Application of an Autonomous Agent Network to Support the Architecture of a Holonic Manufacturing System

Abstract

To remain a competitive force in the world market, manufacturing enterprises must design and produce new products in an effective way. To reduce the product launching time, manufacturing enterprises must be versatile, open to changes, and capable of designing and modifying their own facilities and processes efficiently for the design of new products. In this context, the concept of autonomous, adaptive, cognitive and cooperating entities known as "holons" is conceived which leads to the evolution of a holonic manufacturing system (HMS) where highly distributed control paradigms are adopted to alleviate the problems related to frequent process disturbances. In order to streamline the functioning of an HMS, it is necessary to form an efficient, flexible and responsive network of agents, which are intra-holonic entities that inherit the same characteristics as the holons. This network of agents can be termed an autonomous agent network. The agent is formed by the parties, which are the functional units of the holonic manufacturing system. The aim of this paper is to specify the communication protocols and subsequently synthesise and cluster the individual parties into autonomous agents in accordance with the basic constraints of a holonic manufacturing system. Here a fuzzy c-means clustering algorithm is proposed to club the parties to capture effectively the uncertainty and imprecision associated with them. Besides the grouping of the parties to form agents, the proposed fuzzy-based clustering algorithm ensures that the agents formed are more amenable to the dynamic environment prevailing on the shop floor of present day automated manufacturing systems and thus makes the essence of a holonic manufacturing system successful . Keeping in mind the imprecision, uncertainty, and conflicting nature of objectives, the proposed approach aptly models the problem, and its applicability is exemplified by a test problem.