A grid-enabled asynchronous metamodel-assisted evolutionary algorithm for aerodynamic optimization

被引：17

作者：

Asouti, V. G. ^{[1
]}

Kampolis, I. C. ^{[1
]}

Giannakoglou, K. C. ^{[1
]}

机构：

[1] Natl Tech Univ Athens, Sch Mech Engn, Lab Thermal Turbomachines, Parallel CFD & Optimizat Unit, Athens 15710, Greece

来源：

GENETIC PROGRAMMING AND EVOLVABLE MACHINES | 2009年 / 10卷 / 04期

关键词：

Asynchronous evolutionary algorithms; Metamodels; Grid computing; Aerodynamic shape optimization; GENETIC ALGORITHMS; LOW-COST; DESIGN;

D O I：

10.1007/s10710-009-9090-5

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A Grid-enabled asynchronous metamodel-assisted evolutionary algorithm is presented and assessed on a number of aerodynamic shape optimization problems. An efficient way of implementing surrogate evaluation models or metamodels (artificial neural networks) in the context of an asynchronous evolutionary algorithm is proposed. The use of metamodels relies on the inexact pre-evaluation technique already successfully applied to synchronous (i.e. generation-based) evolutionary algorithms, which needs to be revisited so as to efficiently cooperate with the asynchronous search method. The so-created asynchronous metamodel-assisted evolutionary algorithm is further enabled for Grid Computing. The Grid deployment of the algorithm relies on three middleware layers: GridWay, Globus Toolkit and Condor. Single- and multi-objective CFD-based designs of isolated airfoils and compressor cascades are handled using the proposed algorithm and the gain in CPU cost is demonstrated.

引用

页码：373 / 389

页数：17

共 42 条

[31] Total pressure loss minimization in turbomachinery cascades using a new continuous adjoint formulation [J].

Papadimitriou, D. I. ;

Giannakoglou, K. C. .

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART A-JOURNAL OF POWER AND ENERGY, 2007, 221 (A6) :865-872

[32] A continuous adjoint method with objective function derivatives based on boundary integrals, for inviscid and viscous flows [J].

Papadimitriou, D. I. ;

Giannakoglou, K. C. .

COMPUTERS & FLUIDS, 2007, 36 (02) :325-341

[33] Structural optimization using evolution strategies and neural networks [J].

Papadrakakis, M ;

Lagaros, ND ;

Tsompanakis, Y .

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 1998, 156 (1-4) :309-333

[34] Turbomachinery blade design using a Navier-Stokes solver and artificial neural network [J].

Pierret, S ;

Van den Braembussche, RA .

JOURNAL OF TURBOMACHINERY-TRANSACTIONS OF THE ASME, 1999, 121 (02) :326-332

[35] Hybridization of a multi-objective genetic algorithm, a neural network and a classical optimizer for a complex design problem in fluid dynamics [J].

Poloni, C ;

Giurgevich, A ;

Onesti, L ;

Pediroda, V .

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2000, 186 (2-4) :403-420

[36] A surrogate assisted parallel multiobjective evolutionary algorithm for robust engineering design [J].

Ray, Tapabrata ;

Smith, Andwarren .

ENGINEERING OPTIMIZATION, 2006, 38 (08) :997-1011

[37]

Spalart P. R., 1994, RECH AEROSPATIALE, V1, P5, DOI [DOI 10.2514/6.1992-439, DOI 10.1063/1.2840200]

[38] Differential evolution - A simple and efficient heuristic for global optimization over continuous spaces [J].

Storn, R ;

Price, K .

JOURNAL OF GLOBAL OPTIMIZATION, 1997, 11 (04) :341-359

[39] Distributed computing in practice: the Condor experience [J].

Thain, D ;

Tannenbaum, T ;

Livny, M .

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2005, 17 (2-4) :323-356

[40]

Tomassini M., 1999, Evolutionary Algorithms in Engineering and Computer Science, P113

← 1 2 3 4 5 →