Transactions of Materials Processing (소성∙가공)

The Korean Society for Technology of Plasticity and materials processing (한국소성∙가공학회)
권호 표지
DOI QR코드

DOI QR Code

Comparative Study on Surrogate Modeling Methods for Rapid Electromagnetic Forming Analysis

  • Lee, Seungmin (Department of Aerospace Engineering, Pusan National University) ;
  • Kang, Beom-Soo (Department of Aerospace Engineering, Pusan National University) ;
  • Lee, Kyunghoon (Department of Aerospace Engineering, Pusan National University)
  • Received : 2017.11.01
  • Accepted : 2018.01.19
  • Published : 2018.02.01
Download PDF
⟨ Previous Next ⟩

Abstract

Electromagnetic forming is a type of high-speed forming process to deform a workpiece through a Lorentz force. As the high strain rate in an electromagnetic-forming simulation causes infeasibility in determining constitutive parameters, we employed inverse parameter estimation in the previous study. However, the inverse parameter estimation process required us to spend considerable time, which leads to an increase in computational cost. To overcome the computational obstacle, in this research, we applied two types of surrogate modeling methods and compared them to each other to evaluate which model is best for the electromagnetic-forming simulation. We exploited an artificial neural network and we reduced-order modeling methods. During the construction of a reduced-order model, we extracted orthogonal bases with proper orthogonal decomposition and predicted basis coefficients by utilizing an artificial neural network. After the construction of the surrogate models, we verified the artificial neural network and reduced-order models through training and testing samples. As a result, we determined the artificial neural network model is slightly more accurate than the reduced-order model. However, the construction of the artificial neural network model requires a considerably larger amount of time than that of the reduced-order model. Thus, a reduced order modeling method is more efficient than an artificial neural network for estimating the electromagnetic forming and for the rapid approximation of structural simulations which needs repetitive runs.

Keywords

References

  1. H. G. Noh, K. Lee, B. S. Kang, J. Kim, 2016, Inverse Parameter Estimation of the Cowper-Symonds Material Model for Electromagnetic Free Bulge Forming, Int. J. Precis. Eng. Manuf., Vol. 17, No. 11, pp. 1483-1492. https://doi.org/10.1007/s12541-016-0174-x
  2. K. Lee, H. G. Noh, J. Kim, 2016, Reduced Order Modeling of Electromagnetic Metal Forming for the Identification of a Flow Stress Model, The 12th World Congress in Computational Mechanics, Seoul, Republic of Korea.
  3. A. Forrester, A. Keane, 2008, Engineering Via Surrogate Modeling: a Practical Guide, John Wiley & Sons, New York. pp. 49-56.
  4. K. Lee, T. Nam, C. Perullo, D. N. Mavris, 2011, Reduced-order Modeling of a High-fidelity Propulsion System Simulation, AIAA J., Vol. 49, No. 8, pp. 1665-1682. https://doi.org/10.2514/1.J050887
  5. H. M. Gomes, A. M. Awruch, P. A. M. Lopes, 2011, Reliability Based Optimization of Laminated Composite Structures using Genetic Algorithms and Artificial Neural Networks, Struct. Saf., Vol. 33, No. 3, pp. 186-195. https://doi.org/10.1016/j.strusafe.2011.03.001
  6. L. Marin, D. Trias, P. Badallo, G. Rus, J. A. Mayugo, 2012, Optimization of Composite Stiffened Panels Under Mechanical and Hydrothermal Loads using Neural Networks and Genetic Algorithms, Compos. Struct., Vol. 94, No. 11, pp. 3321-3326. https://doi.org/10.1016/j.compstruct.2012.04.024
  7. Z. Zhang, K. Friedrich, 2003, Artificial Neural Networks Applied to Polymer Composites: a Review, Compos. Sci. Technol., Vol. 63, No. 14, pp. 2029-2044. https://doi.org/10.1016/S0266-3538(03)00106-4
  8. L. Lanzi, V. Giavotto, 2006, Post-buckling Optimization of Composite Stiffened Panels: Computations and Experiments, Compos. Struct., Vol. 73, No. 2, pp. 208-220. https://doi.org/10.1016/j.compstruct.2005.11.047
  9. H. M. Gomes, A. M. Awruch, 2005, Reliability Analysis of Concrete Structures with Neural Networks and Response Surfaces, Eng. Comput., Vol. 22, No. 1, pp. 110-128. https://doi.org/10.1108/02644400510572433
  10. V. Lenaerts, G. Kerschen, J. C. Golinval, 2003, Identification of a Continuous Structure with a Geometrical Non-linearity. Part II: Proper Orthogonal Decomposition, J. Sound Vib., Vol. 262, No. 4, pp. 907-919. https://doi.org/10.1016/S0022-460X(02)01132-X
  11. C. Shane, R. Jha, 2011, Proper Orthogonal Decomposition Based Algorithm for Detecting Damage Location and Severity in Composite Beams, Mech. Syst. Sig. Process., Vol. 25, No. 3, pp. 1062-1072. https://doi.org/10.1016/j.ymssp.2010.08.015
  12. V. Lenaerts, G. Kerschen, J. Golinval, 2001, Proper Orthogonal Decomposition for Model Updating of Non-linear Mechanical Systems, Mech. Syst. Sig. Process., Vol. 15, No. 1, pp. 31-43. https://doi.org/10.1006/mssp.2000.1350
  13. P. Kerfriden, P. Gosselet, S. Adhikari, S. P. A. Bordas, 2011, Bridging Proper Orthogonal Dcomposition Methods and Augmented Newton-Krylov Algorithms: an Adaptive Model order Reduction for Highly Nonlinear Mechanical Problems, Comput. Methods Appl. Mech. Eng., Vol. 200, No. 5, pp. 850-866. https://doi.org/10.1016/j.cma.2010.10.009
  14. U. Galvanetto, G. Violaris, 2007, Numerical Investigation of a New Damage Detection Method Based on Proper Orthogonal Decomposition, Mech. Syst. Sig. Process., Vol. 21, No. 3, pp. 1346-1361. https://doi.org/10.1016/j.ymssp.2005.12.007
  15. D. C. Montgomery, E. A. Peck, G. G. Vining, 2015, Introduction to Linear Regression Analysis, John Wiley & Sons., New York. pp. 526-529.
  16. Y. Liang, H. Lee, S. Lim, W. Lin, K. Lee, C. Wu, 2002, Proper Orthogonal Decomposition and Its 462 Applications-part i: Theory, J. Sound Vib., Vol. 252, No. 3, pp. 527-544. https://doi.org/10.1006/jsvi.2001.4041
  17. R. Pinnau, 2008, Model Reduction Via Proper Orthogonal Decomposition, Model Order Reduction: Theory, Research Aspects and Applications, Springer, Vol. 13, pp. 95-109.