IFAC LSS'98, Large Scale Systems: Theory and Applications, July 15-17, 1998, Rio Patras, Greece 73 FUZZY COGNITIVE MAPS MODELLING SUPERVISORY LARGE SCALE CONTROL SYSTEMS Chrysostomos D. Stylios, Voula C. Georgopoulos* and Peter P. Groumpos Laboratory for Automation and Robotics, Department of Electrical and Computer EngineeringUniversity of Patras, Rion 26500, GREECE *School of Electrical Engineering and Computer Science, Ohio University, Athens, OH 45701,USA Abstract: This paper investigates the implementation of a hybrid methodology, which combines fuzzy logic and neural networks, Fuzzy Cognitive Map (FCM), for the modeling of the supervisor of Large Scale Systems. The description and the construction of Fuzzy Cognitive Map will be extensively examined and it will be proposed a model for the supervisor. There is an oncoming need for more autonomous and intelligent systems, especially in Large Scale Systems and the application of Fuzzy Cognitive Map for the modeling of the Supervisor may contribute in the development of more autonomous systems. Copyright © 1998 IFAC. Keywords: Modeling, Supervisory Control, Cognitive Systems 1. INTRODUCTION Modern systems are characterized as large-scale systems with a variety of variables and factors. For complex dynamical systems, conventional methods have a limited contribution in modeling and controlling such systems. New methods are proposed for complex systems, which will utilize existence knowledge, human experience, will have learning capabilities and will have advanced characteristics such as failure detection and identification qualities. In this paper a new methodology, Fuzzy Cognitive Map (FCM), is proposed for modeling systems which may contribute to the effort for more intelligent control methods. A Fuzzy Cognitive Map draws a causal picture to represent the model and behavior of system, within this representation, concepts of FCM interact according to imprecise rules and the operation of the complex large scale system is simulated. Fuzzy Cognitive Map is a symbolic representation of the description and modeling of the system. It consists of concepts, that illustrate different aspects in the behavior of the system and these concepts interact each other showing the dynamics of the system (Kosko, 1986). The human experience and knowledge on the operation of the system is behind a Fuzzy Cognitive Map, as a result of the method by which it is constructed, i.e., using human experts that know the operation of system and its behavior in different circumstances. FCMs describe the behavior of a system in terms of concepts, each concept represents a state or a characteristic of the system (Dickerson and Kosko, 1994). FCMs illustrate the whole system by a graph showing the cause and effect along concepts, and are a simple way to describe the system’s behavior in a symbolic manner, exploiting the accumulated knowledge of the system. Fuzzy Cognitive Map (FCM) Theory, the methods that it uses to describe and model the behavior of a system and its application in the modeling the supervisor of large-scale systems are examined. (Stylios, et al., 1997). Fuzzy Cognitive Maps have been used for decision analysis, management science and operations research (Craiger, et al., 1996). The objective here is to focus on the use of FCM in modeling systems and show how appropriate FCMs are to exploit the knowledge and experience which has been accumulated for years on the operation of a complex plant. These technologies are crude analogs of systems that exist in human and animal systems and have their origins in behavioral phenomena related to these beings (Medsker, 1995). So, FCM represents knowledge in a symbolic manner and relates states, events and inputs in an analogous to