Buy article PDF
The purchased file will be sent to you
via email after the payment is completed.
US$ 35
|
Smart Structures and Systems Volume 2, Number 1, January 2006 , pages 81-100 DOI: https://doi.org/10.12989/sss.2006.2.1.081 |
|
|
|
Evaluation of shear capacity of FRP reinforced concrete beams using artificial neural networks |
||
M. Nehdi, H. El Chabib and A. Said
|
||
| Abstract | ||
| To calculate the shear capacity of concrete beams reinforced with fibre-reinforced polymer (FRP), current shear design provisions use slightly modified versions of existing semi-empirical shear design equations that were primarily derived from experimental data generated on concrete beams having steel reinforcement. However, FRP materials have different mechanical properties and mode of failure than steel, and extending existing shear design equations for steel reinforced beams to cover concrete beams reinforced with FRP is questionable. This paper investigates the feasibility of using artificial neural networks (ANNs) to estimate the nominal shear capacity, Vn of concrete beams reinforced with FRP bars. Experimental data on 150 FRP-reinforced beams were retrieved from published literature. The resulting database was used to evaluate the validity of several existing shear design methods for FRP reinforced beams, namely the ACI 440-03, CSA S806-02, JSCE-97, and ISIS Canada-01. The database was also used to develop an ANN model to predict the shear capacity of FRP reinforced concrete beams. Results show that current guidelines are either inadequate or very conservative in estimating the shear strength of FRP reinforced concrete beams. Based on ANN predictions, modified equations are proposed for the shear design of FRP reinforced concrete beams and proved to be more accurate than existing equations. | ||
| Key Words | ||
| neural networks; fibre-reinforced polymer; shear strength; RC beams. | ||
| Address | ||
| Department of Civil and Environmental Engineering, The University of Western Ontario, London, Ontario, Canada N6A 5B9 | ||