Hybrid firefly-ANN model for shear strength estimation in SFRC beams

Determining the shear strength of steel fiber-reinforced concrete (SFRC) beams is a persistent challenge in structural engineering, especially when aiming to balance precision with practical applicability in real-world projects. Although numerous design codes and empirical equations are available, they often fall short in delivering both accuracy and simplicity. The present study proposes a novel hybrid machine learning model – FOA-ANN – which combines an artificial neural network (ANN) with the optimization power of the firefly algorithm (FOA). The model was trained and validated using a comprehensive experimental dataset of SFRC beams to derive a user-friendly closed-form equation for shear strength prediction. A high-accuracy FOA – ANN model to overcome the limitations of existing design codes in predicting the shear strength of SFRC beams developed, providing a more reliable and practical tool for structural design. Extensive comparisons were made between the FOA-ANN model and several widely accepted prediction methods to evaluate its performance. While conventional equations showed varying degrees of reliability, the FOA-ANN model achieved high accuracy with a more concise mathematical formulation. This integrated approach not only enhances predictive performance but also provides engineers with a practical and effective tool for assessing SFRC beam behavior during both design and retrofitting phases in civil infrastructure projects.