Predicting the compressive strength of advanced concrete structures by developed African vulture optimization algorithm-Elman neural networks

Abstract

ABSTRACT: Concrete plate structures’ compressive strength and natural frequency are connected by the mechanical characteristics of the material and structural dynamics. Concrete’s elastic modulus rises along with its compressive strength, making the structure stiffer. Since the natural frequency is proportional to the square root of the stiffness over the mass, the increased stiffness raises the natural frequency. In this work, the relationship between natural frequency and compressive strength in advanced concrete constructions reinforced with graphene oxide particles is examined. Also, the structure is under applied pressure. By using a trigonometric shear deformation plate theory, we hope to improve compressive strength prediction accuracy. Navier’s technique is used as the analytical solution process in the analysis. This study contributes to the design and assessment of more durable and effective structural systems by offering a reliable framework for estimating the compressive strength of reinforced concrete structures. This paper presents a novel method by combining Elman Neural Networks (ENNs) with the developed African Vulture Optimization Algorithm (DAVOA) to estimate the frequency of the structure. With the help of this integration, researchers and engineers can now more precisely estimate the compressive strength of sophisticated concrete structures, leading to the creation of stronger and more robust structural solutions.