基于机器学习的粉煤灰基地聚合物混凝土抗压强度预测

石旭峰; 丁丹婧; 宋慧平; 吴海滨; 安全

doi:10.3724/j.gyjzG24102302

基于机器学习的粉煤灰基地聚合物混凝土抗压强度预测

doi: 10.3724/j.gyjzG24102302

石旭峰^1,2,3,
丁丹婧^1,2,3,
宋慧平^1,2,3, ,,
吴海滨^1,2,3,
安全^1,2,3

1. 山西大学资源与环境工程研究所, 太原 030006;
2. 黄河流域资源增效减碳教育部工程研究中心, 太原 030006;
3. 山西省黄河试验室, 太原 030006

基金项目:

国家自然科学基金项目（22378241）。

详细信息

作者简介:
石旭峰，博士研究生，主要从事机器学习方面的研究，1319532857@qq.com。

通讯作者:
宋慧平，教授，博士生导师，主要从事煤炭废弃物资源化利用的研究，songhp@sxu.edu.cn。

计量
- 文章访问数: 71
- HTML全文浏览量: 26
- PDF下载量: 1
- 被引次数: 0
出版历程
- 收稿日期: 2024-10-23

Prediction of Compressive Strength of Fly Ash-Based Geopolymer Concrete Based on Machine Learning

SHI Xufeng^1,2,3,
DING Danjing^1,2,3,
SONG Huiping^{1,2,3
, ,},
WU Haibin^1,2,3,
AN Quan^1,2,3

1. Institute of Resources and Environmental Engineering, Shanxi University, Taiyuan 030006, China;
2. Yellow River Basin Resource Efficiency and Carbon Reduction Engineering Research Center of Ministry of Education, Taiyuan 030006, China;
3. Shanxi Yellow River Laboratory, Taiyuan 030006, China

摘要

摘要: 探究了利用机器学习技术预测粉煤灰基地聚合物混凝土抗压强度。共收集112组数据，选取粉煤灰掺量、组成成分等11个变量为输入，抗压强度为输出，按70%和30%的比例划分成训练集和测试集进行分析。选用一种单个机器学习算法（SVM）和两种集成机器学习算法（RF，Adaboost）构建预测模型。使用训练集和测试集对模型的性能进行评估，同时使用SHAP值算法分析了各因素的影响规律。结果表明：所有模型在两个集上都表现出较强的预测能力，其中，RF模型表现最好，其测试集的决定系数R²=0.91、均方误差Δ_MES=14.76、均方根误差Δ_RMSE=3.84、平均绝对误差Δ_MAE=2.89；使用SHAP值算法确定了粉煤灰掺量、粉煤灰中Al₂O₃和SiO₂含量、NaOH摩尔浓度和水掺量是影响混凝土抗压强度最重要的5个因素。粉煤灰掺量大于400 kg/m³、粉煤灰中SiO₂含量小于60%和较高的NaOH浓度都有助于混凝土强度的提升；粉煤灰中Al₂O₃含量大于15%时，混凝土强度随Al₂O₃含量的增加而增加；水掺入过多会增加混凝土孔隙，使得抗压强度降低。
- 粉煤灰 /
- 地聚合物混凝土 /
- 抗压强度 /
- 机器学习 /
- 可解释性
Abstract: Machine learning technology is used to predict the compressive strength of fly ash-based geopolymer concrete. A total of 112 sets of data were collected， and 11 variables such as fly ash content and composition were selected as inputs and compressive strength was output variable， which were divided into training sets and test sets according to the proportion of 70% and 30% for analysis. A single machine learning algorithm （SVM） and two integrated machine learning algorithms （RF， Adaboost） were used to construct the prediction model. The performance of the models was evaluated using the training set and the test set， and the results showed that all models showed strong predictive ability on both sets. Among them， RF model had the best performance， its test set R²=0.91，Δ_MES=14.76，Δ_RMSE=3.84，Δ_MAE=2.89. The SHAP value algorithm was used to determine that fly ash content， Al₂O₃ and SiO₂ content in fly ash， NaOH molar concentration and water content were the five most important factors affecting the compressive strength of concrete. When the fly ash dosage was greater than 400 kg/m³， the SiO₂ content in fly ash was less than 60%， and the NaOH concentration was relatively high， all these factors contributed to the enhancement of concrete strength. When the Al₂O₃ content in fly ash was greater than 15%， the concrete strength increased with the increase of Al₂O₃ content. Excessive water addition would increase the porosity of concrete， thereby reduced its compressive strength.
- fly ash /
- geopolymer concrete /
- compressive strength /
- machine learning /
- interpretability

HTML全文

参考文献(34)

[1]	左骁遥,房晓红,曾凡桂,二氧化碳在高岭石孔隙中吸附的分子模拟[J].矿产综合利用,2020(1):163-167.
[2]	SHI C,JIMÉNEZ A F,PALOMO A. New cements for the 21st century:the pursuit of an alternative to Portland cement[J]. Cement and Concrete Research,2011,41(7):750-763.
[3]	POUDYAL L,ADHIKARI K. Environmental sustainability in cement industry:an integrated approach for green and economical cement production[J]. Resources,Environment and Sustainability,2021,4,100024.
[4]	MCLELLAN B C,WILLIAMS R P,LAY J,et al. Costs and carbon emissions for geopolymer pastes in comparison to ordinary Portland cement[J]. Journal of Cleaner Production,2011,19(9/10):1080-1090.
[5]	CHINDAPRASIRT P,CHAREERAT T,HATANAKA S,et al. High-strength geopolymer using fine high-calcium fly ash[J]. Journal of Materials in Civil Engineering,2011,23(3):264-270.
[6]	KONG D L Y,SANJAYAN J G. Effect of elevated temperatures on geopolymer paste,mortar and concrete[J]. Cement and Concrete Research,2010,40(2):334-339.
[7]	CHINDAPRASIRT P,RATTANASAK U,TAEBUANHUAD S. Resistance to acid and sulfate solutions of microwave-assisted high calcium fly ash geopolymer[J]. Materials and Structures,2013,46:375-381.
[8]	CHINDAPRASIRT P,CHALEE W. Effect of sodium hydroxide concentration on chloride penetration and steel corrosion of fly ash-based geopolymer concrete under marine site[J]. Construction and Building Materials,2014,63:303-310.
[9]	李志强,张轩硕,卜娜蕊,等.基于正交试验金尾矿砂再生混凝土试验研究[J].矿产综合利用,2022(6):73-78.
[10]	王好喜,陈卓,程勋明,等.基于优化支持向量回归的混凝土抗压强度预测研究[J].施工技术(中英文),2023,52(4):117-121,138.
[11]	CHAABENE W B,FLAH M,NEHDI M L. Machine learning prediction of mechanical properties of concrete:critical review[J]. Construction and Building Materials,2020,260,119889.
[12]	AHMAD A,AHMAD W,ASLAM F,et al. Compressive strength prediction of fly ash-based geopolymer concrete via advanced machine learning techniques[J]. Case Studies in Construction Materials,2022,16,e00840.
[13]	NGUYEN H,VU T,VO T P,et al. Efficient machine learning models for prediction of concrete strengths[J]. Construction and Building Materials,2021,266,120950.
[14]	GHAFOOR M T,KHAN Q S,QAZI A U,et al. Influence of alkaline activators on the mechanical properties of fly ash based geopolymer concrete cured at ambient temperature[J]. Construction and Building Materials,2021,273,121752.
[15]	PAVITHRA P,REDDY M S,DINAKAR P,et al. A mix design procedure for geopolymer concrete with fly ash[J]. Journal of Cleaner Production,2016,133:117-125.
[16]	XIE T,OZBAKKALOGLU T. Behavior of low-calcium fly and bottom ash-based geopolymer concrete cured at ambient temperature[J]. Ceramics International,2015,41(4):5945-5958.
[17]	ALIABDO A A,ELMOATY M ABD,SALEM H A. Effect of water addition,plasticizer and alkaline solution constitution on fly ash based geopolymer concrete performance[J]. Construction and Building Materials,2016,121:694-703.
[18]	GUNASEKARA C,LAW D W,SETUNGE S. Long term permeation properties of different fly ash geopolymer concretes[J]. Construction and Building Materials,2016,124:352-362.
[19]	DEB P S,NATH P,SARKER P K. The effects of ground granulated blast-furnace slag blending with fly ash and activator content on the workability and strength properties of geopolymer concrete cured at ambient temperature[J]. Materials&Design,2014,62:32-39.
[20]	TOPARK-NGARM P,CHINDAPRASIRT P,SATA V. Setting time,strength,and bond of high-calcium fly ash geopolymer concrete[J]. Journal of Materials in Civil Engineering,2015,27(7),04014198.
[21]	PHOO-NGERNKHAM T,PHIANGPHIMAI C,DAMRONGWIRIYANUPAP N,et al. A mix design procedure for alkali-activated high-calcium fly ash concrete cured at ambient temperature[J/OL]. Advances in Materials Science and Engineering,[2018-03-25]. https://doi.org/10.1155/2018/2460403.
[22]	RAFEET A,VINAI R,SOUTSOS M,et al. Guidelines for mix proportioning of fly ash/GGBS based alkali activated concretes[J]. Construction and Building Materials,2017,147:130-142.
[23]	FENG D C,LIU Z T,WANG X D,et al. Machine learning-based compressive strength prediction for concrete:an adaptive boosting approach[J]. Construction and Building Materials,2020,230,117000.
[24]	WANG Q C,AHMAD W,AHMAD A,et al. Application of soft computing techniques to predict the strength of geopolymer composites[J]. Polymers,2022,14(6),1074.
[25]	SHI X,YU X,ESMAEILI-FALAK M. Improved arithmetic optimization algorithm and its application to carbon fiber reinforced polymer-steel bond strength estimation[J]. Composite Structures,2023,306,116599.
[26]	HUANG J,ZHOU M,ZHANG J,et al. Development of a new stacking model to evaluate the strength parameters of concrete samples in laboratory[J]. Iranian Journal of Science and Technology,Transactions of Civil Engineering,2022,46(6):4355-4370.
[27]	LI Y,SHEN J,LIN H,et al. Optimization design for alkali-activated slag-fly ash geopolymer concrete based on artificial intelligence considering compressive strength,cost,and carbon emission[J]. Journal of Building Engineering,2023,75,106929.
[28]	NOBLE W S. What is a support vector machine?[J]. Nature Biotechnology,2006,24(12):1565-1567.
[29]	LI Y,SHEN J,LIN H,et al. The data-driven research on bond strength between fly ash-based geopolymer concrete and reinforcing bars[J]. Construction and Building Materials,2022,357,129384.
[30]	LUNDBERG S M,LEE S I. A unified approach to interpreting model predictions[J]. Advances in Neural Information Processing Systems,2017,10:4768-4777.
[31]	LYNGDOH G A,ZAKI M,KRISHNAN N M A,et al. Prediction of concrete strengths enabled by missing data imputation and interpretable machine learning[J]. Cement and Concrete Composites,2022,128,104414.
[32]	PENG Y M,CISE U. Analyzing the mechanical performance of fly ash-based geopolymer concrete with different machine learning techniques[J]. Construction and Building Materials,2022,316,125785.
[33]	KUMAR P S,PUJA R. Comparative analysis of regression and ANN algorithm for predicting compressive strength of sustainable geopolymer concrete at varying NaOH concentration and curing temperature[J]. Iranian Journal of Science and Technology,Transactions of Civil Engineering,2023,48(3):1273-1298.
[34]	DING Y J,WEI W,WANG J J,et al. Prediction of compressive strength and feature importance analysis of solid waste alkali-activated cementitious materials based on machine learning[J]. Construction and Building Materials,2023,407,133545.