Prediction of the fracture energy properties of concrete using COOA-RBF neural network

Evaluating the energy requirements for crack propagation in concrete structures has been a subject of considerable interest since applying fracture mechanics principles to concrete. Concrete fracture energy is important for safe structural design and failure behaviour modelling because it is quasi-brittle. The complex nonlinear behaviour of concrete during fracture has led to ongoing debates regarding fracture energy prediction using existing estimation techniques. Using the previous dataset, prediction approaches were developed to measure the preliminary (Gf) and total (GF) fracture energies of concrete utilising mechanical properties and mixed design elements. Two hundred sixty-four experimental recordings were gathered from an earlier study to construct and analyse ideas. This study combines the radial basis function neural network (RBFNN) with the Coot optimisation algorithm (COOA) and whale optimisation algorithm (WOA). The computation and analysis of Gf and GF used five performance measures, which show that both optimised COOA-RBFNN and WOA-RBFNN evaluations could execute superbly during the estimation mechanism. Therefore, even though the WOA-RBFNN approach has unique characteristics for simulating, the COOA-RBFNN analysis seems quite dependable for calculating. Gf and GF given the rationale and model processing simplicity.