Using artificial neural networks to represent a diesel–biodiesel engine

Abstract

In this work, six computational models based on artificial neural networks were developed to simulate an operating diesel engine fuelled with 8% biodiesel in order to predict performance and emissions of a diesel–biodiesel engine in a group generator. The ANN models were used to simulate a diesel–biodiesel engine that has four cylinders with a volume of 3.9 l, a compression ratio of 17:1, direct injection, and a rated power of 49 kW. The models were validated against experimental data for 10 kW, 20 kW, and 30 kW loads. The models were capable of accurately predicting the output power, thermal efficiency, and emissions of CO2, CO, NO, and NOx. Their comparison with experimental results showed a satisfactory agreement and the reliability of their predicted results for new operating conditions.