A unified cross-series marine propeller design method based on machine learning

Propeller design diagrams, like Bp-delta diagram, are widely applied in ship propeller design. However, different propeller series use various selection approaches, so comparisons between designs are only possible after individual candidates are chosen. This paper proposes a unified approach based on machine learning to allow efficient comparison and facilitate the selection of the optimal propeller amongst the available propeller series. The process starts by compiling propeller series data to generate a comprehensive dataset on propeller performance. This dataset is then used to train an Artificial Neural Network (ANN) model, which accurately predicts open-water propeller performance. Optimization techniques are applied to maximize propeller efficiency based on the specific needs of the vessel, while ensuring compliance with cavitation and noise constraints for safety. The model's accuracy is validated using data from the KRISO Container Ship (KCS), demonstrating the prediction's reliability. The method is then applied to select both open and ducted propellers for a variety of ship types to meet specific operational requirements. Ultimately, the optimized results are ranked by efficiency, offering an organized set of options for selecting the most suitable propeller. This approach eliminates the need for manual dataset correlation, significantly improving the efficacy of generating an outperforming initial design.