Building a database for product design knowledge retrieval-A case study in robotic design database

Jie Sun*, Wen Feng Lu, Han Tong Loh

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)


In product design process, when dealing with technical problems or initiating a new design, R&D personnel would often turn to technical database to seek inspiration. The building of a database with such documents has not been systematically dealt with. In this paper, several issues on how to build up a product design database are investigated: input source, sampling scheme and quality control. A case study of building a database for robotic design is used to demonstrate the concept. It is an archive of more than 1500 relevant technical papers. A total of 16 graduates are employed as operators in the labeling process and subsequently the hypothesis tests are utilized to process the labeling results. To ensure this database quality, the labeling consistency of each operator and the understanding of each category are tested. With the use of statistical methods, this work proposes a feasible and practical way to create such a database for product design.

Original languageEnglish
Pages (from-to)224-229
Number of pages6
JournalRobotics and Computer-Integrated Manufacturing
Issue number3
Publication statusPublished - Jun 2010
Externally publishedYes


  • F-test
  • Labeling policy
  • Product design
  • Robotic design database
  • t-test

Cite this