Home | english  | Impressum | Datenschutz | Sitemap | KIT

Neueste Publikationen

[ 1 ] Stricker, N.; Kuhnle, A.; Sturm, R. & Friess, S. (2018), „Reinforcement learning for adaptive order dispatching in the semiconductor industry“, CIRP Annals - Manufacturing Technology, S. 511-514. https://doi.org/10.1016/j.cirp.2018.04.041
The digitalization of production systems tends to provide a huge amount of data from heterogeneous sources. This is particularly true for the semiconductor industry wherein real time process monitoring is inherently required to achieve a high yield of good parts. An application of data-driven algorithms in production planning to enhance operational excellence for complex semiconductor production systems is currently missing. This paper shows the successful implementation of a reinforcement learning-based adaptive control system for order dispatching in the semiconductor industry. Furthermore, a performance comparison of the learning-based control system with the traditionally used rule-based system shows remarkable results. Since a strict rulebook does not bind the learning-based control system, a flexible adaption to changes in the environment can be achieved through a combination of online and offline learning.

[ 2 ] Coutandin, S.; Brandt, D.; Heinemann, P.; Ruhland, P. & Fleischer, J. (2018), „Influence of punch sequence and prediction of wrinkling in textile forming with a multi-punch tool“, Production Engineering, S. 1-10. https://doi.org/10.1007/s11740-018-0845-9 [13.08.18].
Liquid composite moulding (LCM) processes show a high potential in automated, large scale production of continuous fibre-reinforced plastics (FRP). One of the most challenging steps is the forming of the two-dimensional textile material into a complex, three-dimensional fibre structure. In this paper, a multi-punch forming process is presented. The upper mould of a generic part geometry is divided into 15 independently controllable punches. Depending on the different punch sequences, draping effects as well as defects related to wrinkling and shearing of the textile material are investigated. It has been shown that the sequence of the punches has a significant influence on the final preform quality. To predict the resulting regions of wrinkling and shearing, a finite-element based simulation model is set up. Forming tests and simulations with different punch-sequences are then performed and evaluated for validation purposes. To make a statement about the global preform quality, different objective functions regarding wrinkling are presented and analysed.

[ 3 ] Fleischer, J.; Spohrer, A.; Klee, B.; Mayer, D. & Spiller, Q. (2018), Orientierungshilfe zur Einführung einer vernetzten Produkt- und Produktionsarchitektur in der Landtechnik, VDMA Landtechnik, Frankfurt am Main.
Der vorliegende VDMA-Leitfaden Landtechnik 4.0 soll dem Mitgliederkreis als hilfreiches Kompendium dienen, um den vielfach als disruptiv beschriebenen Wandel der industriellen Produktionspraxis kundig und umsichtig gestalten zu können. Im Kern geht es uns darum, prägnant aufzuzeigen, wie Produktionstechniken mit innovativen IT-Technologien verschmolzen und dabei gleichzeitig Ansätze für neue lösungsorientierte Produkte im Landmaschinenbau geschaffen werden können. Der Leitfaden basiert in seinen Grundzügen auf dem im Jahr 2015 veröffentlichten VDMA-Leitfaden Industrie 4.0, der von Frau Dr. Beate Stahl vom VDMA Forum Industrie 4.0, von Herrn Prof. Dr. Reiner Anderl vom DiK Fachgebiet Datenverarbeitung in der Konstruktion der TU Darmstadt und von Herrn Prof. Dr. Jürgen Fleischer vom wbk Institut für Produktionstechnik des Karlsruher Instituts für Technologie erstellt wurde. Der VDMA-Leitfaden Landtechnik 4.0 ist ein gutes Beispiel für das hervorragende Miteinander der im VDMA organisierten Landmaschinen- und Traktorenhersteller, welches sich durch ebensolche gemeinschaftlichen Projekte wie der Erarbeitung eines Leitfadens zeigt. Er ist als praxistaugliches Tool konzipiert, das dazu beitragen möge, konkrete Ansatzpunkte im Hinblick auf Industrie 4.0 in den Unternehmen zu identifizieren und umzusetzen.

[ 4 ] Urgo, M.; Buergin, J.; Tolio, T. & Lanza, G. (2018), „Order allocation and sequencing with variable degree of uncertainty in aircraft manufacturing“, CIRP Annals, Band 67, Nr. 1, S. 431-436.
Aircraft manufacturers are challenged with increasing demand requiring customers to place orders months in advance respect to the time aircrafts will be operative. Consequently, customers decide aircraft’s size but have additional time to select cabin fittings. Nevertheless, manufacturers must promise a delivery time, regardless real aircraft configuration and resource availability at the production sites. We propose a novel framework for order allocation and sequencing in aircraft manufacturing minimizing the risk for manufacturing costs. Different degrees of uncertainty affecting products, work content and resources are considered as time advances and decisions to be taken change. An industrial application is also presented.

[ 5 ] Kopf, R.; Gottwald, J.; Jacob, A.; Brandt, M. & Lanza, G. (2018), „Cost-oriented planning of equipment for selective laser melting (SLM) in production lines“. CIRP Annals 2018, Hrsg. Procedia CIRP, S. 471-474.
Equipment for selective laser melting (SLM) has mainly been developed for applications in rapid prototyping. This paper provides a methodology for a cost-oriented optimisation and planning of SLM equipment for series production lines. The approach thus supports the transition to more productive and cost-efficient equipment. The paper presents a two-step methodology: at first, setup time is reduced using heuristic rules based on the activity node network plan. Afterwards, the build-up time is optimised by cost and performance parameters like laser power and build chamber size. Using the presented methodology rules for a cost-oriented SLM-equipment can be derived.

Weitere Publikationen finden Sie hier: