A generalised fuzzy least-squares regression approach to modelling relationships in QFD

Chun Kit Kwong, Y. Chen, K. Y. Chan, X. Luo

Research output: Journal article publicationJournal articleAcademic researchpeer-review

38 Citations (Scopus)


In quality function deployment (QFD), information regarding relationships between customer requirements and engineering specifications, and among various engineering specifications, is commonly both qualitative and quantitative. Therefore, modelling the relationships in QFD always involves both fuzziness and randomness. However, previous research only addressed fuzziness and randomness independently of one another. To take both the fuzziness and andomness into account while modelling the relationships in QFD, fuzzy least-squares regression (FLSR) could be considered. However, the existing FLSR is only limited to developing models based on fuzzy type observed data and modelling relationships in QFD often involves both crisp type and fuzzy type observed data. In this article, a generalised FLSR approach to modelling relationships in QFD is described that can be used to develop models of the relationships based on fuzzy observations and/or crisp observations. A case study of a packing machine design is used in this article to illustrate the proposed approach.
Original languageEnglish
Pages (from-to)601-613
Number of pages13
JournalJournal of Engineering Design
Issue number5
Publication statusPublished - 24 Sept 2010


  • Customer satisfaction
  • Functional modeling
  • Fuzzy least-squares regression
  • Fuzzy techniques
  • Quality function deployment
  • Relationship modelling

ASJC Scopus subject areas

  • Engineering(all)


Dive into the research topics of 'A generalised fuzzy least-squares regression approach to modelling relationships in QFD'. Together they form a unique fingerprint.

Cite this