Search

In this article, the concepts of transfer and continual learning are introduced. The ensuing review reveals promising approaches for industrial deep transfer learning, utilizing methods of both classes of algorithms. In the field of computer vision, it is already state-of-the-art. In others, e.g. fault prediction, it is barely starting. However, over all fields, the abstract differentiation between continual and transfer learning is not benefitting their practical use. In contrast, both should be brought together to create robust learning algorithms fulfilling the industrial automation sector's requirements. To better describe these requirements, base use cases of industrial transfer learning are introduced., 12 pages, 4 figures, 2 tables. Accepted for publication by IEEE Industrial Electronics Magazine

We are seeing a boom in the use of real-time position data to automate and optimize tasks in the field of production and logistics. Here we consider the reasons for this, show what has already proven to be industrially viable and give an overview of six current research efforts. We show which use cases have been automated by RTLS and where RTLS could play a role to further optimize production processes or material flows in the future.

The utilization of deep learning in the field of industrial automation is hindered by two factors: The amount and diversity of training data needed as well as the need to continuously retrain as the use case changes over time. Both problems can be addressed by industrial deep transfer learning allowing for the performant, continuous and potentially distributed training on small, dispersed datasets. As a specific example, a dual memory algorithm for computer vision problems is developed and evaluated. It shows the potential for state-of-the-art performance while being trained only on fractions of the complete ImageNet dataset at multiple locations at once.

Recurrent neural networks and exceedingly Long short-term memory (LSTM) have been investigated intensively in recent years due to their ability to model and predict nonlinear time-variant system dynamics. The present paper delivers a comprehensive overview of existing LSTM cell derivatives and network architectures for time series prediction. A categorization in LSTM with optimized cell state representations and LSTM with interacting cell states is proposed. The investigated approaches are evaluated against defined requirements being relevant for an accurate time series prediction. These include short-term and long-term memory behavior, the ability for multimodal and multi-step ahead predictions and the according error propagation. Sequence-to-sequence networks with partially conditioning outperform the other approaches, such as bidirectional or associative networks, and are best suited to fulfill the requirements.

Data-science-driven development projects are increasingly gaining the attention of small and medium sized enterprises. Since SME are often lacking the necessary competencies in data science, cooperation with other companies or universities is required. The efficient handling of data is one of the main challenges in joint cross-enterprise development projects. Actual cost driver is the development of data by labeling and classifying the data by domain experts, which is very time-consuming and labor-intensive with large amounts of data. Furthermore, clearance processes also have a high potential to cause delays before data can be shared with project partners. Moreover, before the actual work can begin, it is often necessary to clean up and repair incomplete or noisy data. The concept of Data Administration Shell presented in this paper addresses the challenge of structured information sharing and information management in joint cross-enterprise engineering. The Data Administration Shell links data sets to information regarding data origin and already performed analyses including their results and program scripts. Adding relations and documentation facilitates the reuse of data sets for subsequent projects. For this purpose, the Data Administration Shell adapts the concepts serving the information sharing in the research field of manufacturing and Digital Twin. The evaluation of the Data Administration Shell was based on time-series measurement data from a production process optimization scenario. Here, the Data Administration Shell manages the data sets of time series data and facilitates the joint cross-enterprise engineering of data-driven solutions.

The system development process is becoming increasingly complex as the systems themselves become more and more complex. At the same time, the various disciplines such as mechanical engineering, electrical engineering and software engineering are becoming increasingly intermixed, so that companies in one discipline are experiencing leaps and bounds in the complexity of their systems and their development. For this reason, this publication presents a concept of a virtual assistant that leads through a development phase. It shows that the software supporting the development needs an information model to store the data of the developed system and to connect it with the existing knowledge. This knowledge can either be available internally or on the web. The development process should therefore support cooperation so that the assistance software and engineers interact with each other.

Future automation systems, operating under increasing dynamic conditions need to be equipped with methods to enhance their adaptability accordingly. Context-aware systems model and apply contextual parameters influencing the interpretation of situations to adapt their operation accordingly. Designing context-aware automation systems requires methods to acquire and process heterogeneous and distributed data in a dynamic and continuous manner. In this contribution, a methodology for processing multimodal data in a flexible and reusable context-model is demonstrated, using concepts of data aggregation and integration, semantic labeling and graph modeling. Based on this approach, the use case of a context-aware medication assistance system is subsequently presented.

Autonomous systems are increasingly discussed in the domain of industrial automation. However, there is no consensus in the literature about the definition of industrial autonomous systems, what characteristics do they possess and how to distinguish them from intelligent industrial automation systems. Another important aspect is the comparison between the degree of automation and autonomy. Addressing this confusion, this paper starts with an analysis of the historical development of the term autonomy. Based on the similarities in the definitions, that were identified in a literature review, a comprehensive definition of industrial autonomous systems is presented, and four main characteristics of an industrial autonomous system are derived. Consequently, the characteristics for the realization of an industrial autonomous system (1) systematic process execution, (2) adaptability, (3) self-governance and (4) self-containedness are described in detail. Another objective of this contribution is to assist the developers of industrial autonomous systems to take the above-mentioned characteristics into account. Furthermore, the developer is advised which abilities can be used to achieve the corresponding essential characteristics of industrial autonomous systems. To illustrate the characteristics and abilities of an industrial autonomous system, this paper gives a detailed description of three realized cases of application in industry.

The frequency of changes in production requirements is continuously increasing due to economic volatility, shorter innovation cycles and product life cycles. Therefore, a prediction of all goals of a production system at development time is impossible, which is leading to an increased reconfiguration demand during operation. Currently, there are still some weaknesses concerning the reconfiguration of production systems, which are highlighted in this article. The future of industrial automation will be dominated by Cyber-Physical Production Systems, which offer many promising potentials. Hence, this contribution discusses the Cyber-Physical Production Systems and some of their potentials regarding the reconfiguration issues. Corresponding concepts are required to utilize these theoretical potentials. Therefore, this research provides a basic concept for self-organized reconfiguration management.

The use of the Digital Twin as a promising technology during the reconfiguration of automated systems enables to meet the challenges of increasing product diversity and shortening product life cycles in today's industry. The use of Digital Twins supports engineers in all phases of the life cycle of a production line. Over time, however, production facilities are often modified and improved, while at the same time the created models during the engineering process of the system remain unchanged and no longer correspond to the real facility. Manual updating of the positions in the digital layout is very time-consuming and therefore expensive. This paper presents a concept for the automatic update of the layout of a production line. In this concept, the positions of the robots and their active and passive peripheral devices are automatically positioned in a digital plant model using information from the current configuration of the robots in a production line. Therefore, engineers can use the resulting synchronized digital plant model, Digital Twin of the system, to further optimize or expand the production plant.

Shorter product life cycles and increasing individualization of production leads to an increased reconfiguration demand in the domain of industrial automation systems, which will be dominated by cyber-physical production systems in the future. In constantly changing systems, however, not all configuration alternatives of the almost infinite state space are fully understood. Thus, certain configurations can lead to process instability, a reduction in quality or machine failures. Therefore, this paper presents an approach that enhances an intelligent Digital Twin with a self-organized reconfiguration management based on adaptive process models in order to find optimized configurations more comprehensively., Comment: 6 pages, 2 figures. Submitted to 54th CIRP Conference on Manufacturing Systems 2021

A multitude of high quality, high-resolution data is a cornerstone of the digital services associated with Industry 4.0. However, a great fraction of industrial machinery in use today features only a bare minimum of sensors and retrofitting new ones is expensive if possible at all. Instead, already existing sensors’ data streams could be utilized to virtually ‘measure’ new parameters. In this paper, a deep learning based virtual sensor for estimating a combustion parameter on a large gas engine using only the rotational speed as input is developed and evaluated. The evaluation focusses on the influence of data preprocessing compared to network type and structure regarding the estimation quality.

Developing consistently well performing visual recognition applications based on convolutional neural networks, e.g. for autonomous driving, is very challenging. One of the obstacles during the development is the opaqueness of their cognitive behaviour. A considerable amount of literature has been published which describes irrational behaviour of trained CNNs showcasing gaps in their cognition. In this paper, a methodology is presented that creates worstcase images using image augmentation techniques. If the CNN's cognitive performance on such images is weak while the augmentation techniques are supposedly harmless, a potential gap in the cognition has been found. The presented worst-case image generator is using adversarial search approaches to efficiently identify the most challenging image. This is evaluated with the well-known AlexNet CNN using images depicting a typical driving scenario., to be published in 16th CASE 2021: Lyon

The success of the reconfiguration of existing manufacturing systems, so called brownfield systems, heavily relies on the knowledge about the system. Reconfiguration can be planned, supported and simplified with the Digital Twin of the system providing this knowledge. However, digital models as the basis of a Digital Twin are usually missing for these plants. This article presents a data-driven approach to gain knowledge about a brownfield system to create the digital models of a Digital Twin and their relations. Finally, a proof of concept shows that process data and position data as data sources deliver the relations between the models of the Digital Twin., 7 Pages, 5 figures. Accepted at IEEE ETFA 2021

The capabilities of a cyber-physical production system are determined by their physical and virtual elements and their interaction. The interaction between virtual and physical entities must be precisely defined, and it is therefore necessary to develop capability models and requirements that enable self-reconfiguration of different elements and their relationships. Furthermore, an ultra-flexible production system requires communication and analysis of huge amounts of data as well as flexible, near-real-time communication between elements. This paper discusses and describes the functional and technical requirements of an ultra-flexible factory and presents an approach to the semantic structuring of elements and capabilities.

The heterogeneity and dynamics of IoT systems pose new challenges for their simulation, especially for hardware-in-the-loop simulations, which can be met by modular co-simulation. Therefore, several existing co-simulation approaches are presented and their suitability for hardware-in-the-loop co-simulations is evaluated. A new concept for dynamic hardware-in-the-loop co-simulation of IoT systems with a multi-agent system is presented, where each IoT component is simulated in its own simulation tool. Each individual simulation is represented by an agent and is therefore able to dynamically enter a co-simulation at run-time, which enables a "plug-and-simulate" behavior. The presented concept is evaluated by a prototypical implementation.

Zusammenfassung Durch zunehmende Agilität im Entwicklungsprozess, kürzere Lebenszyklen und sich ändernde Kunden- und Gesetzgeberanforderungen müssen Produktionssysteme wandlungsfähig sein. Aber jede Veränderung des Systemverhaltens muss anschließend auch erneut abgesichert werden. Zur Absicherung sicherheitskritischer Funktionen eignen sich formale Verifikationsmethoden. Allerdings ist hierzu ein hoher Modellierungsaufwand notwendig, was den Einsatz formaler Verifikationsmethoden in der Praxis hemmt. Zudem empfiehlt sich eine Überprüfung der zur formalen Verifikation eingesetzten Modelle. Zur Bewältigung der Herausforderungen für die Absicherung, die eine Rekonfiguration während des Betriebs nach sich zieht, werden in diesem Beitrag zwei vielversprechende und sich gegenseitig ergänzende Ansätze für die lebenszyklusübergreifende Absicherung von Produktionssystemen vorgestellt.

Zusammenfassung Unvorhersehbare Prozessereignisse und Anomalien sind Treiber erhöhter Ineffizienzen in Form von schwankender Produktqualität. In diesem Beitrag wird ein datengetriebener Ansatz zur Qualitätsoptimierung vorgestellt, auf dessen Basis Anomalien charakterisiert werden, die zur Entwurfszeit des Systems nicht bekannt waren. Es wird eine Netzarchitektur in Form eines Sequence-to-Sequence Netzes mit Long Short-Term Memory (LSTM) Zellen vorgestellt. Dadurch kann vorhergesagt werden, welche Anpassung am Stellgrößenverhalten vorgenommen werden muss, um erwartete Anomalien zu kompensieren. Dadurch wird das Qualitätsergebnis langfristig in der Toleranz gehalten. Der Ansatz wird prototypisch anhand von zwei Prozessketten der diskreten Fertigung umgesetzt und evaluiert.

Society today depends on autonomous systems, such as intelligent service systems, self-driving trains, and remote surgeries.1 The ultimate validation of the Turing test is that we often do not recognize autonomous systems. This growing usage poses many challenges, such as how to provide transparency, which rules or learning patterns are applied in a complex situation, and if these rules are the right ones. Validation is the key challenge, of which we will provide an overview in this article.

The role of a Digital Twin is increasingly discussed within the context of Cyber-Physical Production Systems. Accordingly, various architectures for the realization of Digital Twin use cases are conceptualized. There lacks, however, a clear, encompassing architecture covering necessary components of a Digital Twin to realize various use cases in an intelligent automation system. In this contribution, the added value of a Digital Twin in an intelligent automation system is highlighted and various existing definitions and architectures of the Digital Twin are discussed. Flowingly, an architecture for a Digital Twin and an architecture for an Intelligent Digital Twin and their required components are proposed, with which use cases such as plug and produce, self-x and predictive maintenance are enabled. In the opinion of the authors, a Digital Twin requires three main characteristics: synchronization with the real asset, active data acquisition from the real environment and the ability of simulation. In addition to all the characteristics of a Digital Twin, an Intelligent Digital Twin must also include the characteristics of Artificial Intelligence. The Intelligent Digital Twin can be used for the realization of the autonomous Cyber-Physical Production Systems. In order to realize the proposed architecture for a Digital Twin, several methods, namely the Anchor-Point-Method, a method for heterogeneous data acquisition and data integration as well as an agent-based method for the development of a co-simulation between Digital Twins were implemented and evaluated.

The demand of customer-specific products leads to a fundamental change to manufacturing facilities. To adapt the facilities to new product types, frequently occurring functionality changes in industrial automation systems are expected. Functionality changes are primarily implemented by software changes. These software changes within the operation phase can be implemented, for instance, by over-the-air software updates or ad hoc integration of new components. The effects of these changes are often difficult to estimate, especially in distributed automation systems. This mainly poses a challenge on production line operators, who are required to validate their automation systems after functionality changes have been executed. The goal of this contribution is to assist production line operators in the validation process of their automation systems after software changes. Formal verification methods can support the operators, due to its fully automated execution. However, the creation process of the behavior models needed for the formal verification is complex and error-prone. This is why formal verification is usually not used. Hence, a model-based technique is presented to automate this creation process. By means of this, the subsystem affected by the software change is automatically identified and subsequently a suitable input to a model-based verification tool is generated. The concept is based on the generation of a system model by composing the Petri net models of components within the automation system. In order to identify affected components, an impact analysis is performed, starting from the component in which a modification occurred. Followingly, a tailored subsystem is composed using the component models necessary for verification. This subsystem is applied to verify the system requirements for the affected components. To evaluate the applicability of the concept in the field of industrial automation, a distributed automation system was implemented. A service-oriented, OPC-UA-based, control network is thereby used to implement a technical process. Furthermore, a configuration interface enables change of the components at runtime. This emulates over-the-air updates and ad hoc networking. The concept is implemented with the demonstrator “TestIAS.” This test device detects software changes within the automation system and verifies them automatically according to the model-based approach presented. An empirical evaluation was performed with ten different reconfiguration scenarios showing functional changes. In addition, based on the time measurements of the time saving due to the impact analysis, the efficiency enhancement is substantiated.

Zusammenfassung Bei der Entwicklung automatisierter Systeme im Bereich der Automatisierungstechnik haben Ingenieure viele Aufgaben oft unter Zeitdruck zu bearbeiten, unter anderem Simulationen. Um Ingenieure bei diesen aufwändigen Simulationsaufgaben zu unterstützen, wird ein Framework vorgestellt, das Simulationen basierend auf strukturiertem Wissen parallel und dezentral koordiniert und durchführt. Hierbei können verschiedene Lösungsansätze eines Problems automatisiert simuliert und miteinander verglichen werden. Komplexe Problemstellungen, d. h. umfangreiche und häufig aus mehreren voneinander abhängigen Teilen bestehende Aufgaben, werden hierzu in Teilprobleme zerlegt und ihre Lösungsansätze separat mit dem jeweils geeignetsten Softwaretool bearbeitet. Zur flexiblen Koordination der dezentralen Simulationen werden kooperierende Softwareagenten eingesetzt. Diese autonomen Einheiten kommunizieren miteinander, um die parallelen Tätigkeiten während eines Simulationsprojekts zu steuern. Evaluiert wird das vorgestellte Konzept anhand der Anwendungsgebiete des Regelungsentwurfs und der multiphysikalischen Simulation. Hierzu wurden entsprechende prototypische Agentensysteme mithilfe des entwickelten Frameworks realisiert. Zusätzlich zum Framework zur parallelen Simulation wird auch ein Konzept zur Ergänzung des Agentensystems um eine lernende Case-Based-Reasoning-Komponente vorgestellt. Durch die Ergänzung des Agentensystems um Lernfähigkeit, konnte die Performance der Simulationen weiter gesteigert werden. Aufgrund der parallel durchgeführten Simulation verschiedener Ansätze mit teils stark variierenden Rechenzeiten, stehen Ergebnisse häufig bereits früher zu Verfügung. Auch die Qualität der Simulationsergebnisse kann durch die Untersuchung verschiedener Ansätze mit dem Agentensystem verbessert werden.

Cyber-Physical Systems, characterized by networking capabilities and digital representations, offer many promising potentials for industrial automation. In an attempt to further enrich the system's digital representation by incorporating interdisciplinary models and considering a continuous and synchronized representation of it within the cyber layer, the concept of the Digital Twin emerged, enabling system monitoring, virtual commissioning, failure diagnosis and simulations by managing the Cyber-Physical Systems data along its lifecycle. To add further intelligence into the Digital Twin, the architecture of the intelligent Digital Twin was proposed. Nevertheless, managing and relating the complex and dynamic digital models as well as the heterogeneous data of the intelligent Digital Twin present open challenges. Due to their inherent extensibility and adaptability as well as their semantic expressiveness, Knowledge Graphs are a suitable concept to overcome these challenges and enable reasoning to gain new insights. Prominent applications of Knowledge Graphs are recommendation systems and exploratory search within the semantic web. However, there seems to be a lacking yet potential applicability for Knowledge Graphs in the industrial domain. Therefore, this contribution proposes a Knowledge Graph enhanced architecture of the intelligent Digital Twin, offering capabilities, which are internal linking and referencing, knowledge completion, error detection, collective reasoning and semantic querying. Based on the proposed concept, potential application fields for Knowledge Graph enhanced intelligent Digital Twin are addressed.

The early and robust detection of anomalies occurring in discrete manufacturing processes allows operators to prevent harm, e.g. defects in production machinery or products. While current approaches for data-driven anomaly detection provide good results on the exact processes they were trained on, they often lack the ability to flexibly adapt to changes, e.g. in products. Continual learning promises such flexibility, allowing for an automatic adaption of previously learnt knowledge to new tasks. Therefore, this article discusses different continual learning approaches from the group of regularization strategies, which are implemented, evaluated and compared based on a real industrial metal forming dataset., Comment: 6 pages, 5 figures, 3 tables, submitted to the CIRP Conference on Manufacturing Systems 2021

Deep learning promises performant anomaly detection on time-variant datasets, but greatly suffers from low availability of suitable training datasets and frequently changing tasks. Deep transfer learning offers mitigation by letting algorithms built upon previous knowledge from different tasks or locations. In this article, a modular deep learning algorithm for anomaly detection on time series datasets is presented that allows for an easy integration of such transfer learning capabilities. It is thoroughly tested on a dataset from a discrete manufacturing process in order to prove its fundamental adequacy towards deep industrial transfer learning - the transfer of knowledge in industrial applications' special environment., Comment: 8 pages, 5 figures, 5 tables. Accepted for publication at IEEE ETFA 2021

Ensuring high availability despite the growing frequency of changes in production requirements leads to an increased reconfiguration demand in the domain of industrial automation systems, which will be dominated by Cyber-Physical Production Systems (CPPS) in the future. Therefore, a concept, covering a methodology containing four steps, is utilized to answer the research question how to enhance CPPS with a self-organized reconfiguration management. This contribution focuses on the first two steps of this concept: the identification of reconfiguration demand and the generation of alternative configurations. A condensed presentation of the related work reveals that an interface-oriented formalized process description depicts an appropriate conceptual basis. Building upon this, the presented concept contains a capability model of the CPPS and the reasoning to determine a potential reconfiguration demand, as well as a procedure for the generation of alternative configurations. To evaluate the concept, an agent-based implementation is given, which uses an OPC-UA controlled simulated modular production system as a substitute CPPS in discrete manufacturing.

Increased flexibility and improved resilience in production and manufacturing processes are goals that are becoming more and more important in the context of Industry 4.0 and from the experience of the Covid-19 pandemic. At the same time, efficient operation of production must be guaranteed to achieve economic as well as ecological objectives. Intelligent assistance systems follow the idea to support stakeholders of production systems in their decisions and can thus be useful applications for helping to master the various challenges and to meet these goals. In this paper, we describe functional components of these decision support systems: data provision and data extraction, knowledge base, simulation models, model execution and analytics, and application and user interaction. We show the underlying technologies and illustrate why these assistant systems are valuable for several stakeholders.

Nowadays, formal methods are used in various areas for the verification of programs or for code generation from models in order to increase the quality of software and to reduce costs. However, there are still fields in which formal methods have not been widely adopted, despite the large set of possible benefits offered. This is the case for the area of programmable logic controllers (PLC). This article aims to evaluate the potential of formal methods in the context of PLC development. For this purpose, the general concepts of formal methods are first introduced and then transferred to the PLC area, resulting in an engineering-oriented description of the technology that is based on common concepts from PLC development. Based on this description, PLC professionals with varying degrees of experience were interviewed for their perspective on the topic and to identify possible use cases within the PLC domain. The survey results indicate the technology's high potential in the PLC area, either as a tool to directly support the developer or as a key element within a model-based systems engineering toolchain. The evaluation of the survey results is performed with the aid of a demo application that communicates with the Totally Integrated Automation Portal from Siemens and generates programs via Fastsynth, a model-based open source code generator. Benchmarks based on an industry-related PLC project show satisfactory synthesis times and a successful integration into the workflow of a PLC developer., Comment: 8 pages, 6 figures, 1 table. Accepted for publication at IEEE INDIN 2021

Automated and connected driving up to autonomous vehicles is increasingly being deployed. But the public distrust in their reliability is growing and thus concerns on deployment. The underlying algorithms are not transparent, fast changing and easy to manipulate [1,3,8].

In response to an aging society, the development and application of medical assistance systems is increasing and becoming an integral part of various daily life activities. To enable effective assistance, designing intuitive and elderly-appropriate user interfaces is necessary and represents a challenge due to the lack of standardized design processes. A possible approach for the design is to apply the usability engineering process based on the IEC 62366 standard for medical devices. In this contribution, the design process of a user interface for an automated pill dispenser is shown based on applying the standard, a literature review and a user evaluation.

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.

Recently, ontologies and semantic data technologies have increasingly come back into the focus of research due to the emerging use of knowledge graphs. However, even though the modeling and simulation community has recognized the potential of using this technology for the modeling process, for example for automatic model generation, adaptation or to represent simulation expert knowledge, a general and reusable approach for the aforementioned purposes is still missing. Therefore, in this paper a state of the art review for using knowledge representation during modeling and simulation processes of complex technical systems is conducted, such as factories or process plants with specific focus on the production and logistic domain. Based on that, requirements and benefits of knowledge graphs in this specific domain are evaluated.

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.

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.

Smart Manufacturing adopts an extensive amount of enabling technologies. Progress in ICT constantly drives innovations. Ubiquitous connectivity enabled by IoT technologies, increasing compute capacity and efficiency, and the subsequent push of digitalization in industry enabled new data-driven applications and the re-emergence of AI-technologies over the last decade. At the same time, the deficiencies of current infrastructures and system architectures are revealed when companies fail to adopt data-driven technologies extensively. This paper discusses how modern IT-architectures and infrastructure for cyber-physical production systems can enable their inherent self-x capabilities to pave the road towards higher levels of autonomy facilitated by data-driven technologies.

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.

Modern production systems often form Internet-of-Things-systems (IoT). Because of the flexibility those systems are dynamic, meaning the entering of components during runtime, and heterogeneous. For the simulation of such systems, those challenges of dynamic and heterogeneity have to be met by a dynamic co-simulation. An important aspect of a co-simulation is the synchronization of the used simulations. In this contribution, challenges of synchronizing a co-simulation of IoT-systems are introduced and existing co-simulation synchronization concepts examined with regard to their usability for simulating IoT-systems. Afterwards a synchronization concept is presented, which can be used in the presented agent-based co-simulation concept.

Process anomalies and unexpected failures of manufacturing systems are problems that cause a decreased quality of process and product. Current data analytics approaches show decent results concerning the optimization of single processes but lack in extensibility to plants with high-dimensional data spaces. This paper presents and compares two data-driven self-learning approaches that are used to detect anomalies within large amounts of machine and process data. Models of the machine behavior are generated to capture complex interdependencies and to extract features that represent anomalies. The approaches are tested and evaluated on the basis of real industrial data from metal forming processes.

The increasing change of production leads to differences between the current shop floor and the state of planning. This difference causes significant challenges for production planners while integrating new products into existing production systems. To tackle this issue, this paper presents a concept for the automated creation of a digital twin of a body-in-white production system based on current resources, products as well as process information from the cyber-physical system. The paper focuses on the different data sources and information in cyber-physical systems necessary for integration planning. Furthermore, major parts of the concept are evaluated in a real body-in-white production system. The resulting digital twin enables faster product integration and Industry 4.0 concepts.

Automated manufacturing machines in the discrete manufacturing domain frequently face changes in requirements, such as volatile customer demands or changes in product variants. Due to this, machines need to become more flexible to cope with these changing conditions. Therefore, manufacturing machines have to undergo adaptation processes during their operational phase. The adaptation processes might include mechanical, electrical, and software changes. In industrial practice, experts individually perform these adaptation processes without methodological support, which is time-consuming and highly error-prone. This article proposes a systematic approach for supporting the different phases of the adaptation process. The producibility check of a production request based on a suitable skill model of the system is addressed as well as the automatic generation of adaptation options. Furthermore, the article provides concepts for analyzing the impact, effort and benefit of the generated adaptation options. Additionally, a multi agent architecture is presented for the implementation of the proposed adaptation approaches. The entire assistance concept was applied to a lab-size production machine to validate the applicability of the approach.

Tracking each workpiece provides two major advantages in forging technology. First, the matching of physical workpiece with the monitored process information facilitates root-cause analysis for product quality. Second, the following process steps can be adapted according to the incoming workpiece properties to improve the robustness of hot forging process chain. The paper presents a general tracking methodology and tagging experiments on aluminium and steel forgings for harsh drop-forging technology. Furthermore, a framework for streaming and processing large amounts of real-time data as well as a multidimensional approach to model and analyse the workpiece information for individual and batch-tracking are presented.

Zusammenfassung Änderungen der Funktionalität von Automatisierungssystemen werden zunehmend an der Software durchgeführt. Insbesondere bei verteilten Automatisierungssystemen lassen sich die Auswirkungen von Software-Änderungen oftmals nur schwer abschätzen. Dies stellt insbesondere Anlagenbetreiber vor große Herausforderungen bei der Absicherung von Funktions-Änderungen in der Betriebsphase. Dieser Beitrag beschreibt einen modellbasierten Ansatz, mit dem Auswirkungen von Software-Änderungen erkannt werden können und das betroffene Teilsystem automatisiert über modellbasierte Verifikationsverfahren abgesichert werden kann. Das präsentierte Konzept beruht auf der Komposition eines Systemmodells aus diskreten Verhaltensmodellen der Komponenten des Automatisierungssystems. Abschließend wird das Konzept anhand unterschiedlicher Änderungsszenarien evaluiert.

Based on autonomous software agents capable of calculating individual numerical field problems, a distributed method for solving transient field problems is presented. The software agents are running on distributed resources connected via a network and represent a dynamic calculation environment. Communication and data exchange between multiple agents enables their collaboration and allows decisions based on distributed overall knowledge. As unique characteristics, no central unit influences the solution process at any time. The presented simulation example and its evaluated calculation process proves the method to benefit from redundant resources.