Knowledge modelling for supporting decision making in optimal distributed design process

Abstract

A methodology for distributed knowledge modeling will be presented in this article, in order to contribute to a better decision making during design problems analysis. An optimal design process refers to setting up coherent numerical models and it requires a well structured problem definition. However, a lack of downstream information in early stages of product development leads to a complicated elicitation task that became an issue due to nowadays distributed environments. A Multi-Agent approach is proposed to support the distributed knowledge elicitation process. A set of agents will guide members from the distributed design team, throughout the product life cycle, to extract relevant information and analyze it. The interaction among agents will highlight potential incoherencies during the modeling process, in order to enable partners to avoid inconsistent information. A coherent knowledge base is then constructed and ready to be used to create models to be analyzed by traditional inference engines such as optimization solvers, constraint satisfaction programming, etc.