硅酸盐通报2025，Vol.44Issue(9)：3178-3187,10.DOI:10.16552/j.cnki.issn1001-1625.2025.0079
基于CatBoost优化算法的自密实混凝土工作性预测
Workability Prediction of Self-Compacting Concrete Based on CatBoost Optimization Algorithm
摘要
Abstract
Aiming at the problem that improper control of self-compacting concrete workability can easily lead to defects in concrete structure,this paper presents a method of predicting self-compacting concrete workability based on CatBoost optimization algorithm.First of all,a dataset consisting of 313 sets of data was established through experiment.Subsequently,a predictive model for self-compacting concrete workability was established based on the CatBoost algorithm,and the optimal model hyperparameters were determined using the Optuna automatic hyperparameter optimization framework.Finally,the input parameters of the model were analyzed.The results show that,compared with the dataset without the inclusion of paste test data,the dataset established in this study can effectively improve the prediction accuracy of self-compacting concrete workability.The paste test data exhibits strong correlation and importance in the prediction process.The developed model can accurately predict slump flow and V-shaped funnel time,indicating that the model has good generalization ability and can provide a reference for the design and application of self-compacting concrete.关键词
自密实混凝土/净浆阈值理论/CatBoost算法/Optuna框架/敏感性分析/工作性预测Key words
self-compacting concrete/paste threshold theory/CatBoost algorithm/Optuna framework/sensitivity analysis/workability prediction分类
建筑与水利引用本文复制引用
梁其旻,王喆,梅英杰,孙奥,李鹏飞..基于CatBoost优化算法的自密实混凝土工作性预测[J].硅酸盐通报,2025,44(9):3178-3187,10.基金项目
国家自然科学基金(52379115) （52379115）
重庆市自然科学基金(CSTB2022NSCQ-MSX0509) （CSTB2022NSCQ-MSX0509）
