Concept Generation Algorithms for Repository-Based Early Design
Modern product and engineering design research explores methods for formally generating design concepts from stored knowledge. We discuss a design methodology which utilizes archived design knowledge gained from product dissection to aid novice designers in developing new product designs. In this design paradigm, new designs are developed as a model of the product's intended functionality, rather than a model of actual, physical components. This paper formulates an algorithm to automatically generate a set of components to instantiate such a functional model using archived design knowledge, which maps components to the functions they can satisfy and provides precedents for which components can be connected. In order to avoid generating an exponential number of instantiations, component failure data is leveraged to develop a dynamic programming algorithm. In addition, a method which uses this information to train a Hidden Markov Model is also developed. This Hidden Markov Model is consulted to generate a set of instantiations with low failure rates while avoiding exponential runtime.
J. P. Vucovich et al., "Concept Generation Algorithms for Repository-Based Early Design," Proceedings of DETC/CIE 2006 ASME 2006 Intl Design Engineering & Computers and Information in Engineering Conferences, American Society of Mechanical Engineers (ASME), Jan 2006.
Mechanical and Aerospace Engineering
Keywords and Phrases
Product Development; Hidden Markov Models; New products
Article - Conference proceedings
© 2006 American Society of Mechanical Engineers (ASME), All rights reserved.