shape optimization; automatic differentiation
The purpose of our work is to develop an automatic shape optimization tool for runner wheel blades in reaction water turbines, especially in Kaplan turbines. The fluid flow is simulated using an in-house incompressible turbulent flow solver based on recently introduced isogeometric analysis (see e.g. J. A. Cotrell et al.: Isogeometric Analysis: Toward Integration of CAD and FEA, Wiley, 2009). The proposed automatic shape optimization approach is based on a so-called hybrid optimization which combines gradient-free and gradient-based methods. As the gradient-free method, the Particle Swarm Optimization (PSO) method is used. The gradient-based part exploits a quasi-Newton method implemented in IpOpt software library (Interior Point OPTimizer) and gradients of the objective function with respect to design variables are provided by automatic differentiation of the computer code which is done with the help of CoDiPack software library (Code Differentiation Package).