Estimation of the Shear Strength of FRP Reinforced Concrete Beams Without Stirrups Using Machine Learning Algorithm

Predicting the shear strength of Fiber Reinforced Polymer (FRP) reinforced concrete beams is one of themost complex problems in structural engineering applications. The development of accurate and reliable predictive models is essential and could help to reduce costs. The development of an alternative approach is, therefore, crucial for structural engineers. In this study, a database with 307 shear test results is collected from reliable sources to develop an Artificial Neural Network (ANN) model to predict the shear strength of FRP reinforced concrete beams. Four training algorithms, namely Levenberg-Marquardt (ANN-LM), Quasi-Newton method (ANN-QN), Conjugate gradient (ANN-CG), and Gradient descent (ANNGD) is used to train the ANN models. The evaluation of the models is performed and compared on the training dataset (70% of data) and the testing dataset (the remaining 30% of data), using common statistical criteria. The results show that the ANN-OSS model has the best prediction performance with the correlation coefficient (R) of 0.961, root mean square error (RMSE) of 35.53 and mean absolute error (MAE) of 20.63. These results confirmed the ANN model's effectiveness as a robust algorithm for predicting the shear strength of FRP reinforced concrete beams without stirrups.