Inverse Analysis of Thermal Parameters of Concrete Box Girder Based on DE-BP Neural Network

Authors

YAO Yong, China National Chemical Construction Investment Co ., Ltd., Beijing 102308 , ChinaFollow
YAN Yu, China National Chemical Construction Investment Co ., Ltd., Beijing 102308 , China
SUN Bo wen, China National Chemical Construction Investment Co ., Ltd., Beijing 102308 , China
WANG Yuesong, Central Southern Safety & Environment Technology Institute Co ., Ltd., Wuhan , Hubei 430081 , China
JIANG Tianyong, School of Civil and Environmental Engineering , Changsha University of Science & Technology , Changsha , Hunan 410114 , ChinaFollow

Corresponding Author

蒋田勇，男，博士，教授.E-mail：tianyongjiang@csust.edu.cn

Abstract

In view of temperature cracks in concrete box girders easily occurring during construction,an inverse analysis method based on uniform design theory and differential evolution back propagation (DE-BP ) neural network was proposed to accurately obtain the thermal parameters of concrete box girders and ensure the reliability of temperature analysis of concrete box girders.This method established the nonlinear relationship between the temperature peak of characteristic points and the thermal parameters through the DE-BP neural network.By using the uniform design method and the Abaqus finite element numerical model,130 sets of sample data were generated.Based on the ratio of 12∶1 for training samples to test samples,the back analysis model was trained.The results show that the mean absolute percentage errors EMAPE of the DE-BP neural network model are all less than 3%,and the relative errors are less than 5%.This indicates that the prediction accuracy of the BP neural network can be effectively improved by the DE algorithm.The maximum error of the temperature peak for the characteristic points based on inversion analysis is 2.05 ℃,and the calculated temperature histories are in good agreement with the actual ones.In a word,the back analysis method of thermal parameters for the concrete box girder based on the DE-BP neural network and uniform design theory demonstrates high accuracy and a stable inversion process with good reliability,which can provide a theoretical basis for temperature control of other similar projects.

Publication Date

6-23-2025

DOI

10.14048/j.issn.1671-2579.2025.03.014

First Page

112

Last Page

120

Submission Date

August 2025

Recommended Citation

Yong, YAO; Yu, YAN; Bo wen, SUN; Yuesong, WANG; and Tianyong, JIANG (2025) "Inverse Analysis of Thermal Parameters of Concrete Box Girder Based on DE-BP Neural Network," Journal of China & Foreign Highway: Vol. 45: Iss. 3, Article 14.
DOI: 10.14048/j.issn.1671-2579.2025.03.014
Available at: https://zwgl1980.csust.edu.cn/journal/vol45/iss3/14

Reference

[1]胡健中,李阳,张申昕.大体积混凝土施工水化热分析与控制 [J].中外公路,2020,40(4):110-115.HU Jianzhong,LI Yang,ZHANG Shenxin.Control and analysis of hydration heat for mass concrete during construction [J].Journal of China & Foreign Highway,2020,40(4):110-115.
[2]朱岳明,刘勇军,谢先坤.确定混凝土温度特性多参数的试验与反演分析 [J].岩土工程学报,2002,24(2):175-177.ZHU Yueming,LIU Yongjun,XIE Xiankun.Determination of thermal parameters of concrete by reverse analysis of test results [J].Chinese Journal of Geotechnical Engineering,2002,24(2):175-177.
[3]吕彬,李莹炜,雷永军,等.基于改进遗传算法的大体积混凝土温度场预测模型 [J].中外公路,2021,41(5):155-159.LYU Bin,LI Yingwei,LEI Yongjun,et al.Prediction model of temperature field of mass concrete based on improved genetic algorithm [J].Journal of China & Foreign Highway,2021,41(5):155-159.
[4]袁军峰,张建东,刘朵,等.大跨连续箱梁桥 0#块高强混凝土 水 化 热 及 温 控 措 施 分 析 [J].中 外 公 路,2019,39(5):97-101.YUAN Junfeng,ZHANG Jiandong,LIU Duo,et al.Analysis of hydration heat and temperature control measures for high-strength concrete of the zero block of long span continuous box girder bridge [J].Journal of China & Foreign Highway,2019,39(5):97-101.
[5]张宁,周鑫,刘永健,等.基于点阵式测量的混凝土箱梁水化热温度场原位试验 [J].土木工程学报,2019,52(3):76-86.ZHANG Ning,ZHOU Xin,LIU Yongjian,et al.In-situ test on hydration heat temperature of box girder based on array measurement [J].China Civil Engineering Journal,2019,52(3):76-86.
[6]孙维刚,张光磊,刘来君,等.基于标准粒子群算法的混凝土 箱 梁 水 化 热 过 程 热 工 参 数 反 演 [J].江 苏 大 学 学 报 (自然科学版 ),2019,40(5):608-613,620.Thermal parameters inversion in hydration thermal process of concrete box girder based on SPSO algorithm[J].Journal of Jiangsu University (Natural Science Edition ),2019,40(5):608-613,620.
[7]马超.基于 BP神经网络的大体积混凝土温度场正反分析研究 [D].长沙:长沙理工大学,2020.MA Chao.Positive and negative analysis of mass concrete temperature field based on BP neural network [D].Changsha:Changsha University of Science & Technology,2020.
[8]王峰,周宜红,赵春菊,等.基于混合粒子群算法的特高拱坝 不 同 材 料 热 学 参 数 反 演 分 析 [J].清 华 大 学 学 报 (自 然科学版 ),2021,61(7):747-755.WANG Feng,ZHOU Yihong,ZHAO Chunju,et al.Thermal parameter inversion for various materials of super high arch dams based on the hybrid particle swarm optimization method [J].Journal of Tsinghua University (Science and Technology ),2021,61(7):747-755.
[9]徐 江 宇.RCC 重 力 坝 固 结 灌 浆 期 间 仓 面 裂 缝 成 因 探 讨[D].武汉:武汉大学,2017.XU Jiangyu.Discussion on surface cracks of RCC gravity dam during consolidation grouting [D].Wuhan:Wuhan University,2017.
[10]曾令福,邹爽,陈兴梅,等.基于响应面优化的堆石混凝土热学参数反分析 [J].水利规划与设计,2021 (9):81-86.ZENG Lingfu,ZOU Shuang,CHEN Xingmei,et al.Back analysis of thermal parameters of rockfill concrete based on response surface optimization [J].Water Resources Planning and Design,2021 (9):81-86.
[11]何伟,袁亚芳,白冰,等.融合遗传算法与改进响应面技术的混凝土热学参数反分析 [J].水力发电,2020,46(3):56-60.HE Wei,YUAN Yafang,BAI Bing,et al.Inverse analysis of thermal parameters of concrete combining genetic algorithm and improved response surface technique [J].Water Power,2020,46(3):56-60.
[12]张石,李同春,程井,等.基于人工蜂群算法的大体积混凝土 温 度 场 参 数 反 演 [J].水 电 能 源 科 学,2014,32(11):115-117,62.ZHANG Shi,LI Tongchun,CHENG Jing,et al.Parameter inversion of massive concrete temperature field based on artificial bee colony algorithm [J].Water Resources and Power,2014,32(11):115-117,62.
[13]章 国 美,朱 岳 明.基 于 快 速 模 拟 退 火 算 法 的 混 凝 土 热 学参数反演分析 [J].水利水电技术,2007,38(1):56-58.ZHANG Guomei,ZHU Yueming.Inverse analysis on concrete thermal parameters based on fast simulated annealing algorithm [J].Water Resources and Hydropower Engineering,2007,38(1):56-58.
[14]倪 智 强,周 兰 庭.基 于 改 进 蚁 群 算 法 的 混 凝 土 坝 热 学 参数反演 [J].水电能源科学,2018,36(4):82-85.NI Zhiqiang,ZHOU Lanting.Inverse analysis of concrete dam thermal parameters based on improved ant colony algorithm [J].Water Resources and Power,2018,36(4):82-85.
[15]邹科辉,魏李威,邓群,等.基于改进鲸鱼优化算法的大体积 混 凝 土 热 学 参 数 反 演 [J].水 电 能 源 科 学,2022,40(3):162-165,157.ZOU Kehui,WEI Liwei,DENG Qun,et al.Thermal parameter inversion of mass concrete based on improved whale optimization algorithm [J].Water Resources and Power,2022,40(3):162-165,157.
[16]张 玉 平,马 超,李 传 习,等.基 于 均 匀 设 计 及 BP神 经 网 络的大体积混凝土热学参数反分析 [J].土木与环境工程学报(中英文 ),2021,43(2):148-157.ZHANG Yuping,MA Chao,LI Chuanxi,et al.Inverse analysis on thermal parameters of mass concrete based on uniform design and BP neural network [J].Journal of Civil and Environmental Engineering,2021,43(2):148-157.
[17]王润英,李天翔,曾凤华.基于小波神经网络的混凝土热力 学 参 数 反 演 [J].水 电 能 源 科 学,2014,32(12):107-109,113.WANG Runying,LI Tianxiang,ZENG Fenghua.Back analysis of concrete thermal parameters based on wavelet neural network [J].Water Resources and Power,2014,32(12):107-109,113.
[18]王放.考虑测点灵敏度的高拱坝混凝土热学参数反演方法研究 [D].宜昌:三峡大学,2018.WANG Fang.Inversion method of high arch dam concrete thermal parameters considering measuring point sensitivity [D].Yichang:China Three Gorges University,2018.
[19]王 月.高 温 季 节 拱 坝 孔 口 混 凝 土 温 控 反 馈 分 析 [D].宜昌:三峡大学,2020.WANG Yue.Feedback analysis of temperature control of arch dam orifice concrete in high temperature season [D].Yichang:China Three Gorges University,2020.
[20]韩燕华,傅少君,王书法.基于水化度的热学参数对混凝土 温 度 场 影 响 分 析 [J].武 汉 大 学 学 报 (工 学 版 ),2019,52(12):1064 -1069.HAN Yanhua,FU Shaojun,WANG Shufa.Influence of thermal parameters on temperature field of concrete based on hydration degree [J].Engineering Journal of Wuhan University,2019,52(12):1064 -1069.
[21]朱伯芳.大体积混凝土温度应力与温度控制 [M].2版.北京:中国水利水电出版社,2012.ZHU Bofang.Temperature stress and temperature control of mass concrete [M].2nd ed.Beijing:China Water & Power Press,2012.