Model-based systems engineering and digital twins for industrial control systems

The big vision of the Josef Ressel Center for Intelligent and Secure Industrial Automation (JRC ISIA) is the creation of a digital assistant for industrial control systems of discrete automation (e.g., production systems) that shall assist humans and intelligently control machines. A conceptual overview is shown in the following figure:

Such a digital assistant acts to a certain extent as a digital twin of the machines in the sense of Kritzinger¹ on the one hand and as an intelligent agent in the sense of Russel & Norvig² on the other hand.

Aside from control, AI and security research the following research lines concerning architectural aspects originated from the above vision:

1. Aspects of model-based system architectures and digital twins for industrial control systems.

2. Aspects of OPC UA architectures that enable the integration of AI and Big Data into industrial control systems.

3. Aspects of OT security architectures and threat modeling for industrial control systems.

Here we present the first of those research lines. In the first phase of the JRC ISIA we built up a complete production testbed with three injection molding machines, four robots, a conveyor system, a SCADA system and the entire IT infrastructure. All has been implemented with components of our company partners B&R Industrial Automation, COPA-DATA and SIGMATEK. Below is a picture of the production scenario and the testbed.

From this vision originate research questions concerning the overall system architecture, the convergence of IT and OT and the integration of machine learning operations into these architectures. Digital twins and model-based systems engineering are methods we investigated to this end.

Embedding MLOps into OT Reference Models

In [SBLH25] we analyzed the obstacles when combining MLOps with OT environments and proposed a systematic approach to embed MLOps practices into established OT reference models.

We evaluated the suitability of the Reference Architectural Model for Industry 4.0 (RAMI 4.0) and the ISA-95 model of the automation pyramid for MLOps integration and presented a detailed mapping of MLOps lifecycle components to RAMI 4.0 exemplified by a real-world use case. Our findings demonstrate that while standard MLOps practices cannot be directly transplanted to OT environments, structured adaptation using existing reference models can provide a pathway for successful integration.

Digital Twins as Enablers for IT-OT Integration

In [WSBHH23] we proposed the so-called Industrial Business Process Twin (IBPT) as a digital twin of business processes to enable IT-OT integration. The IBPT acts as an intermediary between the realms of IT and OT, allowing for the application of methods from one domain to another through a representation that is in bidirectional exchange with the other domain. This work provides three contributions:

1. Illustration of Digital Twins (DTs) of industrial business processes for interconnecting IT and OT systems.

2. A novel way of reducing OT system complexity from an IT perspective by providing unified interfaces to OT systems through the IBPT.

3. Service Oriented Architecture (SOA)-centric business case modeling approach for industrial settings, which allows for an easy integration of IT and OT components, based on OPC UA.

We demonstrated the IBPT concept in a gamified Industry 4.0 scenario of playing the game of Nine Men’s Morris, which serves well for agent-based Artificial Intelligence (AI) research and education. We developed an Open Platform Communications Unified Architecture (OPC UA) information and communication model and evaluated the IBPT component with respect to the different views of the Reference Architecture Model Industry 4.0 (RAMI4.0).

This way we demonstrate all four essential Industry 4.0 design paradigms identified by Hermann³: information transparency, technical assistance, decentralized decisions and and interconnection.

In [SWRBNH24] we built upon the previously introduce IBPT concept and investigated the effects of this approach during the design phase. We argued that, by eliminating potentially conflicting direct interfaces between IT and OT stakeholders within the organizational structure, this approach effectively eliminates conflicting communication channels within the system design.