Mass customization optimization via social network product architecture representation

Mohit Jolly, Paul Winward, Vijit Pandey, Deborah Thurston

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Mass customization has opened a new realm of product design optimization. These problems require optimization of multiple objectives and have a very vast possible solution space. This paper presents an approach to solve this class of problems using social network based product representations to obtain component level information and then applying Genetic Algorithms to optimize the problem. We consider the case of assembling a PC from 16 subcomponents to demonstrate our approach, and use an established multi-objective GA Non-dominated Sorting Genetic Algorithm II to optimize the problem. The objectives considered are cost, expected product life required by the user and product performance. Our results reduce the possible solution set from a 10 order to a 10 order figure. The approach is intrinsically robust and produces correct results even when the constraints specified by the user have a small error.

Original languageEnglish (US)
Title of host publicationProceedings of 2006 ASME International Design Engineering Technical Conferences and Computers and Information In Engineering Conference, DETC2006
PublisherAmerican Society of Mechanical Engineers (ASME)
ISBN (Print)079183784X, 9780791837849
DOIs
StatePublished - Jan 1 2006
Event2006 ASME International Design Engineering Technical Conferences and Computers and Information In Engineering Conference, DETC2006 - Philadelphia, PA, United States
Duration: Sep 10 2006Sep 13 2006

Publication series

NameProceedings of the ASME Design Engineering Technical Conference
Volume2006

Other

Other2006 ASME International Design Engineering Technical Conferences and Computers and Information In Engineering Conference, DETC2006
CountryUnited States
CityPhiladelphia, PA
Period9/10/069/13/06

ASJC Scopus subject areas

  • Modeling and Simulation
  • Mechanical Engineering
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Fingerprint Dive into the research topics of 'Mass customization optimization via social network product architecture representation'. Together they form a unique fingerprint.

Cite this