📅 August 23–28, 2026
📍 Busan, Korea
We are excited to announce our Open Invited Track on:
DigitalTwins and Artificial Intelligence are reshaping the way industrial systems are engineered, monitored, and operated.
The Asset Administration Shell (AAS) - a key enabler of Industry40 - provides a standardized, interoperable, and semantically rich representation of industrial assets, enabling structured data exchange across organizations and systems.
When combined with AI technologies, AAS-based infrastructures enable new capabilities: automated ingestion and contextualization of industrial data, AI-enhanced engineering workflows, predictive maintenance, and autonomous operations - all while supporting confidential, resilient, and on-premise AI deployments at the industrial edge.
This track brings together experts from academia and industry to discuss semantic interoperability, trustworthy AI, local AI, digital twins, and scalable architectures for engineering and automation. Contributions may include theoretical models, system architecture, and case studies demonstrating the integration of AAS and AI in industrial environments.
✅ Key topics include:
👉 Submit your paper via the IFAC World Congress 2026 (Busan, Korea) submission system (https://ifac.papercept.net/conferences/scripts/start.pl) (select "Submit a contribution to IFAC WC 2026" and "Submit Open invited track paper" and enter the submission code: 𝗺𝘆𝟴𝘆𝟭).
Organizers:
Abstract
The integration of standardized digital asset representations and intelligent automation technologies is transforming engineering and operations of industrial systems. The Asset Administration Shell (AAS), a key enabler of Industry 4.0, provides semantically rich and interoperable digital representations of assets, facilitating structured data exchange across organizational and system boundaries. When combined with Artificial Intelligence (AI), AAS-based infrastructures enable the automated ingestion and contextualization of data from enterprise sources such as raw data, data lakes, data ware-houses, and industrial information systems. These enriched digital representations serve not only as a semantic back-bone for engineering workflows (such as system design, configuration, and lifecycle management) but also as operation-al enablers for tasks like predictive maintenance, process optimization, and autonomous control within industrial auto-mation environments. Advances in local LLM deployments also allow the processing of this data on customers’ premises (e.g., within an industrial edge) to accommodate with high confidentiality and resilience requirements of industrial cus-tomers.
This invited track will explore the scientific and practical advancements in digital data exchange enabled by AAS and AI. It will bring together experts from academia and industry to discuss semantic interoperability, trustworthy AI, local AI, digital twins, and scalable architectures for engineering and automation. Contributions may include theoretical models, system architecture, and case studies demonstrating the integration of AAS and AI in industrial environments.
Detailed Description
The digital transformation of engineering and industrial automation systems is increasingly shaped by the convergence of standardized data exchange frameworks and intelligent technologies. Central to this transformation are Industry 4.0 enablers such as the Asset Administration Shell (AAS), OPC UA, and AutomationML, which together provide the founda-tion for interoperable, scalable, and semantically rich digital infrastructures.
The AAS serves as a digital representation of industrial assets, encapsulating their properties, capabilities, and lifecycle information in a structured and machine-readable format. When integrated with OPC UA, a widely adopted industrial communication protocol, AAS enables secure and standardized data exchange between heterogeneous systems, includ-ing PLCs, SCADA, MES, edge, and cloud platforms. This interoperability is essential for holistic engineering workflows such as system design, configuration, commissioning, and lifecycle management, as well as for operational tasks like predictive maintenance, process optimization, and autonomous control.
Recent work has emphasized the role of semantic interoperability in aligning data models across domains. Ontology-based approaches and companion specifications (e.g., OPC UA Companion Specifications) ensure that engineering se-mantics are preserved and understood across systems. Bousdekis (2025) introduced the Semantic AAS as an ontology-driven framework for modeling digital twins, enabling sustainable interoperability in Industry 4.0 environments. Similar-ly, Chavez and Wollert (2024) developed an Industry 4.0 ontology to support semantic integration at the field level, bridg-ing gaps between automation systems and enterprise platforms.
The integration of Artificial Intelligence (AI) with AAS-based infrastructures allows for the automated ingestion and con-textualization of data from sources such as raw sensor streams, data lakes, and enterprise data warehouses. These en-riched digital twins serve as operational enablers for intelligent decision-making, anomaly detection, and closed-loop control. Sajadieh and Noh (2025) reviewed the convergence of AI and digital twins, highlighting their role in simulation-based autonomy and smart manufacturing. Zhang et al. (2025) further explored AI-enhanced digital twin systems engi-neering as a pathway toward the industrial metaverse and Industry 5.0.
Beyond AAS, technologies like OPC UA FX and AutomationML are increasingly used to support plug-and-produce capa-bilities, dynamic reconfiguration, and skill-based production planning. The joint discussion paper by AutomationML e. V., IDTA, OPC Foundation, and VDMA (2023) outlines a comprehensive vision for industrial interoperability, emphasizing the complementary roles of these technologies in achieving cross-domain integration.
This invited track will explore the following themes:
In this track, we seek to create meaningful exchange between disciplines, driving forward innovation in digital data ex-change and intelligent automation. By connecting diverse perspectives from engineering, AI, and industrial systems, we aim to support the development of automation solutions that are not only technically robust, but also transparent, adaptable, and ready for real-world deployment.
References
Copyright © AUT 2025
Letzte Änderung: 12. Nov. 2025