Optimization of the exergy efficiency, exergy destruction, and engine noise index in an engine with two direct injectors using NSGA-II and artificial neural network

Abstract

Direct Dual Fuel Stratification (DDFS) strategy is a novel Low Temperature Combustion (LTC) strategy that has comparable thermal efficiency to the Reactivity Controlled Compression Ignition (RCCI) strategy, while it offers more control over the combustion process and the rate of heat release. The DDFS strategy uses two direct injectors for the low- and high-reactivity fuels (gasoline and diesel) to benefit from the RCCI concept. In this study, the injection strategy of the injectors of a gasoline/diesel DDFS engine was optimized from the thermodynamic perspective to maximize exergy efficiency and minimize exergy destruction and an engine noise index. An artificial neural network was developed with 576 samples from a CFD code to predict the DDFS mode behavior, and the non-dominated sorting genetic algorithm (NSGA-II) was used to obtain the Pareto Front and the optimal solutions. Compared to the base case, the exergy efficiency of the optimal cases increased by up to 2%, exergy destruction and Peak Pressure Rise Rate (PPRR) reduced by about 2.3%, and 2 bar/deg, respectively, in the optimal solutions. NOX and soot emissions were reduced by 40% and 35%, respectively, in the best-case scenarios.