Time-Continuous dynamic models are essential for various Cyber-Physical System (CPS) applications. To ensure effective usability in different lifecycle phases, such behavioral information in the form of differential equations must be contextualized and integrated with further CPS information. While knowledge graphs provide a formal description and structuring mechanism for this task, there is a lack of reusable ontological artifacts and methods to reduce manual instantiation effort. Hence, this contribution introduces two artifacts: Firstly, a modular semantic model based on standards is introduced to represent differential equations directly within knowledge graphs and to enrich them semantically. Secondly, a method for efficient knowledge graph generation is presented. A validation of these artifacts was conducted in the domain of aviation maintenance. Results show that differential equations of a complex Electro-Hydraulic Servo Actuator can be formally represented in a knowledge graph and be contextualized with other lifecycle data, proving the artifacts’ practical applicability.

Advances in Automation and Artificial Intelligence continue to enhance the autonomy of process plants in handling various operational scenarios. However, certain tasks, such as fault handling, remain challenging, as they rely heavily on human expertise. This highlights the need for systematic, knowledge-based methods. To address this gap, we propose a methodological framework that integrates Large Language Model (LLM) agents with a Digital Twin environment. The LLM agents continuously interpret system states and initiate control actions, including responses to unexpected faults, with the goal of returning the system to normal operation. In this context, the Digital Twin acts both as a structured repository of plant-specific engineering knowledge for agent prompting and as a simulation platform for the systematic validation and verification of the generated corrective control actions. The evaluation using a mixing module of a process plant demonstrates that the proposed framework is capable not only of autonomously controlling the mixing module, but also of generating effective corrective actions to mitigate a pipe clogging with only a few reprompts.

In the following contribution, a method is introduced that integrates domain expert-centric ontology design with the Cross-Industry Standard Process for Data Mining (CRISP-DM). This approach aims to efficiently build an application-specific ontology tailored to the corrective maintenance of Cyber- Physical Systems (CPS). The proposed method is divided into three phases. In phase one, ontology requirements are systematically specified, defining the relevant knowledge scope. Accordingly, CPS life cycle data is contextualized in phase two using domain-specific ontological artifacts. This formalized domain knowledge is then utilized in the CRISP-DM to efficiently extract new insights from the data. Finally, the newly developed data-driven model is employed to populate and expand the ontology. Thus, information extracted from this model is semantically annotated and aligned with the existing ontology in phase three. The applicability of this method has been evaluated in an anomaly detection case study for a modular process plant.

Cyber-Physical Production Systems necessitate efficient configuration and continuous reconfiguration to adapt to evolving requirements and shifting goals. This process involves integrating various system structures to derive new functions and behaviors. The concept of the Digital Twin, which allows for effective integration and testing, is instrumental in facilitating this task. However, a fundamental prerequisite is that Digital Twins of individual system components must be composed efficiently and in accordance with dynamic System-of-Systems. We address this challenge by introducing an approach for the automated horizontal and vertical composition of Digital Twins, aimed at minimizing manual intervention and enhancing adaptability. Therefore, a pipeline specifically designed for this goal is proposed, which includes the generation of new functions and behaviors. This approach is intended to provide a foundation for future research.

The following contribution introduces a concept that employs Large Language Models (LLMs) and a chatbot interface to enhance SPARQL query generation for ontologies, thereby facilitating intuitive access to formalized knowledge. Utilizing natural language inputs, the system converts user inquiries into accurate SPARQL queries that strictly query the factual content of the ontology, effectively preventing misinformation or fabrication by the LLM. To enhance the quality and precision of outcomes, additional textual information from established domain-specific standards is integrated into the ontology for precise descriptions of its concepts and relationships. An experimental study assesses the accuracy of generated SPARQL queries, revealing significant benefits of using LLMs for querying ontologies and highlighting areas for future research.

In the age of Industry 4.0 and Cyber-Physical Production Systems (CPPSs) vast amounts of potentially valuable data are being generated. Methods from Machine Learning (ML) and Data Mining (DM) have proven to be promising in extracting complex and hidden patterns from the data collected. The knowledge obtained can in turn be used to improve tasks like diagnostics or maintenance planning. However, such data-driven projects, usually performed with the Cross-Industry Standard Process for Data Mining (CRISP-DM), often fail due to the disproportionate amount of time needed for understanding and preparing the data. The application of domain-specific ontologies has demonstrated its advantageousness in a wide variety of Industry 4.0 application scenarios regarding the aforementioned challenges. However, workflows and artifacts from ontology design for CPPSs have not yet been systematically integrated into the CRISP-DM. Accordingly, this contribution intends to present an integrated approach so that data scientists are able to more quickly and reliably gain insights into the CPPS. The result is exemplarily applied to an anomaly detection use case.

In order to react efficiently to changes in production, resources and their functions must be integrated into plants in accordance with the plug and produce principle. In this context, research on so-called capabilities and skills has shown promise. However, there are currently two incompatible approaches to modeling capabilities and skills. On the one hand, formal descriptions using ontologies have been developed. On the other hand, there are efforts to standardize submodels of the Asset Administration Shell (AAS) for this purpose. In this paper, we present ongoing research to connect these two incompatible modeling approaches. Both models are analyzed to identify comparable as well as dissimilar model elements. Subsequently, we present a concept for a bidirectional mapping between AAS submodels and a capability and skill ontology. For this purpose, two unidirectional, declarative mappings are applied that implement transformations from one modeling approach to the other - and vice versa.

Model-Based Anomaly Detection has been a successful approach to identify deviations from the expected behavior of Cyber-Physical Production Systems. Since manual creation of these models is a time-consuming process, it is advantageous to learn them from data and represent them in a generic formalism like timed automata. However, these models - and by extension, the detected anomalies - can be challenging to interpret due to a lack of additional information about the system. This paper aims to improve model-based anomaly detection in CPPS by combining the learned timed automaton with a formal knowledge graph about the system. Both the model and the detected anomalies are described in the knowledge graph in order to allow operators an easier interpretation of the model and the detected anomalies. The authors additionally propose an ontology of the necessary concepts. The approach was validated on a five-tank mixing CPPS and was able to formally define both automata model as well as timing anomalies in automata execution.

In the manufacturing domain the topic of the Digital Twin is of growing interest, in particular its integration into the company’s own processes. Although the potential is undisputed, essential questions remain unanswered when it comes to the implementation. Many users find it difficult to weigh up efforts and benefits involved in the creation. Digital Twins can be built for any entity of a system, including those that are composed to ‘System-of-Systems’. However, is it really necessary to create a separate Digital Twin from a factory level down to the smallest screw? On the one hand it would require massive resources to build fine granular models and establish the necessary data flows. Especially small and medium sized enterprises (SME’s) are not able to provide these ad hoc. On the other hand, depending on the situation, such a high effort is not necessary for every use case. In this paper, a method is presented that supports potential users, especially SME’s, in the selection and implementation of Digital Twins. Essential information attributes that are of significance in answering the question above are considered as evaluation criteria at decision points. The applicability of the method has been tested on the basis of three use cases with the aim of reducing inefficiencies in planning and control tasks of material flows. The goal is to demonstrate that implementing Digital Twins in the own company does not have to be an all or nothing decision.