Offshore Power-to-X platforms enable flexible conversion of renewable energy, but place high demands on adaptive process control due to volatile operating conditions. To face this challenge, using Digital Twins in Power-to-X platforms is a promising approach. Comprehensive knowledge integration in Digital Twins requires the combination of heterogeneous models and a structured representation of model information. The proposed approach uses a standardized description of behavior models, semantic technologies and a graph-based model understanding to enable automatic adaption and selection of suitable models. It is implemented using a graph-based knowledge representation with Neo4j, automatic data extraction from Asset Administration Shells and port matching to ensure compatible model configurations.

As Federated Learning (FL) expands to larger and more distributed environments, consistency in training is challenged by network-induced delays, clock unsynchronicity, and variability in client updates. This combination of factors may contribute to misaligned contributions that undermine model reliability and convergence. Existing methods like staleness-aware aggregation and model versioning address lagging updates heuristically, yet lack mechanisms to quantify staleness, especially in latency-sensitive and cross-regional deployments. In light of these considerations, we introduce SyncFed, a time-aware FL framework that employs explicit synchronization and times-tamping to establish a common temporal reference across the system. Staleness is quantified numerically based on exchanged timestamps under the Network Time Protocol (NTP), enabling the server to reason about the relative freshness of client updates and apply temporally informed weighting during aggregation. Our empirical evaluation on a geographically distributed testbed shows that, under SyncFed, the global model evolves within a stable temporal context, resulting in improved accuracy and information freshness compared to round-based baselines devoid of temporal semantics.

The transition to connected vehicles (CVs) is shaping the future of autonomous and highly connected vehicles. As the vehicles’ reliance on increasingly complex software increases, more central points of failure are introduced. This necessitates more thorough and scalable anomaly and intrusion detection systems. Conventional approaches can struggle with the complex and dynamic structures of CVs while not providing any automatic response actions. Therefore, machine learning-based anomaly detection methods are gaining popularity. Reinforcement Learning especially has shown the potential to increase configurability and provide end-to-end solutions. Thus, this paper presents a Systematic Literature Review (SLR) on Reinforcement Learning (RL) for anomaly and intrusion detection, applicable for CVs. In it, different RL algorithms and the analysis of how they can be used for training and detecting anomalies are presented. The problem formulations for different approaches are compared, their advantages and challenges are discussed. Additionally, the potential of using RL to react to anomalies is presented, discussed and advocated for. The results of the survey indicate that many of the identified RL formulations are not inherently superior from supervised learning approaches. However, RL techniques can result in better configurability of anomaly detection system, enabling site reliability engineers to efficiently adjust the model via reward functions. Furthermore, it becomes evident that the strengths of RL-based anomaly detection are best leveraged when used for reacting to anomalies. Therefore, the authors propose to focus on the contextual or sequential decision making formulation including corrective actions, compared to the classification-based detection formulations using RL.

Large Language Models (LLMs) offer flexible reasoning capability but lack physical embodiment, while traditional automation systems can execute physical processes yet lack cognitive capability. This paper presents a layered architecture that bridges this gap by integrating LLMs with digital twins and physical automation systems, with reference to practical case studies as proof of concept. The proposed architecture comprises three layers: a cognitive layer powered by LLMs, a bridging layer based on digital twins, and a physical layer consisting of technical process and automation system. Within the digital twin layer, we introduce three design paradigms for structuring information to support effective LLM integration: state snapshot modeling, event message modeling, and plan sequence modeling. These paradigms are demonstrated through prototypical case studies on robotic automation control and process simulation. To address challenges such as hallucination, task complexity, and system reliability, we distill a set of practical strategies, including multi-agent system design, human validation, and test-driven development. Additionally, we propose the concept of "Return on Intelligence" as a conceptual tool for evaluating the efficacy of investments in intelligent automation. This research contributes to the theoretical foundation and the architecture design for developing intelligent, adaptive automation systems powered by LLMs.

Traditional industrial automation systems require specialized expertise to operate and complex reprogramming to adapt to new processes. Large language models offer the intelligence to make them more flexible and easier to use. However, LLMs’ application in industrial automation settings is underexplored. This paper introduces a framework for integrating LLMs to achieve end-to-end control of industrial automation systems. At the core of the framework is an agent system designed for industrial automation tasks. A structured prompting method and an event-driven modeling mechanism provide the information for LLMs to perform reasoning on different context levels, allowing them to semantically interpret the information, generate production plans, and control operations on the automation system. Furthermore, this framework facilitates the creation of structured datasets for fine-tuning LLMs on this specific downstream application. Our contribution includes a formal system design, proof-of-concept implementation, and a method for generating task-specific datasets for LLM fine-tuning and testing. This approach enables a more adaptive automation system that can respond to spontaneous events, allowing intuitive system operation and configuration through natural language. Demo videos and detailed evaluation data are accessible on GitHub: https://github.com/YuchenXia/LLM4IAS.

Software systems often evolve into multiple variants to meet diverse requirements. This is usually achieved with the clone-and-own approach, where an existing variant is copied and modified. While efficient in the short term, this approach presents challenges for long-term maintenance. A suitable solution to overcome this, is to re-engineer the variants into a software product line (SPL). However, this process is labor-intensive and prone to errors. Although initial studies explore the use of large language models (LLMs) to assist in the re-engineering tasks, they do not address challenges such as hallucination and limited context windows, which restricts the applicability.In this paper, we present a novel approach to assist the transformation of cloned software variants into an SPL using an LLM. To mitigate hallucination, we propose a self-refinement feedback loop to validate the generated SPL. Additionally, we introduce a variation point filtering technique that reduces the input size, while preserving essential information. To quantify and evaluate the generated output, we propose the use of existing metrics that can be employed for the evaluation. Our evaluation demonstrates the effectiveness of the self-refinement feedback loop and variation point filtering based on an existing case study. The results, benchmarked against the proposed variability metrics, indicate that the generated SPL maintains equivalent complexity and potential for reusability, to the system it is compared against.

A Digital Twin of a production plant comprises a variety of simulation models. When these models are coupled for co-simulation, they can reflect the behavior of the entire production plant and be used in various application scenarios. To leverage the benefits of the Digital Twin and simulation during the operational phase, manual efforts in model adaption must be automated. This contribution presents a flexible co-simulation approach that enables automated selection of simulation tool interfaces, parameterization, and execution of different model configurations. Finally, application scenarios in the context of Power-to-X production are discussed, and the current implementation of the approach is presented.

The rapid innovation in the automotive industry highlights the increasing importance of user comfort, especially when integrated with advanced learning scenarios. However, there is a noticeable gap in research focusing on vehicle cabin comfort, particularly in the context of learning and personalization of features. This study conducts a systematic literature review to assess the current state of research in this area. By utilizing federated learning with personalization, a novel and promising technique, various use cases related to vehicle interior comfort are explored. These use cases help derive the requirements needed to address the research question. The methodology of the systematic literature review is detailed, including the evaluation of specific prerequisites. The key finding reveals that no existing study meets all the predefined requirements, underscoring the need for further research in this domain.

Most of the existing vehicle comfort features operate solely based on user input, lacking consideration for individual preferences, and environmental conditions. This manual adjustment while driving can lead to potential distractions, and jeopardizing user safety. On the other hand, implementing a system where the vehicle control unit learns individual preferences and autonomously adjusts accordingly would significantly enhance the driving experience. In this paper, we examine the thermal comfort of users as one of the comfort features within software-defined vehicles. Given that thermal comfort is influenced by both physiological and external factors, and people have diverse individual preferences, this paper proposes leveraging personalized federated learning to automate and personalize temperature regulation, thereby enhancing thermal comfort of passengers in the vehicle cabin. To validate this concept, we conducted experiments employing a prototype equipped with sensors to collect real-time data, which is then used to train a predictive model. The model's accuracy was assessed using metrics and compared against a centralized approach. In addition, we used a simulator to visualize the potential improvement in thermal comfort with the predicted values. Our findings indicate that temperature control in the vehicle cabin, utilizing federated learning for individualized regulation, outperforms conventional learning approaches, thus yielding significant improvement for thermal comfort of passengers.

Software-intensive systems emerge in a multitude of variations to meet diverse customer requirements. To develop such variant-rich software systems, software product line (SPL) Engineering has emerged as a key strategy for managing the variability. However, the adoption of SPLs is highly complex due to the diversity of feature model formats and specifications, and the complexity of implementing variability. Leveraging the capabilities of powerful large language models (LLMs) can facilitate the adoption of SPLs. Nonetheless, these LLMs often lack knowledge of the various specifications of potential feature models as well as efficient implementation of different variability mechanisms. To address these challenges, we propose a novel method based on retrieval-augmented generation. This method generates reusable artefacts and a corresponding feature mapping based on a given feature model, thereby aiding system engineers in adopting an SPL.

This paper presents a novel design of a multi-agent system framework that applies large language models (LLMs) to automate the parametrization of simulation models in digital twins. This framework features specialized LLM agents tasked with observing, reasoning, decision-making, and summarizing, enabling them to dynamically interact with digital twin simulations to explore parametrization possibilities and determine feasible parameter settings to achieve an obj ective. The proposed approach enhances the usability of simulation model by infusing it with knowledge heuristics from LLM and enables autonomous search for feasible parametrization to solve a user task. Furthermore, the system has the potential to increase user-friendliness and reduce the cognitive load on human users by assisting in complex decision-making processes. The effectiveness and functionality of the system are demonstrated through a case study, and the visualized demos and codes are available at a GitHub Repository: https://github.comlYuchenXia/LLMDrivenSimulation

This paper presents a novel application of Large Language Models (LLMs) to improve Failure Mode and Effect Analysis (FMEA) for managing risks in technical processes and products. We designed an LLM multi-agent system that utilizes Retrieval Augmented Generation (RAG) for risk analysis and text generation. This system interfaces directly with an FMEA knowledge database to dynamically extract relevant information, perform reasoning based on user input and retrieved information, and generate targeted text recommendations for completing FMEA spreadsheets. By automating the analysis and synthesis of risk information, this system can provide expert knowledge and reduces the cognitive load on users, speeding up the FMEA process. The effectiveness and functionality of this LLM-enhanced FMEA application is demonstrated through a prototype, accessible via a GitHub Repository at: https://github.com/YuchenXia/LLMRiskAnalyzer.

In safety-critical applications such as automotive or railway technology, prediction of the condition and remaining life of electronic components is a major challenge. To determine the condition, a comprehensive digital fingerprint of the components is needed, which already starts during the production phase. Currently, inspection data such as SPI, AOI and AXI data are used to group the components into two groups ("OK" and "not OK"). In the future, however, this inspection data will also be used to predict the service life and current condition of the assembly. This article deals with the investigation and processing of the imaging inspection data, as well as the geometry parameters determined from it. First, a dimensional reduction of the input data is carried out with the help of mathematical methods (PCA, t-SNE and Autoencoder). This reduction extracts the relevant information from the input data from the point of view of the AI. So far, clustering methods such as K-Means, DBSCAN and Hierarchical Clustering have been used to generate groups. In the future, these groupings can be used to predict the service life together with the loads on the components and thus make a statement about the current condition of the components

Industrial automation is driven by trends such as autonomy, intelligence and networking. Increasing energy demands, scarce resources and shorter product lifecycles pose challenges to production systems such as interoperability, flexibility and extensibility. The concept of the Digital Twin, acting as a virtual representation of a production system, can address these challenges. This paper presents a concept that realizes a dynamic production scheduling as partial function of the Digital Twin using the Asset Administration Shell and a service-oriented architecture. The authors specifically address automated asset production scheduling and propose an MQTT broker with a Functionality Dictionary server. Through the Asset Administration Shell interface, the proposed production scheduler communicates with the proposed product calendar to generate a specialized production schedule for each product. The evaluation scenario in a cyber-physical laboratory shows the advantages of this concept.

The Digital Twin is a well-known concept of Industry 4.0 and is the cyber part of a cyber-physical production system providing several benefits such as virtual commissioning or predictive maintenance. The existing production systems are lacking a Digital Twin which has to be created manually in a time-consuming and error-prone process. Therefore, methods to create digital models of existing production systems and their relations between them were developed. This paper presents the implementation of the methodology for the creation of multi-disciplinary relations and a quantitative and qualitative evaluation of the benefits of the methodology.

Industrial automation is becoming increasingly networked, intelligent and autonomous. Digital Twins, which serve as virtual representations, are a key technology in this context. The Digital Twin of a modular production system contains many different models that are mostly created for specific applications and fulfil different requirements. In particular, simulation models created in the development phase can be used in the operational phase for applications such as prediction or operation-parallel simulation. Due to the high heterogeneity of the model landscape in the context of a modular production system, the plant operator is faced with the challenge of adapting the models in order to ensure an application-oriented realism in the event of changes to the asset and its environment or the addition of applications. Therefore, this paper proposes an approach for the continuous model adaption in the Digital Twin of a modular production system during the operational phase. An agent-based implementation of the concept demonstrates the benefits of the approach for an operational phase application scenario.

Machine learning implementations in an industrial setting poses various challenges due to the heterogeneous nature of the data sources. A classical machine learning algorithm cannot adapt to dynamic changes in the environment, such as the addition, removal, or failure of a data source. However, to handle heterogeneous data and the challenges coming with this, it is a mandatory capability to build robust and adaptive machine learning models for industrial applications. In this work, a novel architecture for robust and adaptive machine learning is proposed to address these challenges. For this, an architecture consisting of different modular layers is developed, where different models can be easily plugged in. The architecture can handle heterogeneous data with different fusion techniques, which are discussed and evaluated in this paper. The proposed architecture is then evaluated on two public datasets for condition monitoring of automation systems to prove its robustness and adaptiveness. The architecture is compared with baseline models and shows more robust performance in case of failing/removed data sources. In addition, new data sources can easily be added without the need to retrain the whole model. Furthermore, the architecture can detect and locate faulty data sources.

Advancements in the Internet of Things (IoT) applied by automation systems lead to an increasing and flexible interconnection of various devices and the generation of voluminous data. In the domain of home automation for instance, having a multitude of interconnected data leveraged to knowledge could enhance user-centeredness and energy efficiency, among other use cases. However, the data as well as data sources are dynamic and heterogeneous, posing a great challenge to unfold their full capabilities. Thus, a unifying and correspondingly dynamic architecture is needed for supporting the flexibility and extensibility of such systems and data sources. In this paper, we present the concept and implementation of a context-aware INTElligent LIVing (inteLiv) architecture. Consisting of a data layer, a context layer and a service layer, the architecture abstracts the heterogeneous data of the linked devices via a middleware. The resulting system enables the collection of data across networked heterogeneous devices and models the collected data by using a unified dynamic context model. A hybrid approach was chosen for the designed context model: A combination of an ontology-based and property graph-based model represent a core aspect of this work as opposed to common static ontological representations and pre-defined context-based use cases. In the following contribution, the inteLiv ontology is first defined to describe the concepts of the intelligent living system. Based on the modeled context, reasoning algorithms also enable the derivation of new context information. The context is stored as a knowledge graph and can be used for context-aware applications, which can be designed during runtime. Furthermore, a user interaction with the system is possible via a web interface.

An increasing proportion of software characterizes modern automated systems such as vehicles. It can be used to provide new functions to improve the customer experience in terms of automation, personalization, and connectivity. For system development, this means that classic processes must be rethought and supplemented by new strategies. This is mapped via the trend of the software-defined systems. In this context, individual components can be improved over the entire life cycle. In order for these updates to function properly, testing before deployment is commonplace. However, since the software is complex and it is infeasible to test 100% of the possible scenarios, a software update can still lead to unforeseen side effects. At the same time, it must be monitored whether the desired update effects actually apply. In the worst case, the side effects include errors that must be found as quickly as possible in order not to negatively influence product quality and subsequent innovation cycles. The goal of this work is to detect side effects that manifest themselves as anomalies at runtime and to trace them back to the corresponding code change. For this purpose, a new approach is presented that uses the digital twin of the vehicle as an information base, providing operational data and simulations parallel to operation. The simulation generates synthetic data also containing the rare and risky cases that can then be matched against the operational data to identify anomalies. Once an anomaly is detected, a subsequent analysis follows that relates the anomaly to a causal code sequence. The presented approach is realized using the example of a model vehicle with microcontrollers and corresponding peripherals such as sensors and motors. The model vehicle is simulated using the simulation software SimulIDE, which provides the synthetic data. The evaluation shows that the trace back of side effects to the respective code sequences can successfully be achieved.

In this paper, we present a novel framework that combines large language models (LLMs), digital twins and industrial automation system to enable intelligent planning and control of production processes. We retrofit the automation system for a modular production facility and create executable control interfaces of fine-granular functionalities and coarse-granular skills. Low-level functionalities are executed by automation components, and high-level skills are performed by automation modules. Subsequently, a digital twin system is developed, registering these interfaces and containing additional descriptive information about the production system. Based on the retrofitted automation system and the created digital twins, LLM-agents are designed to interpret descriptive information in the digital twins and control the physical system through service interfaces. These LLM-agents serve as intelligent agents on different levels within an automation system, enabling autonomous planning and control of flexible production. Given a task instruction as input, the LLM-agents orchestrate a sequence of atomic functionalities and skills to accomplish the task. We demonstrate how our implemented prototype can handle un-predefined tasks, plan a production process, and execute the operations. This research highlights the potential of integrating LLMs into industrial automation systems in the context of smart factory for more agile, flexible, and adaptive production processes, while it also underscores the critical insights and limitations for future work. Demos at: https://github.com/YuchenXia/GPT4IndustrialAutomation

The creation of a Digital Twin for existing manufacturing systems, so-called brownfield systems, is a challenging task due to the needed expert knowledge about the structure of brownfield systems and the effort to realize the digital models. Several approaches and methods have already been proposed that at least partially digitalize the information about a brownfield manufacturing system. A Digital Twin requires linked information from multiple sources. This paper presents a graph-based approach to merge information from heterogeneous sources. Furthermore, the approach provides a way to automatically identify templates using graph structure analysis to facilitate further work with the resulting Digital Twin and its further enhancement.

Failure analysis is essential for improving the reliability and manufacturability of electronic devices. With the time-domain reflectometry method, failures can be analyzed non-destructively. The method enables the detection, location, and characterization of hard interconnection failures (open or shorts) as well as of soft interconnection failures, which can give an outlook on imminent hard failures. Generating measurement data from real failed devices is costly since failed devices need to be selected and the measurements need to be performed and prepared. In contrast, simulation models are often available where all possible kinds of failures can be created. Therefore, we propose simulation to real transfer learning for the failure analysis on time-domain reflectometry data. A deep learning model shall first be trained on time-domain reflectometry simulation data and then be transferred to measurement data of a power transistor. We investigate different possibilities of transfer and evaluate the performance of a SiC power transistor.

In partially automated manufacturing, humans work together with mobile robots. Trajectory prediction, i.e. predicting future positions of human workers, improves collaboration and coexistence between humans and robots on the shop floor. In this paper, we discuss the interrelated research questions of how human motion trajectories can be predicted and how mobile robots such as Autonomous Mobile Robots and Automated Guided Vehicles can take such predictions into account in their pathfinding and navigation. On the robot side, advanced D* pathfinding algorithms allow robots to take dynamic obstacles into account. For trajectory prediction, the position of human workers is determined by an Ultra-Wideband-based Real-Time Locating System. A trajectory prediction framework is introduced to support the implementation and use of pattern- and planning-based trajectory prediction algorithms. The evaluation is based on scenarios from the addressed problem area of manufacturing.

Industrial mobile robots increasingly operate in dynamic and complex environments, resulting in risks that arise from the situation. Consequently, mobile robots need knowledge about the situative risk to make responsible decisions, e.g., when planning a trajectory. In this paper, the authors present a new approach to evaluate these situative risks at runtime. To compute the situative risk, the proposed approach uses multi-agent adversarial reinforcement learning. Unlike the usual approach that uses the self-play mechanism to harden the agents against disturbances, the approach directly uses the self-play to determine the confidence that the system can handle the current situation. Based on the evaluation of the strength of the perceived perturbations, the robot’s digital twin calibrates the action space of the adversarial agents. In this way, the adversarial agents represent the disturbances that are likely to occur. From the simulation results of the competing agents, the digital twin infers the confidence with which the system can handle the situation. In the event that the system cannot handle the situation and crashes in the simulation, the digital twin calculates the probability that the simulated scenario will occur in reality. To calculate this probability, the authors propose the method of game-theoretic event trees. Combining the probability of an accident scenario with the damage caused by the simulated hazard, the results of situative risk are obtained. The approach is qualitatively evaluated using a case study. In this case study, a industrial mobile robot called Robotino is considered that connects workstations in a matrix production system. The case study shows that the approach is promising.

In the production of the future, people and robots will work together in dynamic environments. Industrial mobile robots drive past workers and obstacles to the assemblers' workstations, pick up workpieces and deliver them to the next free workstation. To ensure reliable production, robots must carefully consider their actions based on the current situation to minimize losses. In order to reason about losses, it is necessary to identify loss scenarios that are likely to arise from the system's situation. In this paper, the authors propose a novel methodology for identifying these likely loss scenarios based on fault injectors. The fault injectors are trained using reinforcement learning. Based on a probability model of disruptive events (faults), the agents learn to destabilize the system by simulating such events. When a chain of these events leads to a loss, a loss scenario is found. The higher the probability of the loss scenario, the higher the reward for the agent. In this way, the fault injectors optimize for maximally likely loss scenarios. After describing the methodology, the authors propose a framework for systematically classifying different types of fault injectors and give advice on how to build them. Finally, the authors demonstrate reinforcement learning-based fault injectors on the path planning of the mobile robot platform Robotino.

Current industrial automation systems are facing increasing dynamics. Thus, acquiring and managing heterogeneous data within the Digital Twin to enable decision making is necessary although challenging. Knowledge Graphs unify and relate data, enabling the derivation of new insights. In this contribution, an approach for context-enriched modeling of cyber-physical production systems is proposed, in order to realize a Knowledge Graph enhanced intelligent Digital Twin further considering the context. Therefore, the modeling approach of the Knowledge Graph considers context and serves as a base for the graph embeddings to gain further knowledge about the production system. This knowledge is used within the architecture of the intelligent Digital Twin. The resulting benefits, i.e. diverse manifestations of an improved decision making, are highlighted by the use case of self-organized reconfiguration management.

Behavior models in the Digital Twin are relevant to many use cases such as digital product development, virtual system optimization or virtual commissioning. However, such behavior models are structured in the literature according to different criteria and levels, which complicates the selection of the correct properties for specific use cases. One criterion discussed very differently is the modeling depth of behavior models. This paper presents different approaches to structure behavior models from literature and introduces a new concept with focus on the modeling depth. These levels of modeling depths, as well as the characteristics of the different modeling depths, are illustrated using a representative industry scenario.

The use of Digital Twins is versatile and offers a wide range of advantages. However, their creation is often a manual process and therefore very time-consuming and cost-intensive. The creation of behavior models stands out as particularly time-consuming. Therefore, this paper deals with the creation of Digital Twins from the perspective of an industrial component manufacturer, with a particular focus on the creation of behavior models. An automated approach based on libraries is presented. The creation of behavior models is validated in an industry-relevant application scenario and compared with the manual creation process.

Today’s systems engineering is challenged by an increasing number of requirements aimed at smaller target audiences. This leads to a rise of variants to fulfill individual consumer demands. Because of the complexity introduced by the surge of software-defined mechatronic systems, deriving new variants manually is becoming increasingly difficult. As of today, however, there exist no well-established methods or tools to assist in variant generation. This article aims to fill this gap by presenting a novel approach that enables an automated, requirements-based variant generation. For this purpose, a variant meta-model capable of both storing and interconnecting physical parameters and qualitative criteria of system components is designed and translated into a machine-readable form. The resulting data model is described to be stored inside a multi-model database, allowing for the integration of past project data by using data mining techniques. Additionally, a variant generation algorithm with a strategy for targeted exploration of the variant solution space is presented. The complete approach is realized by implementing a demo application that includes both the multi-model database and a java application for algorithm execution. Our work is evaluated by benchmarks using a dataset with real-world components, indicating that requirements-conform variants can be generated in a reasonable time.

The Asset Administration Shell (AAS) is a standardized data container for sharing data in the context of Industry 4.0. It allows different participants or systems to communicate their information based on shared meaning. Today, however, AAS makes data interoperable at the cost of extra development effort. Developers must map a proprietary information model to a standardized AAS model during the data transformation. In this work-in-process paper, a novel data transformation method based on transfer learning with neural language model is proposed to automatically map the data properties from an arbitrary information model into a standardized AAS model. The term "semantic fingerprint" is used to characterize a pivot intermediate vector generated by a neural network, containing latent conceptual meaning about a data property, which is in turn used for generating the mappings between data properties with similar conceptual meaning. By this means, the proposed approach fills the research gap on automated generation of AAS models with semantic analysis and is able to lower the barrier to adopting AAS with tool support.

Automation systems are increasingly being used in dynamic and various operating conditions. With higher flexibility demands, they need to promptly respond to surrounding dynamic changes by adapting their operation. Context information collected during runtime can be useful to enhance the system's adaptability. Context-aware systems represent a design paradigm for modeling and applying context in various applications such as decision-making. In order to address context for automation systems, a state-of-the-art assessment of existing approaches is necessary. Thus, the objective of this work is to provide an overview on the design and applications of context and context models for automation systems. A systematic literature review has been conducted, the results of which are represented as a knowledge graph.

Systematic Literature Reviews aim at investigating current approaches to conclude a research gap or determine a futuristic approach. They represent a significant part of a research activity, from which new concepts stem. However, with the massive availability of publications at a rapid growing rate, especially digitally, it becomes challenging to efficiently screen and assess relevant publications. Another challenge is the continuous assessment of related work over a long period of time and the consequent need for a continuous update, which can be a time-consuming task. Knowledge graphs model entities in a connected manner and enable new insights using different reasoning and analysis methods. The objective of this work is to present an approach to partially automate the conduction of a Systematic Literature Review as well as classify and visualize the results as a knowledge graph. The designed software prototype was used for the conduction of a review on context-awareness in automation systems with considerably accurate results compared to a manual conduction.

This paper presents a study about a runtime mechanism to monitor the performance degradation in intra-vehicular networks. The proposed mechanism focuses on the integration of fault modeling in communication protocols, as non-functional requirements (NFR), using aspect-oriented modeling (AOM), to model the performance degradation generated by faults, linking test and design phases of distributed control systems. A case study analyzing the mechanism performance in both CAN and CAN-FD protocols was conducted considering the NFR specification related to fault disturbances. In order to evaluate and simulate the mechanism under real fault scenarios, an active suspension control system was considered as an example of a critical control system and faults were injected using the hardware Vector VH6501 (CAN disturbance interface). The network performance analysis was made based on the software Vector CANoe considering different network busloads and CAN/CAN-FD rates between 1 to 4 Mbps. Results show that the mechanism efficiently detects anomalous events on performance with short response time with busloads up to 30%. The performed experiments show better performance on CAN-FD registering lower average jitter during fault injection in all busloads tested scenarios.

Advances in automation technology and AI research, as well as the trend toward digitalization and networking, make modern automation systems complex, heterogeneous and dynamic, i.e., changes to the system and its environment are increasingly becoming the norm. Under such conditions, the classic safety process of certifying a snapshot at the end of the design phase becomes insufficient. To overcome this, we propose an approach that evaluates the safety of the actions of such systems at runtime. In doing so, the approach addresses three fundamental challenges of online safety assurance, namely, incorporating safety requirements into the online design process, coping with dynamic changes in the environment, and dealing with the uncertainties arising from dynamics and unpredictable environments and the adaptation of the system to them. The presented approach is applied to a specific scenario that shows promising results in simulation.

Digital Twins are being increasingly used in manufacturing industry to support the whole plant lifecycle. The constantly changing environmental parameters, interactions between various systems and their Digital Twin as well as changes inside the Digital Twin influences the context of the available information. This context information is insufficiently considered to analyze process and optimize the interaction. This article presents an approach to model the internal and external context of a system using a graph-based context tier model. The usage and benefits of the concept are shown for a flexible production system.

Large-scale manufacturing systems consist of multiple complex process steps that are highly interdependent and characterized by dynamic nonlinear physics. These processes are subject to model uncertainties and external disturbances that cause reduced process stability and fluctuant product quality. To avoid defects and to ensure a high product quality, an adequate detection and control of disturbance effects is needed. Hence, the paper presents a novel adaptive control scheme with disturbance rejection property for discrete large-scale manufacturing systems. To model the complex process physics and disturbance effects, Long short-term memory (LSTM) networks are applied. These recurrent networks improve the modeling of time-variant systems regarding short-term and long-term dependencies. The adaptive control scheme is predicated on a self-learning and cooperative prediction of process and disturbance to achieve an improved performance. Based on this neural prediction, a compensation of disturbance effects and thus a part-centered quality optimization can be achieved. The approach is tested and evaluated for a plant of hot forging.

Digital Twins will change how systems and products are engineered and operated. Individual virtual representations of assets help to develop, maintain and change single components or whole factories. Aerospace engineering, product design and intelligent manufacturing are hot spots for the use of Digital Twins. Simultaneously, globalized markets lead to a growing awareness of dependability and quality, which increases the importance of verification and validation. The Digital Twin could prove to be key enabler for efficient verification and validation processes. This paper presents the results of the literature review of approaches that use Digital Twins for verification and validation purposes. Many solutions have been found for a wide range of challenges in various fields of application. This survey discusses the underlying methods and the elements of Digital Twins already in use. Most research approaches focus on simulations and three methodological clusters of approaches sharing similar ideas were identified.

Flexible intralogistics systems use automated guided vehicles (AGV) to transport goods. In assembly and warehouses, AGVs and human workers often work side by side. For optimal navigation, AGVs must consider human movement and estimate future positions of workers. Using real-time locating systems (RTLS) to improve human-robot collaboration enables more energy-efficient and safer AGV wayfinding strategies. This paper gives a summary on the topics RTLS, AGV wayfinding and trajectory prediction and introduces the momentum-based approach to predicting future worker positions in factories and warehouses. The results show that ultra-wideband-based RTLS are very well suited for trajectory prediction in the production sector.

Fault prediction based upon deep learning algorithms has great potential in industrial automation: By automatically adapting to different usage contexts, it would greatly expand the usefulness of current predictive maintenance solutions. However, restrictions regarding the centralized accumulation of data necessary for such automatic adaption call for a distributed approach to training these algorithms. Therefore, in this paper, a continual learning based algorithm for fault prediction is presented, allowing for distributed, cooperative learning by elastic weight consolidation. This algorithm is then evaluated on a large NASA turbofan engine dataset and shows promising results regarding the performant training on decentral sub-datasets for industrial automation scenarios.

Networked and intelligent cyber-physical systems are being increasingly applied in automation technology. Surrounding parameters representing the ambient environment and the users interacting with these systems can greatly influence their operation and tend to be heterogeneous and dynamic. There is insufficient consideration for these parameters and how they relate to the system and can contribute to optimizing its analysis and operation. Enabling context-awareness for cyber-physical systems presents an approach to consider surrounding and situational factors. In this contribution, the design of context-aware cyber-physical systems is addressed with the goal to first introduce a fitting definition for context-aware cyber-physical systems as well as propose an approach to dynamically model the system's context in relation to its user and environment. The concept is shown for a user-centric pill dispenser, based on which the role as well as applicability of the context model is presented.

This paper presents an approach to monitor the performance degradation in CAN networks and the fault effect on time constraints of periodic control tasks. The work proposes the use of a test-based method supported by fault and error injection that helps the engineer to define how these faults degrade the system performance. In addition, a runtime jitter monitoring technique is proposed and applied to a CAN-based vehicular network. The runtime jitter analyses the performance oscillation according to a time window and with a tolerance range defined during previous performance tests. A case study was conducted monitoring a critical control system during error injection and the analysis technique was applied in order to verify the performance oscillation detection. Results show that with a typical CAN rate of 1 Mbps, the runtime jitter detect anomalies in performance during a short time period up to 30% of busload. The experiments show the degradation of 4,2 times on average jitter between 10% and 30% of busload with fault injection. The detection is also possible with higher busload 50% and 80%, but with an increase in the detection time. The present study emphasizes the importance of performance monitoring with the recent advances in automotive electronics.

This Innovative Practice Work in Progress presents the proposal and the development of a simulator for an Evolvable Production System that aims to represent a complete mechatronic system, simulate its operation, and support the learning of associated subjects. A mechatronic system is composed of mechanical and electronic modules that in turn may be associated with a software layer that is responsible for the intelligence of the entire system. This intelligence comes through interactions among software agents belonging to the software layer. The mechatronic devices are described through Finite State Machines, whose transitions are triggered by mechatronic software agents. The output of the simulator is a list with the set of skill calls, the time in which such calls are made, the respective system's answer, and the set of communication messages exchanged among the agents' peers. By using this simulator in engineering classrooms, it is possible to construct several proposals of mechatronic systems, represent those systems as complete manufacturing processes, and use intelligent software agents to simulate the complete functionality of the designed system. Afterward, with the results obtained from the simulation, students are prepared to implement real systems. The proposed simulator has been used in engineering courses at the Federal University of Amazonas, and the goal of this paper is describing the characteristics of the simulator and the results of its use in engineering disciplines.

Internet-of-Things-(IoT)-systems will pose new challenges for the simulation of such systems, like the dynamic entering of components during runtime and the huge heterogeneity of the components. Various existing approaches for the simulation of IoT-systems are described. Additionally a concept is presented, which meets the described challenges. To satisfy the heterogeneity each component is modelled individually in separate modelling tools. The concept utilizes a multi-agentsystem to simulate the communication between the different models and to enable them to be integrated during simulation time. With the presented concept it is also possible to integrate real components into the simulation.

In this document we describe an approach to interconnect existing industrial automation systems with cooperation networks, like the internet of things, even if the industrial automation system uses a different communication protocol. To realize this, we have developed the concept of connector which provides system-dependent interfaces for different industrial automation and a universal interface for the cooperation network. Between these interfaces the messages are processed and translated by services, which act as a representation of the industrial automation system.

Product lifecycles are getting increasingly shorter, but the lifecycles of industrial automation systems remain stable. Since future requirements for the industrial automation systems made by the market are often unknown at the beginning of the planning process, industrial automation systems have to be adaptable at later times. In addition, the efforts of planning should be reduced continuously without losses in the quality in order to reduce costs. The aim of the approach presented in this paper is the development of an assistance system, which supports the planner during the planning and the adaptation of industrial automation systems by generating and evaluating different solution alternatives for the changed requirements and constraints. The implementation of the assistance system is based on a resource-based view of an industrial automation system and bottom-up planning which is realized with the help of a multi-agent system.

Unibral is a program that supports research and education cooperation actions between German and Brazilian universities. This work in progress paper will describe a new version of such an old experience of Unibral, a project between the Federal University of Amazonas and the University of Stuttgart. This edition started in 2013 and joined two institutes related to the electrical and computer engineering courses. The German side is represented by the Institute of Industrial Automation and Software Engineering (IAS) and the Brazilian side by the Electrical and Computer Engineering Courses. The main topics of the research and technology transfer are related to the new industrial automation issues concerning modularity and flexibility, product automation (focusing on health), and cyber physical systems. The project will evaluate the introduction of new curricular directions and new subjects in both sides, as well as, joint research action that will put together people from both institutions. This paper will describe the experiences already done in this work in progress emphasizing the new directions in this project phase. Our goal is to contribute with other universities all over the world wishing to establish similar cooperation actions.

In this paper a new model for controlling and monitoring industrial Automation Systems will be described. The architecture of this model does not limit it to be connected to only one specific Industrial Automation System, but enables it to be connected to different systems simultaneously, as well as reused for new systems, packing any industrial communication protocol. Controlling and monitoring is then done through a network service that allows remote devices to access the Automation Systems. The basic components have their hardware and software described, as well as the interfaces with the industrial Automation System and components in between. Thus, the proposed structure is presented and later it is shown how it is possible to reuse this system for other applications.

In this paper an automation system for controlling industrial and building plant using voice commands, spoken in natural language, will be described. This system uses cloud computing services to process spoken sentences and to identify the user's desired request, i.e. it converts voice commands in electronic commands. It also presents a software and hardware architecture that allows the system to be connected to several different Automation Plants, enabling this voice control feature for a larger number of devices without requiring the development of a new control system. Thus, the proposed structure is presented and later it is shown the first prototype that uses this system.

Limited test time and restricted number of test resources confront test managers with big challenges, especially in the system test. Consequently, the test manager has to prioritize test cases before each test cycle. There is much information available for determining a reasonable prioritization order in software projects. However, due to the complexity of current software systems and the high number of existing test cases, the abundance of information relevant for prioritization is not manageable for the test manager, even with high effort. In this paper we present a concept for an automated prioritization of test cases using software agents and fuzzy logic. Our prioritization system determines the prioritization order which increases the test effectiveness and the fault detection rate.

Motivated by increasing demands for efficiency, reuse approaches have been increasingly gaining significance during the last years. System engineering shifted from single systems to product lines. Although the engineering paradigm changed, industrial automation systems within a product line are created with the same engineering tools as single systems. Hence, it becomes relevant to analyze which requirements engineering tools shall fulfill in order to increase reuse within a product line of industrial automation systems. The identified requirements are interesting for the following reasons: first, they are relevant for developers of engineering tools, since they aim to provide competitive products. Second, they are relevant for developers of industrial automation systems, since they reuse existing artifacts in designing new industrial automation systems with the help of engineering tools. Third, the topic is interesting for researchers and practitioners in the field of product line engineering for industrial automation systems who want to know which aspects are already supported by current engineering tools.