文献类型：期刊文献

英文题名：Predicting the compressive strength of modified recycled aggregate concrete

作者：Yang, Cuina[1];Feng, Hongwei[1];Esmaeili-Falak, Mahzad[2]

第一作者：杨萃娜

通讯作者：Yang, CN[1]

机构：[1]Xinxiang Univ, Sch Civil Engn & Architecture, Xinxiang 453000, Henan, Peoples R China;[2]Islamic Azad Univ, Dept Civil Engn, North Tehran Branch, Tehran, Iran

第一机构：新乡学院土木工程与建筑学院

通讯机构：[1]corresponding author), Xinxiang Univ, Sch Civil Engn & Architecture, Xinxiang 453000, Henan, Peoples R China.|[1107114]新乡学院土木工程与建筑学院;[11071]新乡学院;

年份：0

外文期刊名：STRUCTURAL CONCRETE

收录：;EI(收录号：20220711643466);Scopus(收录号：2-s2.0-85124506614);WOS:【SCI-EXPANDED(收录号:WOS:000754021700001)】；

语种：英文

外文关键词：AI-based methods; compressive strength prediction; glass fiber; recycled aggregates concrete; silica fume

摘要：Reuse and recycling of construction wastes effectively prevent further destruction of the environment and nature due to the construction industry. One of the conventional methods is the reapplication of recycled aggregates (RAs) in concrete mix design and construction. Compressive strength (CS) is a considerable representation of the mechanical properties of recycled aggregate concrete (RAC). The present study is divided into two parts of experimental and predicting. In the laboratory studies phase, RA was used with 100% replacement. Due to the proven defects in RAC, glass fibers and silica fume (variables) have been used to compensate for these defects. Different mixing designs were used to construct concrete samples, and then the CS of each specimen was measured in the laboratory. Afterward, these data were used as training and testing in various conventional, ensembled and hybrid models as the tree-based learning algorithms, rules, Lazy-learning Algorithms, Functions, and Meta classifiers. Considering the applied performance statistical criteria (R2, root mean squared error, mean absolute error, and mean absolute percentage error), all models have provided excellent and acceptable results, which the precision of the multilayer perceptron single model and additive regression-random Forest hybrid model have the best agreement with measured values of CS of RAC.