In the composites industry, each change must take into account lot of parameters before being able to set it up. This requires an important amount of data sharing in a limited time. Nonetheless, only a minor part of this data is concretely used by the planners for an almost real- time analysis and optimization within production systems.

This paper proposes a multi-agent approach for dynamic planning integrated to production and maintenance. According to the supply chain operations reference model (SCOR), to focus on the process of transforming products to a finished state to meet projected or actual demand, we will work on the “make” area of supply chain.

This paper aims to present the problem of supply chain dynamic planning considering maintenance interventions and using a multi-agent system (MAS). The main objective of the system is ensuring collaboration between three different entities, planning, production and maintenance in order to take better decisions. To model the proposed system, we used the multi- agent system engineering (MaSE) methodology.