Prediction of PAHs Emitted from Marine Diesel Engine Using Artificial Neural Networks Combining Genetic Algorithms

Abstract

Experimental studies on operating a marine diesel engine to determine the performance map under different working conditions need to consume a lot of money and labor. To solve this problem, a mathematical model based on Artificial Neural Networks (ANNs) combined genetic algorithms (GA) to predicate the performance emissions of the marine diesel engine is firstly reported in this paper. The predicted result showed that the network performance is sufficient for all target emission outputs. The input layer without transfer function consisted of 11 neurons is used, and output layer predicted 16 polycyclic aromatic hydrocarbons (PAHs). Electronic parameters such as VIC, SOI, CRP, NUN, VEO and VEC have influences on the PAHs emissions. The actual data obtained from the diesel is well agreed with the predicted data. The usage of ANNs is highly recommended to predict engine emissions instead of having to undertake complex and time-consuming experimental studies.