Felix Gehlhoff

Hamied Nabizada, Thomas Wirt, Luis Miguel Vieira da Silva et al.

Engineers designing production systems need to verify that a given layout supports all required production sequences. Automated planning techniques can answer such questions, but formulating the required planning problems in the Planning Domain Definition Language (PDDL) demands specialized expertise that production engineers typically lack. Asset Administration Shells (AAS) have emerged as the standardized Digital Twin for industrial assets in Industry 4.0. We show that AAS capability models, structured using four established Industry 4.0 standards (VDI 3682 for process descriptions, IEC 61360-1 for semantic property qualification, IDTA 02011 for type hierarchies, and IDTA 02016 for instance descriptions), contain sufficient information to generate complete PDDL problems automatically. Unlike prior work that introduced PDDL-specific submodels, our approach derives all planning elements from domain-level descriptions of resource functions, so-called capabilities, allowing engineers to model capabilities without any exposure to PDDL syntax or planning concepts. Our extraction algorithm transforms distributed Multi-AAS architectures into complete PDDL planning problems. We validate the approach on AAS models of a laboratory production system, comparing four layout variants using optimal planning to demonstrate how engineers can systematically explore design trade-offs by modifying the AAS model and regenerating the planning domain

Luis Miguel Vieira da Silva, Nicolas König, Felix Gehlhoff

In modern industry, dynamic environments and the complexity of modular and reconfigurable resources require automated planning of process sequences. Capability-based planning approaches address this by automatically generating plans from semantic knowledge models that describe resource functions in a machine-interpretable form. Their practical use, however, remains limited: solver feedback, especially in the case of unsatisfiability, is difficult to interpret, and the knowledge models require adaptation as operational conditions change or requests become infeasible. This paper presents a hybrid assistance system that augments an existing capability-based Satisfiability Modulo Theories (SMT) planning approach with an Large Language Model (LLM)-based layer for natural-language interaction, explanation, and adaptation. Formal planning correctness remains with the symbolic planner, while the LLM layer handles natural-language access and flexible knowledge model adaptation under explicit Human-in-the-Loop (HitL) approval. The system decomposes into four components: Capability Grounding, Symbolic Planning, Result Interpretation, and Planning Adaptation, realized as a routed agentic workflow in which a central router delegates to five specialized agents. The system is evaluated on a modular production system across four scenario types. Of 23 test cases, 9 of 10 knowledge queries and all 4 satisfiable planning cases were handled correctly, 3 of 4 unsatisfiable cases produced concrete repair proposals, and all 5 adaptive planning scenarios resolved into satisfiable plans through iterative, user-approved knowledge model modifications. The findings confirm that combining formal planning with LLM-based assistance substantially improves accessibility and adaptability in industrial automation.

Lasse Matthias Reinpold, Lukas Peter Wagner, Felix Gehlhoff et al.

To achieve a highly agile and flexible production, it is envisioned that industrial production systems gradually become more decentralized, interconnected, and intelligent. Within this vision, production assets collaborate with each other, exhibiting a high degree of autonomy. Furthermore, knowledge about individual production assets is readily available throughout their entire life-cycles. To realize this vision, adequate use of information technology is required. Two commonly applied software paradigms in this context are Software Agents (referred to as Agents) and Digital Twins (DTs). This work presents a systematic comparison of Agents and DTs in industrial applications. The goal of the study is to determine the differences, similarities, and potential synergies between the two paradigms. The comparison is based on the purposes for which Agents and DTs are applied, the properties and capabilities exhibited by these software paradigms, and how they can be allocated within the Reference Architecture Model Industry 4.0. The comparison reveals that Agents are commonly employed in the collaborative planning and execution of production processes, while DTs typically play a more passive role in monitoring production resources and processing information. Although these observations imply characteristic sets of capabilities and properties for both Agents and DTs, a clear and definitive distinction between the two paradigms cannot be made. Instead, the analysis indicates that production assets utilizing a combination of Agents and DTs would demonstrate high degrees of intelligence, autonomy, sociability, and fidelity. To achieve this, further standardization is required, particularly in the field of DTs.

Felix Gehlhoff, Alexander Fay

Individualized products and shorter product life cycles have driven companies to rethink traditional mass production. New concepts like Industry 4.0 foster the advent of decentralized production control and distribution of information. A promising technology for realizing such scenarios are Multi-agent systems. This contribution analyses the requirements for an agent-based decentralized and integrated scheduling approach. Part of the requirements is to develop a linearly scaling communication architecture, as the communication between the agents is a major driver of the scheduling execution time. The approach schedules production, transportation, buffering and shared resource operations such as tools in an integrated manner to account for interdependencies between them. Part of the logistics requirements reflect constraints for large workpieces such as buffer scarcity. The approach aims at providing a general solution that is also applicable to large system sizes that, for example, can be found in production networks with multiple companies. Further, it is applicable for different kinds of factory organization (flow shop, job shop etc.). The approach is explained using an example based on industrial requirements. Experiments have been conducted to evaluate the scheduling execution time. The results show the approach's linear scaling behavior. Also, analyses of the concurrent negotiation ability are conducted.

Milapji Singh Gill, Tom Westermann, Gernot Steindl et al.

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.

Hamied Nabizada, Tom Jeleniewski, Felix Gehlhoff et al.

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.

Jonathan Reif, Tom Jeleniewski, Milapji Singh Gill et al.

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.

Nane Zimmermann, Lukas P. Wagner, Luca von Rönn et al.

Increasing penetration of electric vehicles, heat pumps, and rooftop photovoltaics is creating thermal and voltage stress in low-voltage distribution grids. This work links three German energy transition pathways (2025-2045) with state estimation performance requirements, evaluated on two SimBench reference networks across three equipment quality levels (good, medium, poor) and three VDE Forum Netztechnik/Netzbetrieb (VDE FNN) measurement constellations that differ in the availability of transformer and feeder-level instrumentation. Congestion is caused exclusively by transformer overloading and voltage-band violations. No individual line exceeds its thermal rating. Equipment quality is the primary factor: under good equipment, congestion remains nearly absent through 2045 (1/26 scenarios), under medium equipment it emerges from 2035 (10/26), under poor equipment from 2025 (25/26), reaching 208 % peak transformer loading. Without transformer instrumentation, voltage estimation errors remain at 6-35% regardless of smart meter penetration. Adding a single transformer measurement reduces errors by a factor of 3 to 24, achieving median errors below 1.1% under poor equipment. Per-feeder measurements achieve comparable accuracy and outperform the transformer-only configuration under poor equipment in rural networks (0.8% vs. 1.1%). In urban networks under poor and medium equipment, transformer and feeder-level instrumentation meet the VDE FNN voltage accuracy target without requiring customer-side sensors. These findings motivate prioritizing transformer instrumentation as an effective first step for grid observability and supplementing the current consumption-driven metering rollout with risk-based deployment criteria linked to local congestion exposure.

Marvin Schieseck, Philip Topalis, Lasse Reinpold et al.

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. Validated through a practical example, the model demonstrates its effectiveness in improving documentation practices and aiding the sustainable implementation of AI in industrial settings.

Niklas Jobs, Luis Miguel Vieira da Silva, Jayanth Somashekaraiah et al.

Industrial automation increasingly requires flexible control strategies that can adapt to changing tasks and environments. Agents based on Large Language Models (LLMs) offer potential for such adaptive planning and execution but lack standardized benchmarks for systematic comparison. We introduce a benchmark with an executable simulation environment representing the Blocksworld problem providing five complexity categories. By integrating the Model Context Protocol (MCP) as a standardized tool interface, diverse agent architectures can be connected to and evaluated against the benchmark without implementation-specific modifications. A single-agent implementation demonstrates the benchmark's applicability, establishing quantitative metrics for comparison of LLM-based planning and execution approaches.

Vincent Henkel, Felix Gehlhoff, David Kube et al.

Foundation models, particularly large language models, are increasingly integrated into agent architectures for industrial tasks such as decision support, process monitoring, and engineering automation. Yet evidence on their purposes, capabilities, and limitations remains fragmented across domains. This work examines how mature foundation-model-based agent systems are in industrial contexts, how their functional profile differs from conventional agent systems, and which limitations persist. A systematic literature survey following the PRISMA 2020 guideline is presented, screening 2,341 publications and synthesising a corpus of 88 publications through a structured coding scheme. The results show that reported systems are predominantly at prototype and early validation stages (75.0% at TRL 4-6), with deployment-oriented evidence remaining rare (9.1%). Operational goals are most frequently positioned in user assistance, monitoring, and process optimisation, while conventional production-control purposes such as planning and scheduling are less prominent. Compared with an established baseline for industrial agent systems, the capability profile reveals substantial gains in human interaction (+37%) and dealing with uncertainty (+35%), but a pronounced deficit in negotiation (-39%). The most widely reported limitations concern lack of generalization, hallucination and output instability, data scarcity, and inference latency. A working definition of foundation-model-based industrial agents is also proposed, bridging conventional agent theory, automation-engineering standards, and the foundation-model paradigm.

Luis Miguel Vieira da Silva, Aljosha Köcher, Felix Gehlhoff et al.

Capability ontologies are increasingly used to model functionalities of systems or machines. The creation of such ontological 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.

Vincent Henkel, Maximilian Kilthau, Felix Gehlhoff et al.

In response to the global shift towards renewable energy resources, the production of green hydrogen through electrolysis is emerging as a promising solution. Modular electrolysis plants, designed for flexibility and scalability, offer a dynamic response to the increasing demand for hydrogen while accommodating the fluctuations inherent in renewable energy sources. However, optimizing their operation is challenging, especially when a large number of electrolysis modules needs to be coordinated, each with potentially different characteristics. To address these challenges, this paper presents a decentralized scheduling model to optimize the operation of modular electrolysis plants using the Alternating Direction Method of Multipliers. The model aims to balance hydrogen production with fluctuating demand, to minimize the marginal Levelized Cost of Hydrogen (mLCOH), and to ensure adaptability to operational disturbances. A case study validates the accuracy of the model in calculating mLCOH values under nominal load conditions and demonstrates its responsiveness to dynamic changes, such as electrolyzer module malfunctions and scale-up scenarios.

Tom Westermann, Malte Ramonat, Johannes Hujer et al.

AutomationML has seen widespread adoption as an open data exchange format in the automation domain. It is an open and vendor neutral standard based on the extensible markup language XML. However, AutomationML extends XML with additional semantics that limit the applicability of common XML-tools for applications like querying or data validation. This article demonstrates how the transformation of AutomationML into OWL enables new use cases in querying with SPARQL and validation with SHACL. To support this, it provides practitioners with (1) an up-to-date ontology of the concepts defined in the AutomationML standard and (2) a declarative mapping to automatically transform any AutomationML model into RDF triples. A study on examples from the automation domain concludes that transforming AutomationML to OWL opens up new powerful ways for querying and validation that would have been impossible without this transformation.

Tom Jeleniewski, Hamied Nabizada, Jonathan Reif et al.

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.

Tom Westermann, Aljosha Köcher, Felix Gehlhoff

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 translates textual rules into SHACL constraints, which are then validated against the previously generated AML ontology. Finally, SHACL validation results are automatically interpreted in natural language. 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 ontology technologies.

Milapji Singh Gill, Javal Vyas, Artan Markaj et al.

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.

Luis Miguel Vieira da Silva, Aljosha Köcher, Nicolas König et al.

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.

Hamied Nabizada, Lasse Beers, Alain Chahine et al.

Engineering models created in Model-Based Systems Engineering (MBSE) environments contain detailed information about system structure and behavior. However, they typically lack symbolic planning semantics such as preconditions, effects, and constraints related to resource availability and timing. This limits their ability to evaluate whether a given system variant can fulfill specific tasks and how efficiently it performs compared to alternatives. To address this gap, this paper presents a model-driven method that enables the specification and automated generation of symbolic planning artifacts within SysML-based engineering models. A dedicated SysML profile introduces reusable stereotypes for core planning constructs. These are integrated into existing model structures and processed by an algorithm that generates a valid domain file and a corresponding problem file in Planning Domain Definition Language (PDDL). In contrast to previous approaches that rely on manual transformations or external capability models, the method supports native integration and maintains consistency between engineering and planning artifacts. The applicability of the method is demonstrated through a case study from aircraft assembly. The example illustrates how existing engineering models are enriched with planning semantics and how the proposed workflow is applied to generate consistent planning artifacts from these models. The generated planning artifacts enable the validation of system variants through AI planning.

Luis Miguel Vieira da Silva, Aljosha Köcher, Felix Gehlhoff

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.

Milapji Singh Gill, Tom Jeleniewski, Felix Gehlhoff et al.

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 Servoactuator can be formally represented in a knowledge graph and be contextualized with other lifecycle data, proving the artifacts' practical applicability.

Luis Miguel Vieira da Silva, Aljosha Köcher, Felix Gehlhoff et al.

To achieve a flexible and adaptable system, capability 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.