Propeller optimization by interactive genetic algorithms and machine learning

Marine propeller design can be carried out with the aid of automated optimization, but experience shows that a such an approach has still been inferior to manual in industrial scenarios. In this study, optimization is evolved by integrating human–computer interaction as intermediate step. An interactive methodology, based on genetic algorithms (IGAs), developed, where blade designers systematically guide algorithm towards objectives. The visualize and assess shape cavitation evaluation integrated method. IGA further support-vector machine model, order avoid user fatigue, IGA's main disadvantage. results present study show searches solutions more targeted manner eventually finds non-dominated feasible designs also good behaviour agreement designer preference.