Prediction the Springback in Air-Bending Process Using Neural Network Metamodel

Abstract:

To eliminate geometric deviations of sheet metal subjected to an air-bending process from the geometry required by the designer, it is necessary to predict the accurate value of the springback. Springback is the elastic deformation observed upon removal of the load during a bending process. In order to predict the springback amount, a multidimensional function should be approximated. In this paper, a neural network metamodel (NNM) based on the back propagation algorithm is introduced to predict the springback value. A verified nonlinear finite element model is developed to generate NNM training data. To select the training data for the NNM, computer generated D-optimal designs are utilized. The NNM developed model in this research can be used in determination of the springback value in sheet metal bending.

• Periodical: Applied Mechanics and Materials (Volume 619)
• Pages: 3-7
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.619.3
• Online since: August 2014
• Authors: Fayiz Y. Abu Khadra, Jaber E. Abu Qudiri, H.M.A. Hussein
• Keywords: D-Optimal Designs, Metamodels, Neural Network (NN), Springback

References

[1] Sacks, J., et al., Design and Analysis of Computer Experiments. Statistical Science, 1989. 4(4): pp.409-423.

[2] Alam, F.M., K.R. McNaught, and T.J. Ringrose, A comparison of experimental designs in the development of a neural network simulation metamodel. SIMULATION MODELLING PRACTICE AND THEORY, 2004. 12(7-8): pp.559-578.

DOI: 10.1016/j.simpat.2003.10.006

[3] Simpson, T.W., et al., Metamodels for Computer-based Engineering Design: Survey and recommendations. EWC Engineering With Computers, 2001. 17(2): pp.129-150.

DOI: 10.1007/pl00007198

[4] Booker, A.J., et al., A rigorous framework for optimization of expensive functions by surrogates. STRUCTURAL OPTIMIZATION -BERLIN-, 1999. 17(1): pp.1-13.

DOI: 10.1007/bf01197708

[5] Kleijnen, J.P.C. and R.G. Sargent, A methodology for fitting and validating metamodels in simulation. European Journal of Operational Research European Journal of Operational Research, 2000. 120(1): pp.14-29.

DOI: 10.1016/s0377-2217(98)00392-0

[6] Jin, R., W. Chen, and T.W. Simpson, Comparative studies of metamodelling techniques under multiple modelling criteria. Structural and Multidisciplinary Optimization, 2001. 23(1): pp.1-13.

DOI: 10.1007/s00158-001-0160-4

[7] Fu, Z. and J. Mo, Springback prediction of high-strength sheet metal under air bending forming and tool design based on GABPNN. Int J Adv Manuf Technol The International Journal of Advanced Manufacturing Technology, 2011. 53(5-8): pp.473-483.

DOI: 10.1007/s00170-010-2846-5

[8] Garcia-Romeu, M.L. and J. Ciurana, Springback and Geometry Prediction - Neural Networks Applied to the Air Bending Process. Lecture notes in computer science., 2006(4113): pp.470-475.

DOI: 10.1007/11816157_58

[9] Inamdar, M., et al., Development of an Artificial Neural Network to Predict Springback in Air Vee Bending. The International Journal of Advanced Manufacturing Technology The International Journal of Advanced Manufacturing Technology, 2000. 16(5): pp.376-381.

DOI: 10.1007/s001700050169

[10] Nasrollahi, V., et al., Prediction of springback in sheet metal components with holes on the bending area, using experiments, finite element and neural networks. Materials and Design, 2012. 36: pp.331-336.

DOI: 10.1016/j.matdes.2011.11.039

[11] Myers, R.H., D.C. Montgomery, and C.M. Anderson-Cook, Response surface methodology : process and product optimization using designed experiments2009, Hoboken, N.J.: Wiley.

[12] Haykin, S.S., Neural networks and learning machines2009, New York: Prentice Hall/Pearson.

[13] Hornik, K., M. Stinchcombe, and H. White, Multilayer feedforward networks are universal approximators. Neural Networks, 1989. 2(5): pp.359-366.

DOI: 10.1016/0893-6080(89)90020-8