Emissions prediction of CNG/diesel dual fuel engine based on RBF neural network

摘要

Compressed Natural Gas (CNG)/diesel Dual Fuel Engine (DFE) was one of the best choices for solving energy crisis and environment pollution. In order to study and improve the emission performance of the CNG/diesel DFE, an emission model by means of Radial Basis Function neural network was established. The model identified as a black box model with input-output training data didn't require priori knowledge. There were 100 group experimental data over the operation conditions from low load and low rotate speed to heavy load and high rotate speed used for training the neural network, and 20 group test data used for verifying the model. The study results showed that the predicted results were in good agreement with the experimental data. This proves that the developed emission model can be used to successfully predict and optimize the emission performance of DFE.