0
RESEARCH PAPERS

Multi-Objective Single Product Robust Optimization: An Integrated Design and Marketing Approach

[+] Author and Article Information
B. Besharati

Department of Mechanical Engineering, A. J. Clark School of Engineering, University of Maryland, College Park, MD 20742

L. Luo

Department of Marketing, The Marshall School of Business, University of Southern California, Los Angeles, CA 90089

S. Azarm1

Department of Mechanical Engineering, A. J. Clark School of Engineering, University of Maryland, College Park, MD 20742azarm@umd.edu

P. K. Kannan

Department of Marketing, Robert H. Smith School of Business, University of Maryland, College Park, MD 20742

In a perfect yet unachievable sense, the variation in performance is desired to be zero.

We also considered alternative models with interaction effects between attributes. We did not find any additional improvement in our model fits. Therefore, only main effects are included in our model.

We use 95% confidence level because this is the most commonly used criterion in statistics literature (34). This percentage can be adjusted based on the product manager’s preference.

1

Corresponding author.

J. Mech. Des 128(4), 884-892 (Dec 19, 2005) (9 pages) doi:10.1115/1.2202889 History: Received August 08, 2005; Revised December 19, 2005

We present an integrated design and marketing approach to facilitate the generation of an optimal robust set of product design alternatives to carry forward to the prototyping stage. The approach considers variability in both (i) engineering design domain, and (ii) customer preferences in marketing domain. In the design domain, the approach evaluates performance and robustness of a design alternative due to variations in its uncontrollable parameters. In the marketing domain, in addition to considering competitive product offerings, the approach considers designs that are robust in customer preferences with respect to: (1) the variations in the design domain, and (2) the inherent variations in the estimates of preferences given the fit of the preference model to the sampled data. Our overall goal is to obtain design alternatives that are multi-objectively robust and optimal, i.e., (1) are optimal for nominal values of parameters, and (2) are within a known acceptable range in their multi-objective performance, and (3) maintain feasibility even when they are subject to applications and environments that are different from nominal or standard laboratory conditions. We illustrate the highlights of our approach with the design of a corded power tool example.

FIGURES IN THIS ARTICLE
<>
Copyright © 2006 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

Overall approach

Grahic Jump Location
Figure 2

Multi-objective robustness

Grahic Jump Location
Figure 3

Robust optimization approach

Grahic Jump Location
Figure 4

Integrated design-marketing approach

Grahic Jump Location
Figure 5

Rank ordering of design alternatives in (a) design domain, and (b) marketing domain

Grahic Jump Location
Figure 6

Set of nominal and robust Pareto design alternatives

Grahic Jump Location
Figure 7

Final set of robust design and product alternatives: (a) engineering design domain, and (b) marketing domain

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