The manufacturing industry is facing an escalating threat landscape, as cybercriminals develop increasingly sophisticated attack vectors that exploit the convergence of IT and Operational Technology (OT) through the proliferation of Internet of Things devices. Effective security management demands up-to-date and comprehensive knowledge of systems under protection. This paper presents a novel approach to modeling OT networks, significantly enhancing threat hunting capabilities and leveraging the power of the Asset Administration Shell. We detail a methodology for accurately modeling network aspects, alongside a robust framework for securing collected data, enabling its utilization as a trusted and centralized knowledge base for security-critical applications. Built upon established Industry 4.0 standards, our preliminary metamodel demonstrates the potential for semi-automated modeling of complex OT environments and the associated data flows. This facilitates improved situational awareness, supports proactive threat detection, and addresses the inherent challenges of data inconsistency often found within OT environments. Furthermore, the model provides powerful visualization of relationships within OT processes, enabling the detection of yet undiscovered attack patterns.

Checking and ensuring product quality is an important element in many B2B scenarios. However, the process of quality management is often not yet digitalized and therefore usually comes with large efforts. This is especially true in food productions industry. This paper presents a model based approach for a digitalized quality audit in production of food beverages. The proposed method used the Asset Administration Shell (AAS) in combination with Business Process Model and Notation (BPMN) to provide an open interface for machine operators to conduct quality audits. The concept follows a model based approach, where every part can be processed on different IT infrastructure depending on the demanded requirements for data sovereignty and security.

In view of the dynamic cybersecurity threat land-scape and the increasingly interconnected information technol-ogy (IT) and operational technology (OT) environments, the management of security risks to both IT and OT systems becomes paramount, including efficient and comprehensive risk assessment. Such risk assessments, however, require extensive manual work, the availability of trained security personnel as well as considerable time and financial resources. Additionally, a consistent quality of results often cannot be guaranteed due to a dependency on individual expert knowledge and experience. A promising approach to alleviate these challenges is to use software-based support to automate risk assessment processes and increase efficiency and consistency. This work proposes a con-cept for software-supported automated security risk assessments with a focus on industrial components and the manufacturing industry. It presents key challenges, solution approaches, and further research directions that need to be considered in order to practically implement the concept. Additionally, current research that is already in process towards a practical implementation and a preliminary software prototype are presented.

In order to utilize the full potential of an assembly assistant, it is necessary for the system to be able to adapt to the worker’s individual needs and capabilities. The required amount of necessary assistance changes during the assembly work because the worker memorizes the steps and learns the task and might be bothered by unnecessary assistance. Finding the point in time where the learning phase of the worker is finished is therefore an important aspect. In this work, we propose and evaluate a novel method to identify the end of the worker’s learning phase. The method makes use of learning curve models and curve fitting in order to determine the progress of the worker.

In production environments, manual assembly is often used, when there is a high demand for flexibility which needs to be met economically. In this circumstance, assembly assistance systems are often used to ensure production standards. However, the individual requirements of each worker call for a way for the system to adapt towards the workers needs. This often requires modelling and configuration effort to include expert knowledge into an assistance system. This hinders an economical operation in an industrial environment. In this paper, an approach is presented, facilitating methods of online modelling, to generate a model, which represents the workers behavior during an assembly process. This behavior model is then used to deduce suitable adaptive assembly assistance in real time.

Data-driven algorithms can be used to derive new information from data. In modern production plants, this can be used to reduce manual effort, e.g. to create a behavior model. In this work, one offline and one online algorithm are introduced that can determine the production cycles automatically. The algorithms use learned automaton to detect production cycles. A first evaluation is presented, which points out differences of the algorithms. However, overall the results are promising.

The vision of smart factories are self-diagnosing, self-optimizing and self-adapting Cyber-Physical Production Systems (CPPS). Self-adaption, on which this paper focuses on, means that the CPPS can adapt itself to a changing environment, so that the downtime costs can be reduced by using the system modules most efficient. An architecture is introduced and demonstrated on a concrete use case to show how this capability can be achieved by using different Artificial Intelligence (AI) techniques. For each technique, we define challenges that have to be solved to use it in a real world environment. Additionally, we illustrate the symbolic and subsymbolic AI and argue why symbolic AI is an important aspect in the context of CPPS.

Many production processes are still realized with manual assembly, due to its flexibility and efficiency. The individual needs of the customers lead to a bigger variety of products and components in manual assembly workstations. With the variety of the components and products, the scope of the manual assembly workstation as well as its overall complexity increases. In this paper, we present a method to counter this effect by dividing the manual workstation into multiple subsystems. Our method minimizes the number of times a worker has to switch between the individual subsystems in order to search for components. Experimental results indicate that our method performs better on this task compared to other approaches and can this way be used to increase the productivity of a manual assembly workstation.

The design processes of todays more and more complex automation systems require computer-based support to maintain their manageability. As a base for that, the authors introduce a holistic design approach for these systems. Requirements on the system to be designed are represented by an extended feature model which serves as consistent requirements model during the entire design process. A grammar-based synthesis applies formalised expert knowledge to generate solutions to these requirements. The paper's main contribution is to combine formalisms from overlapping areas of artificial intelligence and software engineering to obtain a holistic design process for industrial automation systems.

In this paper, the authors present an engineering approach for generating automation system solutions based on formalised requirements. This enables assistant systems which guide engineers during the design phase of todays more and more complex automation systems. A software prototype is used for the evaluation of this approach in practice. The main contribution is to directly use a formal requirements model as input for the automated synthesis of automation systems and to formalise the expert knowledge for this synthesis. The result are consistent, maintainable automation systems and with that shorter and reproducible development cycles.

Today's production plants are not conceivable without automation systems. Due to the increasing complexity of production plants and therefore of automation systems, delays and interruptions in automation projects are observed. A design model for more efficient planning of industrial automation systems is introduced. It is based on a new and practical proceeding for the construction of a requirements model. Extended feature models as formal requirements representation enable to verify the consistency of requirements. New insights on the necessary capabilities of a formal reasoning system for planning the whole automation system are deduced from the design model.