An optimal design of axial-flow fan blades by the machining method and an artificial neural network

Abstract

The geometry design and machining of blades for axial-flow fans are important issues because the twisted profile and flowfield of blades are complicated. The rapid design of a blade that performs well and satisfies machining requirements is one of the goals in designing fluid machinery blades. In this study, an integrated approach combining computational fluid dynamics (CFD), an artificial neural network, an optimization method and a machining method is proposed to design a three-dimensional blade for an axial-flow fan. From the machining point of view, the three-dimensional surface geometry of a fan blade can be defined as the swept surface of the tool path created by using the generated machining method. By taking advantage of its powerful learning capability, a back-propagation artificial neural network is used to set up the flowfield models and to forecast the flow performance of the axial-flow fan. The desired optimal blade geometry is obtained by using a complex optimization method.

Keywords

axial-flow fan optimal blade design generated machining method back-propagation artificial neural network complex optimization method

Get full access to this article

View all access options for this article.

References

Lewis

R. I.

Turbomachinery Performance Analysis, 1996 (John Wiley, New York).

Wallis

R. A.

Axial Flow Fans and Ducts, 1983 (John Wiley, New York).

Turton

R. K.

Principles of Turbomachinery, 2nd edition, 1995 (Chapman and Hall).

Dang

Isgro

Euler-based inverse method for turbomachine blades. Part 1: 2D cascades. Am. Inst. Aeronaut. Astronaut. J., 1995, 33(12), 2309–2315.

Damle

Dang

Practical use of three-dimensional inverse method for compressor blade design. Trans. ASME, J. Turbomachinery, 1999, 121(2), 321–325.

Nerurkar

A. C.

Dang

T. Q.

Reddy

E. S.

Reddy

D. R.

Design study of turbo-machinery blades by optimization and inverse techniques. AIAA-96-2555, 1996 (American Institute of Aeronautics and Astronautics, Lake Buena Vista, Florida).

Pierret

Van den Braembussche

R. A.

Turbomachinery blade design using a Navier-Stokes solver and artificial neural network. Trans. ASME, J. Turbomachinery, 1999, 121(2), 326–332.

Lee

S. P.

Lin

B. J.

Tung

N. R.

Hung

C. I.

Application of artificial neural network on the blade design of axial flow fan (in Chinese). In Proceedings of 16th National Conference on Mechanical Engineering, Shinchu, Taiwan, 1999, Vol. Thermal-Fluid and Energy, pp. 391–398 (CSME).

Fan

H. 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.

10.

Greenman

R. M.

Roth

K. R.

High-lift optimization design using neural networks on a multi-element airfoil. Trans. ASME, J. Fluids Engng, 1999, 121, 434–440.

11.

Tsay

D. M.

Lin

B. J.

Design and machining of globoidal index cams. Trans. ASME, J. Mfg Sci. Engng, 1997, 119, 21–29.

12.

Wang

W. P.

Wang

K. K.

Geometric modeling of swept volume of moving solids. IEEE Computer Graphics and Applic., 1986, 6(12), 8–17.

13.

Goetz

An Introduction to Differential Geometry, 1970 (Addison-Wesley, Reading, Massachusetts).

14.

Stroke

J. J.

Differential Geometry, 1969 (John Wiley, New York).

15.

CFX-TASCflow Computational Fluid Dynamics Software: Primer Manual, Version 2.10, May 2000 (AEA Technology Engineering Software Limited).

16.

Lee

L. C.

Chen

S. H.

S. B.

Hsu

W. Y.

Interactive grid generation for turbomachinery applications. In the Chinese Third CFD Conference, Taiwan, 1995, pp. 541–552.

17.

Cruz

C. A.

Understanding Neural Networks: A Primer, 1988 (Graeme Publishing Corporation, Amsterdam, Netherlands).

18.

Rao

S. S.

Engineering Optimization: Theory and Practice, 3rd edition, 1996 (John Wiley, New York).

19.

Taguchi

Konishi

Taguchi Methods: Orthogonal Arrays and Linear Graphs: Tools for Quality Engineering, 1987 (American Supplier Institute, Center for Taguchi Methods, Dearborn, Michigan).