A GMDH model and parametric investigation of geopolymeric recycled concrete FRP-spiral-confined members

Abstract

For the sustainability of the environment, minimization of the carbon dioxide (CO2) emissions from the production of cement and resolving the issues related to the dumping of construction and demolition waste have become the most important measures. Furthermore, deep learning and numerical models have been required for the accurate predictions of the axial structural efficiency of glass fiber reinforced polymer (GFRP) reinforced geopolymeric recycled aggregate concrete (GRC) columns with synthetic fibers (GGRC columns). The present study investigated the behavior of novel GGRC columns under concentric and eccentric loads. A set of 9 circular spirals confined concrete columns (300 mm x 1200 mm) was produced. A new three-dimensional (3-D) finite element model (FEM) for capturing the mechanical efficacy of GGRC columns was put forward. A parametric study was carried out using the projected FEM to examine the impact of reinforcement of longitudinal FRP rebars (ρl), compression stress of concrete (fco′), the diameter of GGRC columns (D), Young’s modulus of FRP rebars (Ef), the height of GGRC members (H), and the ultimate tensile stress of FRP rebars (fy). The results indicated that the GGRC members presented better structural efficiency in terms of axial stress and ductility under concentric and eccentric loads. The increment in axial stress for GGRC concentric members was noticed to be 9% at a reduction of spiral spacing from 100 mm to 50 mm. The suggested FEM portrayed 1.66% and 9.13% divergence of results for axial stress and relative axial strain of the samples, correspondingly. An artificial neural network (ANN) model was projected using the Group Method of Data Handling (GMDH) based on the previous experimental database for predicting the stress of GGRC members. The advised GMDH model performed well over the dataset by involving the axial contribution of GFRP bars and the confinement efficiency of spirals and reported the highest accuracy with MAE = 195.67, RMSE = 255.41, and R2 = 0.94 as compared with the previous models.