Shokoohozaman Chamanzari - Department of Civil Engineering, University of Birjand, Birjand, Iran
Aliaskar Dorostkar - Department of Computer Engineering, University of Birjand, Birjand, Iran,
Abolfazl Yosefi - Department of Civil Engineering, University of Birjand, Birjand, Iran,
HamidReza Nasseri - Department of Civil Engineering, University of Birjand, Birjand, Iran,

Concrete structures play a pivotal role in the realm of civil engineering, with reinforcement techniques employed to amplify their robustness and resilience. The utilization of steel fibers and polymer fibers, such as FRP sheets, has displayed auspicious outcomes in enhancing the properties of concrete. Nonetheless, the evaluation and comparison of the performance between reinforced and unreinforced concrete necessitate meticulous sampling and experimental examinations. This is precisely where artificial intelligence algorithms come to the fore. Artificial intelligence, particularly artificial neural networks (ANN), bestows a potent instrument for precise calculations and prognostications in civil engineering. Through training ANN models with pertinent data, engineers can accurately gauge the ductility and durability of reinforced concrete structures. This paper delves into the implementation of diverse artificial intelligence algorithms and places particular emphasis on the application of ANN in estimating flexural strength. Ultimately, it underlines the merits of ANN models in terms of assimilating, forecasting, and adapting to evolving data and environments.

Reinforced concrete beams،Concrete structures،Gradient Boosting،Artificial Intelligence