Genetic Algorithm optimization of initial blank shape in deep drawing of a stepped work piece

Abstract

This study considers the effect of forging direction on the initial shape of sheet to create a stepped work piece. The purpose of this study is to consider rolling direction in 0°, decreasing the waste while producing workpieces and so decreasing total cost of process. To this end, the assumed workpiece was made of a low carbon and anisotropic st14 steel sheet. To find the most appropriate direction and the shortest modification steps for final shape, the expansion level of the sheet was first imaged in the rolling direction and then the piece was shaped by the geometry. This approach was based on the coupling between the simulation and Genetic Algorithm. A Genetic Algorithm based approach is developed to optimize dimensions through integrating a finite element code running to compute the objective functions for each generation. Those points with a few materials modified through Genetic Algorithm yielded better results.

Keywords

Deep drawing forge initial shape Genetic Algorithm optimization

Get full access to this article

View all access options for this article.

References

Kakandikar

Nandedkar

. Prediction and optimization of thinning in automotive sealing cover using Genetic Algorithm. J Comput Des Eng 2016; 3: 63–70.

Date PP. Sheet metal formability. In: Proceedings of the training program of sheet metal forming research association, Indian Institute of Technology, Mumbai, 2005.

Menassa

DeVries

. Optimization methods applied to selecting support positions in fixture design. ASME J Eng Ind 1991; 113: 412–418.

Meyer

Liou

. Fixture analysis under dynamic machining. Int J Prod Res 1997; 35(5): 1471–1489.

Melkote

. Improved work piece location accuracy through fixture layout optimization. Int J Mach Tools Manuf 1999; 39: 871–883.

Roy

Liao

. Geometric reasoning for re-allocation of supporting and clamping positions in the automated fixture design system. IEEE Trans 1999; 31: 313–322.

Tao

Kumar

Nee

AYC

. A computational geometry approach to optimum clamping synthesis of machining fixtures. Int J Prod Res 1999; 37(15): 3495–3517.

Liao

. Flexible multi body dynamics based fixture work piece analysis model for fixturing stability. Int J Mach Tools Manuf 2000; 40: 343–362.

Melkote

. Optimal fixture design accounting for the effect of work piece dynamics. Int J Adv Manuf Technol 2001; 18: 701–707.

10.

Amaral

Rencis

Rong

. Development of a finite element analysis tool for fixture design integrity verification and optimization. Int J Adv Manuf Technol 2004; 21: 411–419.

11.

Tan

EYT

Kumar

Fuh

JYH

et al.

Modeling, analysis and verification of optimal fixturing design. IEEE Trans Automat Sci Eng 2004; 1(2): 121–132.

12.

Gelin JC and Ghouati O. An inverse method for determining viscoplastic properties of aluminium alloys. Journal of Materials Processing Technology 1994; 45(1): 435–440.

13.

Schenk O and Hillmann M. Optimal design of metal forming die surfaces with evolution strategies. Computers & Structures 2004; 82(20): 1695–1705.

14.

Farhang-Mehr A and Azarm S. Diversity assessment of Pareto optimal solution sets: An entropy approach. Proceedings of the World on Congress on 2002, pp. 723–728.

15.

Papalambros

Wilde

. Principles of optimal design, New York, USA: Cambridge University Press, 2000. ISBN 0-521-62727.

16.

Cao J, Shi MF, Stoughton TB, et al. The Numisheet 2005 Benchmark Study. In: Proceedings of NUMISHEET 2005, Detroit, MI, USA, 2005.

17.

Yingxue

Xiaoli

. Tool wear detection with fuzzy classification and wavelet fuzzy neural network. Int J Mach Tool Manuf 1999; 213: 1525–1538.

18.

Warren

. Manufacturing process modeling and optimization based on multi-layer perceptron network. ASME Trans J. Manuf Sci Eng 1998; 89: 109–119.

19.

Diffie

Hellman

. New directions in cryptography. IEEE Trans Inf Theory 1986; 14–15: 644–654.

20.

Goldberg

. Genetic Algorithms in search, optimization and machine learning, Reading, MA: Addison-Wesley, 1989.

21.

Deb

. An introduction to genetic algorithms. Sadhana J 1999; 24(4–5): 293–315.