Structured intelligence for self-organizing manufacturing systems NAOYUKI KUBOTA 1 and TOSHIO FUKUDA 2 1 Department of Mechanical Engineering, Osaka Institute of Technology,Omiya 5-16-1, Osaka 535, Japan 2 Department of Micro System Engineering, Nagoya University, Furo-cho 1, Chikusa-ku, Nagoya 464-01, Japan This paper deals with fuzzy scheduling and path planning problems by genetic algorithms. We have proposed a self-organizing manufacturing system (SOMS) that is composed of a number of autonomous modules. Each module decides output through interaction with other modules, but the module does not share complete information concerning other modules in the SOMS. Therefore, we require structured intelligence as a whole system. In this paper, we consider a manufacturing line composed of machining centres and conveyor units. The manufacturing procedure can be divided into a sequence of three modules: (a) tool locating module, (b) scheduling module, and (c) path planning module. The tool locating problems have been already solved. In this paper, we ®rst solve the scheduling problem as global preplanning. Here we assume that the processing time is not constant, because some delay may occur in the machining centres. We therefore apply fuzzy theory to represent incomplete information about the machining time. We solve the fuzzy scheduling problem with a genetic algorithm. After global preplanning, the path planning module transports materials and products. Next, the scheduling module acquires the actual processing time of each machining centre. Based on the processing time, the schedule module generates a fuzzy number for the processing time. We discuss the eectiveness of the proposed method through the computer simulation results. Keywords: Intelligent manufacturing system, self-organization, genetic algorithm, fuzzy theory, scheduling problem 1. Introduction Recently, intelligent systems have been discussed in various ®elds such as knowledge engineering, computer science, mechatronics and robotics. In general, the intelligent sys- tem requires learning ability, a reasoning mechanism, and others, on the fundamental abilities of sensing decision making and action. The intelligence of a system emerges from the close linkage of these abilities as a whole system. Furthermore, the intelligence of systems evolves through learning and adaptation to dynamic environments. Vari- ous methodologies concerning intelligence have been suc- cessfully developed with the progress of computation capability. Arti®cial intelligence (AI) describes and builds an intelligent agent, which perceives its environment, makes decision and action (Russell and Norvig, 1995). McCulloch and Pitts suggested that suitably de®ned net- works could learn (Anderson and Rosenfeld 1988), and furthermore, Newell and Simon developed the General Problem Solver (Russell and Norvig, 1995). Afterwards, knowledge-based systems, including expert systems, were developed. Furthermore, the recent research ®elds concerning intel- ligence, include brain science,soft computing, arti®cial life and computational intelligence (Zadeh, 1965; Anderson et al., 1988; Marks, 1993; Zurada et al., 1994; Langton, 1995; Palaniswami et al., 1995; Russell and Norvig, 1995; Jang et al., 1997). It is very dicult to distinguish one research ®eld from another, but we simply describe the aim of each research ®eld. Brain science aims to understand the bio- chemical and physical mechanisms of the human brain and to construct a highly interconnected neural network similar to a human brain (Anderson et al., 1988; Zurada et al., 1994; Pu and Hughes, 1994; Palaniswami et al., 1995; Russell and Norvig, 1995). Soft computing, which was proposed by Zadeh, is a new concept for information processing, and its objective is to realize a new approach for analysing and creating ¯exible information processing of human beings such as sensing, understanding, learning, recognizing and thinking (Zadeh, 1965; Jang et al., 1997). Arti®cial life Journal of Intelligent Manufacturing (1999) 10, 121±133 0956-5515 Ó 1999 Kluwer Academic Publishers