An inverse design method of diffuser blades by genetic algorithms

A genetic algorithm incorporating a neural network technique is proposed to search for a turbomachinery diffuser blade profile that produces a given velocity distribution on its surface. Such a new inverse design method works through minimizing the error between the surface velocity distribution of candidate blades and the target velocity distribution. For ease of employing the genetic algorithm, the blade profiles to be searched are parameterized by Bezier curves. To fix the surface velocity distribution of a candidate blade, a special type of back propagation (BP) neural network is implemented. The proposed approach is illustrated by a diffuser having two-dimensional blades with constant height and thickness. The simulations show that the new method is not only feasible but also reliable and efficient.