DEEP LEARNING IN SHEET-BULK METAL FORMING PART DESIGN

Within the Transregional Collaborative Research Centre 73, a self-learning engineering workbench is being developed. It assists product developers in designing sheet-bulk metal formed (SBMF) parts by computing the effects of given product and process characteristics on the product properties. This contribution presents a novel approach to using deep learning methods for the properties prediction. By making use of a parameter study of 20 SBMF part designs, a metamodel is trained and used to predict the total equivalent plastic strain on local level as an indicator for part manufacturability.

[1]  Richard J. Beckman,et al.  A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output From a Computer Code , 2000, Technometrics.

[2]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[3]  Sandro Wartzack,et al.  A classification system for secondary design features for the use within sheet-bulk metal forming , 2013 .

[4]  Christian Borgelt,et al.  Computational Intelligence , 2016, Texts in Computer Science.

[5]  Geoffrey Boothroyd.  Design for Manufacture and Assembly: The Boothroyd-Dewhurst Experience , 1996 .

[6]  Sandro Wartzack,et al.  Improved Sheet Bulk Metal Forming Processes by Local Adjustment of Tribological Properties , 2011 .

[7]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[8]  Schleich Benjamin,et al.  Einsatz von Deep Learning zur ortsaufgelösten Beschreibung von Bauteilei-genschaften , 2017 .

[9]  Norbert Hoffmann.  Kleines Handbuch neuronale Netze - anwendungsorientiertes Wissen zum Lernen und Nachschlagen , 1993 .

[10]  J. R. Quinlan.  Learning With Continuous Classes , 1992 .

[11]  H. Schiefer,et al.  Statistische Versuchsplanung, Design of Experiments (DoE) , 2018 .

[12]  Johannes Will,et al.  Meta-model of Optimal Prognosis-An automatic approach for variable reduction and optimal meta-model selection , 2009 .

[13]  Quoc V. Le,et al.  Neural Architecture Search with Reinforcement Learning , 2016, ICLR.

[14]  Thilo Breitsprecher and Sandro Wartzack.  Architecture and realization of a selflearning engineering assistance system for the use within sheetbulk metal forming , 2012 .