Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Artificial Neural Network Based Prediction for FRP-Confined Concrete Under Cyclic Loading

Artificial Neural Network Based Prediction for FRP-Confined Concrete Under Cyclic Loading Artificial neural network (ANN)-based model is developed for predicting the stress and strain enhancement of FRP wrapped concrete. An experimental database is considered in the investigations, which includes confinement using carbon, glass and aramid FRP on concrete. The aspect ratio, form of FRP wrap, number of confining layers, unconfined power, confining pressure and FRP characteristics are used as input parameters. Performance of proposed ANN models was evaluated by considering two indices, coefficient of determination and measure of root mean square error. The hoop strain, which is a main influencing parameter in confining pressure and dilation of FRP-confined concrete, is also predicted using ANN, for which no model predictions are available as of today. The predictive accuracy of some of the currently available models from the literature has been assessed by estimating the stress and strain enhancement due to FRP confinement by evaluating the root mean square error. The findings from the investigations show that ANN-based models can accurately predict the response close to experimental response and competitive enough compared to already existing mathematical models. The results pave way toward opening up the scope of data-driven models for the design of FRP confinement for structures. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of The Institution of Engineers (India):Series A Springer Journals

Artificial Neural Network Based Prediction for FRP-Confined Concrete Under Cyclic Loading

Loading next page...
 
/lp/springer-journals/artificial-neural-network-based-prediction-for-frp-confined-concrete-yOBhHBYPmN
Publisher
Springer Journals
Copyright
Copyright © The Institution of Engineers (India) 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
ISSN
2250-2149
eISSN
2250-2157
DOI
10.1007/s40030-022-00678-6
Publisher site
See Article on Publisher Site

Abstract

Artificial neural network (ANN)-based model is developed for predicting the stress and strain enhancement of FRP wrapped concrete. An experimental database is considered in the investigations, which includes confinement using carbon, glass and aramid FRP on concrete. The aspect ratio, form of FRP wrap, number of confining layers, unconfined power, confining pressure and FRP characteristics are used as input parameters. Performance of proposed ANN models was evaluated by considering two indices, coefficient of determination and measure of root mean square error. The hoop strain, which is a main influencing parameter in confining pressure and dilation of FRP-confined concrete, is also predicted using ANN, for which no model predictions are available as of today. The predictive accuracy of some of the currently available models from the literature has been assessed by estimating the stress and strain enhancement due to FRP confinement by evaluating the root mean square error. The findings from the investigations show that ANN-based models can accurately predict the response close to experimental response and competitive enough compared to already existing mathematical models. The results pave way toward opening up the scope of data-driven models for the design of FRP confinement for structures.

Journal

Journal of The Institution of Engineers (India):Series ASpringer Journals

Published: Dec 1, 2022

Keywords: Fiber reinforced polymer; ANN; Predictive model; RMSE; Hoop strain

References