Key points are not available for this paper at this time.
Digital Twins (DTs) are foundational in smart manufacturing, supporting data-driven monitoring and optimization. Yet, many implementations remain monolithic, limiting interoperability and reusability. This paper introduces a semantic and modular architecture for orchestrating AI-driven DTs, designed to enable scalable integration and standardized coordination across industrial systems. The system employs a semantic API aligned with NGSI-LD, to expose industrial entities such as processes, anomalies, assets, and contextual KPIs (e.g., energy usage, CO 2 emissions, tool wear, product quality). AI techniques ranging from threshold adjustment to symbolic learning are encapsulated as modular agents, each performing targeted optimization tasks. These agents operate over the semantic API, which ensures consistent, interpretable interactions across modules. A Manager and a Recommender agent are defined to coordinate execution; while not yet deployed at runtime, their logic is implemented through semantic interfaces that support traceable, modular activation. The system is validated using synthetic data simulating machining, assembly, and inspection tasks. Results show measurable improvements in sustainability-related KPIs following each module’s activation. More importantly, the semantic orchestration layer enables modularity, interoperability, and AI reuse. This work contributes a standards-compliant foundation for next-generation DTs, supporting integration with ecosystems such as FIWARE, Catena-X, and IDS, and aligned with the principles of Industry 4.0 and 5.0. • Semantic data space (NGSI-LD) enables traceable and secure Digital Twin exchange. • A multi-agent layer coordinates four plug-and-play real-time optimization modules. • AI services include Threshold Tuning, Anomaly Repair, and Pattern Optimization. • Data space supports pub/sub, IDS policies, and semantic lifecycle metadata. • Bench tests show less CO 2 , better energy use, and improved product quality.
Juarez et al. (Tue,) studied this question.