基于GA-BP神经网络的拱坝地震易损性分析

于京池, 金爱云, 潘坚文, 王进廷, 张楚汉

清华大学学报(自然科学版) ›› 2022, Vol. 62 ›› Issue (8) : 1321-1329.

PDF(12383 KB)
PDF(12383 KB)
清华大学学报(自然科学版) ›› 2022, Vol. 62 ›› Issue (8) : 1321-1329. DOI: 10.16511/j.cnki.qhdxxb.2022.25.028
智能预测反馈

基于GA-BP神经网络的拱坝地震易损性分析

  • 于京池1, 金爱云2, 潘坚文1, 王进廷1, 张楚汉1
作者信息 +

GA-BP artificial neural networks for predicting the seismic response of arch dams

  • YU Jingchi1, JIN Aiyun2, PAN Jianwen1, WANG Jinting1, ZHANG Chuhan1
Author information +
文章历史 +

摘要

拱坝在其生命周期内可能会承受强烈地震,其地震易损性引起了广泛的关注。一般而言,采用非线性有限元法进行拱坝的地震易损性分析,需要大量的计算工作量。该文提出了一种预测拱坝地震响应的方法——基于遗传算法(genetic algorithm,GA)的多层前馈(back propagation,BP)神经网络,该方法可以替代部分非线性有限元分析计算,显著减少计算成本。以大岗山拱坝的易损性分析为算例,基于已有的390个有限元非线性动力分析工况数据,将结构的响应设定为BP神经网络的输出,地震强度参数IM作为输入,进行BP神经网络的训练和验证。结果表明,该文提出的GA-BP神经网络采用390个有限元结果中的30%的数据进行训练,即可得到满足精度的预测结果,给出合理的拱坝地震易损性曲线,说明采用GA-BP神经网络后可节省70%的非线性有限元计算成本。

Abstract

Arch dams may be subjected to strong earthquakes during their lifecycle and their seismic response has attracted extensive attention in dam engineering. Nonlinear finite element seismic response analyses of arch dams require large amounts of computational effort. This paper presents a back propagation (BP) genetic algorithm (GA) method for predict the seismic responses of arch dams which replaces some of the finite element analysis calculations and significantly reduces the computational cost compared with the finite element method. A BP neural network was trained and validated for the Dagangshan arch dam based on 390 nonlinear dynamic response cases calculated using the finite element method with the structural response as the BP neural network output and the seismic intensity parameter, IM, as the input. The results show that the GA-BP neural network can properly predict the dam seismic response and give reasonable seismic response curves using 30% of the 390 cases for training which shows that the GA-BP neural network can save 70% of the nonlinear finite element cost.

关键词

拱坝 / 地震易损性分析 / 人工神经网络 / 遗传算法

Key words

arch dam / seismic fragility analysis / artificial neural network / genetic algorithm

引用本文

导出引用
于京池, 金爱云, 潘坚文, 王进廷, 张楚汉. 基于GA-BP神经网络的拱坝地震易损性分析[J]. 清华大学学报(自然科学版). 2022, 62(8): 1321-1329 https://doi.org/10.16511/j.cnki.qhdxxb.2022.25.028
YU Jingchi, JIN Aiyun, PAN Jianwen, WANG Jinting, ZHANG Chuhan. GA-BP artificial neural networks for predicting the seismic response of arch dams[J]. Journal of Tsinghua University(Science and Technology). 2022, 62(8): 1321-1329 https://doi.org/10.16511/j.cnki.qhdxxb.2022.25.028

参考文献

[1] CHEN H J, XU W Y, WU Q X, et al. Reliability analysis of arch dam subjected to seismic loads[J]. Arabian Journal for Science and Engineering, 2014, 39(11):7609-7619.
[2] YAO X W, ELNASHAI A S, JIANG J Q. Analytical seismic fragility analysis of concrete arch dams[C]//Proceedings of the 15th World Conference on Earthquake Engineering. Lisbon, Portugal:WCEE, 2012.
[3] WANG J T, ZHANG M X, JIN A Y, et al. Seismic fragility of arch dams based on damage analysis[J]. Soil Dynamics and Earthquake Engineering, 2018, 109:58-68.
[4] ANDERSON D, MCNEILL G. Artificial neural networks technology[R]. New York:Data & Analysis Center for Software, 1992.
[5] LIU K, GUO W Y, SHEN X L, et al. Research on the forecast model of electricity power industry loan based on GA-BP neural network[J]. Energy Procedia, 2012, 14:1918-1924.
[6] FENG G L, LI L. Application of genetic algorithm and neural network in construction cost estimate[C]//Proceedings of the 2012 2nd International Conference on Computer and Information Application. Paris, France:Atlantis Press, 2012:1036-1039.
[7] 余功栓. 人工智能技术在大坝安全分析中的应用[D]. 杭州:浙江大学, 2004. YU G S. Application of artificial intelligent in safety analysis of embankment[D]. Hangzhou:Zhejiang University, 2004. (in Chinese)
[8] DING S F, SU C Y, YU J Z. An optimizing BP neural network algorithm based on genetic algorithm[J]. Artificial Intelligence Review, 2011, 36(2):153-162.
[9] MATA J. Interpretation of concrete dam behaviour with artificial neural network and multiple linear regression models[J]. Engineering Structures, 2011, 33(3):903-910.
[10] SONG L F, XU B, KONG X J, et al. Reliability analysis of 3D rockfill dam slope stability based on the Copula function[J]. International Journal of Geomechanics, 2021, 21(3):04021001.
[11] LIU J, WANG G Y, CHEN Y. Research and application of GA neural network model on dam displacement forecasting[C]//11th Biennial ASCE Aerospace Division International Conference on Engineering, Science, Construction, and Operations in Challenging Environments. Long Beach, California, USA:ASCE, 2008, 323:1-9.
[12] 苏怀智, 吴中如, 温志萍, 等. 遗传算法在大坝安全监控神经网络预报模型建立中的应用[J]. 水利学报, 2001(8):44-48. SU H Z, WU Z R, WEN Z P, et al. The application of genetic algorithm in establishment of neural network forecast model for dam safety monitoring[J]. Journal of Hydraulic Engineering, 2001(8):44-48. (in Chinese)
[13] MCCULLOCH W S, PITTS W. A logical calculus of the ideas immanent in nervous activity[J]. The Bulletin of Mathematical Biophysics, 1943, 5(4):115-133.
[14] HOPFIELD J J. Neural networks and physical systems with emergent collective computational abilities[J]. Proceedings of the National Academy of Sciences of the United States of America, 1982, 79(8):2554-2558.
[15] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088):533-536.
[16] 刘春艳, 凌建春, 蔻林元, 等. GA-BP神经网络与BP神经网络性能比较[J]. 中国卫生统计, 2013, 30(2):173-176, 181. LIU C Y, LING J C, KOU L Y, et al. Performance comparison between GA-BP neural network and BP neural network[J]. Chinese Journal of Health Statistics, 2013, 30(2):173-176, 181. (in Chinese)
[17] 金爱云. 高拱坝地震易损性研究[D]. 北京:清华大学, 2020. JIN A Y. Seismic fragility analysis of high arch dams[D]. Beijing:Tsinghua University, 2020. (in Chinese)
[18] TOTHONG P, LUCO N. Probabilistic seismic demand analysis using advanced ground motion intensity measures[J]. Earthquake Engineering & Structural Dynamics, 2007, 36(13):1837-1860.
[19] HARIRI-ARDEBILI M A, SAOUMA V E. Probabilistic seismic demand model and optimal intensity measure for concrete dams[J]. Structural Safety, 2016, 59:67-85.
[20] ARIAS A. A measure of earthquake intensity[M]//HANSEN R J. Seismic Design for Nuclear Power Plants. Cambridge, MA, USA:MIT Press, 1970:438-483.
[21] 崔恩文. 基于速度谱强度高铁列车地震报警阈值研究[D]. 哈尔滨:中国地震局工程力学研究所, 2014. CUI E W. Study on spectral intensity of speed based earthquake alarm threshold of high speed trains[D]. Harbin:China Earthquake Administration, 2014. (in Chinese)
[22] YANG D X, PAN J W, LI G. Non-structure-specific intensity measure parameters and characteristic period of near-fault ground motions[J]. Earthquake Engineering & Structural Dynamics, 2009, 38(11):1257-1280.
[23] ZHANG C H, JIN F, WANG J T, et al. Nonlinear behavior and seismic safety evaluation of concrete dams[M]. Beijing:Tsinghua University Press, 2012.
[24] 潘坚文, 王进廷, 张楚汉. 超强地震作用下拱坝的损伤开裂分析[J]. 水利学报, 2007, 38(2):143-149. PAN J W, WANG J T, ZHANG C H. Analysis of damage and cracking in arch dams subjected to extremely strong earthquake[J]. Journal of Hydraulic Engineering, 2007, 38(2):143-149. (in Chinese)
[25] LIU J B, LI B. A unified viscous-spring artificial boundary for 3-D static and dynamic applications[J]. Science in China Series E-Engineering & Materials Science, 2005, 48(5):570-584.
[26] LEE J, FENVES G L. Plastic-damage model for cyclic loading of concrete structures[J]. Journal of Engineering Mechanics, 1998, 124(8):892-900.
[27] 潘坚文. 高混凝土坝静动力非线性断裂与地基辐射阻尼模拟研究[D]. 北京:清华大学, 2010. PAN J W. Nonlinear static and seismic fracture analysis of high concrete dams and modeling of radiation damping for foundation[D]. Beijing:Tsinghua University, 2010. (in Chinese)
[28] SHOME N, CORNELL C A. Probabilistic seismic demand analysis of nonlinear structures[D]. Stanford:Stanford University, 1999.
[29] 吕大刚, 于晓辉, 潘峰, 等. 基于改进云图法的结构概率地震需求分析[J]. 世界地震工程, 2010, 26(1):7-15. LÜ D G, YU X H, PAN F, et al. Probabilistic seismic demand analysis of structures based on an improved cloud method[J]. World Earthquake and Engineering, 2010, 26(1):7-15. (in Chinese)

基金

国家自然科学基金项目(51725901,52022047,51639006)

PDF(12383 KB)

Accesses

Citation

Detail

段落导航
相关文章

/