0
TECHNICAL PAPERS

Finite Element and Neural Network Modeling of Viscoelastic Annular Extrusion

[+] Author and Article Information
Han-Xiong Huang

Center for Polymer Processing Equipment and Intellectualization, College of Industrial Equipment and Control Engineering, South China University of Technology, Guangzhou, P.R.C.mmhuang@scut.edu.cn

Yan-Sheng Miao

Center for Polymer Processing Equipment and Intellectualization, College of Industrial Equipment and Control Engineering, South China University of Technology, Guangzhou, P.R.C.

J. Fluids Eng 129(2), 218-225 (Jul 25, 2006) (8 pages) doi:10.1115/1.2409357 History: Received September 06, 2005; Revised July 25, 2006

Plastics blow molding has grown rapidly for the past couple of decades. Annular parison extrusion is a critical stage in extrusion blow molding. In this work, numerical simulations on the parison extrusion were performed using finite element (FE) method and the Kaye-Bernstein-Kearsley-Zapas type constitutive equation. A total of 100 simulations was carried out by changing the extrusion die inclination angle, die gap, and parison length. Then a backpropagation artificial neural network (ANN) was proposed as a tool for modeling the parison extrusion using the numerical simulation results. The network architecture determination and the training process of the ANN model were discussed. The predictive ability of the ANN model was examined through several sets of FE simulation results different from those utilized in the training stage. The effects of the die inclination angle, die gap, and parison length on the parison swells can be predicted using the ANN model. The results showed that the die gap has a smaller effect on the diameter swell but a greater effect on the thickness swell. Both diameter and thickness swells increase as the die inclination angle increases. The hybrid method combining the FE and ANN can shorten the time for the predictions drastically and help search out the processing conditions and/or die geometric parameters to obtain optimal parison thickness distributions.

FIGURES IN THIS ARTICLE
<>
Copyright © 2007 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

Schematic of extrusion die of parison and its swells

Grahic Jump Location
Figure 2

Parison extrusion die geometry used in the simulations. All dimensions are in mm. (a) Die 1—Convergent die with a die inclination angle (Ø) of 33.7deg; (b) Die 2—Convergent die with Ø of 23.4deg; (c) Die 3—Straight die; (d) Die 4—Divergent die with Ø of −14.9deg, and (e) Die 5—Divergent die with Ø of −23.4deg.

Grahic Jump Location
Figure 3

Schematic of BP neural network architecture used in this work

Grahic Jump Location
Figure 4

Simulated profiles of the parison with a length 250mm for (a) die 1, (b) die 3, and (c) die 5. The die gap is 2mm.

Grahic Jump Location
Figure 5

Simulated and experimentally determined parison diameter swells extruded from (a) die 1, (b) die 3, and (c) die 5. The die gap is 2mm.

Grahic Jump Location
Figure 6

Simulated (a) diameter and (b) thickness swells of the parison with a length of 50, 150, and 250mm for (1) die 1, (2) die 2, (3) die 3, (4) die 4, and (5) die 5. The die gap is 2mm.

Grahic Jump Location
Figure 7

SSE for the training patterns during the training of the network for (a) diameter and (b) thickness swells

Grahic Jump Location
Figure 8

Comparison of predicted (a) diameter and (b) thickness swells of parison from the network model with numerical simulation results. The die gap is 2mm.

Grahic Jump Location
Figure 9

Effect of the die gap on the ultimate (a) diameter and (b) thickness swells predicted from the network model for the die inclination angle of (1) 24, (2) 16, (3) 8, (4) 0, and (5) −8deg

Grahic Jump Location
Figure 10

Effect of the die inclination angle on the ultimate (a) diameter and (b) thickness swells predicted from the network model for die gap (mm) of (1) 2, (2) 3, and (3) 4

Grahic Jump Location
Figure 11

Predicted parison (a) diameter and (b) thickness swells for different lengths from the network model at the die gap (mm) of (1) 2, (2) 3, and (3) 4. The die inclination angle is 20deg.

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