Home | english  | Impressum | Datenschutz | Sitemap | KIT

M.Sc. Raphael Wagner

Akad. Mitarbeiter
Bereich: Produktionssysteme
Sprechstunden: Nach Vereinbarung
Raum: Geb. 50.36, F 003
Tel.: +49 1523 9502627
Raphael WagnerMeg6∂kit edu

76131 Karlsruhe
Kaiserstraße 12


M.Sc. Raphael Wagner

Forschungs- und Arbeitsgebiete:

  • Qualitätssicherung im Bereich Mikroproduktion
  • Qualitäts-Regelung in der Produktion zur wirtschaftlichen Herstellung von hochpräzisen Produkten
  • Data Analytics zur Prozessoptimierung
  • Entwicklung von Industrie 4.0 Strategien

 

Allgemeine Aufgaben:

  • Vorlesungsbetreuung „Qualitätsmanagement“ an der Hector School
  • Lernfabrik Skalierbare Automatisierung
  • Vorlesungskoordination „Arbeitstechniken im Maschinenbau“ an der Carl Benz School
  • Vorlesungskoordination „Integrative Strategien und deren Umsetzung in der Produktion und Entwicklung von Sportwagen (ISS)“

 

Projekte:

  • AiF Quo Vadis - Qualitätssicherung für Mikro-Zahnränder
  • BMBF ProIQ - prozessübergreifende Qualitätsregelkreisein der Produktion

 

Versuchsstände:

 

Dissertation: Qualitätsregelung mittels Funktionsmodellen zur Erfüllung hoher Qualitätsanforderungen

 

Lebenslauf

seit 05/2016 Wissenschaftlicher Mitarbeiter am Institut für Produktionstechnik (wbk) des Karlsruher Instituts für Technologie (KIT)  
2010 - 2016 Studium des Maschinenbaus am Karlsruher Institut für Technologie (KIT)

Veröffentlichungen

[ 1 ] Wagner, R.; Häfner, B. & Lanza, G. (2016), „Paarungsstrategien für hochpräzise Produkte*“, wt Werkstatttechnik online, Nr. 12, S. 804-808. [08.12.16].
Abstract:
Steigende Anforderungen an die Produktqualität stellen Unternehmen vor die Herausforderung, günstige Produkte nahe der technologischen Fertigungsgrenzen zu produzieren. Die Paarung von Montagekomponenten mit angepassten Produktionsstrategien bietet in diesem Umfeld mögliche Lösungsansätze. Neue Informations- und Kommunikationstechnologien im Kontext von Industrie 4.0 eröffnen hierfür neuartige Möglichkeiten.

[ 2 ] Wagner, R.; Kuhnle, A. & Lanza, G. (2017), „Optimising Matching Strategies for High Precision Products by Functional Models and Machine Learning Algorithms “. WGP-Jahreskongress, Hrsg. Schmitt, R. & Schuh, G., S. 1-9.
Abstract:
Companies are confronted with increasing product quality requirements to manufacture high quality products, close to technological limits, in a cost-effective way. Matching of assembly components offers an approach to cope with this challenge by means of adapted production strategies. To satisfy and optimize precise functionality requirements a model that integrates process variation and functionality is applied to enhance existing matching strategies. This paper demonstrates the implementation of functional models within production strategies for fuel injector systems. The injector system must fulfil high requirements regarding the functionality, i.e. providing a homogeneous fuel mixture at a constant level. To enhance matching strategies and the functional models for the assembled components, a machine learning algorithm will be applied. This model is utilized to determine and quantify a model for the functional relation between pre-process variations and product functionality and to optimize matching strategies by selecting the relevant features.

[ 3 ] Haefner, B.; Biehler, M.; Wagner, R. & Lanza, G. (2018), „Meta-Model Based on Artificial Neural Networks for Tooth Root Stress Analysis of Micro-Gears“. Procedia CIRP 75, Hrsg. Elsevier, S. 155-160.
Abstract:
Micro-transmissions, consisting of micro-gears with a module <200µm, are used in manifold industrial applications, e.g. the medical industry. Due to the technological limits of their manufacturing processes, micro-gears show large shape deviations compared to their size, which significantly influence their lifetime. Thus, for micro-gears a model has been developed to enable a prognosis of their lifetime based on areal measurements of the gear geometry, finite elements simulations as well as lifetime experiments. To significantly reduce the amount of experiments, existing prior knowledge is additionally used as input to the lifetime model by means of Bayesian statistics. To enable a time-efficient application of the model for industrial series production, in this article the application of a machine learning approach based on artificial neural networks is investigated. The uncertainty of the model is evaluated according to the principles of the Guide to the Expression of Uncertainty in Measurement (GUM).

[ 4 ] Wagner, R.; Haefner, B. & Lanza, G. (2018), „Function-Oriented Quality Control Strategies for High Precision Products“. Procedia CIRP 75, Hrsg. Elsevier, S. 57-62.
Abstract:
Companies are confronted with increasing product quality requirements to manufacture high quality products, close to technological limits, in an economic way. The implementation of adaptive quality control strategies (QCS) in production offers an approach to cope with this challenge. In this paper, new function-oriented QCS by means of selectively assembling multiple components are demonstrated based on a functional product model. The implementation of QCS for fuel injector systems, which must fulfil narrow tolerances regarding the product’s functionality, show benefits in quality and cost-effectiveness. In the approach a functional model of the product and a simulation of the production system are implemented.