Prediction of ultimate strength of FRP-confined predamaged concrete using backward multiple regression motivated soft computing methods

Confining structurally deficient concrete columns with externally bonded fiber-reinforced polymer (FRP) has been widely accepted as an effective technology for strengthening the ductility and strength of columns. However, prediction models damaged afterward repaired based on soft computing methods are not available planning maintenance structures. Therefore, this paper adopted two – artificial neural network (ANN) Gaussian process regression (GPR) to analyze observations obtained from 103 datasets concentrically loaded FRP-confined predamaged concrete. The only consider statistically significant variables ultimate multivariate analysis corner radius ratio, FRP thickness, strength, damage degree. coefficient determination developed is greater than 98% there a relatively low error between measured predicted values. results current study highlight merit using in given their extraordinary ability comprehend multidimensional phenomena structures ease high predictivity over existing empirical models.