Shear strength prediction of concrete beams reinforced with FRP bars using novel hybrid BR-ANN model

Shear strength is a very important parameter in designing of reinforced concrete beams or concrete beams reinforced with fiber-reinforced polymer (FRP) bars. So far, numerous studies and design codes have proposed empirical-based formulas for predicting the shear strength of FRP-concrete beams. However, a difference exists between the proposed formulas and experimental results. This study predicts the shear strength of FRP-concrete beams using the novel hybrid BR-ANN model, which integrates artificial neural network (ANN) and Bayesian regularization (BR). For that, a comprehensive database consisting of 303 experimental results is compiled for developing the BR-ANN models. The performance results of BR-ANN are compared with those of 15 existing empirical formulas, which were proposed in typical design codes and well-known published studies. The predicted outputs are evaluated utilizing indicators, which are goodness of fit (R2), root mean squared error (RMSE), and mean value of the ratio Vpredict/ Vtest . The results reveal that the BR-ANN model outperforms other empirical formulas with a very high R2 (0.987), very small RMSE (7.3 kN). In addition, the mean value of the ratio Vpredict/ Vtest is equal to unity. Moreover, effects of input variables on the shear strength are evaluated. Finally, a practical design tool is developed to apply the BR-ANN model in calculating the shear strength of FRP-concrete beams. © 2023, The Author(s), under exclusive licence to Springer Nature Switzerland AG.