0
Research Papers

Development of Evolutionary Method for Optimizing a Roll Forming Process of Aluminum Parts

[+] Author and Article Information
Hong Seok Park1

 School of Mechanical Engineering University of Ulsan 93 Daehak-ro, Nam-gu, Ulsan, South-Korea 680-749phosk@ulsan.ac.kr

Tran Viet Anh

 School of Mechanical Engineering University of Ulsan 93 Daehak-ro, Nam-gu, Ulsan, South-Korea 680-749vietanhntth@gmail.com

1

Corresponding author.

J. Manuf. Sci. Eng 134(2), 021012 (Apr 04, 2012) (12 pages) doi:10.1115/1.4005804 History: Received March 31, 2011; Revised December 07, 2011; Published March 30, 2012; Online April 04, 2012

This paper presents the development of the knowledge-based neural network (KBNN) and genetic algorithm (GA) in modeling and optimization of the roll forming (RF) process of aluminum parts. The idea of a KBNN using multifidelity finite element (FE) models was developed to model the mechanical behaviors of the aluminum sheet. Initially, the less costly but less accurate FE model was used to build the response surface functions for the knowledge path of the KBNN. After that, a small number of the more accurate but expensive finite element analysis (FEA) of the high fidelity FE model were utilized in a multilayer perceptron (MLP) neural network with the prior knowledge to produce the KBNN prediction results. Two powerful optimization algorithms, the Levenberg–Marquadrt (LM) and GA, were applied to train the KBNN. The trained KBNN was used to perform the parametric study for investigating the effects of process parameters on the part quality. After that, the optimization of the process parameters was carried out by employing the combination of the GA and KBNN. The optimization objective was minimizing the overall damage in the aluminum part while keeping the longitudinal strain and spring back angle less than allowable limits to prevent the existence of defects. The modeling and optimization results by using the KBNN and GA were compared with the results from other methods to prove the advantages of the developed one against others.

Copyright © 2012 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

The cross section of the U channel part in experiment

Grahic Jump Location
Figure 2

The stress-strain curve of the aluminum AW 7108 T6

Grahic Jump Location
Figure 3

The major process parameters in the RF process of aluminum parts

Grahic Jump Location
Figure 4

The simulation results of the U channel RF processes in case of aluminum AW 7108 T6 (a) and steel SUS 430 (b)

Grahic Jump Location
Figure 5

The distributions of longitudinal strains in the RF processes of U channel in case of aluminum and steel

Grahic Jump Location
Figure 6

The spring back angles in the RF processes in case of aluminum (a) and steel (b)

Grahic Jump Location
Figure 7

Flow chart of the KBNN approach for modeling RF process

Grahic Jump Location
Figure 9

The schematic description of the KBNN developed for the RF process of aluminum parts

Grahic Jump Location
Figure 10

The performances at the 15th epoch of some KBNN structures tested

Grahic Jump Location
Figure 11

The performances of the KBNN and standard MLP in training process

Grahic Jump Location
Figure 12

The training process of the KBNN by using the GA

Grahic Jump Location
Figure 13

The performances of the KBNN, MLP, and RSM in modeling the damage variable D

Grahic Jump Location
Figure 14

The performances of the KBNN, MLP, and RSM in modeling the maximum longitudinal strain MLS

Grahic Jump Location
Figure 15

The performances of the KBNN, MLP, and RSM in modeling the spring back angle α

Grahic Jump Location
Figure 16

The variations of D, MLS, and α with respect to the variation of d

Grahic Jump Location
Figure 17

The variations of D, MLS, and α with respect to the variation of ω

Grahic Jump Location
Figure 18

The variations of D, MLS, and α with respect to the variation of f

Grahic Jump Location
Figure 19

The variations of D, MLS, and α with respect to the variation of r

Grahic Jump Location
Figure 20

The optimization strategy employing the combination of the KBNN and GA for the RF process of aluminum parts

Grahic Jump Location
Figure 21

The confirmative simulation and experiment to verify the reliability of the optimization results

Grahic Jump Location
Figure 8

The low fidelity FE model (a) and high fidelity FE model (b)

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