基于IAGA-BP算法的高拱坝-坝基力学参数反演分析

庄文宇, 张如九, 徐建军, 殷亮, 魏海宁, 刘耀儒

清华大学学报(自然科学版) ›› 2022, Vol. 62 ›› Issue (8) : 1302-1313.

PDF(12253 KB)
PDF(12253 KB)
清华大学学报(自然科学版) ›› 2022, Vol. 62 ›› Issue (8) : 1302-1313. DOI: 10.16511/j.cnki.qhdxxb.2022.25.034
智能预测反馈

基于IAGA-BP算法的高拱坝-坝基力学参数反演分析

  • 庄文宇1, 张如九1, 徐建军2, 殷亮2, 魏海宁2, 刘耀儒1
作者信息 +

Inversion analysis to determine the mechanical parameters of a high arch dam and its foundation based on an IAGA-BP algorithm

  • ZHUANG Wenyu1, ZHANG Rujiu1, XU Jianjun2, YIN Liang2, WEI Haining2, LIU Yaoru1
Author information +
文章历史 +

摘要

基于监测资料对坝体和坝基的力学参数进行反演,对大坝的安全评价具有重要意义。该文提出了基于改进自适应遗传算法和BP神经网络(IAGA-BP)的力学参数反演分析方法,采用考虑权重的绝对百分误差作为目标函数,可以针对多点监测资料和非线性数值仿真进行力学参数反演。基于正常蓄水位下拱坝坝体、坝基及拱肩槽边坡等25个测点的实测变形,对坝体混凝土、基础岩体及结构面的多个材料分区的11个关键力学参数进行了反演分析。结果表明,反演值和实测值吻合较好,将材料参数作为输入层、测点变形作为输出层有效避免了反演值的“失真”问题。针对高拱坝-坝基系统的力学参数反演,分析了神经网络拓扑结构、目标函数、训练样本数量等对反演结果的影响。

Abstract

Using an inversion analysis to determine the mechanical parameters of a dam and its foundation from monitoring data is of great significance to safety evaluation. An inversion analysis method was developed based on an adaptive genetic algorithm and a BP neural network. The analysis used the weighted absolute percentage error as the objective function to determine the mechanical parameters from multi-point monitoring data and nonlinear numerical simulations. Deformation data from 25 measurement points was used to determine 11 key mechanical parameters for the dam concrete, foundation rock mass and structural plane. The results show that the inversion values are in good agreement with measured data. The inversion accuracy is improved by using the material parameters as the input layer and the deformation as the output layer. The effects of the neural network topology, objective function and the number of training samples on the inversion results was analyzed.

关键词

高拱坝 / IAGA / BP神经网络 / 参数反演

Key words

high arch dam / IAGA / BP neural network / parameter inversion

引用本文

导出引用
庄文宇, 张如九, 徐建军, 殷亮, 魏海宁, 刘耀儒. 基于IAGA-BP算法的高拱坝-坝基力学参数反演分析[J]. 清华大学学报(自然科学版). 2022, 62(8): 1302-1313 https://doi.org/10.16511/j.cnki.qhdxxb.2022.25.034
ZHUANG Wenyu, ZHANG Rujiu, XU Jianjun, YIN Liang, WEI Haining, LIU Yaoru. Inversion analysis to determine the mechanical parameters of a high arch dam and its foundation based on an IAGA-BP algorithm[J]. Journal of Tsinghua University(Science and Technology). 2022, 62(8): 1302-1313 https://doi.org/10.16511/j.cnki.qhdxxb.2022.25.034

参考文献

[1] 程井, 孟凡轩, 李宗樾. 基于实测资料的混凝土拱坝反馈分析及安全度评价[J]. 武汉大学学报(工学版), 2019, 52(4):297-302, 310. CHENG J, MENG F X, LI Z Y. Feedback analysis and safety degree evaluation of concrete arch dam based on measured data[J]. Engineering Journal of Wuhan University, 2019, 52(4):297-302, 310. (in Chinese)
[2] 刘毅, 高阳秋晔, 张国新, 等. 锦屏一级特高拱坝工作性态仿真与反演分析[J]. 水利水电技术, 2017, 48(1):46-51. LIU Y, GAOYANG Q Y, ZHANG G X, et al. Simulation and inversion analysis on working behavior of super-high arch dam of Jinping I Hydropower Station[J]. Water Resources and Hydropower Engineering, 2017, 48(1):46-51. (in Chinese)
[3] 胡清义, 朱喜, 田功臣. 构皮滩拱坝坝体与坝基变形模量反演分析[J]. 武汉大学学报(工学版), 2021, 54(9):801-809. HU Q Y, ZHU X, TIAN G C. Inversion analysis of deformation modulus of Goupitan high arch dam and its foundation rock[J]. Engineering Journal of Wuhan University, 2021, 54(9):801-809. (in Chinese)
[4] 何柱, 刘耀儒, 杨强, 等. 基于位移反分析的小湾拱坝稳定性评价[J]. 岩石力学与工程学报, 2013, 32(11):2242-2249. HE Z, LIU Y R, YANG Q, et al. Research on stability estimation of Xiaowan arch dam based on displacement back analysis[J]. Chinese Journal of Rock Mechanics and Engineering, 2013, 32(11):2242-2249. (in Chinese)
[5] BUKENYA P, MOYO P, BEUSHAUSEN H, et al. Health monitoring of concrete dams:A literature review[J]. Journal of Civil Structural Health Monitoring, 2014, 4(4):235-244.
[6] 何柱, 刘耀儒, 杨强, 等. 溪洛渡拱坝谷幅变形机制及变形反演和长期稳定性分析[J]. 岩石力学与工程学报, 2018, 37(S2):4198-4206. HE Z, LIU Y R, YANG Q, et al. Mechanism of valley deformation of Xiluodu arch dam and back analysis and long-term stabilyty analysis[J]. Chinese Journal of Rock Mechanics and Engineering, 2018, 37(S2):4198-4206. (in Chinese)
[7] 程立, 刘耀儒, 潘元炜, 等. 基于蓄水期反演的锦屏一级拱坝极限承载力分析[J]. 岩土力学, 2016, 37(5):1388-1398. CHENG L, LIU Y R, PAN Y W, et al. Research on ultimate bearing capacity of Jinping-I Arch Dam based on impoundment period inversion[J]. Rock and Soil Mechanics, 2016, 37(5):1388-1398. (in Chinese)
[8] 杨剑, 王进廷, 王吉焕, 等. 二滩拱坝及坝基材料参数反馈分析[J]. 水力发电学报, 2008, 27(2):78-83. YANG J, WANG J T, WANG J H, et al. Feedback analysis of material parameters of Ertan arch dam and its foundation rock[J]. Journal of Hydroelectric Engineering, 2008, 27(2):78-83. (in Chinese)
[9] 梁国贺, 胡昱, 樊启祥, 等. 溪洛渡高拱坝蓄水期谷幅变形特性与影响因素分析[J]. 水力发电学报, 2016, 35(9):101-110. LIANG G H, HU Y, FAN Q X, et al. Analysis on valley deformation of Xiluodu high arch dam during impoundment and its influencing factors[J]. Journal of Hydroelectric Engineering, 2016, 35(9):101-110. (in Chinese)
[10] 赵英华, 李同春, 程井, 等. 基于统计模型及有限元法的重力坝变形模量反演[J]. 水电能源科学, 2015, 33(12):96-100. ZHAO Y H, LI T C, CHENG J, et al. Inverse analysis of deformation modulus of gravity dam based on statistic model and finite element method[J]. Water Resources and Power, 2015, 33(12):96-100. (in Chinese)
[11] 冯帆, 邱信蛟, 张国新, 等. 基于施工期变形监测的特高拱坝力学参数反演研究[J]. 岩土力学, 2017, 38(1):237-246. FENG F, QIU X J, ZHANG G X, et al. Inversion of mechanical parameters of super-high arch dam based on deformation monitoring during construction period[J]. Rock and Soil Mechanics, 2017, 38(1):237-246. (in Chinese)
[12] 李宗樾, 程井, 张枝阳, 等. 基于有限元法的高拱坝分区变形模量反演分析[J]. 三峡大学学报(自然科学版), 2018, 40(4):1-5. LI Z Y, CHENG J, ZHANG Z Y, et al. Parameter inversion of regional deformation modulus for high arch dam using FEM[J]. Journal of China Three Gorges University (Natural Sciences), 2018, 40(4):1-5. (in Chinese)
[13] 黄耀英, 黄光明, 吴中如, 等. 基于变形监测资料的混凝土坝时变参数优化反演[J]. 岩石力学与工程学报, 2007, 26(S1):2941-2945. HUANG Y Y, HUANG G M, WU Z R, et al. Optimization inversion of concrete dam's time-dependent parameters based on deformation monitoring data[J]. Chinese Journal of Rock Mechanics and Engineering, 2007, 26(S1):2941-2945. (in Chinese)
[14] 刘福深, 刘耀儒, 杨强, 等. 基于改进遗传算法的拱坝位移反分析[J]. 岩石力学与工程学报, 2005, 24(23):4341-4345. LIU F S, LIU Y R, YANG Q, et al. Displacement back analysis of arch dams based on improved genetic algorithm[J]. Chinese Journal of Rock Mechanics and Engineering, 2005, 24(23):4341-4345. (in Chinese)
[15] 刘耀儒, 杨强, 刘福深, 等. 基于并行改进遗传算法的拱坝位移反分析[J]. 清华大学学报(自然科学版), 2006, 46(9):1542-1545, 1550. LIU Y R, YANG Q, LIU F S, et al. Inverse analyses of arch dam displacements using improved parallel genetic algorithm[J]. Journal of Tsinghua University (Science & Technology), 2006, 46(9):1542-1545, 1550. (in Chinese)
[16] YAO F H, GUAN S H, YANG H, et al. Long-term deformation analysis of Shuibuya concrete face rockfill dam based on response surface method and improved genetic algorithm[J]. Water Science and Engineering, 2019, 12(3):196-204.
[17] ZHOU W, LI S L, MA G, et al. Parameters inversion of high central core rockfill dams based on a novel genetic algorithm[J]. Science China Technological Sciences, 2016, 59(5):783-794.
[18] ZHU Y, CHI S C. The application of MsPSO in the rockfill parameter inversion of CFRD[J]. Mathematical Problems in Engineering, 2016, 2016:1096967.
[19] CHEN Y J, GU C S, WU B B, et al. Inversion modeling of dam-zoning elasticity modulus for heightened concrete dam using ICS-IPSO algorithm[J]. Mathematical Problems in Engineering, 2019, 2019:9328326.
[20] 李火坤, 邓冰梅, 魏博文, 等. 基于有限测点的高拱坝原型整体动位移场反演研究[J]. 振动与冲击, 2016, 35(10):1-8. LI H K, DENG B M, WEI B W, et al. Inversion of the whole dynamic displacement field of a prototype high arch dam based on limited points measurement[J]. Journal of Vibration and Shock, 2016, 35(10):1-8. (in Chinese)
[21] CHEN B, FU X, GUO X Y, et al. Zoning elastic modulus inversion for high arch dams based on the PSOGSA-SVM method[J]. Advances in Civil Engineering, 2019, 2019:7936513.
[22] SUN Y, JIANG Q H, YIN T, et al. A back-analysis method using an intelligent multi-objective optimization for predicting slope deformation induced by excavation[J]. Engineering Geology, 2018, 239:214-228.
[23] 陈闯, CHELLALI R, 邢尹. 改进遗传算法优化BP神经网络的语音情感识别[J]. 计算机应用研究, 2019, 36(2):344-346, 361. CHEN C, CHELLALI R, XING Y. Speech emotion recognition based on improved genetic algorithm optimized BP neural network[J]. Application Research of Computers, 2019, 36(2):344-346, 361. (in Chinese)
[24] SRINIVAS M, PATNAIK L M. Adaptive probabilities of crossover and mutation in genetic algorithms[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1994, 24(4):656-667.
[25] 苏崇宇, 汪毓铎. 基于改进的自适应遗传算法优化BP神经网络[J]. 工业控制计算机, 2019, 32(1):67-69. SU C Y, WANG Y D. BP neural network optimized by improved adaptive genetic algorithm computer engineering and applications[J]. Industrial Control Computer, 2019, 32(1):67-69. (in Chinese)
[26] 李步遥, 司马军. 基于MEC-BP神经网络的基坑水平位移反演分析[J]. 铁道科学与工程学报, 2021, 18(7):1764-1772. LI B Y, SIMA J. Horizontal displacement back-analysis for deep excavation using MEC-BP neural network[J]. Journal of Railway Science and Engineering, 2021, 18(7):1764-1772. (in Chinese)
[27] LU J S, XIE W D, ZHOU H B. Combined fitness function based particle swarm optimization algorithm for system identification[J]. Computers & Industrial Engineering, 2016, 95:122-134.
[28] LIU Y R, WU Z S, YANG Q, et al. Dynamic stability evaluation of underground tunnels based on deformation reinforcement theory[J]. Advances in Engineering Software, 2018, 124:97-108.
[29] 侯少康, 刘耀儒, 张凯. 基于IPSO-BP混合模型的TBM掘进参数预测[J]. 岩石力学与工程学报, 2020, 39(8):1648-1657. HOU S K, LIU Y R, ZHANG K. Prediction of TBM tunnelling parameters based on IPSO-BP hybrid model[J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39(8):1648-1657. (in Chinese)

基金

国家自然科学基金资助项目(41961134032,51739006);水沙科学与水利水电工程国家重点实验室项目(2019-KY-03)

PDF(12253 KB)

Accesses

Citation

Detail

段落导航
相关文章

/