Advertisement

Development of a Machine Learning Based Fast Running Model to Determine Rapidly the Process Conditions in Drawing Process

  • Donghyuk Cho
  • Youngseog LeeEmail author
Article
  • 19 Downloads

Abstract

This study proposes a fast running model that interconnects input and output data for a single-pass cold bar drawing process through the use of Artificial Neural Network (ANN) and automatically generated a large volume of elastic-plastic finite element (FE) analysis results. The prediction accuracy of the FE analysis was verified by comparing the FE analysis with measurements from a drawing experiment. A Python-based script that automatically controls ABAQUS was coded to sequentially produce output data that varies according to the input data, which is a combination of 18 grades of steel and 1,000 process conditions. The ANN was trained using input and output data, and then a nine-dimensional fast running model was developed. The fast running model predicted the values of output variables (drawing force, strain at the center, strain on the surface, accumulated damage at the center, contact pressure, and the fracture (or non-fracture) of the material) in 0.1 second no matter how the mechanical properties of the steels and process conditions change. With this fast running model, engineers in the drawing industry can easily determine or modify the process conditions to improve productivity and product quality even when a grade of steel that has never been employed before is drawn.

Key words

Machine learning ANN Fast running model Elastic-plastic FE simulation Laboratory bar drawing test 

Nomenclature

Fd

drawing force, kgf

εc

strain at the center of material

εs

strain on the surface of material

Cp

contact pressure at the interface of material and die, MPa

r

reduction ratio, %

α

die semi-angle, °

μ

coulomb friction coefficient

v

drawing speed, mm/min

Tm

material temperature, °C

di

initial diameter of the material, mm

K

strength coefficient, MPa

n

strain hardening exponent

RA

reduction of area in a tensile test, %

YS

yield strength, MPa

EL

uniform elongation, %

UTS

ultimate tensile strength, MPa

ω

accumulative damage parameter

ωc

accumulated damage at the center of material

ωcritical

critical damage value

σ1

maximum principal stress, MPa

σeq

equivalent stress, MPa

σm

mean stress, MPa

η

stress triaxiality

\({\overline \varepsilon_{{\rm{dr}}}}\)

equivalent strain in the material during drawing

\(\overline \varepsilon\)

equivalent strain

nos

number of samples

ti

FE calculation for the ith sample

oi

FR model prediction for the ith sample

DF

ductile fracture

MAPE

mean average percentage error, %

CEE

cross-entropy error

MSE

mean square error

ANN

artificial neural network

FR model

fast running model

VIV

values of each input variable

VOV

values of each output variable

GUI program

graphic user interface program

Notes

Acknowledgement

This work was supported by a grant (NRF-2016 R1D1A1B03935327) from the National Research Foundation of Korea funded by the Korean government (Ministry of Science, ICT & Future Planning, MSIP).

References

  1. Alberti, N., Barcellona, A., Masnata, A. and Micari, F. (1993). Central bursting defects in drawing and extrusion: Numerical and ultrasonic evaluation. CIRP Annals 42, 1, 269–272.CrossRefGoogle Scholar
  2. Byon, S. M., Lee, S. J., Lee, D. W., Lee, Y. H. and Lee, Y. (2011). Effect of coating material and lubricant on forming force and surface defects in wire drawing process. Trans. Nonferrous Metals Society of China 21, Supplement 1, s104–s110.CrossRefGoogle Scholar
  3. Cho, D. and Lee, Y. (2018). Application of ANN-NSGA-II hybrid methodology for the automation of die design in single-pass drawing. Proc. AEPA2018, Jeju, Korea.Google Scholar
  4. Cho, D., Jang, Y. C. and Lee, Y. (2019). Evaluation of the prediction ability of ductile fracture criteria over a wide range of drawing conditions. J. Mechanical Science and Technology 33, 9, 4245–4254.CrossRefGoogle Scholar
  5. Beale, M. H., Hagan, M. T. and Demuth, H. B. (2018). Deep Learning Toolbox User’s Guide. Mathworks Inc. Sherborn, Massachusetts, USA.Google Scholar
  6. Fan, J., Wu, L., Zhang, F., Cai, H., Zeng, W., Wang, X. and Zou, H. (2019). Empirical and machine learning models for predicting daily global solar radiation from sunshine duration: A review and case study in China. Renewable and Sustainable Energy Reviews, 100, 186–212.CrossRefGoogle Scholar
  7. García-Martín, J., Gómez-Gil, J. and Vázquez-Sánchez, E. (2011). Non-destructive techniques based on eddy current testing. Sensors 11, 3, 2525–2565.CrossRefGoogle Scholar
  8. Khuri, A. I. and Cornell, J. A. (2018). Response Surfaces: Designs and Analyses. Routledge. Abingdon-on-Thames, UK.CrossRefGoogle Scholar
  9. Ko, Y. K., Lee, J. S., Huh, H., Kim, H. K. and Park, S. H. (2007). Prediction of fracture in hub-hole expanding process using a new ductile fracture criterion. J. Materials Processing Technology, 187–188, 358–362.CrossRefGoogle Scholar
  10. Maran, J. P. and Priya, B. (2015). Comparison of response surface methodology and artificial neural network approach towards efficient ultrasound-assisted biodiesel production from muskmelon oil. Ultrasonics Sonochemistry, 23, 192–200.CrossRefGoogle Scholar
  11. McClelland, J. L., Rumelhart, D. E. and Group, P. D. P. R. (1986). Parallel Distributed Processing, Explorations in the Microstructure of Cognition. MIT Press. Cambridge, Massachusetts, USA, 216–271.Google Scholar
  12. McCulloch, W. S. and Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. The Bulletin of Mathematical Biophysics 5, 4, 115–133.MathSciNetCrossRefGoogle Scholar
  13. McKay, M. D., Beckman, R. J. and Conover, W. J. (2000). A comparison of three methods for selecting values of input variables in the analysis of output from a computer code. Technometrics 42, 1, 55–61.CrossRefGoogle Scholar
  14. Rosenblatt, F. (1961). Principles of Neurodynamics. Perceptrons and the Theory of Brain Mechanisms. Cornell Aeronautical Lab Inc. Buffalo, New York, USA.CrossRefGoogle Scholar
  15. Scholkopf, B. and Smola, A. J. (2001). Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press. Cambridge, Massachusetts, USA.Google Scholar
  16. Simpson, T. W., Mauery, T. M., Korte, J. J. and Mistree, F. (2001). Kriging models for global approximation in simulation-based multidisciplinary design optimization. AIAA J. 39, 12, 2233–2241.CrossRefGoogle Scholar
  17. Vega, G., Haddi, A. and Imad, A. (2009). Investigation of process parameters effect on the copper-wire drawing. Materials & Design 30, 8, 3308–3312.CrossRefGoogle Scholar
  18. Wang, G. G. and Shan, S. (2007). Review of metamodeling techniques in support of engineering design optimization. J. Mechanical Design 129, 4, 370–380.CrossRefGoogle Scholar
  19. Widrow, B. and Hoff, M. E. (1960). Adaptive Switching Circuits. Stanford Univ Ca Stanford Electronics Labs. Stanford, California, USA.CrossRefGoogle Scholar
  20. Wright, R. N. (2016). Wire Technology: Process Engineering and Metallurgy. Butterworth-Heinemann. Oxford, UK.Google Scholar

Copyright information

© KSAE/112-03 2019

Authors and Affiliations

  1. 1.Department of Mechanical EngineeringChung-Ang UniversitySeoulKorea

Personalised recommendations