Process optimization is crucial in industries with high energy demands like industrial material processing. Neural networks are commonly used for this purpose, but their performance deteriorates over time due to material wear and changes in data distribution. This study addresses these challenges by enhancing modeling, prediction, and optimization through continual learning techniques that detect and adapt to concept drift. This approach maintains model performance despite changing conditions and represents the first contribution to adaptive optimization in industrial material processing. The methodology’s effectiveness is validated with real-world data.

The increasing virtualization of automation software and its decoupling from hardware introduces a significant change in industrial automation. This transition allows classical operational technology software instances, such as programmable logic controllers, to coexist on the same host system alongside applications from various domains. Such coexistence offers substantial potential for a more efficient interconnection between applications from different areas, overcoming typical limitations associated with conventional interfaces. However, current middleware solutions for automation applications are often proprietary and not standardized. In this paper, we present an initial concept for an intra-host middleware based on the OPC Unified Architecture, employing a centralized data directory combined with a shared-memory-based transport mechanism. The proposed concept aims to enable efficient, low-latency, and scalable communication, thereby facilitating seamless interaction between diverse automation applications and promoting the use of microservice architectures.

The evolution of Industry 4.0 standards and trends introduces new challenges for traditional Manufacturing Execution Systems, necessitating their transformation into modular, interconnected components with standardized communication interfaces. Although these trends provide a conceptual framework, a distributed architecture for monitoring and aggregating production data remains underdeveloped. This paper addresses this gap by proposing a system of distributed monitoring components that interact hierarchically and heterarchically using Industry 4.0 technologies. The approach integrates Asset Administration Shells for passive data representation with Multi-Agent Systems and investigates its applicability for different control system architectures in different case studies.

To transition industrial production lines from mass production to lot-size-one production, it is essential to achieve modularization and flexibility throughout the entire production process. For this to be feasible abilities of production resources need to be defined in a manufacturer independent generalized way. This requirement has led to the development of the Capability-Skill-Service model. While current research primarily focuses on production steps, it is crucial not to overlook the importance of flexible communication between production resources. This paper presents an approach to defining network configuration at the field-level in a skill-based manufacturing environment. For this, the abilities to reconfigure communication as well as the ability to be reconfigured are modeled as capabilities and skills. Within the framework of Open Platform Communication Unified Architecture Field eXchange (OPC UA FX), a ConnectionManager entity operates at the field-level to facilitate the reconfiguration of OPC UA communication between AutomationComponents. The presented approach is evaluated using the configuration abilities of the ConnectionManager.

To meet the dynamic demands of Industry 4.0, manufacturing systems require enhanced adaptability and interoperability, particularly in light of the transition from Machinery Directive 2006/42/EC to Machinery Regulation 2023/1230/EU. This transition emphasizes the need for machine-readable and digital documentation standards. However, integrating these standards with capability modeling frameworks such as the Capability-Skill-Service model (CSS model), the Open Platform Communications Unified Architecture (OPC UA) and the Asset Administration Shell (AAS) remains challenging, which limits seamless interoperability and dynamic reconfiguration. This paper addresses these issues by presenting a methodology to automate capability generation using large language models. This approach standardizes technical documentation and bridges gaps through automation. Aligning the CSS model with the OPC UA and AAS frameworks enables integration into Manufacturing-as-a-Service platforms, driving innovation and efficiency in modern manufacturing ecosystems.

Skill-based robotic reconfigurable cyber-physical production modules (RCPPMs) have an aggregated structure, and their functionality depends on the submodules and components that define their current topology. This application-oriented paper proposes a method for integrating the OPC UA Relative Spatial Location (RSL) Companion Specification models and the ROS2 tf2-library functionality to automatically update the SRL models of the RCPPMs when their structure changes. This enables the proper composition and sharing of the necessary information regarding the kinematic structure of each RCPPM’s submodule. On an example, we illustrate how this approach can be employed to enhance the coupling functionality of the skill-based robotic RCPPMs.

The increasing dynamics and complexity of today’s manufacturing environments require greater flexibility and resilience to meet the demands of producing multi-variant products, including batch size one, with minimal additional effort. The Capability, Service and Skill Model provides an answer to this problem by decoupling processes and the resources used. However, especially small and medium-sized enterprises face the challenge of systematically modeling their machines and systems in terms of capabilities and skills, as the required knowledge is often not available in a structured form and is often tied to individual key personnel. To ensure a consistent and practical description of capabilities, a method based on historical data is proposed to help companies integrate their manufacturing resources into a networked system of manufacturing service providers. On this basis, historical manufacturing features are systematically examined to evaluate the potential to use them to determine capabilities.

Modern Digital Twin standards and technologies, designed to enable smart factories in line with the Industry 4.0 vision, have not yet addressed all the challenges associated with contemporary digital twins. This paper shows how to leverage the Asset Administration Shell as an Industry 4.0 compliant Digital Twin technology to provide all necessary data for Artificial Intelligence Planning, represented via the Planning Domain Definition Language. For this purpose, a model for preconditions and effects of planning actions is defined. This model is applied to three different use cases showing different problems of fetching data from different partially standardized shell templates including three defined actions of transport, assembly, and storage.

The current research trends in the field of manufacturing process optimization tackle the question of how to realize manufacturer-independent flexible manufacturing through the standardization of various technologies. Through the combination of Open Platform Communication Unified Architecture Field eXchange (OPC UA FX), the Asset Administration Shell (AAS) and the Capability, Skill, and Service model (CSS model) an automated reconfiguration of real-time capable communication in an industrial environment can be achieved. This paper presents an approach for the first steps of implementation of this concept. First the requirements are discussed which are needed to enable the concept. Then possible AAS submodels that fulfill these requirements are presented. Based on this discussion an example using a linear axis with a movement functionality is modelled in the AAS using the Asset Interface Description (AID) submodel and in the OPC UA information model for evaluation of the approach. Enabling an on-the-fly reconfiguration of real-time capable communication allows for optimization and faster reaction to changes in production demands.

Intralogistics 4.0, a central aspect of Industry 4.0, poses several challenges for Driverless Transport Systems, especially for Autonomous Mobile Robots, which have to navigate in complex environments. The increasing variety of goods with different physical properties is pushing today's intralogistics systems to their limits. A modular production environment with dynamic obstacles, reconfigurable production systems and human influences such as worker interaction, unpredictable movements and manual handling of goods requires the processing of specific information to ensure safe handling and efficient navigation. Furthermore, it requires a classification of products into categories, including those classified as hazardous goods, for individual handling to achieve greater production efficiency. The Asset Administration Shell concept provides a comprehensive virtual representation of these environments and enables the management of safety and hazard information. This paper analyzes existing information models and develops new models that are necessary for the development of an intralogistics infor-mation structure. This structure will include a comprehensive digital representation of autonomous mobile robots and the information needed for individual handling. It demonstrates how this information can be used within an architecture to optimize navigation strategies and hazard handling across stationary and mobile transportation systems to improve the overall production efficiency.

While the benefits of reconfigurable manufacturing systems (RMS) are well-known, there are still challenges to their development, including, among others, a modular software architecture that enables rapid reconfiguration without much reprogramming effort. Skill-based engineering improves software modularity and increases the reconfiguration potential of RMS. Nevertheless, a skills' composition framework with a focus on frequent and rapid software changes is still missing. The behavior trees (BTs) framework is a novel approach that enables the intuitive design of modular hierarchical control structures. BTs have been mostly explored from the AI and robotics perspectives, and little work has been done in investigating their potential for composing skills in the manufacturing domain. This paper proposes a framework for skills' composition and execution in skill-based reconfigurable cyber-physical production modules (RCPPMs). It is based on distributed BTs and provides good integration between low-level devices' specific code and AI-based task-oriented frameworks. We have implemented the provided models for the IEC 61499-based distributed automation controllers. This shows the instantiation of the proposed framework with specific industrial technology to enable its evaluation by the automation community.

The Digital Product Passport (DPP) is a vital enabler of the circular economy. However, creating interoperability among digital representations of products/assets and preserving privacy are core challenges for a successful implementation of the DPP. The Asset Administration Shell (AAS), by offering a consistent metamodel and application programming interface, helps interested parties to communicate via such a standard digital representation. In this paper, we present our Cloud-based system, which enables multiple stakeholders to build their own AAS. With the help of a user interface, different stakeholders can interact with existing AASs and add their own information based on existing templates. In earlier work on the AAS, the manufacturing phase of a product was in the focus. To both leverage the full potential of the AAS and to make the circular economy work, however, it is crucial to take later lifecycle phases and their related stakeholders equally into account. Our work therefore strongly emphasizes a multi-stakeholder perspective on the AAS and hence, the DPP. We demonstrate how the DPP is beneficial for recycling an asset in a real-world use-case. Our solution also addresses concerns about data privacy by implementing role-based access authorization constraints. We also offer the capability to deploy third-party services within our Cloud-based infrastructure.

This paper presents a novel approach to recognize a worker’s intentions for assistive systems in manual assembly. Building on previous research, it introduces a process description for assembling products, addressing the inflexibility and limitations of previous models. This enhancement enables the modeling of assemblies for a substantial amount of products. The proposed pipeline for intention recognition employs object detection, an assembly information model, and a Markov model. One major advantage of the new method is the ability to work with limited or no training data. The online learning capabilities of the model allow for adaptation to individual workers even with just one assembly. This flexibility makes this novel approach ideal for assistive systems. We also discuss about the model’s ability to suit any type of assembly product allowing offline training and guiding unskilled workers during their assembly processes.

Digital Twins and their adoption in Industry 4.0 are trending topics. Asset Administration Shell (AAS) has been introduced as a standard metamodel and application programming interface (API) to cope with interoperability issues. The specification discusses possibilities of serializing the AAS meta-model to various formats such as XML, JSON, and RDF. It also introduced various schemas to check the compliance of serialized content with the specification. In this paper, we show that Shapes Constraint Language (SHACL) is not only possible to be used for schema compliance checks but also for data entry validation. Within our use case, we show the flexibility of our solution, which is also platform independent.

Automated diagnosis of factories becomes increasingly important to avoid production stops and down times. Additionally, market trends such as small batch size induced by individual customer requirements lead to modular production systems elevating flexibility as well as complexity of smart factories. That leads to more difficulties using conventional diagnosis methods. The ever changing constellations of production modules requires to include context information of the manufacturing domain to enable a suitable fault diagnosis.This paper shows the identification and classification of relevant context information for fault diagnosis in skill-based production systems. The concept of faults is embedded into the Capability-Skill-Service Model used to describe the aforementioned context. Suitable entities and their relations in the production system are outlined and the Knowledge Graph technology is used to make the the context information accessible. An implementation in a real-world demonstrator of SmartFactory-KL is presented and an outlook for further research is given.

Flexibility, agility and resilience of value chains are becoming increasingly important. One possible approach to achieving these goals could be the paradigm of cloud manufacturing, especially the shared production scenario, where a federation of trusted partners dynamically share manufacturing capabilities, capacity, and services over digital interfaces throughout the product lifecycle. This includes an automated bidding procedure in a cross-enterprise network. The Capability, Service, Skill (CSS) model provides a common terminology for Industry 4.0 applications. The paper focuses on enabling a shared production based on the CSS model through the implementation of the Asset Administration Shell (AAS), the use of the Industry 4.0 Language (I4.0L) and Gaia-X. It shows what a centralized approach to shared production using these technologies could look like. The scenario of a negotiation process to find suitable manufacturers for a customized product is described, and the different concepts are assigned to the elaborated steps of the I4.0L bidding procedure. In addition, the required AAS and its Submodels are designed for each step of the bidding procedure. Based on the results, the necessary standardization needs are outlined.

In order to react more dynamically and flexibly to individual customer requirements, the concepts of skill-based engineering can also be applied in the field of machining. FeasibilityCheck, PreconditionCheck and SkillExecution have emerged as important basic components of complex manufacturing skills in order to be able to control skills usefully and efficiently, especially for machine tools. This paper describes the roles of each basic skill component in machining skills and shows how they can be used. Furthermore, the concept of IDs for referencing already given ParameterSets is evaluated for machining skills. A prototype implementation shows how these ParameterSetIDs can be used to efficiently interact with the basic skill components. The results show the fundamental sense of this separation of FeasibilityCheck, PreconditionCheck and SkillExecution and support the usefulness of using ParameterSetIDs.

To achieve flexible, resilient and sustainable production, the generation of dynamic cross-company supply chains gains importance. The Shared Production scenario aims at sharing manufacturing services within distributed production network through digital interfaces. A prerequisite is secure data sharing in a trustworthy network with certified participants and a common understanding concerning vocahulary, message structure and interaction patterns Gaia-X provides a solution for a secure and federated data infrastructure according to European values (ie., European Data Protection, transparency and trust). Asset Administration Shells (AAS) provide semantic and vendor-independent information models and VDI/VDE 2193 proposes message structure and interaction protocols for bidding procedures. In this paper, we present the combination of the three concepts to enable the Shared Production scenario. We elaborate on the requirements of Shared Production, develop a system architecture and model AAS Submodel templates to perform an automated bidding procedure. Additionally, the implementation is evaluated based on the bidding of production services to produce model trucks in a demonstrator ecosystem.

To improve the fault tolerance of production systems against unforeseen events, modern production systems must be able to react more autonomously with suitable solutions to reach their goals. Such events within the company, e.g., resource breakdowns, require the possibility of internal replanning of the production schedule. Multi-Agent Systems (MAS) can provide this required flexibility. To enable standardized interaction for agents, a vendor-independent description of products and production equipment, as well as their capabilities and skills, must be developed. The Asset Administration Shell (AAS) provides the standardized meta-model to achieve this goal. In this paper, a product AAS and the submodel for the required production plan are designed. Moreover, the associated MAS and interaction for the execution and replanning of the production sequence are presented. The system is validated using an assembly use-case in the real-world demonstrator environment of the SmartFactoryKL. Combining the concepts of MAS with the standardized structures of the AAS, skills and capabilities tackles the problem of MAS to be deployed in different companies. This approach enables widespread use and scalability of MAS leveraging their advantages in terms of flexibility and efficient reconfiguration.

A skill-based engineering approach uses the concept of skill to abstract machine-specific functionality with a generic interface and common behavior. A skill is treated as a "control level service" and is used to build service-oriented architectures. Though the question of robust and flexible coordination of skills is still open. Current approaches to skills' composition result in tightly-coupled control structures. To allow frequent and rapid system’s reconfiguration a framework to flexibly build complex behaviors from reusable components is needed. Behavior Trees (BTs) have proven to be a powerful tool for specifying characters' behaviors in the gaming industry and recently is getting a lot of attention in the robotics community as well as academia. An approach of using BTs for coordination of industrial skills is proposed in this paper. Combining behavior trees with the existing skill models enhances separation of concerns and modularity of control systems in the factory automation domain. Firstly, we define the requirements for a skills coordination layer and discuss some key properties of BTs that allow to satisfy these requirements. Secondly, we introduce a skill model, which utilizes BTs and has several advantages over the current skill models. Thirdly, we introduce a concept of distributed BTs to effectively distribute functionality over different computational platforms. Finally, we present a small proof of concept example to test feasibility of the proposed approach.

Functionally described capabilities play an important role in the virtualization of manufacturing and the resource-specific realization with the skill-based approach. The importance of this modeling can be seen in a formalization of production capabilities for a holistic usage in a workflow from product orders towards manufacturing on the shop floor. This paper presents a concept for modeling and usage of functionally described capabilities along this workflow with combined modeling approaches. Therefore, the formalism and the setup of product requirements, functionally described capabilities, Petri Net Plans for creation of resource-specific process sequences, and at least their execution with skills are considered. The application and validation of this concept on a virtualized demonstrator example is shown. The achieved results for a given application from a product order towards its simulated manufacturing are presented.

Application of multiple robotic manipulators in a shared workspace is still restricted to repetitive tasks limiting their flexible deployment for production systems. Still, existing motion control algorithms cannot be performed online for arbitrary environments in case of multiple manipulators cooperating with each other. In this work we propose a scalable and real-time capable motion control algorithm based on non-cooperative distributed model predictive control. Furthermore, we propose an optimal scheduling algorithm, which provides optimal setpoints to each robot’s motion controller that prevents possible deadlocks beforehand. We validate our approach on a simulative setup of four robotic manipulators for multiple pick and place scenarios.

We present a comprehensive comparison of hybrid Data-Driven Control (DDC) applied on a hydraulic excavator. DDC offers a state-of-the-art, high performance control based on data and expert knowledge. On the one hand, expert knowledge is complex to adapt to each unique excavator requiring substantial engineering efforts. On the other hand, purely data based control overcomes this drawback by adapting a Neural Network (NN) inverse control directly on measured input/output data. Yet, coverage of the entire phase space and extrapolation to unknown situations is challenging for solely data-driven approaches. On a real demonstrator, we analyze expert white box methods, solely data-driven black box approaches and a hybrid grey box approach which combines a data-driven and simplified expert model. We examine trajectory tracking performance, engineering effort and safe exploration as goal criteria. Besides various experiments for testing safety, we apply a Support-Vector-Machine (SVM) to analyze the extrapolation fitness of the data-driven components to unknown data.

Todays factories are multi-domain facilities where manufacturing equipment, products and processes coexist with the engineering, human interactors, and their interventions. Often these basic entities of such highly ubiquitous and complex systems are lacking common and general interfaces. With the Horizon 2020 EU Research and Innovating program, several research activities have developed concepts to transform today's production workflows for the smart factories of the future to fit agile requirements. The H2020 HyProCell project targets the design and industrial integration of interconnected hybrid production cells in the subtractive and additive manufacturing with aspects of retrofitting of legacy production machines. This work describes and enhances architectural approaches to fit industrial requirements by proposing generic principles that support the automation engineering, cell control and basic data-acquisition. It treats modular requirements, the practical implementation and the testing of a service-oriented and modular architecture in a highly heterogeneous industrial environment in conjunction with MES- and CAx-toolchains.