
HUMAN COGNITION INSPIRED PROCEDURES FOR PART FAMILY FORMATION BASED ON NOVEL INSPECTION BASED CLUSTERING APPROACH
Author(s) -
Naga Sai Ram Gopisetti,
Leonilde Varela,
José Manuel Machado
Publication year - 2021
Publication title -
dyna
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.177
H-Index - 11
eISSN - 1989-1490
pISSN - 0012-7361
DOI - 10.6036/9997
Subject(s) - heuristics , grasp , cluster analysis , cognition , computer science , artificial intelligence , graph , machine learning , benchmark (surveying) , theoretical computer science , psychology , geodesy , neuroscience , programming language , geography , operating system
Human cognition based procedures are promising approaches for solving different kind of problems, and this paper addresses the part family formation problem inspired by a human cognition procedure through a graph-based approach, drawing on pattern recognition. There are many algorithms which consider nature inspired models for solving a broad range of problem types. However, there is a noticeable existence of a gap in implementing models based on human cognition, which are generally characterized by “visual thinking”, rather than complex mathematical models. Hence, the natural power of reasoning - by detecting the patterns that mimic the natural human cognition - is used in this study as this paper is based on the partial implementation of graph theory in modelling and solving issues related to part machine grouping, regardless of their size. The obtained results have shown that most of the problems solved by using the proposed approach have provided interesting benchmark results when compared with previous results given by GRASP (Greedy Randomized Adaptive Search Procedure) heuristics.Keywords: Cellular manufacturing systems; part family formation; human cognition; inspection-based clustering.