Refine
Document Type
- Conference Proceeding (12)
- Article (4)
- Book (1)
Institute
- Forschungszentrum Digital Factory Vorarlberg (17) (remove)
Keywords
- photonics (3)
- Cloud manufacturing (2)
- Ontologies (2)
- 2x2 optical switch (1)
- 3D 1×4 Multimode Interference Splitter (1)
- 3D MMI splitter (1)
- 3D Y-branch splitter (1)
- AWG (1)
- Articifial intelligence (1)
- Auction-based production planning (1)
Concept of probabilistic modeling for real-time prediction of product quality and design automation
(2018)
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.
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.
With the digitalisation, and the increased connectivity between manufacturing systems emerging in this context, manufacturing is shifting towards decentralised, distributed concepts. Still, for manufacturing scenarios manual input or augmentation of data is required at system boundaries. Especially in distributed manufacturing environments, like Cloud Manufacturing (CMfg) systems, constant changes to the available manufacturing resources and products pose challenges for establishing connections between them. We propose a feature-oriented representation of concepts, especially from the manufacturing domain, which serves as the basis for (semi-) automatically linking, e.g., manufacturing resources and products. This linking methodologies, as well as knowledge inferred using it, is then used to support distributed manufacturing, especially in CMfg environments, and enhance product development. The concepts and methodologies are to be evaluated in a real world learning factory.
In this paper, the design of three-dimensional configuration of Y-branch splitter is compared with Multimode Interference splitter. Both splitters use the IP-Dip polymer as a standard material for 3D laser lithography. The optical properties of the splitters for both approaches are discussed and compared.
In this work, we investigated the influence of different etch depths of the rib waveguides on the performance of SiN-based AWGs. For this purpose, an 8-channel 100 GHz AWG was designed for a center wavelength of 850 nm. The design parameters entered were calculated using the AWG-Parameters tool. The simulations were performed with a commercial photonic tool PHASAR from Optiwave. The simulated performance was evaluated using the AWG-Analyzer tool. For the AWG design, we used three identical rib waveguides with different etch depths to simulate possible etch imperfection. The simulations show the wavelength shift and degradation of the AWG performance.