Concrete Slump Prediction Based on Hybrid Optimization XGBoost Algorithm

In this study, a hybrid optimization XGBoost model was used to predict the slump of concrete. This combines grid search and particle swarm (PSO) algorithm. The is determine maximum depth number trees in XGBoost, while optimizes other floating-point hyperparameter ranges improve predictive accuracy model. factors influencing concrete include water, cement, fine aggregate, coarse water reducer, which are represented by seven parameters. performs excellently both training testing sets, with coefficient determination (R2) exceeding 0.97. conclusion, study demonstrates that using algorithm can accurately concrete, significant importance for controlling optimizing production process.