In: Journal of Intelligent and Fuzzy Systems, Vol. 7, No. 2, pages 137-149. 1999.
Abstract: In this paper, a contribution was made in developing a Fuzzy Coloured Petri Nets (FCPNs) model for description and analysis of the dynamic behavior and inexact production inference of Flexible Manufacturing Systems. The basic idea is to integrate the concepts of Coloured Petri Nets and Fuzzy Petri Nets, where the former is good at modeling complicated concurrent processes with embedded data structures, while the latter is good at modeling systems that involve approximate reasoning and uncertainty knowledge inference. Furthermore, a method of assigning a weight parameter to each proposition in the antecedent of a fuzzy production rule is developed which can be used to model the relative degree of importance of each proposition in the antecedent contributing to the consequent. A new weighted fuzzy production rule evaluation method is also devised. Our approach can be used to model and analyze Fuzzy Expert Systems that are used in controlling or supervising flexible manufacturing processes. Throughout this paper, a printed circuit board production system is used to demonstrate the model's capability in simulating the system behavior with weighted fuzzy control rules.
Keywords: deadlock prevention, knowledge representation, reasoning algorithms.