Prediction model of seismic amplification effect in sedimentary valley based on differential evolution-artificial neural network
-
摘要: 探讨了基于差分进化-人工神经网络构建沉积河谷地震响应代理模型的可行性。首先建立沉积河谷对地震波散射的求解方法，以半圆形、V形沉积河谷为例，以入射波条件、沉积内外介质属性、场地形状为特征参数，以沉积河谷地震动放大系数为预测目标参数，构建数据集；其次，建立沉积河谷地震动放大效应人工神经网络、差分进化-人工神经网络算法预测模型，对比两种算法计算精度和稳定性，并进行了特征参数敏感性分析。结果表明：人工神经网络能较好地预测沉积河谷地震动放大效应，使差分进化-人工神经网络预测模型的精度和稳定性显著提高；入射波频率是影响沉积河谷地震动放大系数的主要原因，沉积内外介质密度比的影响较小。本研究结论可对地震作用下更为复杂的局部场地效应预测和评估提供参考。Abstract: Sedimentary valley has obvious amplification effect on ground motions, which has an increase on the engineering damage. However, the propagation mechanism of seismic wave in sedimentary valley is complex, resulting in high nonlinearity and high coupling of influences of incident wave and site parameters on seismic amplification effect. First, based on the boundary element method, the scattering of seismic waves by sedimentary valley is solved. Prediction models of seismic amplification effect of semicircular and V-shaped sedimentary valley are established, with incident wave conditions, material properties and valley shapes as characteristic parameters and the seismic amplification factor of sedimentary valley as target parameters, and the dataset is constructed; Second, the calculation accuracy and stability of artificial neural network （ANN） and its optimization algorithm, i.e., differential evolution, are compared, and the sensitivity of characteristic parameters is analyzed. The results show that the ANN can predict the amplification effect of sedimentary valley, and the accuracy and stability of differential evolution-ANN prediction model are significantly improved; The incident wave frequency is the main influence factor of the seismic amplification coefficient of sedimentary valley, and the density ratio of internal and external medium has little effect. The conclusions can provide references for more complex local site effect prediction and assessment.
-
-
![]()
图 3 本文地表位移放大系数结果与文献结果对比
Figure 3. Comparison of amplification coefficient of surface displacement between the results in this paper and those in literature
![]()
图 4 半圆形河谷（a）和V形河谷（b）的预测模型点位分布
Figure 4. Location distribution of prediction model for semicircular valley （a） and V-shaped valley （b）
![]()
图 6 人工神经网络（左）和差分进化-人工神经网络（右）预测模型测试集决定系数
（a） 半圆形河谷； （b） V形河谷
Figure 6. Artificial neural network （ANN） （left） and differentical evolution-ANN （right） determination coefficient of test set of prediction model
（a） Semicircular valley； （b） V-shaped valley
![]()
图 7 采用边界元法和神经网络预测模型得到的半圆形河谷地表点A−E （a−e）的位移幅值对比
Figure 7. Comparison of displacement amplitudes between boundary element method and neural network prediction model of surface points A−E （a−e） for semicircular valley
![]()
图 8 采用边界元法和神经网络预测模型得到的V形河谷地表点A−E （a−e） 的位移幅值对比
Figure 8. Comparison of displacement amplitudes between boundary element method and neural network prediction model of surface points A−E （a−e） for V-shaped valley
![]()
图 9 基于差分进化-神经网络预测模型的半圆形河谷（a）和V型河谷（b） 地表位移放大系数频谱
Figure 9. Surface displacement amplification factor spectrum based on differential evolution-ANN prediction model for semicircular valley （a） and V-shaped valley （b）
![]()
图 10 基于边界元法的半圆形河谷 （a）和V型河谷（b）地表位移放大系数频谱
Figure 10. Surface displacement amplification factor spectrum based on boundary element method for semicircular valley （a） and V-shaped valley （b）
表 1 预测模型的特征参数及取值范围
Table 1 Characteristic parameters and value ranges of the prediction model
入射角θ/° 无量纲频率η 密度比ρ2/ρ1 剪切波速比c2/c1 半圆形河谷 ［60，90］ ［0.1，5］ ［0.5，1］ ［0.7，0.8］ V形河谷 ［60，90］ ［0.1，5］ ［0，1］ ［0.4，0.6］ 
下载: 导出CSV
-
陈国兴,金丹丹,朱姣,李小军. 2015. 河口盆地非线性地震效应及设计地震动参数[J]. 岩土力学,36(6):1721–1736. Chen G X,Jin D D,Zhu J,Li X J. 2015. Nonlinear seismic response of estuarine basin and design parameters of ground motion[J]. Rock and Soil Mechanics,36(6):1721–1736 (in Chinese).
陈少林,张莉莉,李山有. 2014. 半圆柱型沉积盆地对SH波散射的数值分析[J]. 工程力学,31(4):218–224. Chen S L,Zhang L L,Li S Y. 2014. Numerical analysis of the plane SH waves scattering by semi-cylindrical alluvial valley[J]. Engineering Mechanics,31(4):218–224 (in Chinese).
高玉峰,代登辉,张宁. 2021. 河谷地形地震放大效应研究进展与展望[J]. 防灾减灾工程学报,41(4):734–752. Gao Y F,Dai D H,Zhang N. 2021. Progress and prospect of topographic amplification effects of seismic wave in canyon sites[J]. Journal of Disaster Prevention and Mitigation Engineering,41(4):734–752 (in Chinese).
黄磊,刘中宪,张雪,李程程. 2020. 含流体层的河谷场地对地震波散射的间接边界元法模拟[J]. 地震学报,42(6):657–668. Huang L,Liu Z X,Zhang X,Li C C. 2020. IBEM simulation of seismic wave scattering by valley topography with fluid layer[J]. Acta Seismologica Sinica,42(6):657–668 (in Chinese).
李平,薄景山,李孝波,肖瑞杰. 2016. 安宁河河谷及邛海地区土层场地对地震动的放大作用[J]. 岩土工程学报,38(2):362–369. doi: 10.11779/CJGE201602022 Li P,Bo J S,Li X B,Xiao R J. 2016. Amplification effect of soil sites on ground motion in Anning River valley and Qionghai Lake area[J]. Chinese Journal of Geotechnical Engineering,38(2):362–369 (in Chinese).
李伟华,赵成刚. 2006. 具有饱和土沉积层的充水河谷对平面波的散射[J]. 地球物理学报,49(1):212–224. doi: 10.3321/j.issn:0001-5733.2006.01.028 Li W H,Zhao C G. 2006. Scattering of plane waves by circular-arc alluvial valleys with saturated soil deposits and water[J]. Chinese Journal of Geophysics,49(1):212–224 (in Chinese).
梁建文,巴振宁. 2007. 弹性层状半空间中沉积谷地对入射平面SH波的放大作用[J]. 地震工程与工程振动,27(3):1–9. doi: 10.3969/j.issn.1000-1301.2007.03.001 Liang J W,Ba Z N. 2007. Surface motion of an alluvial valley in layered half-space for incident plane SH waves[J]. Journal of Earthquake Engineering and Engineering Vibration,27(3):1–9 (in Chinese).
刘必灯,周正华,刘培玄,李小军,王伟. 2011. SV波入射情况下V型河谷地形对地震动的影响分析[J]. 地震工程与工程振动,31(2):17–24. Liu B D,Zhou Z H,Liu P X,Li X J,Wang W. 2011. Influence of V-shaped canyon site on ground motions for incident SV waves[J]. Journal of Earthquake Engineering and Engineering Vibration,31(2):17–24 (in Chinese).
潘兆东,谭平,刘良坤,周福霖. 2018. 基于自适应RBF神经网络算法的建筑结构递阶分散控制研究[J]. 土木工程学报,51(1):51–57. Pan Z D,Tan P,Liu L K,Zhou F L. 2018. Hierarchical decentralized control of building structure based on adaptive RBF neural network algorithm[J]. China Civil Engineering Journal,51(1):51–57 (in Chinese).
肖文海. 2009. 大型河谷场地地震动特征研究[D]. 哈尔滨: 中国地震局工程力学研究所: 1–2. Xiao W H. 2009. Research on Ground Motion Characteristic at the Site of Large-Scale Valley[D]. Harbin: Institute of Engineering Mechanics, China Earthquake Administration: 1–2 （in Chinese）.
张宁,高玉峰,何稼,徐婕,陈欣,代登辉. 2017. 平面SH波作用下部分充填圆弧形沉积谷的二维土层和地形放大效应[J]. 地震学报,39(5):778–797. doi: 10.11939/jass.2017.05.012 Zhang N,Gao Y F,He J,Xu J,Chen X,Dai D H. 2017. Two-dimensional soil and topographic amplification effects of a partially filled circular-arc alluvial valley under plane SH waves[J]. Acta Seismologica Sinica,39(5):778–797 (in Chinese).
周国良,李小军,侯春林,李铁萍. 2012. SV波入射下河谷地形地震动分布特征分析[J]. 岩土力学,33(4):1161–1166. doi: 10.3969/j.issn.1000-7598.2012.04.029 Zhou G L,Li X J,Hou C L,Li T P. 2012. Characteristic analysis of ground motions of canyon topography under incident SV seismic waves[J]. Rock and Soil Mechanics,33(4):1161–1166 (in Chinese).
Boore D M. 1973. The effect of simple topography on seismic waves:Implications for the accelerations recorded at Pacoima Dam,San Fernando Valley,California[J]. Bull Seismol Soc Am,63(5):1603–1609. doi: 10.1785/BSSA0630051603
Derras B,Bard P Y,Cotton F,Bekkouche A. 2012. Adapting the neural network approach to PGA prediction:An example based on the KiK-net data[J]. Bull Seismol Soc Am,102(4):1446–1461. doi: 10.1785/0120110088
Derras B,Bard P Y,Cotton F. 2014. Towards fully data driven ground-motion prediction models for Europe[J]. Bull Earthq Eng,12(1):495–516. doi: 10.1007/s10518-013-9481-0
Dhanya J,Raghukanth S T G. 2018. Ground motion prediction model using artificial neural network[J]. Pure Appl Geophys,175(3):1035–1064. doi: 10.1007/s00024-017-1751-3
Ducellier A,Aochi H. 2012. Interactions between topographic irregularities and seismic ground motion investigated using a hybrid FD-FE method[J]. Bull Earthq Eng,10(3):773–792. doi: 10.1007/s10518-011-9335-6
Giacinto G,Paolucci R,Roli F. 1997. Application of neural networks and statistical pattern recognition algorithms to earthquake risk evaluation[J]. Pattern Recogn Lett,18(11/12/13):1353–1362.
Kong Q K,Trugman D T,Ross Z E,Bianco M J,Meade B J,Gerstoft P. 2019. Machine learning in seismology:Turning data into insights[J]. Seismol Res Lett,90(1):3–14. doi: 10.1785/0220180259
Liu Z X,Wang D,Liang J W,Wu F J,Wu C Q. 2018. The fast multi-pole indirect BEM for solving high-frequency seismic wave scattering by three-dimensional superficial irregularities[J]. Eng Anal Bound Elem,90:86–99. doi: 10.1016/j.enganabound.2018.02.009
Luzón F,Sánchez-Sesma F J,Pérez-Ruiz J A,Ramírez-Guzmán L,Pech A. 2009. In-plane seismic response of inhomogeneous alluvial valleys with vertical gradients of velocities and constant Poisson ratio[J]. Soil Dyn Earthq Eng,29(6):994–1004. doi: 10.1016/j.soildyn.2008.11.007
Moayedi H,Raftari M,Sharifi A,Jusoh W A W,Rashid A S A. 2020. Optimization of ANFIS with GA and PSO estimating α ratio in driven piles[J]. Eng Comput,36(1):227–238. doi: 10.1007/s00366-018-00694-w
Paolucci R,Colli P,Giacinto G. 2000. Assessment of seismic site effects in 2-D alluvial valleys using neural networks[J]. Earthq Spectra,16(3):661–680. doi: 10.1193/1.1586133
Raghucharan M C,Somala S N,Rodina S. 2019. Seismic attenuation model using artificial neural networks[J]. Soil Dyn Earthq Eng,126:105828. doi: 10.1016/j.soildyn.2019.105828
Shyu W S,Teng T J,Chou C S. 2018. Effect of geometry on in-plane responses of a symmetric canyon subjected by P waves[J]. Soil Dyn Earthq Eng,113:215–229. doi: 10.1016/j.soildyn.2018.06.003
Sun Y C,Ren H X,Zheng X Z,Li N,Zhang W,Huang Q H,Chen X F. 2019. 2-D poroelastic wave modelling with a topographic free surface by the curvilinear grid finite-difference method[J]. Geophys J Int,218(3):1961–1982. doi: 10.1093/gji/ggz263
Tavakoli H,Kutanaei S S. 2015. Evaluation of effect of soil characteristics on the seismic amplification factor using the neural network and reliability concept[J]. Arab J Geosci,8(6):3881–3891. doi: 10.1007/s12517-014-1458-z
Trifunac M D. 1971. Surface motion of a semi-cylindrical alluvial valley for incident plane SH waves[J]. Bull Seismol Soc Am,61(6):1755–1770. doi: 10.1785/BSSA0610061755
Yuan X M,Liao Z P. 1995. Scattering of plane SH waves by a cylindrical alluvial valley of circular-arc cross-section[J]. Earthq Eng Struct Dyn,24(10):1303–1313. doi: 10.1002/eqe.4290241002
Zhou H,Chen X F. 2008. The localized boundary integral equation-discrete wavenumber method for simulating P-SV wave scattering by an irregular topography[J]. Bull Seismol Soc Am,98(1):265–279. doi: 10.1785/0120060249
-
期刊类型引用(3)
1. 帅向华，温可民，梁超，邓洁仪，李涵梦. 深圳市地震灾害风险评估与讨论. 震灾防御技术. 2024(02): 216-228 . 
百度学术
2. 张锐，王福涛，陈生. 高分辨率遥感在震害监测中的应用综述. 遥感信息. 2024(04): 1-10 . 百度学术
3. 吴刚，侯士通，张建，吴京，傅大放，陈力，王庆，田馨. 城市生命线工程安全多层次监测体系与预警技术研究. 土木工程学报. 2023(11): 1-15 . 百度学术
其他类型引用(1)
计量
- 文章访问数: 363
- HTML全文浏览量: 166
- PDF下载量: 70
- 被引次数: 4
