Low-cost genetic optimization based on inexact pre-evaluations and the sensitivity analysis of design parameters

Multi-Objective Design Exploration and Its Application to Regional-Jet Wing Design

“…ANOVA has been found to compensate this potential drawback by providing the relative importance of design variables. 17) Further research will be required for efficient data mining.…”

“…When the response surface method (RSM) is introduced for data mining as the post-process of optimization, it can also be applied at the pre-process stage for optimization as a surrogate model. [17][18][19] Pre-processing has been an important aspect in the introduction of surrogate models because it greatly reduces the computational expense, while efficiently producing rich non-dominated solutions.…”

An asynchronous metamodel-assisted memetic algorithm for CFD-based shape optimization

“…MetamodelAssisted EAs (MAEAs), in which the metamodels are trained separately from the evolution which is exclusively based on them, can be found in Bull (1999), Pierret and Van den Braembussche (1999), but are beyond the scope of this paper. This paper is concerned with EAs (MAs, in fact) assisted by on-line trained metamodels, in conformity with the method presented in Karakasis and Giannakoglou (2006), Giannakoglou et al (2001). In each generation, the metamodels undertake the so-called inexact pre-evaluation (IPE) of candidate solutions and pinpoint the most promising among them to undergo CFDbased evaluation.…”

Multi-Objective Design Exploration for Aerodynamic Configurations

“…24 ANOVA shows the effect of each design variables on objective functions quantitatively while SOM shows the information qualitatively. When the response surface method (RSM) is introduced for data mining as post-process of optimization, it can be applied to pre-process of optimization as a surrogate model, [25][26][27] too. Pre-process has been an important aspect of introduction of surrogate models because it would reduce the computational expense greatly, while it would produce rich non-dominated solutions efficiently.…”