0
Research Papers

Efficient Global Surrogate Modeling for Reliability-Based Design Optimization

[+] Author and Article Information
Barron J. Bichon

Senior Research Engineer Materials Engineering Department, Mechanical Engineering Division, Southwest Research Institute, San Antonio, TX 78238 e-mail: barron.bichon@swri.org

Michael S. Eldred

Distinguished Member of Technical Staff Optimization and Uncertainty Quantification Department, Sandia National Laboratories, Albuquerque, NM 87185 e-mail: mseldre@sandia.gov

Sankaran Mahadevan

John R. Murray Sr. Professor of Engineering Department of Civil and Environmental Engineering, Department of Mechanical Engineering, Vanderbilt University, Nashville, TN 37235 e-mail: sankaran.mahadevan@vanderbilt.edu

John M. McFarland

Research Engineer Materials Engineering Department, Mechanical Engineering Division, Southwest Research Institute, San Antonio, TX 78238 e-mail: john.mcfarland@swri.org

Contributed by Design Automation Committee of ASME for publication in the Journal of Mechanical Design. Manuscript received April 25, 2011; final manuscript received September 12, 2012; published online December 12, 2012. Assoc. Editor: Christiaan J. J. Paredis.

J. Mech. Des 135(1), 011009 (Dec 12, 2012) (13 pages) Paper No: MD-11-1212; doi: 10.1115/1.4022999 History: Received April 25, 2011; Revised September 12, 2012

Determining the optimal (lightest, least expensive, etc.) design for an engineered component or system that meets or exceeds a specified level of reliability is a problem of obvious interest across a wide spectrum of engineering fields. Various formulations and methods for solving this reliability-based design optimization problem have been proposed, but they typically involve accepting a tradeoff between accuracy and efficiency in the reliability analysis. This paper investigates the use of the efficient global optimization and efficient global reliability analysis methods to construct surrogate models at both the design optimization and reliability analysis levels to create methods that are more efficient than existing methods without sacrificing accuracy. Several formulations are proposed and compared through a series of test problems.

FIGURES IN THIS ARTICLE
<>
Copyright © 2013 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Fig. 1

Final training data from an example application of the Nested EGO/Separate EGRA method to the Short Column problem. The dark dots are points included in the final set of data; the hollow diamonds are points that were evaluated, but were removed. Dashed contours are for the objective function. The solid contour line represents the constraint boundary β* = 2.5 estimated from the final GP model, and the dotted lines are the 95% confidence bounds on the location of this contour based on the uncertainty in the GP model.

Grahic Jump Location
Fig. 2

Converged solutions for all runs of the EGO/EGRA methods applied to the Short Column problem

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