Production systems have always faced changes and disruptions, which require dynamic decision-making to adjust existing plans to the unfolding reality. The interdependence of highly interconnected supply chain networks further adds to this volatility. Given this complexity, mainly caused by ambiguity and the systems’ dynamic, achieving transparency to make decisions in the context of production planning and control is challenging. Simulation models can help assess the outcome of different scenarios through experiments. However, building simulation models by hand requires extensive manual effort and expert knowledge of simulation tools. Although often partly automated, simulation experiments still require the exertion of simulation engineers to be conducted on a large scale. Moreover, the created models are often static and require additional resources to be updated in order to reflect changes in the physical system. To reduce this effort, the authors propose a concept combining the automatic discovery of simulation models from execution data with the semi-automatic generation of scenarios. This facilitates logistical risk analysis and prediction by evaluating the consequences of possible disruptive events. The concept aims to enable domain experts to use digital twins in large-scale virtual scenario evaluation, which is fundamental for increasing the agility of manufacturing systems by speeding up decision processes.
Read full abstract