Language selection

Government of Canada / Gouvernement du Canada

Search

On-line prediction of final part dimensions in blow molding: a neural network computing approach

From National Research Council Canada

DOIResolve DOI: https://doi.org/10.1002/pen.760331102
AuthorSearch for: 1; Search for: 1
Affiliation
  1. National Research Council of Canada. NRC Industrial Materials Institute
FormatText, Article
Abstract
Control over final part thickness distributions in extrusion blow molding would be very useful in resin optimization. An on-line measurement is essential for process monitoring and control of the part dimensions. Excessive resin usage results in material waste and increased cycle times because of increased cooling requirements. An inadequate thickness results in decreased mechanical strength, especially in regions along the part where large blow ratios or complex geometries exist. Neural networks are investigated as a method for the on-line prediction of the final part distribution from the parison dimensions. The purpose of this work is to demonstrate the feasibility, for preliminary use, of neural networks for this application. The network inputs include the initial parison thickness and tempera-ture profiles, the bottle mold geometry and a rheological parameter representative of the material. Varying blow-up ratios are obtained from the bottle mold geome-try. The network accesses data from a pool of eighty data sets for the training sequence. The data sets are broadly distributed with regard to the operating conditions, so as to give the network a wide range of applicability. The simulations are performed on data sets not present in the access pool used for training.
Publication date
PublisherWiley
Society of Plastics Engineers
In
  • Polymer Engineering and Science 33, no. 11 (June 1993): 653–664.
LanguageEnglish
Peer reviewedYes
Export citationExport as RIS
Report a correctionReport a correction (opens in a new tab)
Record identifier00d7d0a9-6857-4ddf-a84b-43dd29c810b9
Record created2023-09-22
Record modified2023-09-22
Date modified: