共查询到20条相似文献，搜索用时 93 毫秒
1.
溜砂坡具有突发、不易预测,且产生危害大的特点。文章对拉萨市周边实地调研测量收集数据,采集了12组具有代表性的溜砂坡灾害点数据集合,运用贝叶斯网络与粒子群算法相结合,并利用算法更新公式弥补单一算法的不足,引入信息熵分析了降雨量、坡度、坡高和植被覆盖率在算法中的权重,以及各因素对溜砂坡稳定性的影响,并对溜砂坡的稳定性进行了等级划分,实验证明该方法有效,对溜砂坡稳定性评价具有一定参考价值。 相似文献
2.
Rita Sousa Karim S. Karam Ana Laura Costa 《Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards》2017,11(1):129-145
ABSTRACTThe paper presents methodologies for exploration planning under uncertain conditions based on virtual exploration and Bayesian updating. The process starts with site characterization using existing information to produce geologic profiles. Initial distributions of cost and time are obtained with a Bayesian network model that optimizes the construction strategy for particular geologic conditions. This is followed by the unique step to determine with a “virtual exploration” if additional exploration (e.g. borings) is warranted, and if so, where it should be best done. All this is then applied to the planned Abu Dhabi subway tunnels providing the transportation planners with necessary information for planning and design. 相似文献
3.
基于PCA-GEP算法的边坡稳定性预测 总被引：5，自引：1，他引：4
提出一种基于主成分分析的基因表达式程序设计算法,并将其用于边坡稳定性预测。该算法先采用主成分分析法对样本数据进行预处理,有效地减少预测模型的输入量,消除输入数据间的相关性,再将得到的新样本数据输入基因表达式,构建边坡稳定性的预测模型。利用该预测模型对82个危险圆弧破坏边坡实例中的71个实例进行学习,对另外11个实例进行预测,取得了较好的效果。在保留传统的以误差值作为评判模型优劣标准的同时,引入AIC信息准则法,分别对v-SVR算法和GA-BP网络算法和PCA-GEP算法三种预测模型进行比较分析,结果表明,运用该算法可以获得更优的预测模型,其预测结果比v-SVR算法和GA-BP网络等其他算法得到的结果具有更高的预测精度。工程实例计算表明,该方法是合理、可行的。 相似文献
4.
针对目前水电边坡工程海量的监测信息和监测数据,为减轻监测信息管理与数据分析的劳动强度,提高劳动生产率,采用Microsoft Visual C++网络编程技术和SQL Server网络数据库开发出具有先进性、可靠性、通用性和可扩充性的岩土工程安全监测信息管理与数据分析远程可视化网络系统。将该系统应用于龙滩水电站大坝左、右岸边坡及导流洞监测资料的分析处理,实现了监测信息和数据的远程实时共享及网络化的管理和分析,使监测分析成果能够及时、准确地反馈给设计人员,对规避设计和施工风险、保证边坡施工和运行安全起到了重要的作用。 相似文献
5.
受工程勘察成本及试验场地限制,可获得的试验数据通常有限,基于有限的试验数据难以准确估计岩土参数统计特征和边坡可靠度。贝叶斯方法可以融合有限的场地信息降低对岩土参数不确定性的估计进而提高边坡可靠度水平。但是,目前的贝叶斯更新研究大多假定参数先验概率分布为正态、对数正态和均匀分布,似然函数为多维正态分布,这种做法的合理性有待进一步验证。总结了岩土工程贝叶斯分析常用的参数先验概率分布及似然函数模型,以一个不排水黏土边坡为例,采用自适应贝叶斯更新方法系统探讨了参数先验概率分布和似然函数对空间变异边坡参数后验概率分布推断及可靠度更新的影响。计算结果表明：参数先验概率分布对空间变异边坡参数后验概率分布推断及可靠度更新均有一定的影响,选用对数正态和极值I型分布作为先验概率分布推断的参数后验概率分布离散性较小。选用Beta分布和极值I型分布获得的边坡可靠度计算结果分别偏于保守和危险,选用对数正态分布获得的边坡可靠度计算结果居中。相比之下,似然函数的影响更加显著。与其他类型似然函数相比,由多维联合正态分布构建的似然函数可在降低对岩土参数不确定性估计的同时,获得与场地信息更为吻合的计算结果。另外,构建似然函数时不同位置处测量误差之间的自相关性对边坡后验失效概率也具有一定的影响。 相似文献
6.
7.
Pinom Ering G. L. Sivakumar Babu 《Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards》2017,11(4):285-298
The study presents a recent slope failure in India which resulted in the burial of a village and claimed large number of lives. Current methods of probabilistic back analysis incorporate uncertainty in the analysis but do not consider spatial variability. In this study, back analysis is performed using Bayesian analysis in conjunction with random field theory. The probabilistic method is shown to be efficient in back-analysing a slope failure. It also provides confidence in parameter values to be used for post-failure slope design. The back analysis method which does not consider spatial variability overestimates the uncertainty in analysis, which can lead to uneconomical slope remediation design and measures. 相似文献
8.
Ibsen Chivatá Cárdenas 《Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards》2019,13(1):53-65
In this paper, we report on the use of Bayesian networks, BNs, learnt from data generated by physical and numerical models, to overcome to a certain degree a number of complications in traditional slope stability analyses that jointly consider the mechanical and hydraulic properties of soils. Discrete Bayesian networks resulted to be useful and efficient to acquire knowledge from simulated data and to identify significant factors by the combined use of backward inference and global sensitivity analysis. Further, BNs enable decision thresholds to be estimated quickly. Along with this, backward inference and global sensitivity analysis are performed in BNs at low computation costs. Moreover, under conditions in which knowledge is scarce, we show how a practitioner can be better informed using the proposed approach. All these previously under-reported modelling features in the specialised literature encourage the further application of the proposed approach to enhance slope stability analysis. 相似文献
9.
Monte Carlo Simulation (MCS) method has been widely used in probabilistic analysis of slope stability, and it provides a robust and simple way to assess failure probability. However, MCS method does not offer insight into the relative contributions of various uncertainties (e.g., inherent spatial variability of soil properties and subsurface stratigraphy) to the failure probability and suffers from a lack of resolution and efficiency at small probability levels. This paper develop a probabilistic failure analysis approach that makes use of the failure samples generated in the MCS and analyzes these failure samples to assess the effects of various uncertainties on slope failure probability. The approach contains two major components: hypothesis tests for prioritizing effects of various uncertainties and Bayesian analysis for further quantifying their effects. Equations are derived for the hypothesis tests and Bayesian analysis. The probabilistic failure analysis requires a large number of failure samples in MCS, and an advanced Monte Carlo Simulation called Subset Simulation is employed to improve efficiency of generating failure samples in MCS. As an illustration, the proposed probabilistic failure analysis approach is applied to study a design scenario of James Bay Dyke. The hypothesis tests show that the uncertainty of undrained shear strength of lacustrine clay has the most significant effect on the slope failure probability, while the uncertainty of the clay crust thickness contributes the least. The effect of the former is then further quantified by a Bayesian analysis. Both hypothesis test results and Bayesian analysis results are validated against independent sensitivity studies. It is shown that probabilistic failure analysis provides results that are equivalent to those from additional sensitivity studies, but it has the advantage of avoiding additional computational times and efforts for repeated runs of MCS in sensitivity studies. 相似文献
10.
用神经网络评价边坡稳定性 总被引：21，自引：0，他引：21
影响边坡稳定性因素是复杂且具有随机和模糊特性。神经网络的性能特征使适用于解决非性的边坡稳定性评价问题，本文建立了边坡稳定性评价的复合网络模型，并利用边坡工程的失稳及稳定实例对网络进行了训练和测试，计算分析表明，网络模型对于评价边坡的稳定性有较好的适用性。 相似文献
11.
为了分析边坡的稳定性,利用协调粒子群算法和BP网络建立了边坡稳定性CPSO-BP预测模型。BP网络能够很好地描述边坡稳定性与其影响因素之间复杂的非线性关系,将内摩擦角、边坡角、岩石重度、边坡高度、黏聚力、孔隙压力比6个主要影响因素作为网络的输入,将边坡稳定性系数作为网络的输出。为避免BP网络陷入局部最优,利用协调粒子群算法的全局优化能力确定BP网络的连接权值和阀值,使BP网络的优势得到分发挥,达到提高模型预测精度目的。实例表明CPSO-BP模型有更好地预测精度以及将其应用于边坡稳定性预测是可行的。 相似文献
12.
Hazard analysis of seismic submarine slope instability 总被引：1，自引：0，他引：1
Rafael Rodríguez-Ochoa Farrokh Nadim José M. Cepeda Michael A. Hicks Zhongqiang Liu 《Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards》2015,9(3):128-147
To assess the risk associated with a submarine landslide, one must estimate the probability of slope failure and its consequences. This paper proposes a procedure to estimate the probability of earthquake-induced submarine slope failure (hazard) based on probabilistic seismic hazard analyses, ground response analyses and advanced laboratory tests. The outcomes from these analyses are treated in a probabilistic framework, with analytical simulations using mathematical techniques such as the first-order reliability method, Monte Carlo simulation and Bayesian updating. Fragility curves of slope failure during the earthquake (co-seismic) and after the earthquake (post-seismic) were developed in this study, and were shown to provide a clear and well-organized procedure to estimate the annual failure probability of a submarine slope under earthquake loading. 相似文献
13.
14.
基于神经网络范例推理的边坡稳定性评价方法 总被引：13，自引：4，他引：9
提出了基于神经网络范例推理的边坡稳定性评价方法。针对边坡的稳定性影响因素的复杂多变性和相当强的不确定性,建立了基于神经网络的边坡范例检索模型。运用神经网络强大的自适应、自组织、自学习的能力以及高度的非线性映射性、泛化性和容错性的特点,通过边坡范例的神经网络学习,建立了当前边坡和边坡范例之间相似性计算关系,最终实现了当前边坡的稳定性评价。对于8个验证边坡范例,模型的预测准确性达到了100 %,范例中的160组数据的相关性也达到了 0.981 5,表明建立的模型具有很高的预测准确性,模型的泛化能力很强。 相似文献
15.
结合已有岩质边坡工程实例,针对岩质边坡稳定性预测中存在的问题,提出了运用BP网络预测岩质边坡稳定性的方法,并构造了相应的网络模型。预测结果表明,模型具有较高的预测精度,能够满足实际工程需要,是有一定实用价值和参考价值的边坡稳定性预测方法。 相似文献
16.
贝叶斯信息标准在滑坡因子敏感性分析中的应用 总被引：5，自引：0，他引：5
滑坡因子敏感性分析是滑坡预测和治理的重要前提。以巫山县新址西区作为试验区,运用滑坡影响因素与历史滑坡之间建立的Logistic回归模型,通过贝叶斯信息标准进行模型优劣程度的比较,以期得出本区滑坡因子的敏感程度。设计了逐个加入影响因子进行非嵌套模型的优劣程度对比的试验方法。试验区滑坡因子敏感程度计算结果排队依次为：岩性、高程、距有影响构造线距离、坡度、坡向、坡形。试验为区域斜坡稳定性评价提供了一种新的、可靠的方法。 相似文献
17.
基于GIS与ANN模型的地震滑坡易发性区划 总被引：1，自引：0，他引：1
基于遥感数据、地理信息系统(GIS)技术和人工神经网络(ANN)模型,开展地震滑坡易发性区划研究.2010年4月14日玉树地震后,基于航片与卫星影像目视解译,并辅以野外调查的方法,在地震区圈定了2036处地震诱发滑坡.选择高程、坡度、坡向、斜坡曲率、坡位、与水系距离、地层岩性、与断裂距离、与公路距离、归一化植被指数(NDVI)、与同震地表破裂距离、地震动峰值加速度(PGA)共12个因子作为地震滑坡易发性评价因子.这些因子均是应用GIS技术与遥感影像处理技术,基于地形数据、地质数据、遥感数据得到.训练样本中的滑动样本有两组,一组是滑坡区整个单滑坡体的质心位置,另一组是滑坡滑源区滑前的坡体高程最高的位置.应用这12个影响因子,分别采用这两组评价样本,基于ANN模型建立地震滑坡易发性索引图,基于GIS工具建立地震滑坡易发性分级图.分别应用训练样本中滑坡分布的点数据去检验各自的结果正确率,正确率分别为81.53％与81.29％,表明ANN模型是一种高效科学的地震滑坡易发性区划模型. 相似文献
18.
19.
在节理岩质边坡的稳定性分析中,往往很少考虑结构面的随机分布特征。结构面网络模拟能较好地模拟结构面的随机分布,因此,本文将结构面网络模拟应用于节理岩质边坡的稳定性分析中。首先,运用岩体结构面网络模拟技术,建立岩质边坡的结构面网络模型。然后,将模拟的结果与有限元强度折减法相结合求取边坡的安全系数。最后,对边坡进行一定次数的结构面网络模拟并得到对应的安全系数,进而进行节理岩质边坡的可靠性分析。工程实例结果表明:(1)节理岩质边坡的稳定性主要受坡面附近结构面的数量及切割组合关系影响,结构面的数量越多,连通情况越好,则边坡稳定性安全系数越小; (2)该边坡的平均稳定性安全系数为3.06,失效概率为5%,表明该边坡有较高的可靠性,这与实际情况比较一致。本文的分析方法主要考虑了结构面的随机分布特征,能为节理岩质边坡的稳定性分析提供一条新的思路和方法。 相似文献
20.