Automated retrieval and ranking of similar parts in agile manufacturing

Abstract

The environment considered is an agile enterprise where manufacturing partners share product related data to come up with new, customized, and high quality products at minimal leadtimes. Given this context, this paper addresses the problem of identifying existing parts that are similar, in one or many characteristics, to a new part at the design stage. The proposed method is based on the principles of group technology (GT), and on the definition of the neighborhood of similarity of critical design attributes. A two-step procedure is proposed: (1) a search procedure, which acquires and processes the designer's search intent to retrieve similar parts; and (2) a sorting procedure, which ranks these parts in order of their similarity to the candidate part. Both procedures are based on GT codes, while the second can employ more detailed critical design information. This information is assumed available in the product databases of distributed partners, and can be generated via an existing GT design processor. The approach employs a systematic procedure to combine independent similarity indexes to a unique measure for sorting. A software system using object-oriented technology has been developed to implement the procedure.