基于机器学习的高温损伤后UHPC残余抗压强度预测

头部文案

发布时间：2020-01-06 00:00:00

全国建材科技期刊
全国中文核心期刊
中国科技论文统计源期刊
万方数据-数字化期刊群入网期刊
中国学术期刊（光盘版）全文收录期刊

华东地区优秀科技期刊
江苏省期刊方阵“双效期刊”
中国期刊网全文收录期刊
中国科技期刊数据库全文收录期刊



基于机器学习的高温损伤后UHPC残余抗压强度预测

Machine learning based prediction of residual compressive strength of UHPC after high temperature damage

2025年第2期

超高性能混凝土；残余抗压强度；高温损伤；机器学习；预测

2025年第2期

10.19761/j.1000-4637.2025.02.001.07

国家自然科学基金项目（51708349）；浙江省自然科学基金项目（LY20E080017）；温州市科协服务科技创新项目（kjfw53）。

欧阳利军1，容文照1，谢冰清1，丁斌2

1.上海理工大学环境与建筑学院，上海 200093；2.温州职业技术学院建筑工程系，浙江温州 325035

欧阳利军1，容文照1，谢冰清1，丁斌2

欧阳利军,容文照,谢冰清,等.基于机器学习的高温损伤后UHPC残余抗压强度预测[J].混凝土与水泥制品,2025(2):1-7.

OUYANG L J,RONG W Z,XIE B Q,et al.Machine learning based prediction of residual compressive strength of UHPC after high temperature damage[J].China Concrete and Cement Products,2025(2):1-7.

浏览量:

1000

摘要：以水胶比、m硅灰/m水泥、m粉煤灰/m水泥、m石英砂/m水泥、m石英粉/m水泥、钢纤维掺量、PP纤维掺量、常温标准养护、热水养护、干热养护和加热温度11个影响因素为输入变量，建立了BP神经网络、麻雀搜索算法优化人工神经网络、遗传算法优化人工神经网络（GA-BP）和支持向量机回归四种模型，并对高温损伤后的超高性能混凝土（UHPC）残余抗压强度进行了预测。结果表明：与基于试验经验的计算模型预测结果相比，以上4个机器学习模型的预测精度较高，误差基本控制在15%以内，其中，GA-BP模型的预测结果最优，R2达到0.949。 Abstract: By using 11 influencing factors of water-cement ratio, msilica /mcement, mfly ash /mcement, msand /mcement, mquartz powder /mcement, steel fiber content, PP fiber content, room temperature standard curing, hot water curing, dry heat curing and heating temperature as input variables, four models of a BP neural network, sparrow Search Algorithm Optimized Artificial Neural Network, Genetic Algorithm Optimized Artificial Neural Network(GA-BP), and Support Vector Machine Regression were established to predict the residual compressive strength of ultra-high performance concrete(UHPC) after high temperature damage. The results show that compared with the prediction results of experimental experience calculation models, the four machine learning models have higher prediction accuracy, with an error basically within 15%. Among them, the GA-BP model has the best prediction result, with the R2 of 0.949.

英文名 : Machine learning based prediction of residual compressive strength of UHPC after high temperature damage

刊期 : 2025年第2期

关键词 : 超高性能混凝土；残余抗压强度；高温损伤；机器学习；预测

Key words : 超高性能混凝土；残余抗压强度；高温损伤；机器学习；预测

刊期 : 2025年第2期

DOI : 10.19761/j.1000-4637.2025.02.001.07

文章编号 :

基金项目 : 国家自然科学基金项目（51708349）；浙江省自然科学基金项目（LY20E080017）；温州市科协服务科技创新项目（kjfw53）。

作者 : 欧阳利军1，容文照1，谢冰清1，丁斌2

单位 : 1.上海理工大学环境与建筑学院，上海 200093；2.温州职业技术学院建筑工程系，浙江温州 325035

欧阳利军1，容文照1，谢冰清1，丁斌2

欧阳利军,容文照,谢冰清,等.基于机器学习的高温损伤后UHPC残余抗压强度预测[J].混凝土与水泥制品,2025(2):1-7.

OUYANG L J,RONG W Z,XIE B Q,et al.Machine learning based prediction of residual compressive strength of UHPC after high temperature damage[J].China Concrete and Cement Products,2025(2):1-7.





摘要

参数

结论

参考文献

引用本文

摘要：以水胶比、m_硅灰/m_水泥、m_粉煤灰/m_水泥、m_石英砂/m_水泥、m_石英粉/m_水泥、钢纤维掺量、PP纤维掺量、常温标准养护、热水养护、干热养护和加热温度11个影响因素为输入变量，建立了BP神经网络、麻雀搜索算法优化人工神经网络、遗传算法优化人工神经网络（GA-BP）和支持向量机回归四种模型，并对高温损伤后的超高性能混凝土（UHPC）残余抗压强度进行了预测。结果表明：与基于试验经验的计算模型预测结果相比，以上4个机器学习模型的预测精度较高，误差基本控制在15%以内，其中，GA-BP模型的预测结果最优，R²达到0.949。

Abstract: By using 11 influencing factors of water-cement ratio, m_silica /m_cement, m_{fly ash} /m_cement, m_sand /m_cement, m_{quartz powder} /m_cement, steel fiber content, PP fiber content, room temperature standard curing, hot water curing, dry heat curing and heating temperature as input variables, four models of a BP neural network, sparrow Search Algorithm Optimized Artificial Neural Network, Genetic Algorithm Optimized Artificial Neural Network(GA-BP), and Support Vector Machine Regression were established to predict the residual compressive strength of ultra-high performance concrete(UHPC) after high temperature damage. The results show that compared with the prediction results of experimental experience calculation models, the four machine learning models have higher prediction accuracy, with an error basically within 15%. Among them, the GA-BP model has the best prediction result, with the R² of 0.949.

扫二维码用手机看

[1] 徐妍.基于集成方法的建筑火灾财产损失与伤亡预测[D].大连:大连理工大学,2021.
[2] KODUR V K R,RAUT N K,MAO X Y,et al.Simplified approach for evaluating residual strength of fire-exposed reinforced concrete columns[J].Materials and Structures,2013,46(12):2059-2075.
[3] TAI Y,PAN H,KUNG Y.Mechanical properties of steel fiber reinforced reactive powder concrete following exposure to high temperature reaching 800 ℃[J].Nuclear Engineering and Design, 2011,241(7):2416-2424.
[4] GUO Y,ZHANG J,CHEN G,et al.Compressive behaviour of concrete structures incorporating recycled concrete aggregates, rubber crumb and reinforced with steel fibre, subjected to elevated temperatures[J].Journal of Cleaner Production,2014,72:193-203.

[5] FRANCESCA S,STEFANO F,MARCO F,et al.Ultra-high performance concrete(UHPC) with polypropylene(PP) and steel fibres: Investigation on the high temperature behaviour[J].Construction and Building Materials,2021,304:124608.
[6] 钱云峰,杨鼎宜,夏旸昊,等.纤维对含粗骨料超高性能混凝土高温性能的影响[J].混凝土与水泥制品,2021(2):51-56.
[7] 陈国涛,梅志远,夏奕.舰用复合材料S2/430LV高温压缩性能及预报[J/OL].复合材料学报,2023(5):1-11[2024-03-04].https://doi.org/10.13801/j.cnki.fhclxb.20230526.001.
[8] 欧阳利军,许峰,高皖扬,等.玄武岩纤维布约束高温损伤混凝土方柱轴压力学性能试验[J].复合材料学报,2019,36(2):469-481.
[9] KAHANJI C,FARIS A,ALI N,et al.Effect of curing temperature on the behaviour of UHPFRC at elevated temperatures[J].Construction and Building Materials,2018,182:670-681.
[10] GONG J Q,DENG G Q,SHAN B.Performance evaluation of RPC exposed to high temperature combining ultrasonic test: A case study [J].Construction and Building Materials,2017,157:194-202.
[11] 陈庆,马瑞,蒋正武,等.基于GA-BP神经网络的UHPC抗压强度预测与配合比设计[J].建筑材料学报,2020,23(1):176-191.
[12] GHAFARI E,BANDARABADI M,COSTA H,et al.Design of UHPC using artificial neural networks[J].Brittle Matrix Composites 10,2012,145:61-69.
[13] 刘德胜.基于机器学习算法的混凝土28 d抗压强度预测[J].混凝土与水泥制品,2022(9):20-24.
[14] KANNAN R P R,DURGA P M,SUDHA C,et al.Experimental investigation of reactive powder concrete exposed to elevated temperatures[J].Construction and Building Materials,2020,261:119593.
[15] YANG J,PENG G F,ZHAO J,et al.On the explosive spalling behavior of ultra-high performance concrete with and without coarse aggregate exposed to high temperature[J].Construction and Building Materials,2019,226:932-944.
[16] LI S,LIEW J Y R.Experimental and data-driven analysis on compressive strength of steel fibre reinforced high strength concrete and mortar at elevated temperature[J].Construction and Building Materials,2022,341:127845.
[17] 杨婷,刘中宪,杨烨凯,等.超高性能混凝土高温后性能试验研究[J].土木与环境工程学报(中英文),2020,42(3):115-126.
[18] 欧阳利军,钱鹏,高皖扬,等.养护制度对超高性能混凝土高温损伤后残余力学性能的影响[J].工业建筑,2020,50(8):92-100.
[19] 杨娟,朋改非.钢纤维类型对超高性能混凝土高温爆裂性能的影响[J].复合材料学报,2018,35(6):1599-1608.
[20] JU Y,WANG L,LIU H B.An experimental investigation of the thermal spalling of polypropylene-fibered reactive powder concrete exposed to elevated temperatures[J].Science Bulletin,2015,60(23):2022-2040.
[21] PENG G F,KANG Y R,HUANG Y Z.Experimental research on fire resistance of reactive powder concrete[J].Advances in Materials Science and Engineering,2012,12:1-6.
[22] ASHKEZARI G D,RAZMARA M.Thermal and mechanical evaluation of ultra-high performance fiber-reinforced concrete and conventional concrete subjected to high temperatures[J].Journal of Building Engineering,2020,32:101621.
[23] RAZA S S,QURESHI L A.Effect of carbon fiber on mechanical properties of reactive powder concrete exposed to elevated temperatures[J].Journal of Building Engineering,2021,42:102503.
[24] LIANG X,WU C,SU Y,et al.Development of ultra-high performance concrete with high fire resistance[J].Construction and Building Materials,2018,179:400-412.
[25] 张剑.基于代理模型技术的高速列车性能参数设计及优化[D].成都:西南交通大学,2015.
[26] 蔡自兴,王勇.智能系统原理、算法与应用[M].北京:机械工业出版社,2014.
[27] HORNIK K.Approximation capabilities of multi-layer feed-forward networks[J].Neural Network,1991,4(2):251-257.
[28] XUE J K,SHEN B.A novel swarm intelligence optimization approach: sparrow search algorithm[J].Systems Science and Control Engineering,2020,8(1):22-34.
[29] TU X,ZHOU Y F,ZHAO P,et al.Modeling the static friction in a robot joint by genetically optimized BP neural network[J].Journal of Intelligent and Robotic Systems,2019,94(1):29-41.
[30] KHALICK M,HONG J,WANG D W.Polishing of uneven surfaces using industrial robots based on neural network and genetic algorithm[J].The International Journal of Advanced Manufacturing Technology,2017,93(1-4):1463-1471.
[31] SHEN X R,ZHENG Y X,ZHANG R F.A hybrid forecasting model for the velocity of hybrid robotic fish based on back-propagation neural network with genetic algorithm optimization[J].IEEE Access,2020,8:111731-111741.
[32] CORTES C,VAPNIK V.Support-vector networks [J].Machine Learning,1995,20:273-297.
[33] ZHENG W Z,LI H Y,WANG Y.Compressive behaviour of hybrid fiber-reinforced reactive powder concrete after high temperature[J].Materials and Design,2012,41:403-409.
[34] XIAO J Z,FALKNER H.On residual strength of high-performance concrete with and without polypropylene fibres at elevated temperatures[J].Fire Safety Journal,2006,41(2):115-121.

上一个

缠丝过程中PCCP管芯变形的试验研究与数值模拟

下一个

温度、相对湿度循环下砂浆的硫酸盐半浸泡损伤机理研究

头部文案

基于机器学习的高温损伤后UHPC残余抗压强度预测

相关文件