Information systems engineering with Digital Shadows: Concept and use cases in the Internet of Production

Abstract

Entering the second decade of the Industrie 4.0 vision, the production sector is facing challenges in taking full advantage of global digitalization. Production research has focused on sophisticated mathematical models ranging from molecular materials modeling to production control to supply chain logistics. These models help simulate and control the related physical system but the variety of individual situations and behaviors is captured only as statistical uncertainty. The emergence of data-driven methods adds statistical or AI models learned from real-time production data to Digital Twins, and ideally allows for continuous synchronization (twinning) between physical and virtual system.However, the complexity of today’s production systems precludes Digital Twins covering more than just a few system perspectives, especially if realtime performance is required. To achieve better performance and more precise context adaptation, the interdisciplinary research cluster “Internet of Production” at RWTH Aachen University is exploring the concept of Digital Shadows. We conceptualize Digital Shadows as a generalization of compact views on dynamic processes, whose defining “query” combines condensed measurement data with efficient simplified mathematical models. Their small size makes Digital Shadows amenable to dynamic function allocation in hybrid cloud–edge settings. In addition to showing the similarities and differences to the traditional view concept, we also present a conceptual embedding of Digital Shadows in the context of large distributed system architectures, and sovereign data exchange in international Data Space communities. Two production use case experiences demonstrate that Digital Shadows can be valuable carriers of deep and reusable engineering knowledge for technical and ecological progress.