Refine
Document Type
- Conference Proceeding (12)
- Article (3)
- Book (1)
Institute
- Forschungszentrum Digital Factory Vorarlberg (16) (remove)
Is part of the Bibliography
- yes (16) (remove)
Keywords
- photonics (3)
- Cloud manufacturing (2)
- Ontologies (2)
- 2x2 optical switch (1)
- 3D 1×4 Multimode Interference Splitter (1)
- AWG (1)
- Articifial intelligence (1)
- Auction-based production planning (1)
- Cloud-based research (1)
- Data analytics (1)
The Digital Factory Vorarlberg is the youngest Research Center of Vorarlberg University of Applied Sciences. In the lab of the research center a research and learning factory has been established for educating students and employees of industrial partners. Showcases and best practice scenarios for various topics of digitalization in the manufacturing industry are demonstrated. In addition, novel methods and technologies for digital production, cloud-based manufacturing, data analytics, IT- and OT-security or digital twins are being developed. The factory comprises only a minimum core of logistics and fabrication processes to guarantee manageability within an academic setup. As a product, fidget spinners are being fabricated. A webshop allows customers to individually design their products and directly place orders in the factory. A centralized SCADA-System is the core data hub for the factory. Various data analytic tools and methods and a novel database for IoT-applications are connected to the SCADA-System. As an alternative to on premise manufacturing, orders can be pushed into a cloud-based manufacturing platform, which has been developed at the Digital Factory. A broker system allows fabrication in distributed facilities and offers various optimization services. Concepts, such as outsourcing product configuration to customers or new types of engineering services in cloud-based manufacturing can be explored and demonstrated. In this paper, we present the basic concept of the Digital Factory Vorarlberg, as well as some of the newly developed topics.
In dieser Arbeit wird Supervised Learning verwendet, um die Zuverlässigkeit von Schweißverbindungen zu evaluieren.
Um die Schweißqualität zu bestimmen, wurden End of Life Tests durchgeführt. Für die statistische Auswertung und Vorhersage der zu erwartenden Lebensdauer, wurden die Daten basierend auf einer logarithmischen Normalverteilung und mit einer multivariablen linearen Regression modelliert. Um die signifikanten Einflussfaktoren zu identifizieren, wurde eine schrittweise Regression genutzt. Die Ergebnisse zeigen, dass das entwickelte Modell die Zuverlässigkeit und Lebensdauer der Schweißverbindung akkurat abbildet und präzise Vorhersagen liefern kann.