In this paper a neural network approach is proposed to solve an inverse design problem of a centrifugal impeller when the basic structure parameter and the hub-shroud contours are known, and the expected blade surface velocity distribution is given. The proposed neural networks have a four-layered feedforward architecture and are trained with finite samples by means of a back-propagation algorithm. The simulations show that the trained networks can yield a blade shape that generates the expected velocity distribution on its surface.
FanH.-Y.An inverse design method of diffuser blades by genetic algorithms. Proc. Instn Mech. Engrs, Part A, Journal of Power and Energy, 1998, 212(A4), 261–268.
2.
JansenW.KirschnerA. M.Impeller design method for centrifugal compressor. NASA SP304, National Aeronautics and Space Administration, 1975.
3.
PrasanthR. K.WhitakerK. W.Neuromorphic approach to inverse problems in aerodynamics. Am. Inst. Aeronaut. Astronaut. J., 1995, 33(6), 1150–1152.
4.
RaiM. M.MadavanN. K.Application of artificial neural networks to the design of turbomachinery airfoils. In Proceedings of the AIAA 36th Aerospace Sciences Meeting and Exhibit, Reno, Nevada, 12–15 January 1998, AIAA paper 98-1003.
