Article: Prediction of the fracture energy properties of concrete using COOA-RBF neural network Journal: International Journal of Critical Infrastructures (IJCIS) 2025 Vol.21 No.2 pp.187 - 208 Abstract: 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. Inderscience Publishers - linking academia, business and industry through research

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

Authors: Yongcun Zhang; Zhe Bai

Addresses: School of Civil and Transportation Engineering, Henan University of Urban Construction, Pingdingshan 467036, Henan, China ' School of Civil and Transportation Engineering, Henan University of Urban Construction, Pingdingshan 467036, Henan, China; School of Civil Engineering, Chongqing Vocational Institute of Engineering, Chongqing 402260, China

Abstract: 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 (G_f) and total (G_F) 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 G_f and G_F 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. G_f and G_F given the rationale and model processing simplicity.

Keywords: concrete; fracture energy; neural network; estimation; radial basis function; coot optimisation algorithm; whale optimisation algorithm; WOA.

DOI: 10.1504/IJCIS.2025.145192

International Journal of Critical Infrastructures, 2025 Vol.21 No.2, pp.187 - 208

Received: 19 Jul 2023
Accepted: 26 Sep 2023
Published online: 25 Mar 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

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

Keep up-to-date