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.

References

1.
Yu
,
Z.
,
Lin
,
Z.
, and
Zhao
,
Y.
, 2007, “
Evaluation of Fracture Limit in Automotive Aluminum Alloy Sheet Forming
,”
Mater. Des.
,
28
, pp.
203
207
.
2.
Farzin
,
M.
,
Tehrania
,
M.S.
, and
Shamelia
,
E.
, 2002, “
Determination of Buckling Limit of Strain in Cold Roll Forming by the Finite Element Analysis
,”
J. Mater. Process. Technol.
,
125–126
, pp.
626
632
.
3.
Tehrani
,
M. S.
,
Hartley
,
P.
,
Naeini
,
H. M.
, and
Khademizadeh
,
H.
, 2006, “
Localized Edge Buckling in Cold Roll-Forming of Symmetric Channel Section
,”
Thin-Walled Struct.
,
44
, pp.
184
196
.
4.
Panthi
,
S. K.
,
Ramakrishnan
,
N. M.
,
Ahmed
,
M.
,
Singh
,
S. S.
, and
Goel
,
M. D.
, 2010, “
Finite Element Analysis of Sheet Metal Bending Process to Predict the Spring Back
,”
Mater. Des.
,
31
, pp.
657
662
.
5.
Zeng
,
G.
,
Li
,
S. H.
,
Yu
,
Z. Q.
, and
Lai
,
X. M.
, 2008, “
Optimization Design of Roll Profiles for Cold Roll Forming Based on Response Surface Method
,”
Mater. Des.
,
30
, pp.
1930
1938
.
6.
Park
,
H. S.
, and
Anh
T. V.
, “
Optimization of Process Parameters for Minimizing the Spring Back Angle in Roll Forming Process
,”
Kor. Soc. Mech. Eng. Conf.
,
2
, pp.
105
107
.
7.
Paralikas
,
J.
,
Salonitis
,
K.
, and
Chryssolouris
,
G.
, 2009, “
Optimization of Roll Forming Process Parameters—A Semi-Empirical Approach
,”
Int. J. Adv. Manuf. Technol.
,
47
, pp.
1041
1052
.
8.
Shahani
,
A. R.
,
Setayeshi
,
S.
,
Nodamaie
,
S. A.
,
Asadi
,
M. A.
, and
Rezaie
,
S.
, 2009, “
Prediction of Influence Parameters on the Hot Rolling Process Using Finite Element Method and Neural Network
,”
J. Mater. Process. Technol.
,
209
, pp.
1920
1935
.
9.
Xiong
,
Y. S.
, and
Withers
,
P. J.
, 2005, “
An Evaluation of Recurrent Neural Network Modelling for the Prediction of Damage Evolution During Forming
,”
J. Mater. Process. Technol.
,
170
, pp.
551
562
.
10.
Hooputra
,
H.
,
Gese
,
H.
,
Dell
,
H.
, and
Werner
,
H.
, 2004, “
A Comprehensive Failure Model for Crashworthiness Simulation of Aluminum Extrusions
,”
Int. J. Crashworthiness
,
9
(
5
), pp.
449
464
.
11.
Towell
,
G. G.
, and
Shavlik
,
J. W.
, 1994, “
Knowledge-Based Artificial Neural Networks
,”
Artif. Intell.
,
70
, pp.
119
165
.
12.
Wang
,
F.
, and
Zhang
,
Q.
, 1997, “
Knowledge-Based Neural Models for Microwave Design
,”
IEEE Trans. Microwave Theory Tech.
,
45
(
12
), pp.
2333
2343
.
13.
Leary
,
S. J.
,
Bhaskar
,
A.
, and
Keane
,
A. J.
, 2003, “
A Knowledge-Based Approach To Response Surface Modelling in Multifidelity Optimization
,”
J. Global Optim.
,
26
, pp.
297
319
.
14.
Abdelbar
,
A.
, and
Tagliarini
,
G.
, 1996, “
Honest: A New High Order Feedforward Neural Networks
,”
Proc. IEEE Int. Conf. Neural Netw.
,
2
, pp.
1257
1262
.
15.
Morovvati
,
M. R.
,
Mollaei-Dariani
,
B.
, and
Haddadzadeh
,
M.
, 2010, “
Initial Blank Optimization in Multilayer Deep Drawing Process Using GONNS
,”
ASME J. Manuf. Sci. Eng.
,
132
,
061014
.
16.
Hagan
,
M. T.
, and
Menhaj
,
M. B.
, 1994, “
Training Feedforward Networks With the Marquardt Algorithm
,”
IEEE Trans. Neural Netw.
,
5
(
6
), pp.
989
993
.
You do not currently have access to this content.