Abstract
Over the last few decades design researchers have put forward theories and proposed methodologies that increase the chance that a design team will reliably arrive at the optimal solution to a given design problem. Studies, however, bear out that theories and methodologies alone will not guarantee an optimal or even good design solution. Instead, a breadth of knowledge across multiple engineering domains and the time and tools to thoroughly evaluate the design space are as important as any prescriptive design method. This work presents one of the underlying engineering technologies needed to leverage artificial intelligence approaches to thoroughly search the design space and synthesize concept solutions. Artificial intelligence methods are employed to generate a natural language to formal component terms thesaurus as part of a novel form-initiated concept generation approach. with this fundamental natural language interpretation algorithm, designers may now suggest an initial solution to a problem, expressed in everyday terms, and then rely on a machine to abstract the underlying functionality and conduct a thorough search of the solution space. Copyright © 2009 by ASME.
Recommended Citation
M. R. Bohm and R. B. Stone, "A Natural Language to Component Term Methodology: towards a Form based Concept Generation Tool," Proceedings of the ASME International Design Engineering Technical Conferences and Computers and Information in Engineering Conference 2009, DETC2009, vol. 2, no. PART B, pp. 1341 - 1350, American Society of Mechanical Engineers, Jun 2010.
The definitive version is available at https://doi.org/10.1115/DETC2009-86581
Department(s)
Mechanical and Aerospace Engineering
Publication Status
Available Access
International Standard Book Number (ISBN)
978-079184899-9
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2024 American Society of Mechanical Engineers, All rights reserved.
Publication Date
25 Jun 2010
