An evolutionary computation based method for creative design inspiration generation

Jia Hao (), Yongjia Zhou (), Qiangfu Zhao () and Qing Xue ()
Additional contact information
Jia Hao: Beijing Institute of Technology
Yongjia Zhou: Beijing Institute of Technology
Qiangfu Zhao: University of Aizu
Qing Xue: Beijing Institute of Technology

Journal of Intelligent Manufacturing, 2019, vol. 30, issue 4, No 11, 1673-1691

Abstract: Abstract Product design is an important part of the manufacturing system from a macro point of view. In the design process, creative design is one of the important factors to survive the fierce competition. During creative design process, designers are the most critical component. However, design fixation often negatively influences the design outcomes. Many researches from cognitive science and design science reveal that the presentation of outer information can alleviate design fixation effectively. Among different kinds of outer information, language terms are proved to be effective. This work presents a method of automatically generating language terms as design inspirations based on 500,000 granted patents. This method adopts evolutionary computation as the fundamental algorithm to retrieve language terms from a vocabulary base. To implement the algorithm, the vocabulary is first encoded by high dimensional vectors through word embedding, which is a three layers neural network. Further, two metrics for measuring the inspiration potential of language terms are defined in a computable manner. This work also conducts experiments to validate the method, and the experimental results show that (1) the algorithm is efficient and has the potential to be extended to larger vocabulary; (2) the generated design inspirations have a positive influence on the design outcomes.

Keywords: Design fixation; Design inspiration; Evolutionary computation; Word embedding (search for similar items in EconPapers)
Date: 2019
References: View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://link.springer.com/10.1007/s10845-017-1347-x Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joinma:v:30:y:2019:i:4:d:10.1007_s10845-017-1347-x

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10845

DOI: 10.1007/s10845-017-1347-x

Access Statistics for this article

Journal of Intelligent Manufacturing is currently edited by Andrew Kusiak

More articles in Journal of Intelligent Manufacturing from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().