基于高斯过程回归模型的电石渣激发煤矸石地聚合物强度响应预测与分析

硅酸盐通报 ›› 2024, Vol. 43 ›› Issue (3): 905-913.

所属专题：资源综合利用

基于高斯过程回归模型的电石渣激发煤矸石地聚合物强度响应预测与分析

宁慧员¹, 张菊¹, 闫长旺^1,2, 白茹^3,4

1.内蒙古工业大学土木工程学院,呼和浩特 010051;
2.内蒙古工业大学资源与环境工程学院,呼和浩特 010051;
3.内蒙古工业大学矿产资源绿色开发重点实验室,呼和浩特 010051;
4.生态型建筑材料与装配式结构内蒙古自治区工程研究中心,呼和浩特 010051

收稿日期:2023-09-28 修订日期:2023-11-23 出版日期:2024-03-15 发布日期:2024-03-27
通信作者: 张菊,博士,教授。E-mail:zj970741@126.com
作者简介:宁慧员(1999—),男,硕士研究生。主要从事低碳建筑材料的研究。E-mail:ninghuiyuan2022@163.com
基金资助:
国家自然科学基金(52068059,52368036);中央引导地方科技发展资金(2022ZY0160);鄂尔多斯市重点研发计划(YF20232358);内蒙古自治区直属高校基本科研业务费(JY20220009,JY20230117,JY20220179);内蒙古工业大学博士基金科学研究项目(BS2021049)

Prediction and Analysis of Strength Response of Calcium Carbide Slag Excited Coal Gangue Geopolymer Based on Gaussian Process Regression Model

NING Huiyuan¹, ZHANG Ju¹, YAN Changwang^1,2, BAI Ru^3,4

1. School of Civil Engineering, Inner Mongolia University of Technology, Hohhot 010051, China;
2. School of Resource and Environmental Engineering, Inner Mongolia University of Technology, Hohhot 010051, China;
3. Key Laboratory of Green Development of Mineral Resources, Inner Mongolia University of Technology, Hohhot 010051, China;
4. Ecological Building Materials and Prefabricated Structures Inner Mongolia Autonomous Region Engineering Research Center, Hohhot 010051, China

Received:2023-09-28 Revised:2023-11-23 Online:2024-03-15 Published:2024-03-27

摘要/Abstract

摘要： 地聚合物的抗压强度是评估其能否代替水泥作为新型建筑材料的关键因素之一,但仅依靠大量试验测试强度,既浪费资源又增加成本。为了解决这一问题,通过早期试验收集的电石渣激发煤矸石地聚合物的强度数据,将不同配合比、水胶比、龄期作为输入参数,抗压强度作为输出结果,基于机器学习方法构建强度响应预测模型——高斯过程回归(GPR)模型,并利用模型对不同配合比及龄期的地聚合物强度进行预测,进而建立各组分掺量、水胶比、龄期对强度的影响曲线并探究原因。结果表明:GPR模型经过对样本数据的拟合,可以较好地预测地聚合物的强度,且误差为(-0.001 93～+0.001 83);利用受过训练的模型对未知抗压强度的地聚合物进行强度预测,通过预测结果分析各输入参数(电石渣掺量、煤矸石掺量、水胶比和养护龄期)对强度的影响,发现强度与上述变量均有密切关系,其中电石渣掺量、煤矸石掺量和养护龄期对强度的影响更显著。

关键词: 电石渣, 煤矸石, 地聚合物, 高斯过程回归, 抗压强度预测, 强度影响因素

Abstract: The compressive strength of geopolymer is one of key factors in evaluating whether geopolymer can replace cement as a new building material, but relying only on many tests to test its strength wastes resources and improves costs. To solve this problem, the data of calcium carbide slag excited coal gangue geopolymer collected through early experiments, different mixing ratios, water-binder ratios, and ages were used as input parameters and compressive strength was used as output results. The strength response prediction model—Gaussian process regression (GPR) model was constructed based on machine learning methods. The geopolymer strength of different mixing ratios and ages was predicted by using the model, then the influence curves of each component content, water-binder ratio and age on the strength were established and the reasons were explored. The results show that the GPR model can predict the strength of geopolymer well after fitting the sample data, and the error is in the range of (-0.001 93~+0.001 83). The strength prediction of geopolymer with unknown compressive strength is made by the trained model, and the influences of each input parameters (calcium carbide slag content, coal gangue content, water-binder ratio, and curing age) on the strength were analyzed through the prediction results. It is found that the strength is closely related to the above variables, among which the calcium carbide slag content, coal gangue content and curing age have more influence on the strength.

Key words: calcium carbide slag, coal gangue, geopolymer, Gaussian process regression, compressive strength prediction, strength influencing factor

中图分类号:

TU528.41

宁慧员, 张菊, 闫长旺, 白茹. 基于高斯过程回归模型的电石渣激发煤矸石地聚合物强度响应预测与分析[J]. 硅酸盐通报, 2024, 43(3): 905-913.

NING Huiyuan, ZHANG Ju, YAN Changwang, BAI Ru. Prediction and Analysis of Strength Response of Calcium Carbide Slag Excited Coal Gangue Geopolymer Based on Gaussian Process Regression Model[J]. BULLETIN OF THE CHINESE CERAMIC SOCIETY, 2024, 43(3): 905-913.

参考文献

[1] 2022年中国生态环境状况公报[R]. 中国生态环境部, 2022: 69.
Communiqué on the state of China's ecology and environment in 2022[R]. Ministry of Ecology and Environment of the People's Republic of China, 2022: 69 (in Chinese).
[2] 王悠悠, 袁浩, 谌世英. 固废制备碱激发胶凝材料配比研究[J]. 化工矿物与加工, 2022, 51(12): 1-6.
WANG Y Y, YUAN H, CHEN S Y. Study on preparation of alkali-activated cementing materials using solid wastes with different blending ratios[J]. Industrial Minerals & Processing, 2022, 51(12): 1-6 (in Chinese).
[3] 陈玲玲, 曹星宇, 王志远, 等. 建筑固废制备再生混凝土技术路线应用研究综述[J]. 山西建筑, 2023, 49(8): 29-32.
CHEN L L, CAO X Y, WANG Z Y, et al. Study on the application of the technical route for producing recycled concrete from construction solid waste[J]. Shanxi Architecture, 2023, 49(8): 29-32 (in Chinese).
[4] 丁庆军, 孙孝平, 施建军, 等. 大掺量固废胶凝材料制备C50高耐磨路面混凝土[J]. 混凝土, 2022(4): 176-181.
DING Q J, SUN X P, SHI J J, et al. C50 high wear-resisting pavement concrete prepared by large amount of solid waste cementitious material[J]. Concrete, 2022(4): 176-181 (in Chinese).
[5] 段喜平, 陈杰, 闫长旺, 等. 钢渣对固废基贝利特硫铝酸盐水泥水化的影响[J]. 内蒙古工业大学学报(自然科学版),2023, 42(6): 549-554.
DUAN X P, CHEN J, YAN C W, et al. Effect of steel slag on hydration of solid waste belite sulfoaluminate cement[J]. Journal of Inner Mongolia University of Technology (Natural Science), 2023, 42(6): 549-554 (in Chinese).
[6] 蔡亮学, 何利民, 吕宇玲, 等. 水平定向钻管道穿越孔底泥浆的力学特性[J]. 油气储运, 2011, 30(1): 25-29+4.
CAI L X, HE L M, LV Y L, et al. Hole-bottom slurry mechanical properties of horizontal directional drilling in pipeline crossing project[J]. Oil & Gas Storage and Transportation, 2011, 30(1): 25-29+4 (in Chinese).
[7] 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.
WANG H X, CHEN Z, CHENG X M, et al. Prediction research of concrete compressive strength based on optimal support vector regression[J]. Construction Technology, 2023, 52(4): 117-121+138 (in Chinese).
[8] 徐潇航, 胡张莉, 刘加平, 等. 基于机器学习回归模型的三峡大坝混凝土强度预测[J]. 材料导报, 2023, 37(2): 45-53.
XU X H, HU Z L, LIU J P, et al. Concrete strength prediction of the Three Gorges Dam based on machine learning regression model[J]. Materials Reports, 2023, 37(2): 45-53 (in Chinese).
[9] 王庆贺, 张提睿, 李永进, 等. 基于机器学习的钢-自燃煤矸石混凝土组合梁栓钉抗剪承载力研究[J]. 沈阳建筑大学学报(自然科学版), 2023, 39(2): 227-233.
WANG Q H, ZHANG T R, LI Y J, et al. Shear capacity of studs in steel-spontaneous-combustion coal gangue concrete composite beams using machine learning[J]. Journal of Shenyang Jianzhu University (Natural Science), 2023, 39(2): 227-233 (in Chinese).
[10] 李东泽, 齐咏生, 刘利强. 基于LSTM-ATTENTION融合神经网络的光伏功率预测[J]. 内蒙古工业大学学报(自然科学版), 2023, 42(4): 350-354+384.
LI D Z, QI Y S, LIU L Q. PV power prediction based on LSTM-ATTENTION fusion neural network[J]. Journal of Inner Mongolia University of Technology (Natural Science Edition), 2023, 42(4): 350-354+384 (in Chinese).
[11] 张襄松, 高秀秀. 基于随机森林的逻辑回归预测抗乳腺癌药物的ADMET性质[J]. 内蒙古工业大学学报(自然科学版), 2023, 42(6): 481-487.
ZHANG X S, GAO X X. Prediction of ADMET properties of anti-breast cancer drugs by random forest-based logistic regression[J]. Journal of Inner Mongolia University of Technology (Natural Scienc), 2023, 42(6): 481-487 (in Chinese).
[12] 范向前, 刘决丁, 史晨雨, 等. 基于人工神经网络方法的FRP增强混凝土断裂研究新思路[J]. 防灾减灾工程学报, 2023, 43(3): 626-636.
FAN X Q, LIU J D, SHI C Y, et al. Innovative idea on fracture analysis of FRP reinforced concrete using artificial neural network[J]. Journal of Disaster Prevention and Mitigation Engineering, 2023, 43(3): 626-636 (in Chinese).
[13] 靳江伟, 董春芳, 冯国红. 基于灰色关联支持向量机的混凝土抗压强度预测[J]. 郑州大学学报(理学版), 2015, 47(3): 59-63.
JIN J W, DONG C F, FENG G H. Prediction of concrete compressive strength based on grey relational-support vector machine[J]. Journal of Zhengzhou University (Natural Science Edition), 2015, 47(3): 59-63 (in Chinese).
[14] 王建民, 叶钰蓉, 饶超敏, 等. 基于GBDT算法的混凝土叠合面黏结强度预测分析[J]. 建筑材料学报, 2023, 26(2): 150-155+171.
WANG J M, YE Y R, RAO C M, et al. Prediction on composite interface bonding strength between ceramsite lightweight aggregate concrete and normal concrete based on GBDT algorithm[J]. Journal of Building Materials, 2023, 26(2): 150-155+171 (in Chinese).
[15] SONG H W, AHMAD A, FAROOQ F, et al. Predicting the compressive strength of concrete with fly ash admixture using machine learning algorithms[J]. Construction and Building Materials, 2021, 308: 125021.
[16] 吴贤国, 刘鹏程, 陈虹宇, 等. 基于随机森林的高性能混凝土抗压强度预测[J]. 混凝土, 2022(1): 17-20+24.
WU X G, LIU P C, CHEN H Y, et al. Characteristic screening and prediction of high-performance concrete compressive strength based on random forest method[J]. Concrete, 2022(1): 17-20+24 (in Chinese).
[17] CHEN G, ZHU D L, WANG X A, et al. Prediction of concrete compressive strength based on the BP neural network optimized by random forest and ISSA[J]. Journal of Function Spaces, 2022, 2022: 1-20.
[18] BESKOPYLNY A N, STEL'MAKH S A, SHCHERBAN' E M, et al. Concrete strength prediction using machine learning methods CatBoost, k-nearest neighbors, support vector regression[J]. Applied Sciences, 2022, 12(21): 10864.
[19] 王方成, 刘玉敏, 崔庆安. 基于高斯过程回归的混合型参数建模及优化[J]. 统计与决策, 2023, 39(1): 34-39.
WANG F C, LIU Y M, CUI Q A. Hybrid parameter modeling and optimization based on Gaussian process regression[J]. Statistics & Decision, 2023, 39(1): 34-39 (in Chinese).
[20] 袁干琳. 电石渣基地质聚合物水化特性研究[D]. 呼和浩特: 内蒙古工业大学, 2022.
YUAN G L. Study on hydration characteristics of carbide slag-based geopolymer[D]. Hohhot: Inner Mongolia University of Tehchnology, 2022 (in Chinese).
[21] 郑冠雨. 大型粮仓建筑高强混凝土强度预测的遗传支持向量机方法研究[J]. 河南工业大学学报(自然科学版), 2014, 35(3): 88-91+104.
ZHENG G Y. Study on genetic support vector machine method in strength prediction of high strength concrete for constructing large granary[J]. Journal of Henan University of Technology (Natural Science Edition), 2014, 35(3): 88-91+104 (in Chinese).
[22] 李剑锋. 煤矸石-电石渣地聚物胶凝材料固化软土的试验研究与应用[D]. 广州: 广州大学, 2021.
LI J F. Experimental study and application of coal gangue-carbide slag geopolymer cementing material for curing soft soil[D].Guangzhou: Guangzhou University, 2021 (in Chinese).
[23] 白国良, 刘瀚卿, 刘辉, 等. 煤矸石理化特性与煤矸石混凝土力学性能研究[J]. 建筑结构学报, 2023, 44(10): 243-254.
BAI G L, LIU H Q, LIU H, et al. Study on physicochemical properties of coal gangue and mechanical properties of coal gangue concrete[J]. Journal of Building Structures, 2023, 44(10): 243-254 (in Chinese).
[24] 杨忠波, 黄森乐, 姚冀恺, 等. 养护方式对大掺量粉煤灰混凝土抗压强度的影响[J]. 混凝土, 2022(10): 151-155.
YANG Z B, HUANG S L, YAO J K, et al. Effect of curing method on the compressive strength of high-volume fly ash concrete[J]. Concrete, 2022(10): 151-155 (in Chinese).

基于高斯过程回归模型的电石渣激发煤矸石地聚合物强度响应预测与分析

Prediction and Analysis of Strength Response of Calcium Carbide Slag Excited Coal Gangue Geopolymer Based on Gaussian Process Regression Model

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	陈士军, 龚木联, 刘溯逸, 花思旭, 金修伟, 王昊. 基于响应曲面法的三元地聚合物注浆材料耐久性能研究[J]. 硅酸盐通报, 2024, 43(3): 938-947.
[2]	王稷良, 郭文彬, 宋庆凯, 徐伟东, 刘鹏. 激振搅拌对水泥稳定碎石与煤矸石抗压强度的影响[J]. 硅酸盐通报, 2024, 43(2): 757-765.
[3]	陈友治, 吴修齐, 殷伟淞, 李万民, 汤世昌. 电石渣对复合胶凝材料力学性能和微观结构的影响[J]. 硅酸盐通报, 2023, 42(9): 3196-3203.
[4]	刘扬, 肖欣欣, 陈湘, 王柏文, 罗冬, 鲁乃唯. 电石渣对碱激发粉煤灰-矿渣抗碳化性能的影响[J]. 硅酸盐通报, 2023, 42(9): 3204-3211.
[5]	陈永亮, 张轶轲, 陈铁军, 成亮, 李慧敏, 杨再华, 王全. 碱激发高钙粉煤灰发泡地聚合物的制备及机理[J]. 硅酸盐通报, 2023, 42(8): 2787-2798.
[6]	李昱蓓, 刘松辉, 朱建平, 管学茂. 电石渣制备球霰石型CaCO₃的影响因素研究[J]. 硅酸盐通报, 2023, 42(8): 2799-2807.
[7]	张顶飞, 吕启航, 张鹏, 朱珍, 陈向南, 曹吉昌. 基于响应面法的粉煤灰-电石渣地质聚合物固化软土试验研究[J]. 硅酸盐通报, 2023, 42(8): 2821-2829.
[8]	李庆文, 禹萌萌, 刘艺伟, 曹行, 高森林, 聂帆帆, 李玲. GFRP布被动约束标准煤矸石混凝土圆柱轴压性能细观模拟[J]. 硅酸盐通报, 2023, 42(7): 2458-2471.
[9]	刘维海, 夏晨康, 张鑫源, 郝名远, 苗洋, 高峰. 液-液溶剂置换法制备超疏水SiO₂气凝胶[J]. 硅酸盐通报, 2023, 42(6): 2233-2241.
[10]	胡彪, 李先海, 晏祥政, 赵永庆. 热活化煤矸石粉对基体-骨料界面过渡区性能的影响[J]. 硅酸盐通报, 2023, 42(4): 1315-1322.
[11]	安赛, 王宝民, 陈文秀, 赵庆新. 电石渣激发矿渣-粉煤灰复合胶凝材料的作用机制[J]. 硅酸盐通报, 2023, 42(4): 1333-1343.
[12]	刘扬, 陈湘, 王柏文, 鲁乃唯, 肖欣欣, 罗冬. 碱激发粉煤灰-矿渣-电石渣基地聚物的制备及强度机理[J]. 硅酸盐通报, 2023, 42(4): 1353-1362.
[13]	李秋, 朱翔, 耿海宁, 李宗刚, 马浩森, 陈伟. 地聚合物基多相陶瓷高放废液固化体固化机理与浸出性能[J]. 硅酸盐通报, 2023, 42(4): 1437-1447.
[14]	张敬浩, 孟凡会, 王丽娜, 戴露霏, 姚隆帆, 李忠. 煤矸石基泡沫陶瓷的制备及性能研究[J]. 硅酸盐通报, 2023, 42(3): 960-969.
[15]	黄学辉, 常宇, 宋晓展, 杨娜. 凝胶注模-发泡法制备煤矸石多孔吸声材料的工艺研究[J]. 硅酸盐通报, 2023, 42(3): 970-977.