Auflistung nach:
Auflistung Modellierung 2022 - Workshopband nach Erscheinungsdatum
1 - 10 von 35
Treffer pro Seite
Sortieroptionen
- KonferenzbeitragModeling Digital Shadows in Manufacturing by Using Process Mining(Modellierung 2022 Satellite Events, 2022) Brockhoff, Tobias; Uysal, Merih Seran; van der Aalst, WilFriction in shopfloor-level manufacturing processes often occurs at the intersection of different subprocesses (e. g., joining sub-parts). Therefore, considering the Digital Shadows (DSs) of individual materials/sub-parts is not sufficient when analyzing the processes. To this end, holistic views on shopfloor-level processes that integrate multiple DSs are needed. In this work, we discuss how material-centric DSs supported by discrete assembly events can be integrated using techniques from process mining. In particular, we propose to utilize DSs that contain additional structural information to overcome the main challenges of concurrency and the presence of many different objects.
- KonferenzbeitragMachine trainable software models towards a cognitive thinking AI with the natural language processing platform NLX(Modellierung 2022 Satellite Events, 2022) Schaller, FelixSince the last decade, machine learning, especially with artificial neural networks, has triggered a new quantum leap in computer science. Despite the considerable achievements, these applications still lack a general purpose approach for artificial intelligence (AI). The main reason is the absence of the ability for cognitive reflection or self-awareness. They are mainly highly specialized trained patterns that can solve intricate problems but cannot describe themselves. I would like to contrast this with a new method of trainable software models that shall be capable for self-awareness. Implemented in the project Natural Language Platform NLX it shall be demonstrated that self-aware AI is key for human-like cognitive tasks. The hypothesis claims that to reach this goal, machines require to describe its system context semantically by a formal model. Neuronal networks are good at specific tasks, but the trained patterns cannot derive a reasoning for the trained solution. Only that it satisfies its intended functionality - but not why. Creating formal models instead of patterns has turned out, that the formal nature of natural language is the best to reach that goal of a self-aware AI. Certainly there are other AI’s that do natural language processing with neuronal networks. But most of the models try to resolve the content with too rigid constraints and with little attention to the context. For this project context plays a key role to resolve the meaning of natural language. If the context is resolved correctly, such AI can be used for general purpose tasks resolving anything imaginable.
- KonferenzbeitragWorkshop ModSim4VIBN(Modellierung 2022 Satellite Events, 2022) Schmidt-Vollus, Ronald; Handschuh, Eric; Gödrich, Axel; Hölzer, ChristianDer Workshop stellt das Thema Virtuelle Inbetriebnahme (VIBN) sowie Modellbindung und Simulation im Engineering von automatisierten Maschinen und Anlagen vor. Im Mittelpunkt stehen die Meinungen und Thesen des VDI/VDE-GMA FA 6.11 Virtuelle Inbetriebnahme.
- KonferenzbeitragWorkshop Modeling in (and for) Production(Modellierung 2022 Satellite Events, 2022) Michael, Judith; Koren, IstvánThe production domain is permeated by heterogeneous data sources, a variety of IT systems, and complex industrial use cases - aspects that offer an exciting field for research. The MoPro Workshop aims to be a platform for researchers and practitioners within the production domain to exchange their modeling techniques, interesting use cases, and challenges. We are interested in the use of models for development, production, and usage cycles, as well as model-based and model-driven approaches that span these domains across disciplinary boundaries.
- KonferenzbeitragChallenges in Multi-View Model Consistency Management for Systems Engineering(Modellierung 2022 Satellite Events, 2022) Bergemann, SebastianA way to handle the complexity of cyber-physical systems is model-based systems engineering (MBSE) with multiple viewpoints. These viewpoints satisfy different concerns, but they likely have information dependencies and overlaps among each other. Inconsistencies can be introduced whenever there are changes in only some of the views without consistent synchronization in other dependent views. In this paper, we motivate why consistency management is important in multi-view MBSE and define requirements for it. By analyzing the State of the Art, we identify limitations in (multi-view) consistency management approaches, especially for inconsistency detection. Besides general performance issues, we notice primarily that most approaches are limited to or at least tested on only very specific views and tools with homogeneous models and few specific predefined consistency rules. Furthermore, in most approaches we cannot find solutions regarding subsequent updates of consistency rules by the user, allowance of tolerating inconsistency, and handling confidentiality. These literature gaps pose open research challenges for making multi-view consistency management more applicable in the industry.
- KonferenzbeitragFeatures of AI Solutions and their Use in AI Context Modeling(Modellierung 2022 Satellite Events, 2022) Rittelmeyer, Jack Daniel; Sandkuhl, KurtDespite the implementation of many new artificial intelligence (AI)-based solutions in research and practice every year, companies still encounter problems while introducing AI solutions. One reason for that, from our own experience, are significant problems with understanding the concepts of AI. To cope with this problem, we aimed for developing a morphological box for AI solutions. The developed morphological box, its features and their values are based on four own industrial cases of AI solutions covering different application domains. We previously presented an enterprise architecture-based AI context model to help to better understand the context of an AI solution in a company and thereby minimize the risks of an implementation. We also analyzed that the morphological box supports the AI introduction process by improving and enhancing the three steps of the AI context model, which lead to more complete requirements for AI solutions.
- KonferenzbeitragModelling Pig Rearing as Digital Shadow(Modellierung 2022 Satellite Events, 2022) Zimpel, TobiasPig rearing and animal welfare are increasingly in the interest of society. To enhance animal welfare using data-driven analyses, modeling the pig rearing process is essential to create corresponding data sets. Pig rearing is a complex process for increasing pigs’ weight (from approx. five to 25 kilograms) involving various actors (e. g. farmers, veterinarians) to provide goods (e.g., food, water) and services (e.g., medical care). Thereby, pigs live in pens equipped with condition-measuring sensors, like the pen's temperature or pigs' activity. Manual measurements (e.g., weights) are also conducted, resulting in various data sources. For analyzing these data, measured in different contexts, a digital shadow appears as an approach for modeling these data traces. Therefore, we report on a digital shadow for pig rearing, including the assets pen and pig, sensor sources, data traces (e.g., pens’ temperature), and the purpose of analyzing causes of necrosis (dead tissue) with association rules.
- KonferenzbeitragWorkshop zur Modellierung in der Hochschullehre(Modellierung 2022 Satellite Events, 2022) Ullrich, Meike; Fettke, Peter; Pfeiffer, Peter; Schüler, Selina; Striewe, MichaelDer Workshop befasst sich mit dem Thema Modellierung – nicht wie üblich aus der Perspektive der Modellierung zum Einsatz in Industrie und Unternehmen, sondern aus dem Blickwinkel der Hochschullehre. Somit soll die Frage nach passenden Lernzielen, Lerninhalten und innovativen Unterrichtsmethoden für die Modellierung im Vordergrund stehen, ebenso wie die Frage nach geeigneten Prüfungsformaten und Bewertungsverfahren für die von Studierenden erstellten Modelle.
- KonferenzbeitragDigital Shadows for Cross-Organizational Data Exchange(Modellierung 2022 Satellite Events, 2022) Koren, IstvánProduction settings typically involve heterogeneous systems that create a challenging environment for collecting data in light of digital transformation. Once overcoming these difficulties, data-driven opportunities for manufacturing companies include increasing efficiency and productivity, reducing costs, and improving quality control. On the shop floor, digital shadows and digital twins are elements of these modernization strategies, e.g., to leverage machine learning methods for decision support. Recently, some approaches have transferred these concepts to the organizational level, like digital twins of organizations. In this paper, we envision how we can use data collections from the shop floor, captured as digital shadows, to share data across organizational boundaries to create new business models and ultimately enter new markets. We discuss the necessary enhancements of our conceptual model for digital shadows presented in previous work. We are convinced that digital shadows can help companies embrace innovative, data-driven business models to face challenges like sustainability.
- KonferenzbeitragModellierung in der Informatik-Hochschullehre (ein Trauerspiel)(Modellierung 2022 Satellite Events, 2022) Reisig, WolfgangModellierung in der derzeitigen Informatik-Lehre kann man nicht verbessern. Man muss sie neu aufsetzen, zusammen mit der Gestaltung einer Wissenschaft der Informatik. Dabei müssen auch die Notationen entsprechend überarbeitet werden. Wir haben kein Erkenntnis-Problem, sondern ein Akzeptanz-Problem: an sich ahnen viele Kollegen, dass man Konzepte, Ideen, Algorithmen besser mit passenden Notationen unterrichten sollte, also mit passenden Modellen. Aber üblich sind nun mal Programm-Notationen. Außerdem: Der Informatik geht es zu gut: Mit Hacken kann man herrlich Geld verdienen. Warum soll man es da ordentlich machen (also modellieren)? „Do kannsch au em Ochs ins Horn pfetze!“