0
Research Papers

Concurrent Optimization of Computationally Learned Stylistic Form and Functional Goals

[+] Author and Article Information
Ian Tseng

Department of Mechanical Engineering,  Carnegie Mellon University, 5000 Forbes Ave., Pittsburgh, PA 15213iht@alumni.cmu.edu

Jonathan Cagan

Department of Mechanical Engineering,  Carnegie Mellon University, 5000 Forbes Ave., Pittsburgh, PA 15213cagan@cmu.edu

Kenneth Kotovsky

Department of Psychology,  Carnegie Mellon University, Baker Hall 342c, Pittsburg, PA 15213kotovsky@cmu.edu

J. Mech. Des 134(11), 111006 (Oct 02, 2012) (11 pages) doi:10.1115/1.4007304 History: Received August 11, 2011; Revised June 19, 2012; Published October 02, 2012; Online October 02, 2012

Great design often results from intelligently balancing tradeoffs and leveraging of synergies between multiple product goals. While the engineering design community has numerous tools for managing the interface between functional goals in products, there are currently no formalized methods to concurrently optimize stylistic form and functional requirements. This research develops a method to coordinate seemingly disparate but highly related goals of stylistic form and functional constraints in computational design. An artificial neural network (ANN) based machine learning system was developed to model surveyed consumer judgments of stylistic form quantitatively. Coupling this quantitative model of stylistic form with a genetic algorithm (GA) enables computers to concurrently account for multiple objectives in the domains of stylistic form and more traditional functional performance evaluation within the same quantitative framework. This coupling then opens the door for computers to automatically generate products that not only work well but also convey desired styles to consumers.

FIGURES IN THIS ARTICLE
<>
Copyright © 2012 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

Sample matlab survey

Grahic Jump Location
Figure 2

Curves in vehicle design model

Grahic Jump Location
Figure 3

Generated design most sporty (left) and least sporty (right) for participant 18

Grahic Jump Location
Figure 4

Generated design most rugged (left) and least rugged (right) for participant 18

Grahic Jump Location
Figure 5

Generated design most beautiful (left) and least beautiful (right) for participant 18

Grahic Jump Location
Figure 6

Generated design most fuel efficient (left) and least fuel efficient (right) for participant 18

Grahic Jump Location
Figure 7

Average ratings for generated designs, unfiltered

Grahic Jump Location
Figure 8

Average ratings for generated designs, with less consistent participants filtered out

Grahic Jump Location
Figure 9

The Pareto Frontier of optimal tradeoffs between the ruggedness rating and aerodynamic performance

Grahic Jump Location
Figure 10

Pareto optimal solutions for (a) Point A, (b) Point B, (c) Point C, and (d) Point D in Fig. 9

Grahic Jump Location
Figure 11

(a) Most aerodynamic solution, 65 cu. ft., (b) most aerodynamic solution, 75 cu. ft., and (c) most aerodynamic solution, 85 cu. ft.

Grahic Jump Location
Figure 12

(a) Participant 3 65 cu. ft., (b) participant 18 65 cu. ft., (c) participant 3 75 cu. ft., (d) participant 18 75 cu. ft., (e) participant 3 79.96 cu. ft., and (f) participant 18 82.59 cu. ft.

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In