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

Application of an Artificial Neural Network Model to Obtain Constitutive Equation Parameters of Materials in High Speed Forming Process

고속 성형 공정에서 재료의 구성 방정식 파라메터 획득을 위한 인공신경망 모델의 적용

  • 우민아 (부산대학교 항공우주공학과) ;
  • 이승민 (부산대학교 항공우주공학과) ;
  • 이경훈 (부산대학교 항공우주공학과) ;
  • 송우진 (부산대학교 일반대학원 융합학부) ;
  • 김정 (부산대학교 항공우주공학과)
  • Received : 2018.08.22
  • Accepted : 2018.10.01
  • Published : 2018.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

Electrohydraulic forming (EHF) process is a high speed forming process that utilizes the electric energy discharge in fluid-filled chamber to deform a sheet material. This process is completed in a very short time of less than 1ms. Therefore, finite element analysis is essential to observe the deformation mechanism of the material in detail. In addition, to perform the numerical simulation of EHF, the material properties obtained from the high-speed status, not quasi static conditions, should be applied. In this study, to obtain the parameters in the constitutive equation of Al 6061-T6 at high strain rate condition, a surrogate model using an artificial neural network (ANN) technique was employed. Using the results of the numerical simulation with free-bulging die in LS-DYNA, the surrogate model was constructed by ANN technique. By comparing the z-displacement with respect to the x-axis position in the experiment with the z-displacement in the ANN model, the parameters for the smallest error are obtained. Finally, the acquired parameters were validated by comparing the results of the finite element analysis, the ANN model and the experiment.

Keywords

SSGGB@_2018_v27n6_331_f0001.png 이미지

Fig. 1 Schematic diagram for electrohydraulic forming process

SSGGB@_2018_v27n6_331_f0002.png 이미지

Fig. 2 Experimental apparatus for electrohydraulic forming

SSGGB@_2018_v27n6_331_f0003.png 이미지

Fig. 3 Current curve from the experiment at 8 kV

SSGGB@_2018_v27n6_331_f0004.png 이미지

Fig. 4 Final deformation shape of Al 6061-T6 at 8 kV

SSGGB@_2018_v27n6_331_f0005.png 이미지

Fig. 5 Finite element model for electrohydraulic forming

SSGGB@_2018_v27n6_331_f0006.png 이미지

Fig. 6 Training samples with respect to C and p values

SSGGB@_2018_v27n6_331_f0007.png 이미지

Fig. 7 Deformation results in the numerical simulation

SSGGB@_2018_v27n6_331_f0008.png 이미지

Fig. 8 A general structure of artificial neural network

SSGGB@_2018_v27n6_331_f0009.png 이미지

Fig. 9 A system of neural networks to estimate the parameters

SSGGB@_2018_v27n6_331_f0010.png 이미지

Fig. 10 Final deformation shapes of the blank at different parameters

SSGGB@_2018_v27n6_331_f0011.png 이미지

Fig. 11 Test samples from random sampling

SSGGB@_2018_v27n6_331_f0012.png 이미지

Fig. 12 The plot of error according to C and p values

SSGGB@_2018_v27n6_331_f0013.png 이미지

Fig. 13 Stress-strain curves at different strain rate condition of Al 6061-T6

SSGGB@_2018_v27n6_331_f0014.png 이미지

Fig. 14 Comparison of experiment, numerical simulation, and ANN model

Table 1 Numerical validation of the surrogate model with training samples based on ANN

SSGGB@_2018_v27n6_331_t0001.png 이미지

Table 2 Numerical validation of the surrogate model with test samples based on ANN

SSGGB@_2018_v27n6_331_t0002.png 이미지

Table 3 Comparison of MSE between ANN, LS-DYNA, and experiment

SSGGB@_2018_v27n6_331_t0003.png 이미지

References

  1. T. Altan, A. E. Tekkaya, 2012, "Sheet metal forming: processes and applications", ASM International.
  2. S. Golowin,M. Kamal, J. Shang, J. Portier, A. Din, G. S. Daehn, R. Bradley, K. E. Newman, S. Hatkevich, 2007, "Application of a Uniform Press Actuator for Electromagnetic Processes of Sheet Metal", J. Mater. Eng. Perform., Vol. 16, No. 4, pp. 455-460. https://doi.org/10.1007/s11665-007-9085-4
  3. V. Psyk, D. Risch, B. L. Kinsey, A. E. Tekkaya, M. Kleiner. 2011, Electromagnetic forming a review, J. Mater. Process. Tech., Vol. 211, No. 5, pp. 787-829. https://doi.org/10.1016/j.jmatprotec.2010.12.012
  4. V. S. Balanethiram, G. S. Daehn, 1994, Hyperplasticity: Increased forming limits a high workpiece velocity, Scripta Metallurgica et Materialia(United States), Vol. 30, No. 4. pp. 515-520. https://doi.org/10.1016/0956-716X(94)90613-0
  5. H. Kolsky, 1949, Stress wave in Solids, Dover, pp.41-65.
  6. D. T. Chung, 1994, Split Hopkinson Pressure Bar Technique for Stress- strain Measurement, Trans. Korean Soc. Mech. Eng. A, Vol. 18, pp. 33-41
  7. G. T. Gray, 2012, Classic Split-Hopkinson Pressure Bar Technique, ASM handbook, Mechanical Testing and Evaluation, ASM International, Vol. 8.
  8. S. F. Golovashchenko, J. G. Alan, V. M. Alexander, 2013, Formability of dual phase steels in electrohydraulic forming, J. Mater. Process. Tech., Vol. 213, No. 7 pp. 1191-1212. https://doi.org/10.1016/j.jmatprotec.2013.01.026
  9. J. M. Imbert, S. L. Winkler, M. J. Worswick, D. A. Oliveira, S. F. Golovashchenko, 2005, The effect of tool-sheet interaction on damage evolution in electromagnetic forming of aluminum alloy sheet. J. Eng. Mater. Tech., Vol. 127, No. 1, pp. 145-153. https://doi.org/10.1115/1.1839212
  10. W. S. McCulloch, P. Walter, 1943, A logical calculus of the ideas immanent in nervous activity, The bulletin of mathematical biophysics, Vol. 5, Nol. 4, pp. 115-133. https://doi.org/10.1007/BF02478259
  11. A. Forrester, K. Andy, 2008, Engineering design via surrogate modelling: a practical guide. John Wiley & Sons.