This paper deals with the cell formation problem that is the first step in designing cellular manufacturing system (CMS). The previous methods that were based on the array-based clustering for solving the cell formation problem have used the part-machine incidence matrix (PMIM) which was indicated the set of machines for processing each part. The main problem of these methods is the grouping parts and machines regardless of production volume, operational sequences, production cost, inventory and other production system's limitations. In this paper we intend to implement the multiple attribute decision making (MADM) concepts for covering the cause of drawback in the previous array-based clustering methods by considering two definitions of the arrays in PMIM. Four methods are presented that two methods are related to the binary arrays in PMIM and other two methods are considered the operational time as well as the operational sequencing in the definition of the arrays in PMIM. The results of the presented methods that are compared with a well-known approach are also reported.
[1]
Paul J. Schweitzer,et al.
Problem Decomposition and Data Reorganization by a Clustering Technique
,
1972,
Oper. Res..
[2]
J. King.
Machine-component grouping in production flow analysis: an approach using a rank order clustering algorithm
,
1980
.
[3]
M. Chandrasekharan,et al.
An ideal seed non-hierarchical clustering algorithm for cellular manufacturing
,
1986
.
[4]
M. Chandrasekharan,et al.
Grouping efficacy: a quantitative criterion for goodness of block diagonal forms of binary matrices in group technology
,
1990
.
[5]
D. A. Milner,et al.
Direct clustering algorithm for group formation in cellular manufacture
,
1982
.
[6]
Menouar Boulif,et al.
A new branch-&-bound-enhanced genetic algorithm for the manufacturing cell formation problem
,
2006,
Comput. Oper. Res..