An Efficient Knowledge Based System for the Prediction of the Technical Feasibility of Sheet Metal Forming Processes

Abstract:

This paper presents an efficient knowledge based method using data mining and multilayer perceptrons (MLP) for the prediction of the technical feasibility of sheet metal forming processes. The stored forecast models can be applied to similar geometries and forming processes using the digital fingerprint to identify the most suitable MLP. Moreover, we establish an algorithm to detect extrapolation which is a priori applied to each new design in order to avoid probable high errors in the forecast model caused by extrapolation. We demonstrate the benefits of the method on a model problem specially designed to investigate a wide range of industrial relevant forming characteristics.

• Periodical: Key Engineering Materials (Volumes 554-557)
• Pages: 2472-2478
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.554-557.2472
• Online since: June 2013
• Authors: Daniela Steffes Lai, Sven Turck, Christian Klimmek, Tanja Clees
• Keywords: Artificial Neural Network (ANN), Forming Simulation, Interpolation, Multi-Layer Perceptron

References

[1] A.E. Tekkaya: State-of-the-art of simulation of sheet metal forming Journal of Materials Processing Technology, 103:14-22, 2000.

DOI: 10.1016/s0924-0136(00)00413-1

[2] G. Ngaile and T. Altan: Simulations of manufacturing processes: past, present, and future in Advandced Technology of Plasticity 2002 - Proceedings of the 7th ICTP, J. Yanagimoto, ed., Vol. 1, Japan Society for Technology of Plasticity, pp.271-282.

[3] F. Rosenblatt: The perceptron: A probabilistic model for information storage and organization in the brain Psychological Review, 65:386 - 408, 1958.

DOI: 10.1037/h0042519

[4] G. Cybenko: Approximation by superpositions of a sigmoidal function Mathematics of Control, Signals, and Systems (MCSS), 2(4):303 - 314, 1989.

DOI: 10.1007/bf02551274

[5] R. Rojas: Neural Networks - A Systematic Introduction Berlin : Springer-Verlag, 1996.

[6] Ch. Klimmek: Method for determining the ability of a body to change the shape thereof Patent, Pub. No.: WO/2009/024130, International Application No.: PCT/DE2008/001346.

[7] K. Fukunaga and P.M. Narendra: A branch and bound algorithm for computing k-nearest neighbors, IEEE Trans. Computers Vol. 24, Issue 7 (1975), pp.750-753.

DOI: 10.1109/t-c.1975.224297

[8] S. Arya and D.M. Mount and N.S. Netanyahu and R. Silverman and A.Y. Wu: An optimal algorithm for approximate nearest neighbor searching in fixed dimensions in ACM-SIAM Symposium on Discrete Algorithms (1994), pp.573-582.

DOI: 10.1145/293347.293348

[9] D. Steffes-lai and T. Clees: Statistical analysis of forming processes as a first step in a processchain analysis: novel PRO-CHAIN components, Trans Tech Publications, Key Engineering Materials Vol. 504 - 506 (2012), pp.631-636.

DOI: 10.4028/www.scientific.net/kem.504-506.631

[10] Information on http://www.pt-it.pt-dlr.de/_media/Infoblatt_VIPROFORM.pdf (in german).