Predicting the shear strength of concrete beam through ANFIS-GA-PSO hybrid modeling

In this study, we developed an ANFIS-GA-PSO hybrid model for predicting the shear strength of concrete beams. Predicting the shear strength of concrete beams before construction is crucial in evaluating the structure's ability to withstand external forces such as floods and earthquakes. Building robust structures is critical in geotechnical engineering to guarantee that buildings can withstand external stresses. Shear strength is affected by the horizontal reinforcement yield strength, the ratio of shear span to concrete compressive strength, the effective depth, the depth-to-width ratio, and so on. In this study, soft computing (SC) algorithms, such as adaptive neuro-fuzzy inference systems (ANFIS), and genetic algorithms (GA) as the hybrid model were used with an extreme learning machine (ELM) to predict preliminary the analysis time. The outcomes were compared using the regression indices. The outcomes were compared using the regression indices. Comparing the results of all models, the RMSE and r of ANFIS-GA are 0.546, and 0.912, respectively. This is 0.888 and 0.833 for ELM. It was discovered that the generalized artificial intelligence model hybridized with GA-ANFIS could provide higher accurate assessment of the shear behavior of concrete beams than ELM Additionally, ELM displayed the fastest training performance, training the neural network in only seconds. Consequently, the results identify the essential elements that determine the shear strength of reinforced concrete beams with or without transverse reinforcement.