Enhancing machine learning models with metaheuristic Optimization techniques for accurate prediction of PSC in FRP-reinforced concrete slabs

Abstract

The present research examines the utilization of metaheuristic optimization algorithms to enhance the predictive accuracy of the Extreme Gradient Boosting (XGBoost) machine learning model in predicting the capacity for punching shear of Fiber Reinforced Polymer (FRP) reinforced concrete slabs in the absence of shear reinforcement. A database including 610 experimental results is constructed, and the efficiency of twenty metaheuristic algorithms is assessed in optimizing the hyperparameters of the XGBoost model. The enhanced models undergo evaluation and comparison with existing prediction algorithms, showcasing their better accuracy. The study reveals that the DE, MVO, EOA, and VCS algorithms yield the highest precision among the investigated optimization techniques out of which VCS model performed better. Furthermore, the significance of input parameters on the punching shear capacity is analyzed by implementing the Shapley Additive Explanation (SHAP) method. The findings emphasize the potential of metaheuristic optimization in enhancing the estimating abilities of machine learning models for complex engineering problems and provide valuable insights into the key factors influencing the punching shear strength of concrete slabs reinforced with FRP.