基于随机森林和支持向量机的高性能混凝土抗渗性预测研究

硅酸盐通报 ›› 2021, Vol. 40 ›› Issue (3): 829-835.

基于随机森林和支持向量机的高性能混凝土抗渗性预测研究

吴贤国¹, 刘茜¹, 王洪涛², 陈虹宇³, 高飞⁴, 黄汉洋⁴

1.华中科技大学土木与水利工程学院,武汉 430074;
2.中建三局集团有限公司,武汉 430000;
3.南洋理工大学土木工程与环境学院,新加坡 639798;
4.中建商品混凝土有限公司,武汉 430000

收稿日期:2020-09-25 修回日期:2020-12-19 出版日期:2021-03-15 发布日期:2021-04-13
通讯作者: 刘茜,硕士研究生。E-mail:870852150@qq.com
作者简介:吴贤国(1964—),女,教授。主要从事土木工程施工及管理方面的研究。E-mail:wxg0220@126.com
基金资助:
国家重点研发项目(2016YFC0800208);国家自然科学基金(51378235,71571078,51308240)

Prediction of Impermeability of Concrete Based on Random Forest and Support Vector Machine

WU Xianguo¹, LIU Xi¹, WANG Hongtao², CHEN Hongyu³, GAO Fei⁴, HUANG Hanyang⁴

1. School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan 430074, China;
2. China Construction Third Engineering Bureau Co., Ltd., Wuhan 430000, China;
3. School of Civil Engineering and Environment, Nanyang Technological University, Singapore 639798, Singapore;
4. China Construction Commercial Concrete Co., Ltd., Wuhan 430000, China

Received:2020-09-25 Revised:2020-12-19 Online:2021-03-15 Published:2021-04-13

摘要/Abstract

摘要： 为了实现对混凝土抗渗性快速而精确地预测,提出了一种基于随机森林(RF)和支持向量机(SVM)的RF-SVM预测模型。首先以氯离子渗透系数为抗渗性评价指标,基于原材料配比确定了混凝土抗渗性的初始指标体系,然后利用随机森林算法结合后向剔除法进行指标筛选,剔除了冗余指标,得到了用于支持向量机建模的最优指标集,最后在此基础上建立了基于支持向量机的混凝土抗渗性预测模型,并研发了RF-SVM算法。以东北某高速公路项目为背景进行应用分析,结果表明,所提出的RF-SVM模型能够有效筛除冗余因素,得到精度较高的预测结果,且预测结果满足工程实践的要求,能够为混凝土抗渗性预测提供一种快速有效的方法。

关键词: 混凝土, 抗渗性, 预测, 随机森林, 支持向量机, 指标筛选

Abstract: In order to predict the impermeability of concrete quickly and accurately, a RF-SVM prediction model based on random forest (RF) and support vector machine (SVM) was proposed. At first, the permeability coefficient of chloride ion was taken as the evaluation index of impermeability, the initial index system of concrete impermeability was determined based on the ratio of raw materials.Then, the random forest algorithm combined with backward elimination method was used to screen the indexes, and the redundant indexes were eliminated, and the optimal set of indexes for support vector machine modeling was obtained. Finally, a prediction model of concrete impermeability based on support vector machine was established, and a RF-SVM algorithm was developed. Based on a highway project in northeast China, the results show that the proposed RF-SVM model effectively screens out the redundant factors and obtains high precision prediction results, which meets the requirements of engineering practice, and provides a fast and effective method for predicting the impermeability of concrete.

Key words: concrete, impermeability, prediction, random forest, support vector machine, index selection

中图分类号:

TU528

吴贤国, 刘茜, 王洪涛, 陈虹宇, 高飞, 黄汉洋. 基于随机森林和支持向量机的高性能混凝土抗渗性预测研究[J]. 硅酸盐通报, 2021, 40(3): 829-835.

WU Xianguo, LIU Xi, WANG Hongtao, CHEN Hongyu, GAO Fei, HUANG Hanyang. Prediction of Impermeability of Concrete Based on Random Forest and Support Vector Machine[J]. BULLETIN OF THE CHINESE CERAMIC SOCIETY, 2021, 40(3): 829-835.

参考文献

[1] 张瑞稳.早龄期混凝土高温作用后力学性能及抗渗性变化研究[D].兰州:兰州交通大学,2018.
ZHANG R W. Study on the changes of mechanical properties and impermeability of early-age concrete after the high temperature[D]. Lanzhou: Lanzhou Jiatong University, 2018 (in Chinese).
[2] 王德志,陈振,孟云芳.氯盐冻融作用下粉煤灰混凝土抗渗抗冻性研究[J].人民黄河,2017,39(12):131-133+138.
WANG D Z, CHEN Z, MENG Y F. Research on permeability and frost resistance of fly ash concrete under chloride and freeze-thawing[J]. Yellow River, 2017, 39(12): 131-133+138 (in Chinese).
[3] 宁逢伟,蔡跃波,白银,等.膨胀剂和硅灰改善C50喷射混凝土抗渗性能的研究[J].硅酸盐通报,2019,38(10):3253-3259.
NING F W, CAI Y B, BAI Y, et al. Research on impermeability improvement of C50 shotcrete with expansive agent and silica fume[J]. Bulletin of the Chinese Ceramic Society, 2019, 38(10): 3253-3259 (in Chinese).
[4] 梁敏飞,封坤,肖明清,等.基于材料试验和细观模型的混凝土渗透性研究[J].建筑材料学报,2020,23(4):801-809.
LIANG M F, FENG K, XIAO M Q, et al. Water permeability of concrete based on materials experiment and mesoscale model[J]. Journal of Building Materials, 2020, 23(4): 801-809 (in Chinese).
[5] 张岩,杜应吉,张文剑.水胶比对塑性混凝土主要性能影响的试验研究[J].混凝土,2020(1):15-18.
ZHANG Y, DU Y J, ZHANG W J. Experimental study on influence of water-to-binder ratio on main properties of plastic concrete[J]. Concrete, 2020(1): 15-18 (in Chinese).
[6] FAN L, MENG W N, TENG L, et al. Effects of lightweight sand and steel fiber contents on the corrosion performance of steel rebar embedded in UHPC[J]. Construction and Building Materials, 2020, 238: 117709.
[7] LIU H Q, ZHANG Y, TONG R M, et al. Effect of nanosilica on impermeability of cement-fly ash system[J]. Advances in Civil Engineering, 2020: 1-13.
[8] XIAO H G, LIU R, ZHANG F L, et al. Role of nano-SiO₂ in improving the microstructure and impermeability of concrete with different aggregate gradations[J]. Construction and Building Materials, 2018, 188: 537-545.
[9] GRANITTO P M, FURLANELLO C, BIASIOLI F, et al. Recursive feature elimination with random forest for PTR-MS analysis of agroindustrial products[J]. Chemometrics and Intelligent Laboratory Systems, 2006, 83(2): 83-90.
[10] XIONG L J, ZHANG D L, ZHANG Y. Water leakage image recognition of shield tunnel via learning deep feature representation[J]. Journal of Visual Communication and Image Representation, 2020, 71: 102708.
[11] 马富齐.基于复数据经验模态分解和随机森林理论的风电机组多域特征故障诊断研究[D].西安:西安理工大学,2019.
MA F Q. Research on multi-domain feature fault diagnosis of wind turbine based on complex empirical mode decomposition and random forest theory[D]. Xi’an: Xi’an University of Technology, 2019 (in Chinese).
[12] 刘方园,王水花,张煜东.支持向量机模型与应用综述[J].计算机系统应用,2018,27(4):1-9.
LIU F Y, WANG S H, ZHANG Y D. Overview on models and applications of support vector machine[J]. Computer Systems & Applications, 2018, 27(4): 1-9 (in Chinese).
[13] YAN H, ZHANG J X, RAHMAN S S, et al. Predicting permeability changes with injecting CO₂ in coal seams during CO₂ geological sequestration: a comparative study among six SVM-based hybrid models[J]. Science of the Total Environment, 2020, 705: 135941.
[14] XU Y, LI Y Y, AHN C K, et al. Seamless indoor pedestrian tracking by fusing INS and UWB measurements via LS-SVM assisted UFIR filter[J]. Neurocomputing, 2020, 388: 301-308.
[15] 苏有彪.冻融-盐溶液腐蚀作用下混凝土损伤规律研究[D].西安:长安大学,2019.
SU Y B. Study on damage rules of concrete under corrosion of freeze-thaw and saline solution[D]. Xi’an: Chang’an University, 2019 (in Chinese).
[16] 王飞,王少强,王建,等.高性能混凝土耐久性能试验研究[J].混凝土,2020(4):107-109.
WANG F, WANG S Q, WANG J, et al. Experimental study on durability of high performance concrete[J]. Concrete, 2020(4): 107-109 (in Chinese).