Mechanical property design of RTM composites using neural networks

Wei Qin*, Yu Sheng Zhang, Yu Li, Da Qing Lin, Mao Sheng Cao

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

A new method is presented for mechanical property design of carbon fiber braid/epoxy composite. Injection pressure, temperature and time are as input parameters and interlaminar shear strength and bend strength are as output parameters. BP neural network is used to build a model for the relationship between technology parameters and mechanical properties of composites. Based on this model, the relationship between injection pressure and mechanical properties of composites is studied when the injection temperature and time are defined, and the output regular of network is in agreement with experimental regular, which indicate that the model is reliable and can be used to design the mechanical properties of composites.

Original languageEnglish
Pages (from-to)439-441
Number of pages3
JournalCailiao Kexue yu Gongyi/Material Science and Technology
Volume14
Issue number4
Publication statusPublished - Aug 2006
Externally publishedYes

Keywords

  • Composites
  • Epoxy resin
  • Mechanical properties
  • Neural network
  • RTM

Fingerprint

Dive into the research topics of 'Mechanical property design of RTM composites using neural networks'. Together they form a unique fingerprint.

Cite this