On Some Method of Flow Configuration Optimisation in Kaplan Tu rbine

This paper discuses a method of blade profile optimisation for Kaplan-type turbines. This method is based on modelling the interaction between rotor and stator blades. Additionally, the shape of the draft tube is investigated. The influence of the periodic boundary condition vs. full geometry is also discussed. Genetic algorithms are used to find a global optimum that minimises the optimisation criterion (loss coefficient). Artificial neural networks are used for ap proximation to offset long calculation time.