RégéNexus

This work proposes an innovative approach to structuring and managing recycling value chains as dynamic, interconnected and territorially integrated networks.

Based on Systems of Systems (SoS) engineering, the project aims to overcome the limitations of local optimization by integrating multi-level interactions, complex feedback loops and sectoral constraints.

This vision facilitates the coordination of players with potentially divergent objectives, while offering the flexibility needed to respond to uncertain material flows and rapidly changing market and regulatory conditions.

Digital sciences play a central role in this approach, providing the methods and tools needed to model, simulate, analyze and orchestrate these complex networks while integrating technical, economic, environmental and social constraints. The project's main lines of research include:

• Multiscale control: integrating decision-making from the nano level (material, product) to the macro level (territorial or national strategy), taking into account complex interactions and deferred impacts.
• Flow traceability: Use of digital twins to model and track material flows throughout their life cycle, offering greater transparency for industrial players.
• Management of uncertainties: Development of robust tools based on artificial intelligence, machine learning and data fusion to deal with heterogeneous, incomplete and uncertain information. 
• Flexibility and adaptability: Leveraging digital platforms and simulation tools to rapidly adapt to changes in the market, regulations or materials availability. 
• Dynamic orchestration: Coordination of data flows and real-time decision-making to optimize the overall performance of value chains.
• Autonomy and coordination of subsystems: Guarantee interoperability between players while preserving their autonomy thanks to distributed, reconfigurable architectures. 
• Hyperspectral analysis and materials sorting: Developing advanced materials characterization technologies, such as hyperspectral imaging and deep learning, to improve the sorting, separation and regeneration of complex materials.