Premium
A new predictive model for the bond strength of FRP‐to‐concrete composite joints
Author(s) -
Abdellahi Majid,
Heidari Javad,
Bahmanpour Maryam
Publication year - 2014
Publication title -
structural concrete
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.912
H-Index - 34
eISSN - 1751-7648
pISSN - 1464-4177
DOI - 10.1002/suco.201300093
Subject(s) - fibre reinforced plastic , structural engineering , composite number , gene expression programming , compressive strength , materials science , bond strength , composite material , engineering , computer science , adhesive , layer (electronics) , machine learning
In this work, gene expression programming (GEP), as a new tool, has been used to predict the bond strength of fibre‐reinforced polymer‐to‐concrete composite joints as the performance symbol of this structure. Some 238 datasets were collected from the literature, divided into 192 and 46 sets at random and then trained and tested respectively by means of GEP. The parameters width of prism, concrete cylinder compressive strength, width of fibre‐reinforced polymer (FRP), thickness of FRP, modulus of elasticity of FRP and bond length were used as input parameters. Using these input parameters, the bond strength of FRP‐to‐concrete composite joints in different conditions was predicted in the GEP model. The training and testing results in the GEP model show that GEP is a powerful tool for predicting the bond strength values of the FRP‐to‐concrete composite joints in the range considered.