A novel approach for part family formation for reconfiguration manufacturing system

Abstract

The Reconfigurable Manufacturing Systems (RMS) is the next step in manufacturing, allowing the production of any quantity of highly customised and complex parts together with the benefits of mass production. In RMSs, parts are grouped into families, each of which requires a specific system configuration. Initially system is configured to produce the first family of parts. Once it is finished, the system is reconfigured in order to produce the second family, and so forth. The effectiveness of a RMS depends on the formation of the optimum set of part families addressing various reconfigurability issues. For this, a two-phase approach is developed where parts are first grouped into families and then families are sequenced, computing the required machines and modules configuration for each family. In the First phase, parts are grouped into families based on their common features. The correlation matrix is developed as operations sequence similarity coefficient matrix. Principal Component Analysis (PCA) is applied to find the eigenvalues and eigenvectors on the correlation similarity matrix. A scatter plot analysis as a cluster analysis is applied to make parts groups while maximizing correlation between parts as per operations sequence similarity. Agglomerative Hierarchical K-means algorithm improved the parts family formation using Euclidean distance resulting a set of part families. In the second phase, optimal selection and sequences of the resulted part families is achieved by using a Mixed Integer Linear Programming (MILP) model minimizing reconfigurability and under-utilization costs to get the minimum cost solution.