Learning Simulation-Based Digital Twins for Discrete Material Flow Systems: A Review

Digital Twins play a crucial role in the fourth industrial revolution. In the context of discrete material flow systems, companies under constant competitive pressure seek for solutions to minimize cost and maximize performance. Simulation-based digital twins can help taking optimal decisions in the design, planning and control of these systems. Such twins are until now developed and updated by domain experts producing costs and are often not considering the advances made in machine learning to improve prediction quality. Learning digital twins out of data could be the solution for a broader application. A lot of works has already been done that contributes to this endeavor, yet relevant building blocks originate from different scientific areas resulting in use of different terminology. Thus we present a holistic review of relevant work and analyze the state of the art based on a new classification scheme deriving relevant building blocks and gaps for future research.