An ANN-based fuel injection strategy for green hydrogen-enriched advanced CRDI Engine: the paradigm approach of NSGA-II and TOPSIS

This study investigates the influence of fuel injection pressure and timing on the performance, combustion, and emission characteristics of a single-cylinder, 1500 rpm common rail direct injection (CRDI) diesel engine fueled with a diesel–biodiesel blend containing 20% palm kernel methyl ester and 80% diesel, enriched with hydrogen at a flow rate of 10 LPM (PKME20H10). The objective is to enhance engine efficiency and emission control through a green hydrogen–biodiesel strategy. Artificial Neural Network (ANN) models were developed to predict engine responses, and optimization was achieved using the hybrid NonDominated Sorting Genetic Algorithm II (NSGA-II) coupled with the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). Experimental and computational analyses revealed that the optimal combination of an injection timing of 25 before top dead center (BTDC) and an injection pressure of 512 bar achieved a brake thermal efficiency (BTE) of 30.1%, a brake specific fuel consumption (BSFC) of 0.123 kg/kWh, and substantial reductions in emissions. Carbon monoxide emissions decreased by 10%, unburnt hydrocarbon emissions decreased by 45%, and smoke opacity decreased by 17%. The study demonstrates that hydrogen enrichment in biodiesel improves combustion quality and engine sustainability, offering a viable pathway for low-carbon automotive energy systems.