ANN-based modeling and reducing dual-fuel engine's challenging emissions by multi-objective evolutionary algorithm NSGA-II

In this study, the combination of artificial neural network (ANN) and non-dominated sorting genetic algorithm II (NSGA-II) has been implemented for modeling and reducing CO and NOx emissions from a direct injection dual-fuel engine. A multi-layer perceptron (MLP) network is developed to predict the values of the emissions based on experimental data. The controllable variables such as engine speed, output power, intake temperature, mass flow rate of diesel fuel, and mass flow rate of the gaseous fuel are considered as input parameters. In order to identify the uncertainties due to the experiments and the ANN-based model, uncertainty analysis is carried out. Finally, optimum values of intake temperature, mass flow rate of diesel and gaseous fuels are obtained for a desired output power and engine speed via NSGA-II. The use of the developed evolutionary optimization algorithm allows the calculation of the Pareto-optimal set of designs under any combination of engine speed and output power, defined in the range of the experiments.