Association rule mining for product and process variety mapping

  • Authors:

  • J. Jiao;L. Zhang;Y. Zhang;S. Pokharel

  • Affiliations:

  • School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore;School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore;School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore;School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore

  • Venue:
  • International Journal of Computer Integrated Manufacturing
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

Today's manufacturers strive to design and produce a large number of customized products at low cost and quick turnround in order to survive market competition. The consequence of high product variety manifests itself through an exponentially increased number of process variants, which introduces significant constraints to production planning and control. Leveraging upon product and process families has been well recognized as an important area in which manufacturers can exploit mass production efficiency, wherein the linchpin of managing variety propagation from design to production lies in the mapping relationships between product differentiation and process variation. Taking advantage of knowledge discovery from historical data, this paper applies an association rule mining technique to deal with product and process variety mapping. The mapping relationships are embodied in association rules, which can be deployed to support production planning of product families within existing production processes. A case study of mass customization of vibration motors is presented to demonstrate how the association rule mining mechanism helps maintain the coherence between product and process variety. The performance of the association rule mining approach is further evaluated through sensitivity analysis.