Towards decision support for complex system architecture design with innovation integration in early design stages

摘要: The aim of this research work is to propose a method allowing innovation integration in early design stages and supporting architecture complex systems that have significant implications for the rest overall system life-cycle. Focusing on architectures generation support, proposes use Bayesian networks combined with Constraint Satisfaction Problem (CSP) techniques order semi-automatically generate evaluate architectures. network model used represent problem terms decision variables, constraints performances. Furthermore, an algorithm proposed feasible solutions cluster them regard given confidence level threshold. This representing estimation uncertainty system. Estimation performances are also calculated within network. Once generated, CSP optimises component placement regarding optimisation objectives defined by designers. Software has been developed purpose modelling visualisation. Two industrial implementations yielded high number solutions. In test feasibility selection environment, study was conducted integrating four underlined difficulties defining criteria provides recommendations future support.