The Compressive Strength Prediction for FRP-Confined Concrete in Circular Columns by Applying the Normalized AlexNet-ELM and the Advanced Red Fox Optimization Algorithm

Fiber Reinforced Polymers (FRP) can be widely utilized in civil engineering because of their helpful features like high corrosion resistance for aggressive surroundings and high strength to weight ratio. By providing a lateral confining pressure, the concrete compressive strength is increased. Giving an analytic model that can forecast the FRP strength is the purpose of this study. This model is according to the normalized AlexNet Extreme Learning Machine and the Advanced Red Fox Optimization Algorithm (AlexNet-ELM-ARFO). The AlexNet-ELM-ARFO algorithm's innovation includes a formulation of an analytic relation, which doesn't attend to the established effectiveness parameter that is in the models introduced in the literature. An extended empirical dataset is utilized for defining the suggested formulation's variables. The suggested model is applied to circular columns including continuous FRP. The predictions' validation is shown by parametric research and the precision is examined by an empirical against theoretic comparison. A supplementary comparison is demonstrated with consideration of the theoretic prediction gained from the given method and the formulations' results using significant design codes. Outcomes prove that the used method is adapted to the FRP-confined concrete design and ensures an improved precision in comparison with respect to the available competitors.