Prediction of DI diesel engine performance and exhaust emissions with artificial neural network

study investigates the use of artificial neural network (ANN) modeling to predict power, brake specific fuel consumption (BSFC), and exhaust emissions of a DI (Direct Injection) diesel engine. A fourstroke DI diesel engine was modified for the present work and was operated at different engine speeds. For the ANN modeling, the standard back-propagation algorithm was found to be the optimum choice for training the model. A multi-layer network was used for non-linear mapping between the input and output parameters. Comparing ANN model and the experimental data for OM355 diesel engine showed that the performance of the used model or mean square error (MSE) of ANN is about 0.000014, 0.000511, 0.000876, 0.000079, and 0.000847 for the engine power, BSFC, NOx, CO and Soot respectively, that shows perfect results.