Increasing the efficiency of propellers and propulsion systems is crucial for advancing fueleconomy and sustainability in the maritime industry. This paper proposes an optimizationframework that integrates Computational Fluid Dynamics (CFD), Artificial Neural Networks(ANNs), and Genetic Algorithms (GA) to minimize marine fuel consumption. The ANN surrogatemodel, trained on CFD simulation data with legitimate augmentation, demonstrated highpredictive performance (R² = 0.975) in capturing nonlinear hydrodynamic relationships. The GAoptimization identified an optimal propeller configuration, predicting a 15.2% reduction in fuelconsumption. CFD validation confirmed a 13.9% improvement, within acceptable engineeringtolerances (deviation of 1.3%). Sensitivity analysis revealed that rotational speed, advance ratio,and pitch-to-diameter ratio are the most influential parameters on propulsion efficiency. This AIintegrated approach accelerates the design process while ensuring performance validation,providing a transformative tool for ship designers, naval architects, and marine engineers. Thestudy aligns with the revised 2023 IMO GHG Strategy, supporting net-zero emissions fromshipping by or around 2050, with indicative checkpoints of at least 20% (striving for 30%)reduction in GHG emissions by 2030 and 70% (striving for 80%) by 2040 compared to 2008 levels,advancing a low-carbon future for international marine transportation.
Kombo Theophilus-Johnson (Thu,) studied this question.