Prediction of compressive strength of glass powder concrete based on artificial intelligence

被引:14
作者
Miao, Xu [1 ]
Chen, Bingcheng [1 ]
Zhao, Yuxi [1 ]
机构
[1] Zhejiang Univ, Inst Struct Engn, Hangzhou 310058, Zhejiang, Peoples R China
来源
JOURNAL OF BUILDING ENGINEERING | 2024年 / 91卷
基金
中国国家自然科学基金;
关键词
Compressive strength; Machine learning; Glass powder concrete; Correlation analysis; SELF-COMPACTING CONCRETE; WASTE GLASS; RECYCLED AGGREGATE; MECHANICAL-PROPERTIES; DURABILITY PROPERTIES; PARTIAL REPLACEMENT; CEMENT REPLACEMENT; FRIENDLY CONCRETE; FINE AGGREGATE; BEHAVIOR;
D O I
10.1016/j.jobe.2024.109377
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
The investigation of glass powder concrete (GPC) is motivated by the imperative to alleviate the pronounced environmental impact associated with conventional concrete construction and untreated waste glass. Compressive strength (CS) is a crucial criterion for assessing concrete quality. Traditionally, determining compressive strength relies on resource-intensive compression tests. This study addresses these challenges by evaluating GPC's compressive strength using fundamental and hybrid machine learning models. The study employed four machine learning models: Backpropagation Neural Network (BPNN), Extreme Gradient Boosting (XGB), Support Vector Regression (SVR), and Random Forest Regression (RFR). Additionally, four hybrid models (SSABPNN, SSA-XGB, SSA-SVR, SSA-RFR) were devised using the Sparrow Search Algorithm (SSA) to forecast compressive strength. Input variables included cement content, moisture content, sand content, coarse aggregate content, glass powder (GP) content, and curing age. The study reveals that optimized models generally outperform baseline models in predicting accuracy. Specifically, SSA-XGB demonstrated the highest accuracy, with R2 = 0.9645 and RMSE = 3.0640 MPa. Feature importance analysis highlights cement content and curing age as the most influential variables affecting GPC. Two-dimensional partial dependence plots (PDP) elucidate the interrelationship between GP, curing age, and cement content, confirming that, due to the volcanic ash effect and increased alkalinity, GP makes a more substantial contribution to strength. In summary, this study provides systematic recommendations for forecasting GPC, contributing significantly to both literature and practical applications. And the database containing 1045 samples will be disclosed in Appendix Afor researchers to use.
引用
收藏
页数:35
相关论文
共 89 条
[31]   A Comparative Study of Random Forest and Genetic Engineering Programming for the Prediction of Compressive Strength of High Strength Concrete (HSC) [J].
Farooq, Furqan ;
Nasir Amin, Muhammad ;
Khan, Kaffayatullah ;
Rehan Sadiq, Muhammad ;
Javed, Muhammad Faisal ;
Aslam, Fahid ;
Alyousef, Rayed .
APPLIED SCIENCES-BASEL, 2020, 10 (20) :1-18
[32]   Use of Ecofriendly Glass Powder Concrete in Construction of Wind Farms [J].
Garcia del Toro, Eva M. ;
Alcala-Gonzalez, Daniel ;
Mas-Lopez, Maria Isabel ;
Garcia-Salgado, Sara ;
Pindado, Santiago .
APPLIED SCIENCES-BASEL, 2021, 11 (07)
[33]   Modeling of bentonite/sepiolite plastic concrete compressive strength using artificial neural network and support vector machine [J].
Ghanizadeh, Ali Reza ;
Abbaslou, Hakime ;
Amlashi, Amir Tavana ;
Alidoust, Pourya .
FRONTIERS OF STRUCTURAL AND CIVIL ENGINEERING, 2019, 13 (01) :215-239
[34]   Evaluation of mechanical properties of concretes containing coarse recycled concrete aggregates using multivariate adaptive regression splines (MARS), M5 model tree (M5Tree), and least squares support vector regression (LSSVR) models [J].
Gholampour, Aliakbar ;
Mansouri, Iman ;
Kisi, Ozgur ;
Ozbakkaloglu, Togay .
NEURAL COMPUTING & APPLICATIONS, 2020, 32 (01) :295-308
[35]   Estimating the optimal mix design of silica fume concrete using biogeography-based programming [J].
Golafshani, Emadaldin Mohammadi ;
Behnood, Ali .
CEMENT & CONCRETE COMPOSITES, 2019, 96 :95-105
[36]  
Hagger S.E., 2007, Cradle-to-Cradle for Sustainable Development
[37]   Reduction of computational error by optimizing SVR kernel coefficients to simulate concrete compressive strength through the use of a human learning optimization algorithm [J].
Huang, Jiandong ;
Sun, Yuantian ;
Zhang, Junfei .
ENGINEERING WITH COMPUTERS, 2022, 38 (04) :3151-3168
[38]   Machine learning approach for investigating compressive strength of self-compacting concrete containing supplementary cementitious materials and recycled aggregate [J].
Huang, Peng ;
Dai, Kuangyu ;
Yu, Xiaohui .
JOURNAL OF BUILDING ENGINEERING, 2023, 79
[39]   Recycled waste glass powder as a partial replacement of cement in concrete containing silica fume and fly ash [J].
Ibrahim, K. I. M. .
CASE STUDIES IN CONSTRUCTION MATERIALS, 2021, 15
[40]  
Ibrahim K.I.M., 2020, Glob J Eng Sci., V6