Objective Accurately predicting the compressive strength and thermal conductivity of aerogel concrete with different mix ratios is essential. Conventional performance prediction methods involve repeatedly designing mix ratios and measuring performance in the laboratory, which requires substantial manpower and time. Alternatively, formula-based or statistical methods are employed to obtain optimal performance; however, the empirical formulas derived from these methods demonstrate low accuracy, remain highly dependent on specific experiments, and cannot be generalized or applied to other cases. This study proposes an aerogel concrete performance prediction model based on the Extreme Gradient Boosting (XGBoost) algorithm, which enables a clearer understanding of the nonlinear relationships between the components and the performance of aerogel concrete. Methods First, relevant data were collected from research literature to construct a database containing 183 sets of compressive strength data and 152 sets of thermal conductivity data. The input features primarily consisted of mix ratios of materials such as cement, while the output features represented the performance of aerogel concrete, specifically compressive strength and thermal conductivity. Second, the XGBoost algorithm was employed for model training and performance prediction, and evaluation metrics such as the coefficient of determination (R2) and root mean square error (RMSE) were utilized to assess the model’s accuracy. The Bayesian optimization algorithm was applied to determine the optimal hyperparameters of the XGBoost model to enhance prediction reliability and reduce overfitting. Third, since the model contained two types of input methods, one approach used the amounts of materials such as aerogel, cement, silica fume, sand, and water as input variables, while the other used interpretable features such as the water-to-binder ratio, aggregate ratio, aerogel content, silica fume content, and curing age as input variables. The model also generated two output results, compressive strength and thermal conductivity. Three comparison schemes were designed, and their prediction accuracy and performance were assessed using the same database to compare the two input methods and to evaluate the strategies of "building one model to predict both performances" versus "building two models to predict the performances separately". Fourth, to demonstrate the advantages of the BO‒XGBoost algorithm in predicting aerogel concrete performance, comparisons were conducted with multiple classical machine learning algorithms, including Random Forest (RF) and Artificial Neural Networks (ANN). For objectivity, all algorithms used the same unified database and underwent Bayesian optimization for hyperparameter tuning. Fifth, to investigate the generalization capability of the BO‒XGBoost model, it was applied to predict the performance of 12 new sets of aerogel concrete data, and the prediction accuracy of the model was observed. Finally, since machine learning models were inherently "black boxes," making it challenging to characterize complex nonlinear relationships between input and output variables, the Shapley Additive Explanations (SHAP) model was employed for feature interpretability analysis, calculating the contribution of each feature to the model’s predictions and explaining the relationships between input features and output results. Results and Discussions 1) The analysis of the prediction accuracy of models established under the three schemes revealed that all three schemes achieved high accuracy in predicting the performance of aerogel concrete, with R2 values greater than 0.92 for the test set. The model under Scheme 1 yielded the best results, with R2 values of 0.977 and 0.978 for compressive strength and thermal conductivity, respectively, and RMSE values of 2.366 MPa and 0.104 0.128 W/(m·K). 2) When compared to four other traditional machine learning algorithms, the XGBoost model was shown to be more suitable for predicting the performance of aerogel concrete. The compressive strength and thermal conductivity models based on the XGBoost algorithm achieved R2 values of 1.000 and 0.992 for the training set, and R2 values of 0.977 and 0.978 for the test set. In contrast, the R2 values of the test set for RF, ANN, and other classical algorithms were all below 0.963, indicating poor fitting accuracy and significant overfitting, which rendered them unsuitable for predicting aerogel concrete performance. 3) The generalization ability of the model was verified using 12 new sets of aerogel concrete mix ratio data. The R2 values for compressive strength and thermal conductivity prediction were 0.986 and 0.895, respectively, with RMSE values of 1.539 MPa and 0.128 W/(m·K), demonstrating the model’s strong generalization capability. 4) The SHAP model analysis revealed that the primary factors influencing the compressive strength of aerogel concrete are aerogel content and water-to-binder ratio. As the aerogel content and water-to-binder ratio increase, the compressive strength decreases. The primary factors influencing the thermal conductivity of aerogel concrete are also aerogel content and water-to-binder ratio, with higher values leading to reduced thermal conductivity. The results obtained from SHAP analysis are consistent with conclusions drawn from laboratory experiments. Conclusions This study proposes an XGBoost-based performance prediction model for aerogel concrete, designed to predict both the compressive strength and the thermal conductivity of ordinary aerogel concrete. Compared to conventional empirical fitting formulas, the prediction model exhibited higher accuracy and stronger generalization capacity, presenting a novel approach for predicting performance and designing mix ratios of aerogel concrete.
CaiWeiguang, WuYong, NiJiangbo,et al.Research report on carbon emissions from urban infrastructure in China (2023)[J].Urban and Rural Construction,2024(6):52‒61.
VytchikovY, SaparevM, ChulkovA.Analyzing screen heat insulation and its effect on energy consumption while heating building envelopes in conditions of intermittent heating[J].MATEC Web of Conferences,2016,86:04019. doi:10.1051/matecconf/20168604019
[4]
HuXiaojun, WangYue.Feasibility analysis of applying thermal insulation composite wall in residential buildings[J].Advanced Materials Research,2012,461:293‒296. doi:10.4028/www.scientific.net/amr.461.293
[5]
QianFeng.Insulation and energy-saving technology for the external wall of residential building[J].Advanced Materials Research,2014,1073/1074/1075/1076:1263‒1270.
[6]
BerardiU, SprengardC.An overview of and introduction to current researches on super insulating materials for high-performance buildings[J].Energy and Buildings,2020,214:109890. doi:10.1016/j.enbuild.2020.109890
[7]
PanYuelei, ChengXudong, YanMingyuan,et al.Silica aerogel and its application in the field of thermal insulation[J].Chemical Industry and Engineering Progress,2023,42(1):297‒309.
GaoTao, JelleB P, GustavsenA,et al.Aerogel-incorporated concrete:An experimental study[J].Construction and Building Materials,2014,52:130‒136. doi:10.1016/j.conbuildmat.2013.10.100
[10]
LiuZhaohui, DingYidong, WangFei,et al.Thermal insulation material based on SiO2 aerogel[J].Construction and Building Materials,2016,122:548‒555. doi:10.1016/j.conbuildmat.2016.06.096
[11]
NgS, JelleB P, SandbergL I C,et al.Experimental investigations of aerogel-incorporated ultra-high performance concrete[J].Construction and Building Materials,2015,77:307‒316. doi:10.1016/j.conbuildmat.2014.12.064
[12]
LvYang.Analysis of thermal conductivity and influence factor of aerogel-incorporated concrete based on multiscale[D].Chongqing:Chongqing Jiaotong University,2024.
[13]
吕洋.基于多尺度的气凝胶混凝土导热系数及其影响因素研究[D].重庆:重庆交通大学,2024.
[14]
GamilY.Machine learning in concrete technology:A review of current researches,trends,and applications[J].Frontiers in Built Environment,2023,9:1145591. doi:10.3389/fbuil.2023.1145591
[15]
KhambraG, ShuklaP.Novel machine learning applications on fly ash based concrete:An overview[J].Materials Today:Proceedings,2023,80:3411‒3417. doi:10.1016/j.matpr.2021.07.262
[16]
KhanK, AhmadW, AminM N,et al.A systematic review of the research development on the application of machine learning for concrete[J].Materials,2022,15(13):4512. doi:10.3390/ma15134512
[17]
LadyginaP, SamochadinA, VoinovN,et al.Predicting concrete compressive strength using machine learning[C]//Advanced Manufacturing and Automation Ⅺ.Singapore:Springer,2022:450‒457. doi:10.1007/978-981-19-0572-8_57
[18]
XuXiaohang, HuZhangli, Liujiaping,et al.Concrete strength prediction of the three gorges dam based on machine learning regression model[J].Materials Reports,2023,37(2):45‒53.
ZhangWei, LeeD, LeeJ,et al.Residual strength of concrete subjected to fatigue based on machine learning technique[J].Structural Concrete,2022,23(4):2274‒2287. doi:10.1002/suco.202100082
[21]
UkwaththaU J, LiyanarachchiT S D, KulasooriyaW K V J B,et al.Use of interpretable machine learning methods to predict the fundamental period of masonry infilled reinforced concrete frame structures[C]//Proceedings of the 2024 Moratuwa Engineering Research Conference (MERCon).Moratuwa:IEEE,2024: 127‒132. doi:10.1109/mercon63886.2024.10688600
[22]
DaiLichao, WangChong, YuanPing,et al.Prediction model for shear capacity of corroded RC beams based on interpretable machine learning[J].Journal of Jilin University(Engineering and Technology Edition), 2024, 54(11): 3231‒ 3243.
ZhouShuai, JiaYue, LiKai,et al.Mix proportion optimization of Ultra-high performance concrete based on machine learning[J].Journal of Tongji University(Natural Science),2024,52(7):1018‒1023.
LiuYanning.High-performance concrete strength prediction based on machine learning[J].Computational Intelligence and Neuroscience,2022,2022:5802217. doi:10.1155/2022/5802217
[27]
WangWenhu, ZhongYihui, LiaoGang,et al.Prediction of compressive strength of concrete specimens based on interpretable machine learning[J].Materials,2024,17(15):3661. doi:10.3390/ma17153661
[28]
NguyenM H, NguyenT A, LyH B.Ensemble XGBoost schemes for improved compressive strength prediction of UHPC[J].Structures,2023,57:105062. doi:10.1016/j.istruc.2023.105062
[29]
HanFenglei, LvYang, LiuYan,et al.Exploring interpretable ensemble learning to predict mechanical strength and thermal conductivity of aerogel-incorporated concrete[J].Construction and Building Materials,2023,392:131781. doi:10.1016/j.conbuildmat.2023.131781
[30]
LyngdohG A, ZakiM, Anoop KrishnanN M,et al.Prediction of concrete strengths enabled by missing data imputation and interpretable machine learning[J].Cement and Concrete Composites,2022,128:104414. doi:10.1016/j.cemconcomp.2022.104414
[31]
LiuTingbin, HuangTao, JiaxiangOu,et al.Prediction method of bond strength of corroded reinforced concrete at high temperature based on ANN and XGB algorithm[J].Engineering Mechanics,2024,41(Supp1): 300‒309.
WangFei, LiuZhaohui, DengZhiping,et al.Effect on the performance of mortar using different volume content of SiO2 aerogel[J].Journal of Functional Materials,2016,47(4):4064‒4069.
FengJincai, LiTao, LiuWengying.Experimental study on influence of aggregate contents on properties of silica aerogel thermal insulation mortar[J].Journal of Changzhou University(Natural Science Edition),2019,31(2):88‒92.
YangYuxiang.Preparation and performance study of nanoparticles aerogelcement-based materials[D].Lanzhou:Lanzhou Jiaotong University,2023.
[38]
杨玉祥.纳米气凝胶水泥基材料制备及性能研究[D].兰州:兰州交通大学,2023.
[39]
ZhuPinghua, YuShuqi, ChengCheng,et al.Durability of silica aerogel cementitious composites‒freeze‒thaw resistance,water resistance and drying shrinkage[J].Advances in Cement Research,2020,32(12):527‒536. doi:10.1680/jadcr.18.00145
[40]
WangXinjie, XuDonghang, ZhuPinghua,et al.Effect of curing temperature on tunnel fire insulation of aerogel cement paste coatings[J].Journal of Wuhan University of Technology‒Mater Science,2021,36(1):93‒102. doi:10.1007/s11595-021-2381-2
[41]
ZhouRonglai, ChenHao, ZhangMei,et al.Study on SiO2 aerogel insulation mortar and its mechanical properties[J].Jiangsu Construction,2018,(Supp1):62‒65.
HanFenglei, LiuYan, LiuTao,et al.Experimental study on the influence of silica aerogel on the properties of superfine-cement composites[J].Materials Reports,2023,37(15):97‒103.
LiuTao.Study on prediction model of physical and mechanical properties and thermal conductivity of SiO2 aerogel-incorporated concrete[D].Chongqing:Chongqing Jiaotong University,2022.
[46]
刘涛.SiO2气凝胶混凝土物理力学性能及导热系数预测模型研究[D].重庆:重庆交通大学,2022.
[47]
ZhuPinghua, SunYuanqian, FengJincai,et al.Experimental study on the influence of particle size of the SiO2 aerogel onproperties of silica aerogel tunnel fireproof mortar[J].Concrete,2017(12):132‒135.
ZhuPinghua, BrunnerS, ZhaoShanyu,et al.Study of physical properties and microstructure of aerogel-cement mortars for improving the fire safety of high-performance concrete linings in tunnels[J].Cement and Concrete Composites,2019,104:103414. doi:10.1016/j.cemconcomp.2019.103414
[50]
LiuZhaohui, DingYidong, WangFei,et al.Thermal insulation material based on SiO2 aerogel[J].Construction and Building Materials,2016,122:548‒555. doi:10.1016/j.conbuildmat.2016.06.096
[51]
LiuZhaohui, DingYidong, WangFei,et al.Influences of KH550 Modified SiO2 Aerogel on Mortar Property[J].Equipment Environmental Engineering,2017,14(1):71‒77.