A mathematical approach for the formation of manufacturing cells

One of the major steps in designing cellular manufacturing systems is to form cells. This involves identification of machine cells and part families. This paper proposes a new mathematical approach for forming manufacturing cells. The proposed approach involves two phases. In the first phase, machine cells are identified by applying factor analysis to the matrix of similarity coefficients. In the second phase, an integer-programming model is used to assign parts to the identified machine cells. To evaluate its performance, the proposed approach was applied to sample problems from the literature and a real life problem from a manufacturing plant. The results indicate that the proposed approach performs very well in terms of a number of criteria and compares favorably to well-known existing cell formation methods. In addition to its good performance, the proposed approach has the flexibility to allow the cell designer to either identify the required number of cells in advance, or consider it as a dependent variable. Using algorithms which are available in many commercial software packages is the other advantage of the proposed approach.