Агентно-ориентированный подход к проектированию гибких производственных систем

Abstract

The article considers the process of designing modules of a flexible production site using multi-agent technology. For a comprehensive organization of the design, there has been proposed an algorithm of intelligent automated design of the complex technical systems, flexible manufacture systems (FMS) being used as an example. It has been stated that the research at the stages of the conceptual design of the FMS is carried out by collecting prototype variants with using expert knowledge and interaction of agents-designers according to the method of self-realizing computer aided design. Building a distributed system for the intelligent design of a hybrid architecture using the features of agent technology is considered. A flexible manufacture system is chosen as a design object, which is a complex technical object of research, the process of its design is multi-stage and iterative. To design such systems using 
 a common functional model at the initial stage, a set of tasks is defined to facilitate the computing design of the FMS. This approach to the design of FMS requires implementing the solutions of a large number of local problems 
 of different purposes. To solve the local problems of design procedures there has been proposed a multi-agent design technology, where the agent-designer performs a specific local task of the design process. The developed formalisms and algorithms help automate the synthesis of technical objects of the FMS. To build an automated conceptual design system as main decision-making for the multi-agent systems, there has been proposed a technical solution based on the knowledge of intelligent multi-agent systems. Using a multi-agent system makes it possible to build a distributed parallel design system with ability to be transferred to various hardware and software platforms. There has been also proposed the structure of a multi-agent system for the intelligent computer-aided design based on the designer's knowledge base.