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.

The formalization of process knowledge using ontologies enables consistent modeling of parameter interdependencies in manufacturing. These interdependencies are typically represented as mathematical expressions that define relations between process parameters, supporting tasks such as calculation, validation, and simulation. To support cross-context application and knowledge reuse, such expressions are often defined in a generic form and applied across multiple process contexts. This highlights the necessity of a consistent and semantically coherent model to ensure the correctness of data retrieval and interpretation. Consequently, dedicated mechanisms are required to address key challenges such as selecting context-relevant data, ensuring unit compatibility between variables and data elements, and verifying the completeness of input data required for evaluating mathematical expressions. This paper presents a set of verification mechanisms for a previously developed ontology-based process model that integrates standardized process semantics, data element definitions, and formal mathematical constructs. The approach includes (i) SPARQL-based filtering to retrieve process-relevant data, (ii) a unit consistency check based on expected-unit annotations and semantic classification, and (iii) a data completeness check to validate the evaluability of interdependencies. The applicability of the approach is demonstrated with a use case from Resin Transfer Molding (RTM), supporting the development of machine-interpretable and verifiable engineering models.

This paper presents a SysML profile that enables the direct integration of planning semantics based on the Planning Domain Definition Language (PDDL) into system models. Reusable stereotypes are defined for key PDDL concepts such as types, predicates, functions and actions, while formal OCL constraints ensure syntactic consistency. The profile was derived from the Backus-Naur Form (BNF) definition of PDDL 3.1 to align with SysML modeling practices. A case study from aircraft manufacturing demonstrates the application of the profile: a robotic system with interchangeable end effectors is modeled and enriched to generate both domain and problem descriptions in PDDL format. These are used as input to a PDDL solver to derive optimized execution plans. The approach supports automated and model-based generation of planning descriptions and provides a reusable bridge between system modeling and AI planning in engineering design.

In modern software development, maintaining consistency between architectural documentation and implementation remains a significant challenge. This research explores how large language models (LLMs) can be integrated into an encoder-decoder framework to enable real-time architectural documentation and seamless conversion between semi-formal models (e.g., UML diagrams) and natural language descriptions. Building on previous work in LLM-based requirements verification, we develop a system that automatically converts models into text and vice versa. By allowing LLMs to assess textual descriptions for compliance with requirements, this approach reduces the need for extensive model-side validation through rule-based queries. Additionally, the decoder helps transform text-based process descriptions into structured architectural models, supporting digitalization in organizations. The system’s effectiveness is evaluated by comparing reconstructed models with their originals, assessing how well information is preserved and how accurately the transformations are performed.

Mobile robots, becoming increasingly autonomous, are capable of operating in diverse and unknown environments. This flexibility allows them to fulfill goals independently and adapting their actions dynamically without rigidly predefined control codes. However, their autonomous behavior complicates guaranteeing safety and reliability due to the limited influence of a human operator to accurately supervise and verify each robot’s actions. To ensure autonomous mobile robot’s safety and reliability, which are aspects of dependability, methods are needed both in the planning and execution of missions for autonomous mobile robots. In this article, a twofold approach is presented that ensures fault removal in the context of mission planning and fault prevention during mission execution for autonomous mobile robots. First, the approach consists of a concept based on formal verification applied during the planning phase of missions. Second, the approach consists of a rule-based concept applied during mission execution. A use case applying the approach is presented, discussing how the two concepts complement each other and what contribution they make to certain aspects of dependability.

Explicit modeling of capabilities and skills – whether based on ontologies, Asset Administration Shells, or other technologies – requires considerable manual effort and often results in representations that are not easily accessible to Large Language Models (LLMs). In this work-in-progress paper, we present an alternative approach based on the recently introduced Model Context Protocol (MCP). MCP allows systems to expose functionality through a standardized interface that is directly consumable by LLM-based agents. We conduct a prototypical evaluation on a laboratory-scale manufacturing system, where resource functions are made available via MCP. A general-purpose LLM is then tasked with planning and executing a multi-step process, including constraint handling and the invocation of resource functions via MCP. The results indicate that such an approach can enable flexible industrial automation without relying on explicit semantic models. This work lays the basis for further exploration of external tool integration in LLM-driven production systems.

Modern automation systems increasingly rely on modular architectures, with capabilities and skills as one solution approach. Capabilities define the functions of resources in a machine-readable form and skills provide the concrete implementations that realize those capabilities. However, the development of a skill implementation conforming to a corresponding capability remains a time-consuming and challenging task. In this paper, we present a method that treats capabilities as contracts for skill implementations and leverages large language models to generate executable code based on natural language user input. A key feature of our approach is the integration of existing software libraries and interface technologies, enabling the generation of skill implementations across different target languages. We introduce a framework that allows users to incorporate their own libraries and resource interfaces into the code generation process through a retrieval-augmented generation architecture. The proposed method is evaluated using an autonomous mobile robot controlled via Python and ROS 2, demonstrating the feasibility and flexibility of the approach.

The development of high-performance machine learning models has traditionally required extensive expertise, thereby excluding domain experts without a formal AI background. To overcome this barrier, we propose LangBO, a novel framework that systematically integrates domain-specific prior knowledge into the Bayesian Optimization (BO) process via natural language input. By leveraging Large Language Models (LLMs) in combination with Retrieval-Augmented Generation (RAG) and a self-evaluation mechanism, unstructured domain expert knowledge is transformed into a structured Dirichlet prior distribution, thereby guiding the optimization of neural architectures and hyperparameters. Initial experiments on a real-world classification task demonstrate accelerated convergence without compromising final model performance while improving interpretability and sample-efficient AutoML for users lacking machine learning expertise.

AutomationML (AML) enables standardized data exchange in engineering, yet existing recommendations for proper AML modeling are typically formulated as informal and textual constraints. These constraints cannot be validated automatically within AML itself. This work-in-progress paper introduces a pipeline to formalize and verify such constraints. First, AML models are mapped to OWL ontologies via RML and SPARQL. In addition, a Large Language Model (LLM) translates textual rules into SHACL constraints, which are then validated against the previously generated AML ontology. Finally, SHACL validation results are automatically translated to natural language by an LLM. The approach is demonstrated on a sample AML recommendation. Results show that even complex modeling rules can be semi-automatically checked — without requiring users to understand formal methods or ontologies.

Model-based systems Engineering (MBSE) approaches can be applied in the early engineering phases of the development of production systems. They help the system engineer to determine the suitability of production systems and assist in design decisions. To achieve this in a structured manner, several Domain-Specific Modeling Languages (DSMLs) were developed in this contribution using the UML profile mechanism and then integrated into an MBSE workflow. These DSMLs are based on industry standards which consider the Product, Process, and Resource (PPR) structures, allowing consistent modeling while considering the system variability. The application of the DSMLs is demonstrated through the development of a highly automated production system for aircraft fuselage components. Additionally, this contribution showcases how different implementation variants can be compared through simulation.

Manufacturing and logistics companies are forced to rethink their strategies due to increasing product variety, shorter product life cycles, and a shortage of skilled workers. Conventional system structures with central control instances are too inflexible to respond quickly and efficiently to dynamic influences such as short-term adjustments to process sequences or individual process conditions. To counteract these influences, increasingly intelligent and coordinated subsystems with specific areas of competence and functionalities are being integrated into production and logistics processes. Based on the analysis of challenges to intralogistics, this work presents a concept for controlling so-called coordination requirement points. In these locations, the interactions between system objects in internal material transport are coordinated, which is exemplarily implemented in a simulation environment. By varying complexity properties, the achievement of logistical targets at different degrees of autonomous control is analyzed, finding an increased “on time delivery” rate for increasing autonomy and the incorporation of order-relevant information.

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.

The increasing complexity of automated production systems, especially in industries like aircraft manufacturing, calls for a methodological framework to efficiently manage and validate control program changes. This paper proposes a novel approach, Continuous Virtual Commissioning in Operation (CVCO), designed to detect and validate such changes during operational phases. CVCO enhances system efficiency and reliability by integrating virtual commissioning, which focuses on validating only the identified changes, thereby minimizing downtime. This structured framework ensures operational integrity through the identification and validation of program changes. Validation through a scenario involving a single robotic system illustrates the feasibility and effectiveness of the approach, indicating its potential applicability in various manufacturing domains involving complex scenarios.

Nowadays, companies face a variety of changes and challenges that often require adjustments and reconfiguration of manufacturing systems and processes. One topic of great importance in this regard are the interdependencies among process parameters. By modeling these interdependencies and making them accessible to experts and decision makers, these stakeholders can be supported in gaining a deeper understanding of production processes. This article presents a comprehensive overview of the oppor-tunities offered by a semantic model of parameter interdepen-dencies. Based on industrial standards, the semantic framework proposed aims to bridge the gap in current ontological models by providing a formal description of parameters, their interde-pendencies, and their effects on manufacturing processes. By leveraging the capabilities of Semantic Web technologies, this contribution describes the composition and decomposition of interdependency knowledge, its integration in process descriptions, and an interdependency data consistency check.

Manually creating Planning Domain Definition Language (PDDL) descriptions is difficult, error-prone, and requires extensive expert knowledge. However, this knowledge is already embedded in engineering models and can be reused. Therefore, this contribution presents a comprehensive workflow for the automated generation of PDDL descriptions from integrated system and product models. The proposed workflow leverages Model-Based Systems Engineering (MBSE) to organize and manage system and product information, translating it automatically into PDDL syntax for planning purposes. By connecting system and product models with planning aspects, it ensures that changes in these models are quickly reflected in updated PDDL descriptions, facilitating efficient and adaptable planning processes. The workflow is validated within a use case from aircraft assembly.

Simulation models are essential tools in the process industry for supporting plant operators in process optimization and predictive analysis. However, deviations often arise between simulation model output and real-world data, posing challenges to the reliability and effectiveness of these models. Identifying the causes of deviations and adjusting the simulation model accordingly is a tedious and error-prone task, requiring expertise both in the process domain and the simulation tool. Therefore, this paper introduces a model-based approach to automate root-cause identification for deviations between simulation model output and plant data, aiming to reduce manual effort, required knowledge, and susceptibility to errors. The approach builds upon an Adaptive Causal Directed Graph originating from the root-cause identification in alarm floods, presented in previous work. In this paper, the graph is extended to enable an identification of parameters to be adjusted based on detected deviations. Thus, it facilitates a cause-based simulation model adaptation in the context of model calibration and can be repurposed to assist model-based plant diagnosis tasks.

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.

The integration of Artificial Intelligence (AI) into automation systems has the potential to enhance efficiency and to address currently unsolved existing technical challenges. However, the industry-wide adoption of AI is hindered by the lack of standardized documentation for the complex compositions of automation systems, AI software, production hardware, and their interdependencies. This paper proposes a formal model using standards and ontologies to provide clear and structured documentation of AI applications in automation systems. The proposed information model for artificial intelligence in automation systems (AIAS) utilizes ontology design patterns to map and link various aspects of automation systems and AI software. Applied to a practical example, the model demonstrates its effectiveness in improving documentation practices and aiding the sustainable implementation of AI in industrial settings.

A team of heterogeneous autonomous mobile robots (AMRs) has the potential to perform complex missions for a variety of industrial and non-industrial applications. However, suitable means of command and control for multiple AMRs pose a major challenge for a human operator, as this complicates the predictability and controllability of individual AMRs. This insufficient ability to accurately assess each robot's behavior makes it difficult to conduct adequate human oversight, which is demanded by law. Addressing this challenge, this article presents an approach for a hardware-agnostic supervision of AMRs. This approach aims to ensure adequate human oversight of heterogeneous AMRs by providing support through technical monitoring. For this purpose, monitors are used as communication partners for AMRs and query necessary information on safe behavior at runtime. Gathered information is compared with a set of rules and violations of safety constraints are reported to the human operator. Thus, the behavior of each AMR to be supervised effectively without the need for additional sensors or detailed knowledge of the respective hardware.

Capability ontologies are increasingly used to model functionalities of systems or machines. The creation of such onto-logical models with all properties and constraints of capabilities is very complex and can only be done by ontology experts. However, Large Language Models (LLMs) have shown that they can generate machine-interpretable models from natural language text input and thus support engineers / ontology experts. Therefore, this paper investigates how LLMs can be used to create capability ontologies. We present a study with a series of experiments in which capabilities with varying complexities are generated using different prompting techniques and with different LLMs. Errors in the generated ontologies are recorded and compared. To analyze the quality of the generated ontologies, a semi-automated approach based on RDF syntax checking, OWL reasoning, and SHACL constraints is used. The results of this study are very promising because even for complex capabilities, the generated ontologies are almost free of errors.

To achieve a flexible and adaptable system, capabil-ity ontologies are increasingly leveraged to describe functions in a machine-interpretable way. However, modeling such complex ontological descriptions is still a manual and error-prone task that requires a significant amount of effort and ontology expertise. This contribution presents an innovative method to automate capability ontology modeling using Large Language Models (LLMs), which have proven to be well suited for such tasks. Our approach requires only a natural language description of a capability, which is then automatically inserted into a predefined prompt using a few-shot prompting technique. After prompting an LLM, the resulting capability ontology is automatically verified through various steps in a loop with the LLM to check the overall correctness of the capability ontology. First, a syntax check is performed, then a check for contradictions, and finally a check for hallucinations and missing ontology elements. Our method greatly reduces manual effort, as only the initial natural language description and a final human review and possible correction are necessary, thereby streamlining the capability ontology generation process.

Simulations offer opportunities in the examination of manufacturing processes. They represent various aspects of the production process and the associated production systems. However, often a single simulation does not suffice to provide a comprehensive understanding of specific process settings. Instead, a combination of different simulations is necessary when the outputs of one simulation serve as the input parameters for another, resulting in a sequence of simulations. Manual planning of simulation sequences is a demanding task that requires careful evaluation of factors like time, cost, and result quality to choose the best simulation scenario for a given inquiry. In this paper, an information model is introduced, which represents simulations, their capabilities to generate certain knowledge, and their respective quality criteria. The information model is designed to provide the foundation for automatically generating simulation sequences. The model is implemented as an extendable and adaptable ontology. It utilizes Ontology Design Patterns based on established industrial standards to enhance interoperability and reusability. To demonstrate the practicality of this information model, an application example is provided. This example serves to illustrate the model's capacity in a real-world context, thereby validating its utility and potential for future applications.

Traditional centrally controlled production and logistics systems of mass production exhibit difficulties to cope with the new reality of frequent changes in manufacturing technology and product design. Agent-based decentralized decision-making can be a means to cope with the complex nature of modern manufacturing systems. This contribution proposes an agent architecture to integrate production and transportation scheduling and process planning. It also incorporates shared resources, such as operators, into the process, which further improves the solution. To be suitable for quick rescheduling, the approach includes an efficient underlying communication protocol. The integrated scheduling of overhead cranes serves as an application example and illustration of the approach. The runtime efficiency of the algorithm makes it suitable for practical applications within manufacturing systems.

Shorter product lifecycles and increasing product complexity are important trends that drive the need for increased flexibility of production companies. One way to cope with this problem is to engage in flexible production networks where companies can find missing production capabilities and offer their own ones. To enable this connection across company borders and software platforms, an agent-based communication approach is proposed that is based on the OPC UA standard. This paper also develops an optimization concept that can increase a company's benefits, i.e. profits, by applying a learning algorithm as well as an approach to calculate optimal margins, which is encapsulated in an optimization agent.

Dynamic markets drive the need for more flexible and robust production systems. Agents are a means to cope with this new reality by providing dynamic scheduling functionalities. However, agents have rarely made the step from research labs to real production environments so far. To perform in these environments, the agents need to cope with real and therefore often imperfect information. This holds especially true for agent-systems performing integrated scheduling of production and transportation processes using real-time location information. In this paper, a modeling framework is proposed that is based on accuracy, granularity, and frequency as universal quality dimensions for information that should be incorporated in decision-making. These dimensions are applied within an agent-based system that is to perform integrated dynamic scheduling in a real manufacturing environment.