Thilo Breitsprecher

Neural network based modeling and optimization of deep drawing --- extrusion combined process

A combined deep drawing–extrusion process is modeled with artificial neural networks (ANN’s). The process is used for manufacturing synchronizer rings and it combines sheet and bulk metal forming processes. Input–output data relevant to the process was collected. The inputs represent geometrical parameters of the synchronizer ring and the outputs are the total equivalent plastic strain (TEPS), contact ratio and forming force. This data is used to train the ANN which approximates the input-output relation well and therefore can be relied on in predicting the process input parameters that will result in desired outputs provided by the designer. The complex method constrained optimization is applied to the ANN model to find the inputs or geometrical parameters that will produce the desired or optimum values of TEPS, contact ratio and forming force. This information will be very hard to obtain by just looking at the available historical input–output data. Therefore, the presented technique is very useful for selection of process design parameters to obtain desired product properties.

Acquisition of Heuristic Knowledge for the Prediction of the Frictional Behavior of Surface Structures Created by Self-Excited Tool Vibrations

The selective control of the frictional behavior (tailored friction) in metal forming processes is of high importance with regard to technical and economic aspects. This applies especially for the sheet-bulk-metal forming process. Milling with intentionally invoked regenerative tool vibrations can be applied in order to generate structured surfaces with tailored friction properties on the forming tool. These structures affect the formation of lubrication pockets during the forming process which determine the local frictional properties exceedingly. The full potential of this emerging technology can, however, only be revealed if the heuristic and design-relevant knowledge is acquired and provided to the tool-designer already in the early phases of process development. One thing the tool-designer has to specify is the local frictional behavior on the tool surface. But, however, he does not know which milling parameters lead to the necessary surface structures because in most cases he has no expert knowledge in milling, tribology and forming tools. In this paper data mining is used to determine the frictional behavior based on these parameters. The potential of this method in the described context is revealed by the application on data derived from simulation results, both from milling simulations and contact simulations. The latter are performed by using a Halfspace model for rough surface contact. Both approaches for these simulations, the data mining process and the results are explained to the reader.

Einsatz von Data-Mining in modernen Produktentstehungsprozessen

Kurzfassung Das Arbeitsumfeld von Produktentwicklern und Konstrukteuren unterliegt einem ständigen Wandel. Die fortschreitende Globalisierung der Märkte, der steigenden Innovationsdruck und die erhöhten Individualität und Dynamik der einzelnen Absatzregionen, lassen die Anforderungen an Produkte sowie an Produktentstehungsprozesse immer differenzierter werden. Der Lehrstuhl für Konstruktionstechnik (KTmfk) der Friedrich-Alexander Universität Erlangen-Nürnberg (FAU) erforscht Data-Mining-Lösungen für die Produktentstehung, die den Unternehmen helfen mit dieser Entwicklung Schritt halten zu können.

Methodengestützte Referenzvorgehensweise für neue Umformverfahren

Kurzfassung Neue Umformverfahren zielen auf eine Steigerung der Prozessrobustheit und eine Verkürzung der Prozesskette ab. Mit der Entwicklung der Blechmassivumformung (BMU) innerhalb des Sonderforschungsbereiches Transregio 73 wird durch das Zusammenführen der konventionellen Blech- und Massivumformung zudem das Überwinden derzeitiger Prozessgrenzen verfolgt. Zur Gewährleistung einer strukturierten und zielführenden Entwicklung der BMU wurde eine methodengestützte Referenzvorgehensweise für neue Umformverfahren konzipiert und in unterschiedlichen Entwicklungsbereichen angewendet.