An intelligent-agent framework for concurrent product design and planning

Abstract

This paper proposes a multi-agent framework to develop product design and planning using the concurrent engineering approach. The ideas in the framework draw on design-team behavior in many domains. The goal is to provide information that will help teams of designers, engineers and managers from various functional areas improve initial designs so that they satisfy a wider variety of concerns. Our model provides support to bring together constraints from the different team members in the development cycle. By integrating downstream constraints into the design phase, we reduce the need for redesign (due to design mistakes) later in the product development cycle. Our framework integrates a blackboard architecture with an intelligent agent (IA) network. Our methodology uses conflict-resolution (CR) techniques and design-improvement suggestions to refine the initial product design, and process plan generation and simulation to verify the manufacturability of the design. The contributions of the paper are threefold. First, our framework provides a more realistic way of modeling design teams by providing a way to model an individual team member's perspective as a segment of a continuum of task knowledge. Second, we identify the essential components of concurrent engineering needs, and develop a framework for integrating these components so as to ensure adequate coordination among the processes involved. Third, our methodology uniquely meshes together design constraints with factory resource considerations, so that the final product design is ensured to be feasible and manufacturable.