Predicting The Compressive Strength Of High-Performance Concrete Utilizing Radial Basis Function Model Integrating With Metaheuristic Algorithms

Ordinary concrete is well-documented in the construction of ordinary buildings, but this type of concrete cannot be used for special structures such as dams, silos, and skyscrapers, due to low compressive strength (CS), durability, and workability. The solution to this problem is to use high-performance concrete (HPC). To improve the mechanical properties has been added some additives, such as water-cement ratio, fly ash, and blast furnace slag. However, achieving a suitable mix design of HPC is complex, time, and energy-consuming. For this reason, the usage of machine learning (ML) makes it easier to obtain the acceptable mix design saving time and money. The artificial neural network (ANN) model is the subset of ML, which the experimental tasks can replace. One of these neural networks is the radial basis function (RBF), with one input layer, one or more hidden layers, and one output layer. In addition, RBF is combined with the Sine Cosine Algorithm (SCA) and the African Vulture Optimization Algorithm (AVOA) to obtain the desired results close to the experimental values. At the end of this article, it is seen that the SCA algorithm can combined better with the RBF model and achieve favorable and more satisfactory results with more accuracy and fewer errors.