Towards an LLM-powered expert system for AAS-based product digital twin development

Manufacturing-as-a-Service (MaaS) is emerging as a cornerstone of Industry 4.0 and 5.0, enabling production requesters and providers to orchestrate manufacturing and supply chain processes as interoperable digital services. At the core of this paradigm are Product Digital Twins (PDTs), which extend beyond virtual representations of physical assets to encompass the entire product lifecycle—from design and configuration to maintenance, recycling, and sustainability compliance. In this context, accurate PDT design requires both deep product understanding and systematic integration of diverse information models, such as bill of materials, bill of services, and including Digital Product Passports (DPP) for circularity and regulatory authorities. This paper presents an initial conceptual approach to a Large Language Model (LLM)-powered expert system engineered to support Asset Administration Shell (AAS)-based PDT development within a MaaS ecosystem. It illustrates how an LLM-powered technology can support and augment domain experts and system engineers in collaboratively creating, refining, and deploying PDTs, thereby contributing to global manufacturing resilience.