RF Optimizer Model for Predicting Compressive Strength of Recycled Concrete

作     者：LIU Lin WANG Liuyan WANG Hui SUN Huayue 刘琳;王柳燕

作者机构：School of Civil Engineering and ArchitectureShenyang UniversityShenyang 110000China 

出 版 物：《Journal of Wuhan University of Technology(Materials Science)》 (武汉理工大学学报（材料科学英文版）)

年 卷 期：2025年第40卷第1期

页      面：215-223页

核心收录：

学科分类：08[工学] 081304[工学-建筑技术科学] 0805[工学-材料科学与工程（可授工学、理学学位）] 080502[工学-材料学] 0813[工学-建筑学] 

基　　金：Funded by China National Key Research and Development Program for Application and Verification of Typical Groundwater Contaminated Sites(No.2019YFC1804805) Shenyang Key Laboratory of Safety Evaluation and Disaster Prevention of Engineering Structures(No.S230184) the Funding Project of Northeast Geological S&T Innovation Center of China Geological Survey(No.QCJJ2023-39) 

主　　题：machine learning recycled concrete compressive strength 

摘      要：Traditional machine learning(ML)encounters the challenge of parameter adjustment when predicting the compressive strength of reclaimed *** address this issue,we introduce two optimized hybrid models:the Bayesian optimization model(B-RF)and the optimal model(Stacking model).These models are applied to a data set comprising 438 observations with five input variables,with the aim of predicting the compressive strength of reclaimed ***,we evaluate the performance of the optimized models in comparison to traditional machine learning models,such as support vector regression(SVR),decision tree(DT),and random forest(RF).The results reveal that the Stacking model exhibits superior predictive performance,with evaluation indices including R2=0.825,MAE=2.818 and MSE=14.265,surpassing the traditional ***,we also performed a characteristic importance analysis on the input variables,and we concluded that cement had the greatest influence on the compressive strength of reclaimed concrete,followed by ***,the Stacking model can be recommended as a compressive strength prediction tool to partially replace laboratory compressive strength testing,resulting in time and cost savings.