Knowledge Extraction from Aerodynamic Design Data and its Application to 3D Turbine Blade Geometries

author: Lars Graening, Honda Research Institute Europe
published: July 20, 2009,   recorded: July 2009,   views: 4857


Related Open Educational Resources

Related content

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.


Applying numerical optimisation methods in the field of aerodynamic design optimisation normally leads to a huge amount of heterogeneous design data. While often only the most promising results are investigated and used to drive further optimisations, general methods for investigating the entire design data set are rare. It is our target to extract comprehensive knowledge from the design data concerning the interrelation between the shape and the performance of the design. The extracted knowledge is prepared in a way that it is usable for guiding further computational as well as manual design and optimisation processes. For the design of complex aerodynamic shapes it is common to use different kinds of representations, what makes it difficult or even impossible to analyse the entire design data set. We suggest the transformation of the design data into discrete unstructured surface meshes and hence result in a homogeneous parametrisation of the designs. This makes it possible to analyse the design data independent of the representation used during the design and optimization process. On the basis of discrete unstructured surface meshes we propose a displacement measure in order to analyse local differences between designs1. The measure provides information on the amount and the direction of surface modifications. We recently introduced a framework2 that uses the displacement data in conjunction with statistical methods and techniques from machine learning to provide meaningful knowledge from the dataset at hand. The framework comprises a number of approaches for the displacement analysis, sensitivity analysis, dimensionality reduction and rule extraction. In order to demonstrate the feasibility of the suggested framework, we applied the proposed methods to a data set of a ultra-low aspect ratio transonic turbine stator blade of a small Honda turbofan engine that resulted from a computational optimisation run3. Decision trees have been formulated to generate a set of design rules which refer to a pre-defined blade design. The results have been verified by means of modifying the turbine blade geometry using direct manipulation of free form deformation (DMFFD)4 techniques. The performance of the deformed blade design has been calculated by running computational fluid dynamic (CFD) simulations. It is shown that the suggested framework provides reasonable results which can directly be transformed into design modifications in order to guide the design process.

See Also:

Download slides icon Download slides: mla09_graening_kefad_01.ppt (9.0┬áMB)

Help icon Streaming Video Help

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Write your own review or comment:

make sure you have javascript enabled or clear this field: