Location: EU Supported » PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning » International Workshop - Machine Learning for Aerospace

Multi-Objective Design Exploration (MODE) - Visualization and Mapping of Design Space

author:Shigeru Obayashi, Institute of Fluid Science, Tohoku University
published: July 20, 2009,   recorded: July 2009,   views: 58
You might be experiencing some problems with Your Video player.

Slides

Slides
0:00 Multi-Objective Design Exploration (MODE) - Visualization and Mapping of Design Space
0:21 Outline
1:57 Flow Visualization -1
4:54 Flow Visualization -2
6:47 Flow Visualization -3
9:09 Flow Visualization -4
12:16 Aircraft Design
14:00 How to Solve MOP
16:37 How to Understand MOP
21:17 Visualization of Tradeoffs
23:00 Self-Organizing Map SOM
25:12 How to understand SOM better?
27:56 Rough Set - Pawlak(1982)
30:02 Rough Set and Attribute (1)
30:56 Rough Set and Attribute (2)
31:16 Rough Set and Attribute (3)
31:30 Rough Set and Attribute (4)
31:52 Rough Set and Attribute (5)
31:57 Rough Set and Attribute (6)
32:51 Rough Set and Attribute (7)
33:21 Rough Set and Attribute (8)
34:56 What is MODE?
36:02 Small Jet Aircraft R&D Project
37:17 Present MODE System
39:00 Optimization of Wing-Nacelle-Pylon-Body Configuration
39:50 Definition of Optimization Problem - Objective Functions
41:40 Definition of Optimization Problem - Design Variables
42:27 Performances of baseline shape and sample points
44:16 Definition of Configuration Variables for Data Mining
46:30 Visualization of Design Space (1)
47:34 Analysis of Sweet–Spot Cluster
48:14 Visualization of Design Space (2)
49:46 Visualization of SOM Clusters by Parallel Coordinates
50:47 Discretization of Configuration Variables by Equal Frequency Binning
51:12 Finding Design Rules by Visualization
52:56 Flowchart of Data Mining Using Rough Set
53:36 Generated rules to belong to sweet spot cluster with support of more than eight occurrence
54:03 Statistics of rule conditions and comparison with previous results
55:28 Statistics of rule conditions for all objectives
56:24 Conclusions
56:59 Acknowledgements
57:17 Mitsubishi Regional Jet (MRJ)
57:39 - Questions

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.

Description

Multi-Objective Design Exploration (MODE) and its application are presented. MODE reveals the structure of the design space from the trade-off information and visualizes it as a panorama for Decision Maker. Self-Organizing Map is incorporated into MODE as a visual data mining tool for the design space. The resulting MODE was applied to the multi-disciplinary wing design problem and revealed the design sweet spot and the detailed trade-off information about aerodynamic and structural performance successfully.

See Also:

Download slides icon Download slides: mla09_obayashi_mode_01.ppt (7.8 MB)

Launch Windows Media PlayerLaunch in a standalone WM Player

WMedia PlayerSwitch to Windows Media Player

View slides View slides

Help icon Streaming Video Help

WebLink icon Windows Media Player Firefox Plugin - Download

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: