Predictive modeling of compressive strength of geopolymer concrete before and after high temperature applying machine learning algorithms

被引:2
作者
Yang, Haifeng [1 ,2 ]
Li, Hongrui [1 ,2 ]
Jiang, Jiasheng [1 ,2 ]
机构
[1] Guangxi Univ, State Key Lab Featured Met Mat & Life Cycle Safety, Nanning 530004, Guangxi, Peoples R China
[2] Guangxi Univ, Coll Civil Engn & Architecture, Guangxi Key Lab Disaster Prevent & Struct Safety, Nanning, Guangxi, Peoples R China
关键词
compressive strength; feature importance analysis; geopolymer concrete; high temperatures; machine learning; partial dependence analysis; FLY-ASH; THERMAL-BEHAVIOR; MECHANICAL-PROPERTIES; RESIDUAL STRENGTH; EXPOSURE; PERFORMANCE; AGGREGATE; METAKAOLIN; RESISTANCE;
D O I
10.1002/suco.202400552
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Geopolymer concrete (GPC) is regarded as a more environmentally friendly construction material compared to conventional cement concrete, and its exceptional environmental capabilities are highly favored by the contemporary construction sector. Studying the mechanical properties of GPC upon exposure to elevated temperatures is a crucial aspect of evaluating structural damage and enhancing fire safety measures. Nevertheless, properly predicting the compressive performance of GPC upon exposure to high temperatures remains a formidable task. This study employs various machine learning techniques, such as single models, integrated models, neural network models, and hybrid models, to predict the compressive strength of GPC from room temperature to 1000 degrees C. The results of each model are summarized, and the significant factors influencing compressive strength are analyzed to evaluate the thermal behavior of GPC. These findings offer recommendations for future in-depth machine learning applications in the GPC field. The K-fold cross-validation shows that the hybrid model genetic algorithm-random forest has the highest prediction accuracy, while the single model performs the worst. Other models also provide favorable prediction results. The feature importance analysis revealed that the compressive strength of GPC is primarily influenced by heating temperature (HT) and hydroxide ion concentration, with fly ash and ground granulated blast furnace slag content being secondary factors. The partial dependence plot-2D analysis indicates that as HTs increase, the influence of other variables on GPC compressive strength decreases significantly. These findings can inform the design of GPC mixing ratios for high-temperature exposure. The machine learning technique proposed in this study accurately predicts GPC compressive strength across various temperatures, reducing experimental time and costs while promoting the GPC sector.
引用
收藏
页码:1699 / 1732
页数:34
相关论文
共 124 条
[1]   Effects of elevated temperatures on the thermal behavior and mechanical performance of fly ash geopolymer paste, mortar and lightweight concrete [J].
Abdulkareem, Omar A. ;
Al Bakri, A. M. Mustafa ;
Kamarudin, H. ;
Nizar, I. Khairul ;
Saif, Ala'eddin A. .
CONSTRUCTION AND BUILDING MATERIALS, 2014, 50 :377-387
[2]   Mechanical and Microstructural Evaluations of Lightweight Aggregate Geopolymer Concrete before and after Exposed to Elevated Temperatures [J].
Abdulkareem, Omar A. ;
Abdullah, Mohd Mustafa Al Bakri ;
Hussin, Kamarudin ;
Ismail, Khairul Nizar ;
Binhussain, Mohammed .
MATERIALS, 2013, 6 (10) :4450-4461
[3]  
Agamy M.H., 2020, Int. J. Eng. Adv. Technol., V9, P1241, DOI [10.35940/ijeat.D7935.049420, DOI 10.35940/IJEAT.D7935.049420]
[4]   Prediction of Geopolymer Concrete Compressive Strength Using Novel Machine Learning Algorithms [J].
Ahmad, Ayaz ;
Ahmad, Waqas ;
Chaiyasarn, Krisada ;
Ostrowski, Krzysztof Adam ;
Aslam, Fahid ;
Zajdel, Paulina ;
Joyklad, Panuwat .
POLYMERS, 2021, 13 (19)
[5]   Support vector regression (SVR) and grey wolf optimization (GWO) to predict the compressive strength of GGBFS-based geopolymer concrete [J].
Ahmed, Hemn Unis ;
Mostafa, Reham R. ;
Mohammed, Ahmed ;
Sihag, Parveen ;
Qadir, Azad .
NEURAL COMPUTING & APPLICATIONS, 2023, 35 (03) :2909-2926
[6]   Properties of Ambient-Cured Normal and Heavyweight Geopolymer Concrete Exposed to High Temperatures [J].
Aslani, Farhad ;
Asif, Zohaib .
MATERIALS, 2019, 12 (05)
[7]   Thermal behaviour of geopolymers prepared using class F fly ash and elevated temperature curing [J].
Bakharev, T .
CEMENT AND CONCRETE RESEARCH, 2006, 36 (06) :1134-1147
[8]   Synthesis and thermal behaviour of potassium sialate geopolymers [J].
Barbosa, VFF ;
MacKenzie, KJD .
MATERIALS LETTERS, 2003, 57 (9-10) :1477-1482
[9]   A solution against well cement degradation under CO2 geological storage environment [J].
Barlet-Gouedard, V. ;
Rimmele, G. ;
Porcherie, O. ;
Quisel, N. ;
Desroches, J. .
INTERNATIONAL JOURNAL OF GREENHOUSE GAS CONTROL, 2009, 3 (02) :206-216
[10]  
Bellum R R., 2022, Journal of Building Pathology and Rehabilitation, V7, P25, DOI [10.1007/s41024-022-00163-4, DOI 10.1007/S41024-022-00163-4]