0
Research Papers

Initial Blank Optimization in Multilayer Deep Drawing Process Using GONNS

[+] Author and Article Information
M. R. Morovvati1

Department of Mechanical Engineering, Amirkabir University of Technology, P.O. Box 4413-15875, Tehran, Iranreza.morovvati@aut.ac.ir

B. Mollaei-Dariani, M. Haddadzadeh

Department of Mechanical Engineering, Amirkabir University of Technology, P.O. Box 4413-15875, Tehran, Iran

1

Corresponding author.

J. Manuf. Sci. Eng 132(6), 061014 (Dec 20, 2010) (10 pages) doi:10.1115/1.4003121 History: Received December 10, 2009; Revised November 11, 2010; Published December 20, 2010; Online December 20, 2010

The initial blank in the deep drawing process has a simple shape. After drawing, its perimeter shape becomes very complex. If the initial blank shape is designed in such a way that it is formed into the desired shape after the drawing process, not only does it reduces the time of trimming process but it also decreases the raw material needed substantially. In this paper, the genetically optimized neural network system (GONNS) is proposed as a tool to predict the initial blank shape for the desired final shape. Artificial neural networks (ANNs) represent the final blank shape after a training process and genetic algorithms find the optimum initial blank. The finite element method is employed for simulating the multilayer plate deep drawing process to provide training data for ANN. The GONNS results were verified through experiment in which the error was found to be about 0.2 mm. At last, variations of deformation force, thickness distribution, and thickness strain distribution were investigated using optimum blank. The results show 12% reduction in deformation force and more uniform thickness distribution as well as more consistent thickness strain distribution in the optimum blank shape.

Copyright © 2010 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 6

(a) Maximum punch force and increasing mesh refinement and (b) maximum blank holder and increasing mesh refinement

Grahic Jump Location
Figure 15

Symmetry lines of oil pan in (a) top view and (b) perspective view

Grahic Jump Location
Figure 16

The optimized blank with GONNS for oil pan

Grahic Jump Location
Figure 17

FEM result of oil pan with optimized blank

Grahic Jump Location
Figure 14

Comparison of thickness distribution in two deformed layer parts: (a) up layer, SUS 304 and (b) bottom layer, Al 1100

Grahic Jump Location
Figure 1

Feed-forward neural network mode

Grahic Jump Location
Figure 2

Sum-squared network error for epochs

Grahic Jump Location
Figure 3

(a) Flowchart of proposed model, (b) input and output data for ANN, and (c) output of GA (optimized initial blank shape)

Grahic Jump Location
Figure 4

Prototype of deep drawing die

Grahic Jump Location
Figure 5

Section of finite element model

Grahic Jump Location
Figure 7

Experimental and FEM (plastic strain diagram) results for square blank: (a) experimental and (b) FEM

Grahic Jump Location
Figure 8

Comparison of thickness distribution between EXP and FEM: (a) up layer, SUS 304 and (b) bottom layer, Al 1100

Grahic Jump Location
Figure 9

Experimental result for optimum blank modification with trial and error method: (a) blank shape and (b) deformed shape

Grahic Jump Location
Figure 10

(a) Optimum initial blank modification with GONNS and (b) FEM result (plastic strain diagram) for deformed blank shape

Grahic Jump Location
Figure 11

Experimental result for optimum blank modification with GONNS: (a) deformed blank and (b) blank shape

Grahic Jump Location
Figure 12

Deformation force for two different initial blank (square and optimum blank)

Grahic Jump Location
Figure 13

Comparison of thickness distribution in two deformed layer parts: (a) up layer, stainless steel and (b) bottom layer, aluminum

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In