The Prediction of Maximum Failure Loads of Two Serial Pinned/Bolted Composite Joints with ANN

Komur M. A., Sen F., Sayman O.

JOURNAL OF ADVANCED MATERIALS, vol.43, no.1, pp.90-103, 2011 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 43 Issue: 1
  • Publication Date: 2011
  • Journal Name: JOURNAL OF ADVANCED MATERIALS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.90-103
  • Dokuz Eylül University Affiliated: Yes

Abstract

The scope of this study is to examine the development of an artificial neural network (ANN) method for the prediction of maximum failure loads of two serial pinned/bolted E-glass reinforced epoxy composite joints. The experimental data provided from the previous study with different geometrical parameters without preload moments and various applied preload moments were used for developing the ANN model. Comparisons of ANN results with desired values pointed out that there is an excellent agreement between input and output variables of the experimental data. Consequently, ANN was showed to be a suitable powerful tool for the prediction of maximum failure loads of two serial pinned/bolted composite joints.