Multi-layered self organizing neural network for machine clustering

The design of cellular manufacturing systems (CMSs) is a complex problem which needs the consideration of a number of often conflicting objectives. The first step towards the design of a CMS or converting a firm´s facility into a cellular manufacturing layout is the development of an initial cell design which has evolved as a result of the consideration of a number of practical constraints. The authors present a multilayered neural network which can deal with practical constraints and objectives. These constraints and objectives are embedded within the network as transfer functions which help impose the practical constraints and guide the cell design process. A case study is presented which illustrates the efficacy of the network to deal with multiple constraints and come up with practical cell designs. The network is also capable of generating different cell configurations as specified by the user. The approach is comprehensive and can be easily expanded to include other constraints and objectives as needed