A Cuckoo Search Clustering Algorithm for Design Structure Matrix

Abstract

Modularity is a concept that is applied to manage complex systems by breaking them down into a set of modules that are interdependent within and independent across the modules. Benefits of modularity are often achieved from module independence that allows for independent development to reduce overall lead time and to reach economies of scale due to sharing similar modules across products in a product family. The main objective of this paper is to support design products under modularity, cluster products into a set of modules or clusters, with maximum internal relationships within a given module and minimum external relationships with other modules. The product to be designed is represented in the form of a Design Structure Matrix (DSM) that contains a list of all product components and the corresponding information exchange and dependency patterns among these components. In this research Cuckoo Search (CS) optimization algorithm is used to find the optimal number of clusters and the optimal assignment of each component to specific cluster in order to minimize the total coordination cost. Results obtained showed an improved performance compared to published studies.