基于机器学习的高温后聚丙烯纤维混凝土强度预测

硅酸盐通报 ›› 2021, Vol. 40 ›› Issue (2): 455-464.

所属专题：水泥混凝土

基于机器学习的高温后聚丙烯纤维混凝土强度预测

梁宁慧^1,2, 游秀菲^1,2, 曹郭俊^1,2, 刘新荣^1,2, 钟祖良^1,2

1.重庆大学土木工程学院,重庆 400045;
2.库区环境地质灾害防治国家地方联合工程研究中心(重庆大学),重庆 400045

收稿日期:2020-10-13 修回日期:2020-11-22 出版日期:2021-02-15 发布日期:2021-03-10
作者简介:梁宁慧(1971—),女,博士,副教授。主要从事纤维混凝土方面的研究。E-mail:liangninghui0705@163.com
基金资助:
重庆市研究生科研创新项目(CYS20027)

Strength Prediction of Mechanical Properties of Polypropylene Fiber Reinforced Concrete after High Temperature Based on Machine Learning

LIANG Ninghui^1,2, YOU Xiufei^1,2, CAO Guojun^1,2, LIU Xinrong^1,2, ZHONG Zuliang^1,2

1. College of Civil Engineering, Chongqing University, Chongqing 400045, China;
2. National Joint Engineering Research Center of Geohazards Prevention in the Reservoir Areas Chongqing University, Chongqing 400045, China

Received:2020-10-13 Revised:2020-11-22 Online:2021-02-15 Published:2021-03-10

摘要/Abstract

摘要： 影响高温后聚丙烯纤维混凝土(PFRC)力学性能的因素众多,因此相关试验的周期长,试验量大。如何利用现有试验数据预测高温后聚丙烯纤维混凝土的强度能够有效提高试验效率,为实际工程提供参考。通过研究纤维尺度、纤维掺量和温度对混凝土强度的影响,建立纤维尺度、掺量和温度为因子的回归树(RT)、支持向量机回归(SVR)和BP神经网络三种模型。将聚丙烯纤维混凝土在不同受热温度(20 ℃、200 ℃、400 ℃、600 ℃、800 ℃)下的劈裂抗拉强度和抗压强度试验值与预测值进行比较,结果表明:三种模型均能以较高的精度预测高温后聚丙烯纤维混凝土的劈裂抗拉强度和抗压强度;与实测值相比,三种模型预测值与实测值的相对误差基本控制在15%以内,个别数据出现较大预测误差;比较三种模型的平均绝对误差(MAE)和平均相关系数R²,人工神经网络(ANN)模型的预测结果较好,验证了基于机器学习的高温后聚丙烯纤维混凝土力学性能预测的可靠性。

关键词: 机器学习, 聚丙烯纤维, 混凝土, 高温, 强度预测

Abstract: There are many factors affecting the mechanical properties of polypropylene fiber reinforced concrete (PFRC) after high temperature. Therefore, the relevant experimental period is long and experimental volume is large. How to use the existing experimental data to predict the strength of PFRC after high temperature effectively improves the test efficiency and provide reference for practical projects. By studying the influences of fiber scale, fiber content and temperature on concrete strength, three models, namely regression tree (RT), support vector regression (SVR) and BP artificial neural network, were established. The experimental values of splitting tensile strength and compressive strength of PFRC at different heating temperatures (20 ℃, 200 ℃, 400 ℃, 600 ℃, 800 ℃) were compared with the predicted values. The results show that three models predict the splitting tensile strength and compressive strength of PFRC at high temperature with high precision. Compared with the measured value, the relative error between the predicted value and the measured value of three models are basically controlled within 15%, except for individual data. By comparing the mean absolute error (U_MAE) and average correlation coefficient R² of three models, the prediction results of artificial neural network (ANN) model are better, which verifies the reliability of machine learning in predicting the mechanical properties of PFRC after high temperature.

Key words: machine learning, polypropylene fiber, concrete, high temperature, strength prediction

中图分类号:

TU528.572

梁宁慧, 游秀菲, 曹郭俊, 刘新荣, 钟祖良. 基于机器学习的高温后聚丙烯纤维混凝土强度预测[J]. 硅酸盐通报, 2021, 40(2): 455-464.

LIANG Ninghui, YOU Xiufei, CAO Guojun, LIU Xinrong, ZHONG Zuliang. Strength Prediction of Mechanical Properties of Polypropylene Fiber Reinforced Concrete after High Temperature Based on Machine Learning[J]. BULLETIN OF THE CHINESE CERAMIC SOCIETY, 2021, 40(2): 455-464.

参考文献

[1] LI M, QIAN C X, SUN W. Mechanical properties of high-strength concrete after fire[J]. Cement and Concrete Research, 2004, 34(6): 1001-1005.
[2] 余志武,丁发兴,罗建平.高温后不同类型混凝土力学性能试验研究[J].安全与环境学报,2005,5(5):1-6.
YU Z W, DING F X, LUO J P. Experimental research on mechanical properties of different type of concrete after high temperature[J]. Journal of Safety and Environment, 2005, 5(5): 1-6 (in Chinese).
[3] 司秀勇,潘慧敏.纤维对混凝土早期抗裂性能的影响[J].硅酸盐通报,2011,30(6):1425-1429.
SI X Y, PAN H M. Influences of fiber on early crack resistance of concrete[J]. Bulletin of the Chinese Ceramic Society, 2011, 30(6): 1425-1429 (in Chinese).
[4] 金凤杰,许金余,范飞林,等.钢纤维混凝土的高温动态强度特性[J].硅酸盐通报,2013,32(4):683-686.
JIN F J, XU J Y, FAN F L, et al. Strength property of steel fiber reinforced concrete at elevated temperature[J]. Bulletin of the Chinese Ceramic Society, 2013, 32(4): 683-686 (in Chinese).
[5] 张琦,高雪,杜红秀.聚丙烯纤维对高强混凝土高温作用后氯离子渗透性的影响研究[J].混凝土,2015(3):87-89.
ZHANG Q, GAO X, DU H X. Study on the effect of polypropylene fiber about chloride permeability of high performance concrete after high temperature[J]. Concrete, 2015(3): 87-89 (in Chinese).
[6] 吴佳,杜红秀,郝晓玉.聚丙烯纤维长径比对高温后高性能混凝土抗压强度的影响[J].混凝土,2016(3):65-67+75.
WU J, DU H X, HAO X Y. Effect of the aspect ratio of polypropylene fiber on high strength concrete after exposure to high temperature[J]. Concrete, 2016(3): 65-67+75 (in Chinese).
[7] 柳献,袁勇,叶光,等.高性能混凝土高温爆裂的机理探讨[J].土木工程学报,2008,41(6):61-68.
LIU X, YUAN Y, YE G, et al. Investigation on the mechanism of explosive spalling of high performance concrete at elevated temperatures[J]. China Civil Engineering Journal, 2008, 41(6): 61-68 (in Chinese).
[8] 牛旭婧,赵庆新,陈天红.聚丙烯粗纤维对高强混凝土高温后性能影响[J].硅酸盐通报,2013,32(12):2583-2588.
NIU X J, ZHAO Q X, CHEN T H. Effect of polypropylene macro-fiber on properties of high-strength concrete after being exposed to high temperature[J]. Bulletin of the Chinese Ceramic Society, 2013, 32(12): 2583-2588 (in Chinese).
[9] 李地红,高群,夏娴,等.基于BP神经网络的混凝土综合性能预测[J].材料导报,2019,33(s2):317-320.
LI D H, GAO Q, XIA X, et al. Prediction of comprehensive performance of concrete based on BP neural network[J]. Materials Reports, 2019, 33(s2): 317-320 (in Chinese).
[10] HADZIMA-NYARKO M, NYARKO E K, LU H F, et al. Machine learning approaches for estimation of compressive strength of concrete[J]. The European Physical Journal Plus, 2020, 135(8): 682.
[11] CHOPRA P, SHARMA R K, KUMAR M, et al. Comparison of machine learning techniques for the prediction of compressive strength of concrete[J]. Advances in Civil Engineering, 2018, 2018: 1-9.
[12] TANYILDIZI H. Prediction of the strength properties of carbon fiber-reinforced lightweight concrete exposed to the high temperature using artificial neural network and support vector machine[J]. Advances in Civil Engineering, 2018, 2018: 1-10.
[13] CHEN B T, CHANG T P, SHIH J Y, et al. Estimation of exposed temperature for fire-damaged concrete using support vector machine[J]. Computational Materials Science, 2009, 44(3): 913-920.
[14] YANG H Y, DONG Y F. Modelling concrete strength using support vector machines[J]. Applied Mechanics and Materials, 2013, 438/439: 170-173.
[15] 梁宁慧,曹郭俊,刘新荣,等.基于三点弯曲试验的聚丙烯纤维桥接应力研究[J].材料导报,2020,34(2):2153-2158.
LIANG N H, CAO G J, LIU X R, et al. Study on bridging stress of polypropylene fiber based on three-point bending test[J]. Materials Reports, 2020, 34(2): 2153-2158 (in Chinese).
[16] 梁宁慧,刘新荣,孙霁.多尺度聚丙烯纤维混凝土单轴拉伸试验[J].重庆大学学报,2012,35(6):80-84+124.
LIANG N H, LIU X R, SUN J. Uniaxial tensile test of multi-scale polypropylene fiber reinforced concrete[J]. Journal of Chongqing University, 2012, 35(6): 80-84+124 (in Chinese).
[17] 张海燕,刘岩,马丽萌,等.决策树算法的比较与应用研究[J].华北电力技术,2017(6):42-47.
ZHANG H Y, LIU Y, MA L M, et al. Comparison and application of decision tree algorithm[J]. North China Electric Power, 2017(6): 42-47 (in Chinese).
[18] 段小手.深入浅出Python机器学习[M].北京:清华大学出版社,2018.
DUAN X S. Start with Python machine learning[M]. Beijing: Tsinghua University Press, 2018 (in Chinese).
[19] 胡鑫.基于人工神经网络的HPC强度预测[D].长沙:湖南大学, 2014.
HU X. Prediction of high performance concrete strength based on artificial neural network[D]. Changsha: Hunan University, 2014 (in Chinese).
[20] 周志华.机器学习[M].北京:清华大学出版社,2016.
ZHOU Z H. Machine learning[M]. Beijing: Tsinghua University Press, 2016 (in Chinese).
[21] YAN K Z, SHI C J. Prediction of elastic modulus of normal and high strength concrete by support vector machine[J]. Construction and Building Materials, 2010, 24(8): 1479-1485.
[22] 王继宗,倪宏光.基于BP神经网络的水泥抗压强度预测研究[J].硅酸盐学报,1999,27(4):3-5.
WANG J Z, NI H G. Prediction of compressive strength of cement based on BP neural networks[J]. Journal of the Chinese Ceramic Society, 1999, 27(4): 3-5 (in Chinese).
[23] 沈花玉,王兆霞,高成耀,等.BP神经网络隐含层单元数的确定[J].天津理工大学学报,2008,24(5):13-15.
SHEN H Y, WANG Z X, GAO C Y, et al. Determining the number of BP neural network hidden layer units[J]. Journal of Tianjin University of Technology, 2008, 24(5): 13-15 (in Chinese).

基于机器学习的高温后聚丙烯纤维混凝土强度预测

Strength Prediction of Mechanical Properties of Polypropylene Fiber Reinforced Concrete after High Temperature Based on Machine Learning

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]	刘恩铭, 林明强, 谢群. 再生粗骨料混凝土抗冻性能研究进展[J]. 硅酸盐通报, 2022, 41(9): 2963-2978.
[2]	韩强强, 路伟, 姜鲁, 王亚妹. 微生物菌落体系对混凝土裂缝自修复效果的影响综述[J]. 硅酸盐通报, 2022, 41(9): 2993-3007.
[3]	佘亮, 傅平丰, 邓威, 陈雨齐, 王显聪. 联合活化多元辅助胶凝材料对蒸养混凝土性能的影响[J]. 硅酸盐通报, 2022, 41(9): 3059-3067.
[4]	肖世玉, 彭丙杰, 吴涛, 罗小东, 陶俊. 砂率及机制砂特性对混凝土流动性与颗粒膜层厚度的影响[J]. 硅酸盐通报, 2022, 41(9): 3068-3076.
[5]	单继雄, 李军, 侯永生, 胡艳民, 刘畅. 钙铝类水滑石对混凝土抗盐冻性能的影响[J]. 硅酸盐通报, 2022, 41(9): 3084-3090.
[6]	余波, 黄俊辉, 汪加梁, 秦荷成. 考虑材料参数和应力水平的氯离子扩散系数多因素预测模型[J]. 硅酸盐通报, 2022, 41(9): 3091-3099.
[7]	王萧萧, 冯蓉蓉, 荆磊, 刘曙光, 闫长旺, 姜琳. 冰凌作用下天然浮石混凝土磨损规律研究[J]. 硅酸盐通报, 2022, 41(9): 3100-3106.
[8]	楼建敏, 张国辉, 杨振东, 孙俊崇, 李虎. 基于楔入劈拉法的湿态混凝土双K断裂特性试验研究[J]. 硅酸盐通报, 2022, 41(9): 3107-3114.
[9]	赵雅明, 张振, 王畔, 张明飞. 矿物掺合料对UHPC性能的影响[J]. 硅酸盐通报, 2022, 41(9): 3170-3175.
[10]	王晨晨, 王学志, 陈东林, 贺晶晶. 基于正交试验的粉煤灰-硅锰渣再生混凝土力学性能研究[J]. 硅酸盐通报, 2022, 41(9): 3190-3201.
[11]	李成, 耿晨梓, 代丹, 王春雨, 宋维凯, 姚晓. 废弃玻璃粉对水泥石高温抗压强度和微观结构的影响[J]. 硅酸盐通报, 2022, 41(9): 3219-3226.
[12]	董博, 闵昌胜, 陈博, 邓承继, 谢哲, 杨千秋, 丁军, 祝洪喜, 杨昕雨, 余超. 陶瓷相结合粉煤灰漂珠轻质隔热材料的制备及性能研究[J]. 硅酸盐通报, 2022, 41(9): 3315-3323.
[13]	韦建刚, 陈荣, 黄伟, 陈镇东, 陈宝春, 陈培标, 朱卫东. 静水压力下超高性能混凝土的抗氯离子渗透性能[J]. 硅酸盐通报, 2022, 41(8): 2706-2715.
[14]	张庆章, 方燕, 宋力, 徐宁, 康子寒. 混凝土孔结构及其分形维数与氯离子扩散性能的关系[J]. 硅酸盐通报, 2022, 41(8): 2716-2727.
[15]	孙杰, 冯川, 吴爽, 马稳, 孙明星. 持续荷载与冻融循环耦合作用下纤维混凝土损伤性能研究[J]. 硅酸盐通报, 2022, 41(8): 2728-2738.