was capable of predicting the performance and emission parameters with commendable accuracy as observed from correlation coefficients within the range of 0.99833–0.99999, mean absolute percentage error in the range of 0.045–1.66% along with noticeably low root mean square errors provided an acceptable index of the robustness of the predicted accuracy.