1 - 10 of 50
-
PublicationTowards live decision-making for service-based production: Integrated process planning and scheduling with Digital Twins and Deep-Q-Learning( 2023)Production flow is becoming increasingly complex since manufacturers must react quickly to changing markets demands and diverse customer requirements. In order to ensure production efficiency, it is essential to have an adequate scheduling system capable of managing diverse process flows and handling unforseen changes. In this paper, we present an approach leveraging Digital Twins (DTs) and Deep-Q-Learning to perform integrated process planning and scheduling for service-based production. DTs of production assets provide live information about their physical entities for our approach to perform live decision-making based on the current operation conditions. We use Deep-Q-Learning which is a deep Reinforcement Learning (RL) algorithm to perform integrated process planning and scheduling. We present two RL-designs that deal with different situations of live decision-making. We have evaluated the learning efficiency and scalability of the RL-designs on a virtual aluminum cold rolling mill developed by the SMS Group,1 in the context of the BaSys 4.2 project.2 The results show that the first RL-design is suitable for deriving schedules for individualized production with small lots where process plans must be re-calculated frequently, while the second RL-design is optimal for production with large job quantities where jobs arrive continuously.
-
PublicationManufacturing-X: Die Branche der Fabrikausrüster( 2023)Die deutsche Ausrüsterindustrie beliefert weltweit Fabriken mit Produktionslinien, Maschinen, Komponenten, Automatisierungstechnik und produktionsnaher Software. Über viele Jahre waren die Auftragsbücher voll und die Entwicklungs- und Produktionskapazitäten ausgelastet. Die Frage ist: wird das auch in der Zukunft so sein und: wie können die deutschen Ausrüster ihre Wettbewerbsfähigkeit erhalten oder sogar noch verbessern? Welche Rolle spielt dabei die Digitalisierung? Viele Ausrüster haben in den Jahren seit dem Start von „Industrie 4.0“ zaghafte Schritte in die Digitalisierung gemacht, mehr oder weniger erfolgreich; viele proprietäre Lösungen blieben weit hinter den Erwartungen zurück. Entsprechend zurückhaltend sind die Unternehmen nun bei den nächsten Schritten. Damit bleiben sie aber in Bezug auf die Digitalisierung und den mit ihr verbundenen Möglichkeiten für zusätzliche datenbasierte Dienstleistungen rund um Maschinen und Komponenten zurück und verpassen möglicherweise wichtige Innovationschancen. Qualitativ hochwertige Maschinen, Anlagen und Komponenten zu entwickeln, herzustellen und zu liefern wird in Zukunft für den Geschäftserfolg der deutschen Ausrüster nicht mehr ausreichen – sie müssen dringend in datenbasierte Dienste investieren, denn die Kunden von morgen werden diese erwarten. Um die Kräfte bei der Software- und Diensteentwicklung zu bündeln, schlagen die Autoren mehrerer Fraunhofer-Institute die Beteiligung der Ausrüster an industriellen Datenräumen vor: dabei teilen sich die beteiligten Unternehmen die Aufwände zur Entwicklung der ‚Basisdienste‘ und konzentrieren sich vielmehr darauf, Business-Applikationen mit tatsächlichem Kundennutzen zu schaffen. Gleichzeitig gewährleisten Datenräume die Datensouveränität, d.h. die Kontrolle der jeweiligen Dateneigentümer über Daten und deren Nutzung, die sie im Datenraum zur Verfügung stellen, bleibt erhalten. In der hier vorgelegten Studie beschreiben die Autoren zunächst die Branche der Fabrikausrüster und deren Teilbranchen. Basierend auf einer Auswertung aktueller Studien zu Innovationskraft und Digitalisierung der Ausrüsterbranche arbeiten sie heraus, dass es für die Fabrikausrüster höchste Zeit ist, ihr Produktportfolio um digitale Lösungen zu erweitern. Nur so können die Unternehmen den zukünftigen Herausforderungen Stand halten, z.B. Reduzierung der Abhängigkeiten von wenigen Vorleistungslieferanten, verbesserte Resilienz von Lieferketten, Anforderungen an Nachhaltigkeit und Kreislaufwirtschaft oder dem heute schon spürbaren Fachkräftemangel. Aufbauend auf der Faktenlage und den daraus resultierenden Trends formulieren die Autoren dann thesenartig relevante Entwicklungspfade für die Ausrüsterbranche mit konkreten Vorschlägen bis hin zu neuen Möglichkeiten, Ergebnisse aus F&E-Projekten durch gezielten Einsatz digitalen Wissenstransfers für ausrüstende Unternehmen zu nutzen. Mit der hier vorgelegten Studie stellt der Leitmarkt ‚Anlagenund Maschinenbau‘ der Fraunhofer-Gesellschaft unter Beweis, dass die Fraunhofer Institute über ein umfangreiches Angebot für Fabrikausrüster verfügen, um den Weg in die digitale Zukunft der Branche zielgerichtet, innovativ und investitionssicher zu beschreiten.
-
PublicationUser experience key performance indicators for industrial IoT systems: A multivocal literature reviewIn software systems, user experience (UX) is a quality that provides value to its intended users. Therefore, we consider it critical to manage UX and its link to business value quantitatively. Key performance indicators (KPIs) have been widely adopted for objectively measuring factors that influence business success, including measuring UX characteristics and their business contribution in the context of software systems in general. Yet, measuring UX in the context of complex Internet of Things (IoT) systems, especially Industrial IoT (IIoT) systems, remains a challenge. This paper presents a multivocal literature review (MLR) of the UX-KPIs proposed in the context of (I)IoT systems, along with factors influencing UX and challenges of quantifying UX. We investigate the status quo and derive recommendations for measuring the UX of (I)IoT systems. Our analysis of 64 publications shows that UX has so far received relatively little attention in the context of (I)IoT. Although we identified 605 KPIs, 78 influencing factors, and 119 challenges, most of the UX features discussed were defined in a broader context of software systems, i.e., they were less specific to IoT, but rather focused on universal system quality characteristics such as functional suitability, performance efficiency, usability, and reliability. Finally, no generally accepted approach for measuring UX in (I)IoT systems and how these contribute to the overall business value has been proposed yet. We also found little evidence that improving UX or achieving a good UX currently plays an explicit role in the design and development of IoT systems.
-
PublicationTowards the Concept of Trust Assurance Case( 2023)Trust is a fundamental aspect in enabling a smooth adoption of robotic technical innovations in our societies. While Artificial Intelligence (AI) is capable to uplift digital contributions to our societies while protecting environmental resources, its ethical and technical trust dimensions bring significant challenges for a sustainable evolution of robotic systems. Inspired by the safety assurance case, in this paper we introduce the concept of trust assurance case together with the implementation of its ethical and technical principles directed towards assuring a trustworthy sustainable evolution of AI-enabled robotic systems.
-
PublicationVerwaltungsschalenbasierte Datenräume. Möglichkeiten, Herausforderungen und Lösungsansätze auf dem Weg zu datengetrieben resilienten Wertschöpfungsnetzwerken( 2023)Der Austausch von Unternehmensdaten ist eine wichtige Grundlage, um fragile Lieferketten in resiliente und nachhaltige Wertschöpfungsnetzwerke zu transformieren. Im Rahmen dieser Transformation werden die Verfügbarkeit von Daten und die Fähigkeit, diese zu nutzen, die lukrativsten Geschäftsmodelle der Zukunft prägen. Intelligente Systeme können die Daten nutzen, um autonome Entscheidungen bezüglich der Wandlung von Produktionssystemen zu treffen oder Empfehlungen zu geben. Damit diese Transformation gelingt, werden für die notwendigen Entwicklungen verwaltungsschalenbasierte Datenräume benötigt.
-
PublicationFuture Advances in Reference Architectures( 2023)The research area of reference architecture will continuously evolve, offering means to increasingly consolidate reference architectures as one of the most relevant reusable artifacts of well-consolidated architectural knowledge and experience. Moreover, existing reference architectures must also continually evolve according to the evolving nature of the different domains where they contribute. New classes of innovative systems with particular characteristics and new technologies (some of which could drastically change the structure of software architectures) will undoubtedly impact the design and evolution of reference architectures. This chapter discusses the main research directions to be taken by reference architectures that will also require a good alignment of efforts from the academic community and industry.
-
PublicationReference Architectures for Industry 4.0( 2023)The adoption of Industry 4.0 requires reconsideration of plant software architecture due to the strict layers of the automation pyramid hindering the implementation of central Industry 4.0 use cases like the changeable plant. Thus, plant software architecture has to change and, for example, adopt concepts such as the digital twin. In this chapter, we provide an overview of current challenges of the status quo of software architecture in Industry 4.0 and describe how they are solved by reference architectures. Furthermore, we provide guidance on how to classify use cases and reference architectures of Industry 4.0 according to various reference architecture models.
-
PublicationSEC-Learn: Sensor Edge Cloud for Federated Learning( 2022-04-27)
-
PublicationContinuous engineering for Industry 4.0 architectures and systems( 2022)Traditionally, the quality of a software or system architecture has been evaluated in the early stages of the development process using architecture quality evaluation methods. Emergent approaches like Industry 4.0 require continuous monitoring of both run-time and development-time quality properties, in contrast to traditional systems where quality is evaluated at specific milestones using techniques such as project reviews. Considering the dynamics and minimum down-time imposed by the industrial production domain, it must also be ensured that Industry 4.0 system evaluations are continuously performed with high confidence and with as much automation as possible, using simulations, for instance. In this regard, there is a need to develop new methods for continuously monitoring and evaluating the quality properties of software-based systems for Industry 4.0, which must be supported by automated quality evaluation techniques. In this research we analyze traditional architecture evaluation methods and Industry 4.0 scenarios, and propose an approach based on Digital Twins and simulations to continuously evaluate runtime quality aspects of the architecture and systems of industrial production plants. The evaluation is based on the instantiation of our approach for a concrete demand of an automation plant in the automotive domain.
-
PublicationArchitecture Blueprints to Enable Scalable Vertical Integration of Assets with Digital Twins( 2022)Many Industry 4.0 use cases require the integration of live data, e.g., from sensors and devices. However, the large number of legacy fieldbus protocols and proprietary data formats turns this integration into an effort-consuming task. As the number of digital twins in a factory increases rapidly, data source integration has to scale well. Until now, little guidance is available on how to implement this integration in a scalable and reusable manner for Industry 4.0. To close this gap, we define five architecture blueprints based on our experience in various Industry 4.0 projects. These blueprints detail various integration scenarios differentiated by key attributes like frequency of data consumption and data production. In these architecture blueprints, two core components, the Updater and the Delegator, are identified. By providing and evaluating our open-source implementation of these two components, we show the feasibility of the defined blueprints. Utilizing the provided open-source components and the defined architecture blueprints will benefit practitioners as well as researchers when it comes to data integration with digital twins.
- 1 (current)
- 2
- 3
- 4
- 5