Please use this identifier to cite or link to this item:
|Title:||Constrained Aerodynamic Shape Optimization using an Evolutionary Algorithm with Spatially Distributed Surrogates|
|Citation:||Isaacs, A.,Ray, T.,Tsai, H.M. (2008). Constrained Aerodynamic Shape Optimization using an Evolutionary Algorithm with Spatially Distributed Surrogates. Collection of Technical Papers - AIAA Applied Aerodynamics Conference. ScholarBank@NUS Repository.|
|Abstract:||In this paper, an evolutionary algorithm with spatially distributed surrogates (EASDS) is presented for constrained single and multi-objective shape optimization of airfoils. A typical aerodynamic design problem requires a significant number of aerodynamic and geometrical constraints to be satisfied by a design solution. The algorithm performs actual analysis for the initial population and periodically every few generations. An external archive of the unique solutions evaluated using the actual analysis is maintained to train the surrogate models. The data points in the archive are split into multiple partitions using k-Means clustering. A multi-layer perceptron (MLP) network surrogate model is built for each partition using a fraction of the points in that partition. The rest of the points in the partition are used as a validation data to compute the prediction accuracy of the surrogate model. Prediction of a new candidate solution is done by the surrogate model that has the least prediction error in the neighborhood of that point. Results of a series of constrained aerodynamic shape optimization problems are presented to highlight the efficacy of the approach.|
|Source Title:||Collection of Technical Papers - AIAA Applied Aerodynamics Conference|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Oct 19, 2018
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.