MasDISPO: A Multiagent Decision Support System for Steel Production and Control

Sven Jacobi, Esteban León Soto, Cristián Madrigal Mora, Klaus Fischer

In: Proceedings of the Twenty-Second AAAI Conference on Artificial Intelli. AAAI Conference on Artificial Intelligence (AAAI) The AAAI Press 7/2007.


In the majority of cases, steel production constitutes the inception of the Supply Chains they are involved just as in automotive clusters or aerospace. Steel manufacturing companies are affected strongest by bull whip effects or other unpredictable influences along the production chain to the customers. Therefore, flexible planning and realisation as well as fast reorganisation after interferences are indispensable requirements for a competitive position on the market. In this paper, MasDISPO, an agent-based decision support system for production and control inside the steel works of Saarstahl AG, a globally respected steel manufacturer, is presented. It is based on a distributed online planning and online scheduling algorithm to calculate solutions supporting production and control inside the melting shop. It monitors the execution of their chosen solutions and responds to unpredicted changes during production by dynamically adapting the schedules.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence