基于RF算法的混凝土工作性能预测方法研究  

Research on Concrete Workability Prediction Method Based on RF Algorithm

作　　者：苏强 胡以婵 SU Qiang;HU Yi-chan(Guangxi Road and Bridge Engineering Group Co.,Ltd.,Nanning 530011,China)

机构地区：[1]广西路桥工程集团有限公司,南宁530011

出　　处：《价值工程》2025年第12期43-45,共3页Value Engineering

基　　金：中央引导地方科技发展资金项目(20221229);广西重点研发计划项目(桂科AB23026126);交通运输行业重点科技项目(2121MSI026)。

摘　　要：当前获取混凝土塌落度的方法主要依靠试验的方法,造成人力、财力及时间成本的浪费。本文提出一种基于RF算法的混凝土工作性能预测方法。首先,收集62组混凝土配合比数据;其次,采用相关系数法分析输入变量的相关性,最后,通过模型训练与超参数优化,建立基于RF算法的混凝土塌落度预测模型并开展模型的可解释分析。研究结果表明:该模型在预测精度和泛化性能上表现较好,具有较高的合理性与可靠度,研究结果为进一步提高混凝土塌落度的预测精度提供参考。The current method of obtaining concrete slump mainly relies on experimental methods,resulting in waste of manpower,financial resources,and time costs.This article proposes a concrete workability prediction method based on RF algorithm.Firstly,62 sets of concrete mix ratio data are collected.Secondly,the correlation coefficient method is used to analyze the correlation of input variables.Finally,through model training and hyperparameter optimization,a concrete slump prediction model based on RF algorithm is established and interpretable analysis of the model is carried out.The research results show that the model performs well in prediction accuracy and generalization performance,with high rationality and reliability.The research results provide reference for further improving the prediction accuracy of concrete slump.

关 键 词：混凝土 塌落度预测模型 RF算法 相关性分析 

分 类 号：TU528[建筑科学—建筑技术科学]