Neural Network for Performance of Glass Fibre Reinforced Polymer Plated RC Beams
N. Pannirselvam, P.N. Raghunath and K. Suguna
DOI : 10.3844/ajeassp.2008.82.88
American Journal of Engineering and Applied Sciences
Volume 1, Issue 1
Prediction of the properties other than moment carrying capacity of GFRP plated RC beams does not have any straight forward mechanism. This study presents a General Regression Neural Network (GRNN) based computational model for predicting the yield load, ultimate load, yield deflection, ultimate deflection, deflection ductility and energy ductility of such beams. Results from experimental investigations carried out on nine RC beams with steel ratios of 0.419, 0.603 and 0.905% plated 0, 3 and 5 mm thick GFRP laminates were used for generating the GRNN model. The predictions of the model closely agreed with experimental results.
© 2008 N. Pannirselvam, P.N. Raghunath and K. Suguna. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.