Machine Component Clustering with Mixing Technique of DSM, Jaccard Distance Coefficient and k-Means Algorithm

EasyChair Preprint 2296

Abstract

This study aims to introduce a design method for machine component clustering into independent modules so that a machine can be easily modified to achieve its requirement functions. In this study, three techniques of DSM, Jaccard Distance Coefficient and k-Means algorithm are together applied with the 40-component autonomous machine to group all machine components into modules. Clustering steps consist of three steps: 1) Generate a relation matrix, 2) Calculate relationship distance coefficients to build the tree dendrogram and 3) Analyze relationship distance coefficients to find the proper level coefficient. The result shows that the modules of the second level are the most natural.

Keyphrases: AHP, Jaccard Method, K-means algorithm, complete linkage, modular design

@booklet{EasyChair:2296,
  author    = {Tanongsak Kongsin and Sakon Klongboonjit},
  title     = {Machine Component Clustering with Mixing Technique of DSM, Jaccard Distance Coefficient and k-Means Algorithm},
  howpublished = {EasyChair Preprint 2296},
  year      = {EasyChair, 2020}}