Predication emission of an intelligent marine diesel engine based on modeling of BP neural networks

Predicate the emission of the marine diesel using the artificial neural networks (ANNs) has never been reported. The aim of this study is to establish a new approach for prediction of the marine diesel engine emissions based on ANNs. The marine engine exhaust emissions were measured for different engine loads conditions according to the IMO technical code. According to the results, the network performance is sufficient for all emission outputs. In the network, engine speed (N), engine load (L), fuel flow rate (FFR), air mass flow rate (AMR), scavenge air pressure( SAR), maximum injection pressure (MIP), electronic parameters and environmental conditions were taken as the input parameters, and the values of emissions were used as the output parameters. The R² values of the modeling were 0.98, and the mean % errors were smaller. However, filter smoke number (FSN) higher mean errors were obtained due to the complexity of the burning process and the measurement errors. Finally, ANNs modeling was successfully trained by experimental data, and then the model was used to predict engine emission values. The result showed that the values produced by ANNs were parallel to the experimental results.