Feature-based memory association for group technology
This paper presents a new approach for group technology (GT) part family formation and multiple-application set formation using feature-based memory association performed by neural networks. The drawbacks of two GT approaches, production flow analysis (PFA) and coding and classification systems (CCS) are discussed. CCS is useful for similar part retrieval and new part assignment but not adequate for forming machine cells. PFA can form part families and machine cells simultaneously; however, routeing sheets are required and PFA does not provide specific methods for part information retrieval. These drawbacks are rooted in the fact that CCS depends on the relationships between parts and features and PFA relies on the relationships between parts and machines. The presented approach emphasizes the relationships between parts, features and machines together and incorporates memory association into family and cell formation. The feature-based memory association networks (FBMAN) system contains three sub-systems. The FBMAN-I system uses autoassociative memory and relationships between features and parts to cluster parts into families. It also overcomes the problems caused by exceptional parts and the presentation order of seed parts. The FBMAN-II system uses heteroassociative memory and relationship between parts features and machines to form machine cells without routeing sheets being provided. The FBMAN-III system, extended from the FBMAN-II system, can form multiple-application sets at the same time. A case study shows that the FBMAN-III system can also perform part information retrieval, similar part retrieval and new part assignment with autoassociative memory.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media