Modeling parison formation in extrusion blow molding by neural networks

A series of experiments were carried out on the parison formation stage in extrusion blow molding of high-density polyethylene (HDPE) under different die tem- perature, extrusion flow rate, and parison length. The drop time of parison when it reached a given length and its swells, including the diameter, thickness, and area swells, were determined by analyzing its video images. Two back- propagation (BP) artificial neural network models, one for predicting the length evolution of parison with its drop time, the other predicting the swells along the parison, were con- structed based on the experimental data. Some modifica- tions to the original BP algorithm were carried out to speed it up. The comparison of the predicted parison swells using the trained BP network models with the experimentally determined ones showed quite a good agreement between the two. The sum of squared error for the predictions is within 0.001. The prediction of the parison diameter and thickness distributions can be made online at any parison length or any parison drop time within a given range using the trained models. The predicted parison swells were ana- lyzed. © 2005 Wiley Periodicals, Inc. J Appl Polym Sci 96: 2230 -2239, 2005

[1]  R. W. Diraddo,et al.  Modeling of membrane inflation in blow molding: Neural network prediction of initial dimensions from final part specifications , 1993 .

[2]  Hong Huang,et al.  Prediction of parison swell in plastics extrusion blow molding using a neural network method , 2002 .

[3]  S. Eggen,et al.  On-Line measurement of parison geometry during blow molding: Parison swelling for three high-density polyethylenes with different molecular weights and molecular weight distributions , 1996 .

[4]  K. Funatsu,et al.  Numerical simulations of annular extrudate swell of polymer melts , 1997 .

[5]  K. Koyama,et al.  Overall numerical simulation of extrusion blow molding process , 2000 .

[6]  K. Funatsu,et al.  Numerical simulation of blow molding—prediction of parison diameter and thickness distributions in the parison formation process , 1996 .

[7]  G. Ajroldi.  Determination of rheological parameters from parison extrusion experiments , 1978 .

[8]  K. Funatsu,et al.  High weissenberg number simulation of an annular extrudate swell using the differential type constitutive equation , 1998 .

[9]  E. Mitsoulis,et al.  Memory Phenomena in Extrudate Swell Simulations for Annular Dies , 1989 .

[10]  M. E. Ryan,et al.  Effect of die geometry and flow characteristics on viscoelastic annular swell , 1995 .

[11]  K. Funatsu,et al.  Numerical simulation of blow molding-viscoelastic flow analysis of parison formation , 1995 .

[12]  Colin MacBeth,et al.  Effects of Learning Parameters on Learning Procedure and Performance of a BPNN , 1997, Neural Networks.

[13]  Hong Huang,et al.  HDPE/PA6 blends: parison formation behaviour in extrusion blow molding , 2003 .

[14]  Robert DiRaddo,et al.  Integrated numerical modeling of the blow molding process , 1999 .

[15]  K. Funatsu,et al.  Numerical simulations of annular extrudate swell using various types of viscoelastic models , 1999 .

[16]  E. Mitsoulis.  Extrudate swell of Newtonian fluids from annular dies , 1986 .

[17]  Dilip Sarkar,et al.  Methods to speed up error back-propagation learning algorithm , 1995, CSUR.

[18]  Sagar V. Kamarthi,et al.  Accelerating neural network training using weight extrapolations , 1999, Neural Networks.

[19]  S. Tanoue,et al.  Effect of die gap width on annular extrudates by the annular extrudate swell simulation in steady-states , 1999 .