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.

Recent developments in Manufacturing-as-a-Service aim to create more flexible and resilient manufacturing networks by enabling the dynamic allocation of manufacturing tasks across company boundaries. This paper presents a pilot implementation of a shared manufacturing network based on the Capability, Skill and Service model and the Asset Administration Shell. The proposed approach supports semantically rich, platform-independent service descriptions and employs standardized negotiation logic based on the Industrie 4.0 language. A multi-partner prototype demonstrates how service requesters and providers – modeled as proactive AAS instances – can autonomously negotiate manufacturing services using capability and offer submodels. The implementation comprises cross-partner negotiation and feasibility checks, skill-based execution, and dynamic scheduling are handled individually at the partner level. Our findings highlight the benefits and challenges of integrating capabilities, skills and services with Asset Administration Shells standards in shared manufacturing scenarios and provide a foundation for future extensions toward more expressive interaction protocols and scalable, federated manufacturing ecosystems.

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.

In the research area of capabilities and skills, the standardization of terms and models is progressing in working groups of Plattform Industrie 4.0 and Industrial Digital Twin Association. At the same time, there is an increasing amount of publications that use capability models for purposes such as automated selection of capabilities or planning of sequences. However, there is currently no concept and formal description of effects generated by resources when acting on products. Having such a formal effect definition is needed to express both required effects as well as effects achieved by capabilities in order to compare requirements with possible solutions to a desired production step in an automated manner. This article introduces a formalism that can be used to define effects in the context of capabilities. An effect is seen as the change between an initial and a target state, which can both be specified using properties. The formalism is used to express effects in three different manufacturing application examples. Furthermore, an implementation of the formalism using the Web Ontology Language is provided. This ontology is used to model effects in a machine-interpretable way and to automatically compare effects for compatibility.

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.

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.

Heterogeneous teams of autonomous robots offer a number of benefits for a variety of applications. But deploying such robots is a complex task that requires machine-interpretable descriptions in order to be flexible and adaptable. Formal descriptions in the form of ontologies are increasingly used to describe the functions of such autonomous robots in the form of capabilities and skills. However, these ontological descriptions and a corresponding invocation interface for skills need to be created, causing additional efforts for developers which are complex, time-consuming and error-prone. This contribution presents a Python framework that automates all these additional efforts. It supports a developer in implementing functionalities as skills by having them program only the skill behavior. The framework automatically takes care of generating a standardized state machine, an invocation interface and an ontological description. The presented framework can be used to implement arbitrary functionalities as skills using Python. This is demonstrated using two different evaluation case studies: a simplified behavior of a mobile robot as well as a machine learning algorithm used as an analytical skill for quality control. Both are integrated into an existing skill execution system and can interact with other skills based on their ontological description.

While modular plants and their modular automation have received increasing attention in the wake of the development of a standardized interface, the Module Type Package (MTP), suitable approaches for systematic support in early phases of their engineering are still missing. Particularly in early engineering phases, a continuous collaboration between multiple engineering disciplines is essential to define what is required in terms of services and modular automation using MTP. In this contribution, the authors propose an approach for an automated generation of MTP skeletons based on ontologies in the early engineering phases. The approach uses intention-based engineering, wherein the first steps intentions and required functionalities of the modular plant are defined and, subsequently, MTP services are modeled inside an ontology. In a further step, this ontology is automatically transformed into an MTP skeleton representing an MTP without instance-specific implementation of the services. The approach has been evaluated using the Tennessee Eastman Process (TEP), a widely known reference process for control systems design and analysis.

Industry 4.0 envisions Cyber-Physical Production Systems (CPPSs) to foster adaptive production of mass-customizable products. Manufacturing approaches based on capabilities and skills aim to support this adaptability by encapsulating machine functions and decoupling them from specific production processes. At the 2022 IEEE conference on Emerging Technologies and Factory Automation (ETFA), a special session on capability- and skill-based manufacturing is hosted for the fourth time. However, an overview on capability- and skill based systems in factory automation and manufacturing systems is missing. This paper aims to provide such an overview and give insights to this particular field of research. We conducted a concise literature survey of papers covering the topics of capabilities and skills in manufacturing from the last ten years of the ETFA conference. We found 247 papers with a notion on capabilities and skills and identified and analyzed 34 relevant papers which met this survey’s inclusion criteria. In this paper, we provide (i) an overview of the research field, (ii) an analysis of the characteristics of capabilities and skills, and (iii) a discussion on gaps and opportunities.

Being able to quickly integrate new equipment and functions into an existing plant is a major goal for both discrete and process manufacturing. But currently, these two industry domains use different approaches to achieve this goal. While the Module Type Package (MTP) is getting more and more adapted in practical applications of process manufacturing, so-called skill-based manufacturing approaches are favored in the context of discrete manufacturing. The two approaches are incompatible because their models feature different contents and they use different technologies. This contribution provides a comparison of the MTP with a skill-based approach as well as an automated mapping that can be used to transfer the contents of an MTP into a skill ontology. Through this mapping, an MTP can be semantically lifted in order to apply functions like querying or reasoning. Furthermore, machines that were previously described using two incompatible models can now be used in one production process.

While there exist approaches to integrate heterogeneous data using semantic models, such semantic models can typically not be used by existing software tools. Many software tools — especially in engineering — only have options to import and export data in more established data interchange formats such as XML or JSON. Thus, if an information which is included in a semantic model needs to be used in a such a software tool, automatic approaches for mapping semantic information into an interchange format are needed. We aim to develop a generic mapping approach that allows users to create transformations of semantic information into a data interchange format with an arbitrary structure which can be defined by a user. This mapping approach is currently being elaborated. In this contribution, we report our initial steps targeted to transformations from RDF into XML. At first, a mapping language is introduced which allows to define automated mappings from ontologies to XML. Furthermore, a mapping algorithm capable of executing mappings defined in this language is presented. An evaluation is done with a use case in which engineering information needs to be used in a 3D modeling tool.

Current challenges of the manufacturing industry require modular and changeable manufacturing systems that can be adapted to variable conditions with little effort. At the same time, production recipes typically represent important company know-how that should not be directly tied to changing plant configurations. Thus, there is a need to model general production recipes independent of specific plant layouts. For execution of such a recipe however, a binding to then available production resources needs to be made. In this contribution, we select a suitable modeling language to model and execute such recipes. Furthermore, we present an approach to solve the issue of recipe modeling and execution in modular plants using semantically modeled capabilities and skills as well as BPMN. We make use of BPMN to model production recipes using capability processes, i.e. production processes referencing abstract descriptions of resource functions. These capability processes are not bound to a certain plant layout, as there can be multiple resources fulfilling the same capability. For execution, every capability in a capability process is replaced by a skill realizing it, effectively creating a skill process consisting of various skill invocations. The presented solution is capable of orchestrating and executing complex processes that integrate production steps with typical IT functionalities such as error handling, user interactions and notifications. Benefits of the approach are demonstrated using a flexible manufacturing system.

The use of ontologies for models of machines and their capabilities and skills provides advantages for manufacturers that want to quickly adapt to changing customer requirements or fluctuating demands. Unfortunately, creating such models requires a high level of expertise in semantic technologies. In typical automation engineering workflows, there is neither the personnel nor the time to create such models manually.In this contribution, we describe an approach to automatically create skill models from IEC 61131-3 code. This approach consists of a dedicated PLC programming library and an automatic transformation of PLC code to a skill ontology. After implementing a skill as a PLC program using the presented library, this program can be exported as PLCopen XML which in turn is automatically transformed into an ontology. Additional efforts for PLC developers are thereby kept at a minimum. The presented approach has been evaluated using a modular laboratory plant. For two different modules, skills were implemented on separate PLCs. After transforming these skills to our skill ontology, this ontology was used to register the skills at a skill-based control platform. Using this platform, the skills were used together in order to perform one section of a production process.

Semantic technologies such as ontologies are increasingly used to describe the functions of machines in the form of so-called capabilities or skills. Ontologies provide powerful mechanisms to infer new knowledge, but there are no builtin mechanisms to test the presence of information which is needed by other systems, e.g. for skill execution. In this contribution, we show how the Shapes Constraint Language (SHACL) can be used in order to formulate constraints against skills. Such constraints contain all mandatory information and can be used to check the validity of new skills when they are added into an existing production system. This ensures interoperability of skills from different manufacturers as wrongfully modelled skills that lack certain information can be discarded and marked for revision.

In order to approach the vision of quickly integrating new machines and their functionalities into a production plant, machines have to provide a machine-readable description of themselves and their functionalities. With such a description, it becomes possible to find required functions, check compatibility and, finally, execute production processes. In recent years, semantic web technologies have proven to be a promising enabler to realize such descriptions in the form of ontologies. But the creation of such an ontological description is an additional, tedious and error-prone task for a machine developer who might most likely not be an expert in semantic web technologies. In order to support developers in implementing machine functionalities as semantically described skills, we developed a method that highly automates all additional ontology-related tasks. The presented method makes use of information already contained in engineering artifacts, helps in adding additional information, and provides a framework to implement skill behavior. By using the proposed method, machine developers are put in a position to develop formal capability models themselves and with little additional effort.

Manufacturing companies face an environment that is dominated by influences which affect the usage of their manufacturing equipment. Trends like shortening life cycles of products, increasing numbers of product variants and the resulting decrease in lot sizes put pressure on companies' operations. Existing machines have to be adaptable to provide a high degree of flexibility and new machines have to be easily integrated into an existing plant in a plug and produce fashion. Research contributions that focus on a higher level description of machine functionalities are seen as a promising approach to cope with the aforementioned challenges. While there exists quite a large amount of contributions on this topic, these contributions focus either on formal models or on executable functions. The developed models mostly represent project specific contents and are rarely based on industry standards. In this contribution, we present an approach to a formal model of machine capabilities that directly includes a description of executable skills. The presented capability and skill model is based on a variety of separate so-called ontology design patterns that contain the vocabulary of industry standards and therefore provide a profound knowledge which is agreed upon by a large community. In addition to the description of our model, this contribution shows how these models can be used in order to achieve simple and rapid integration of new manufacturing modules and their capabilities.

Cyber-physical systems (CPSs) in the manufacturing domain can be deployed to support monitoring and analysis of production systems of a factory in order to improve, support, or automate processes, such as maintenance or scheduling. When a network of CPS is subject to frequent changes, the semantic interoperability between the CPSs is of special interest in order to avoid manual, tedious, and error-prone information model alignments at runtime. Ontologies are a suitable technology to enable semantic interoperability, as they allow the building of information models that lank machine-readable meaning to information, thus enabling CPSs to mutually understand the shared information. The contribution of this article is twofold. First, we present an ontology building method that is tailored toward the needs of CPSs in the manufacturing domain. For this purpose, we introduce the requirements regarding this method and discuss related research concerning ontology building. The method itself is designed to begin with ontological requirements and to yield a formal ontology. As the reuse of ontologies and other information resources (IRs) is crucial to the success of ontology building projects, we put special emphasis on how to reuse IRs in the CPS domain. Second, we present a reusable set of ontology design patterns that have been developed with the aforementioned method in an industrial use case and illustrate their application in the considered industrial environment. The contribution of this article extends the method introduced, as a postconference paper, by a detailed industrial application. Note to Practitioners-With growing digitalization in industry, the exchange and use of manufacturing-related data are becoming increasingly important to improve, support, or automate processes. Thus, it is necessary to combine information from different data sources that have been designed by different vendors and may, therefore, be heterogeneous in structure and semantics. A system that plans a maintenance worker's daily schedule, for instance, requires information about the status of machines, production plans, and inventory, which resides in other systems, such as programmable logic controllers (PLCs) or databases. When creating such information systems, accessing, searching, and understanding the different data sources is a time-intensive and error-prone procedure due to the heterogeneities of the data sources. Even worse, this procedure has to be repeated for every newly built system and for every newly introduced data source. To allow for eased access, searching, and understanding of these heterogeneous data sources, ontology can be used to integrate all heterogeneous data sources in one schema. This article contributes a method for building such ontologies in the manufacturing domain. Furthermore, a set of ontology design patterns is presented, which can be reused when building ontologies for a domain.