Optimum tooling design for resin transfer molding with virtual manufacturing and artificial intelligence

Citation
J. Luo et al., Optimum tooling design for resin transfer molding with virtual manufacturing and artificial intelligence, COMPOS P A, 32(6), 2001, pp. 877-888
Citations number
17
Language
INGLESE
art.tipo
Article
Categorie Soggetti
Material Science & Engineering
Journal title
COMPOSITES PART A-APPLIED SCIENCE AND MANUFACTURING
ISSN journal
1359-835X → ACNP
Volume
32
Issue
6
Year of publication
2001
Pages
877 - 888
Database
ISI
SICI code
1359-835X(2001)32:6<877:OTDFRT>2.0.ZU;2-E
Abstract
Resin transfer molding (RTM) is a promising fabrication method for low to m edium volume, high-performance polymer composite structures. Yet there exis t several technical issues which impede a wide application base. One of the se issues is tooling design. In the RTM process, the arrangement of injecti on gates and vents of the mold has a significant impact on product quality and process efficiency. In this paper, a systematic approach for optimum de sign of RTM tooling is introduced. This approach is built upon an RTM virtu al manufacturing (simulation) model coupled with a neural network-genetic a lgorithm optimization procedure. The simulation model is employed to predic t resin flow patterns (i.e, potential quality problems) and processing effi ciency (mold filling time). With the simulation results, a neural network i s trained to create a rapid RTM process model. Genetic algorithms are appli ed to this rapid RTM process model to search for the optimum solution to RT M process design. This tooling design scheme enables the engineer to determ ine the optimum locations of injection gates and vents for the best process ing performance, i.e. short filling time and high quality level (minimum de fects). The approach is illustrated with an example. (C) 2001 Elsevier Scie nce Ltd. All rights reserved.