基于MATLAB神经网络工具箱的岩爆预测模型

文章介绍了BP人工神经网络的基本原理，针对其收敛差的缺点，发挥MATLAB神经网络工具箱的优势，分别采用VLBP和LMBP算法建立了改进后的BP神经网络。对于影响岩爆发生的关键因素，总结了专家经验，选取地下硐室围岩最大切向应力与岩石单轴抗压强度比值、岩石单轴抗压强度和抗拉强度比值和岩石冲击性倾向指数作为岩爆预测的评判指标，建立了岩爆预测的神经网络模型，并利用国内外一些岩石地下工程实例进行分析计算校验，计算结果表明，用该模型进行岩爆预测是可行有效的。     

基于遗传神经网络的锚杆极限承载力预测的研究

针对BP人工神经网络具有易陷入局部极小等缺陷,提出了将遗传算法与神经网络结合,同时优化网络结构的权值与阈值的思想,建立了基于遗传算法的锚杆极限承载力预测的遗传神经网络模型。该模型以低应变动测的5个变量作为输入变量来对锚杆极限承载力进行预测,并与BP神经网络预测结果进行比较。数值算例表明,遗传神经网络在锚杆极限承载力预测中具有较高的计算效率和识别精度。     

用神经网络理论预测水库诱发地震

本文运用神经网络理论中改进的ＢＰ算法对水库诱发地震进行了研究，并根据不同的资料和不同的诱震因素，建立了两个水库诱发地震震级预测的神经网络模型。研究结果表明，与一般统计学相比，用神经网络理论预测水库诱发地震具有更高的精度。     

黄土路基震陷系数预测的模糊神经网络方法

以郑（州）-西（安）高速铁路为例,采集黄土样品,进行室内土工试验及动三轴震陷实验,以影响震陷系数主要因素为基础,建立了高速铁路黄土路基震陷系数的模糊神经网络模型,通过对样本的训练和预测,表明该模型预测的结果与动三轴试验震陷结果比较接近,是一种比较理想的预测方法。     

遗传神经网络法在巷道围岩松动圈预测中的应用

针对BP人工神经网络具有易陷入局部极小等缺陷,提出了将遗传算法与神经网络结合,同时优化网络结构的权值与阈值的思想,建立了基于遗传算法的围岩松动圈预测的神经网络模型。用该模型对巷道围岩松动圈厚度进行了预测并与BP预测结果相比较。结果表明,该遗传神经网络模型可靠,预测精度高,用来对围岩松动圈厚度进行预测是有效的和可行的。     

基于GA的混凝土坝抗震可靠度预测的神经网络模型

针对BP人工神经网络具有易陷入局部极小等缺陷,提出了将遗传算法与神经网络结合,同时优化网络结构的权值与阈值的思想,建立了基于遗传算法的混凝土坝抗震可靠度预测的神经网络模型。该模型分别对混凝土坝抗滑稳定可靠度、抗压可靠度和抗拉可靠度进行了预测,并与BP神经网络预测结果进行比较。结果表明,遗传神经网络模型可靠,预测精度高,在岩土工程中利用该方法进行可靠性问题预测是有效及可行的。     

砂土地震液化预测的人工神经网络模型

在简要分析BP算法的基础上,应用BP网络的理论与方法,选取烈度、震中距、平均粒径、不均匀系数、地下水埋深、砂层埋深、标贯击数、剪应力比等8个实测指标,建立了砂土液化预测的神经网络模型。通过实例计算与模型评价、验证了该模型的科学性、高效性并较规范法、Seed简化法等传统方法具有更高的预测精度,说明人工神经网络是解决非线性问题的有效方法之一。     

模糊神经网络在矿震预测中的应用

矿震同天然地震一样会给矿山生产及人身安全等带来重大灾难。也是目前尚不能准确预测的矿山灾害现象之一。根据现有的研究成果可知，矿震是一个多输入、多干扰、单输出的复杂系统。由于干扰项的存在，使利用建模、神经网络等手段对系统进行预测时会导致很大误差。模糊神经网络系统在建立对象输入、输出关系时与传统数学方法不同。即可以建立在无模型基础上，并利用其较强的学习训练特性，自动获取对象的输入、输出关系表达；可以将专家的评价语言作为系统的干扰项引入。这在一定程度上缓解了人为因素对预测结果的影响，且平滑了观测数据的随机性。文章利用改进的模糊神经网络及抚顺老虎台矿的矿震资料，对矿震最大震级的预测方法进行了探索。‘初步探讨了改进的模糊神经网络在矿震预测中的应用。得出在运用模糊神经网络进行预测时，为减小预测误差，应综合多种因素并提高专家评判语言的精确度的结论。指出在建立矿震系统预测模型时，利用干扰项将人为因素引入系统是必需的。通过实际应用证明其可行性。     

基于BP神经网络对边坡稳定性预测分析

采用BP软件建立了人工神经网络的边坡稳定性预测模型,并以杨东坪小学后侧边坡为例进行田边稳定性预测。结果表明,所预测边坡稳定性与实际情况基本相符,能够满足工程需求,因此利用BP神经网络对边坡稳定性进行预测是可行的。     

多隐层BP神经网络模型在径流预测中的应用

基于人工神经网络基本原理和方法,构建多隐层BP神经网络径流预测模型,以新疆伊犁河雅马渡站径流预测为例进行分析,并构建常规单隐层BP以及RBF、GRNN神经网络模型作为对比分析模型,将各模型预测结果与文献[1]中的预测结果进行比较,结果表明:(1)多隐层BP神经网络径流预测模型泛化能力强,预测精度高,算法稳定,模型精度优于IEA-BP网络模型,表明研究建立的多隐层BP神经网络模型用于径流预测是合理可行的,是一种可以应用于水文径流预测预报的新方法.(2)RBF、GRNN神经网络径流预测模型预测精度高于常规单隐层BP网络模型,且RBF与GRNN神经网络模型具有收敛速度快、预测精度高、调整参数少,不易陷入局部极小值等优点,可以更快地预测网络,具有较大的计算优势.     

基于ANN和GIS耦合模型的场地地震液化势评价系统研究

采用组件式GIS (COMGIS)技术开发了结合BP神经网络分析模型的场地地震液化势评价系统,调用水平成层土地震反应分析程序SHAKE91实现设定地震下地震动影响场的模拟。在VB下调用Matlab神经网络工具箱来完成场地地震液化势评价模型在COMGIS系统中的模块化;利用GIS技术对评价结果,即液化势等级进行空间复合,给出场地潜在的地层液化势空间分布图。研究表明,SHAKE91应用程序在系统菜单下可直接调用,实现地震动影响场计算的模块化;BP神经网络技术应用于场地地震液化势评价中能达到较为理想的效果;系统的GIS空间分析功能可使评价结果与场地信息进行空间匹配,实现目标场地潜在地震液化势的快速评估。     

Explanation of liquefaction in after shock of the 2011 great east Japan earthquake using numerical analysis

During the 2011 Great East Japan Earthquake, severe liquefaction occurred in reclaimed ground in Urayasu city, Chiba prefecture. This liquefaction provided important lessons for us to re-recognize the liquefaction mechanism. A distinct feature of the liquefaction in this earthquake is that severe liquefaction happened not only in the main shock but also in an aftershock with a maximum acceleration of 25 gal. In some areas, liquefaction happened in the aftershock is even more serious than that happened in the main shock. In this paper, focus is placed on the characteristic features in the occurrence of liquefaction and consequent ground settlement. Based on the observed data, a series of dynamic–static analyses, considering not only the earthquake loading but also static loading during the consolidation after the earthquake shocks, are conducted in a sequential way just the same as the scenario in the earthquake. The calculation is conducted with 3D soil–water coupling finite element–finite difference analyses based on a cyclic elasto-plastic constitutive model. From the results of analyses, it is recognized that small sequential earthquakes, which cannot cause liquefaction of a ground in an independent earthquake vibration, cannot be neglected when the ground has already experienced liquefaction after a major vibration. In addition, the aftershock has great influence on the long-term settlement of low permeability soil layer. The observed and predicted liquefaction and settlements are compared and discussed carefully. It is confirmed that the numerical method used in this study can describe the ground behavior correctly under repeated earthquake shocks.     

1998 Adana-Ceyhan (Turkey) Earthquake and a Preliminary Microzonation Based on Liquefaction Potential for Ceyhan Town

A moderate earthquake (M_s = 6.2) occurred in the Cukurova region in the southern part of Turkey, on 27 June 1998. It resulted in loss of 145 lives and significant damage particularly in the settlements close to the epicenter at the south of Ceyhan town. Widespread liquefaction and associated sand boils, ground fissures and ground deformations due to lateral spreading occurred during this earthquake. In this study, main characteristics of the earthquake are presented and liquefaction throughout the site was assessed. An attempt was also made to establish preliminary microzonation maps for Ceyhan using the data from liquefaction susceptibility analyses. The results of the analyses indicated that the data from the liquefied sites were within the empirical bounds suggested by the field-performance evaluation method. Fortunately, most of the riversides were used for agricultural purposes alone, damage to structures from liquefaction and associated ground failures were rather limited. Preliminary assessments indicated that at depths of about 5 m the liquefaction potential of thin sand layers tends to diminish.     

Liquefaction analysis and damage evaluation of embankment-type structures

The increasing importance of performance-based earthquake engineering analysis points out the necessity to assess quantitatively the risk of liquefaction of embankment-type structures. In this extreme scenario of soil liquefaction, devastating consequences are observed, e.g., excessive settlements, lateral spreading and slope instability. The present work discusses the global dynamic response and interaction of an earth structure-foundation system, so as to determine quantitatively the collapse mechanism due to foundation’s soil liquefaction. A levee-foundation system is simulated, and the influence of characteristics of input ground motion, as well as of the position of liquefied layer on the liquefaction-induced failure, is evaluated. For the current levee model, its induced damage level (i.e., induced crest settlements) is strongly related to both liquefaction apparition and dissipation of excess pore water pressure on the foundation. The respective role of input ground motion characteristics is a key component for soil liquefaction apparition, as long duration of mainshock can lead to important nonlinearity and extended soil liquefaction. A circular collapse surface is generated inside the liquefied region and extends toward the crest in both sides of the levee. Even so, when the liquefied layer is situated in depth, no significant effect on the levee response is found. This research work provides a reference case study for seismic assessment of embankment-type structures subjected to earthquake and proposes a high-performance computational framework accessible to engineers.     

砂土地震液化的改进进货遗传算法判别

改进了进化遗传算法,提出了新的交叉算子和变异算子,使之具有更好的全局收敛能力。砂土液化是一种危害极大的地震破坏现象,其影响因素很多,选择地震烈度、砂土粒径、相对密度、标贯击数和有效正应力为判据,利用改进了的进化遗传算法建立了砂土地震液化的判别模型。与液化情况比较表明,改进进化遗传算法应用于砂土地震液化的判别效果良好。     

砂土地震液化的改进进化遗传算法判别

改进了进化遗传算法,提出了新的交叉算子和变异算子,使之具有更好的全局收敛能力。砂土液化是一种危害极大的地震破坏现象,其影响因素很多,选择地震烈度、砂土粒径、相对密度、标贯击数和有效正应力为判据,利用改进了的进化遗传算法建立了砂土地震液化的判别模型。与现场液化情况比较表明,改进进化遗传算法应用于砂土地震液化的判别效果良好。     

Role of the confined aquifer in the mechanism of soil liquefaction due to the 7.5 Mw earthquake in Palu (Indonesia) on 28 September 2018

Soil liquefaction on 28 September 2018 in Palu, Indonesia, included one of the largest soil movements ever, where objects on the ground surface moved hundreds of meters away and settlements sank into the mud. Some preliminary studies show that in addition to a strong earthquake, there are strong indications that a confined aquifer in the Palu valley worsened the liquefaction. The role of the confined aquifer can be recognized early on from one of various signs, namely the presence of massive surface inundations suspected due to groundwater expulsion which is thought to originate mostly from the confined aquifer. This paper describes the mechanism of the soil liquefaction in Palu from the perspective of earthquake hydrogeology, focusing on the groundwater expelled from an unconfined aquifer and especially from the underlying confined aquifer through hydraulic inter-connection between the two, which is possible due to simultaneous interaction of excess pore pressure dissipation and enhanced permeability driven by an earthquake in the near field. If this hypothesis proves to be strong, there are implications for engineering practices because the evaluation of potential soil liquefaction carried out currently in the geotechnical engineering field generally only involves the role of shallow groundwater and/or the unconfined aquifer and the role of soil layers not deeper than 30 m from the ground surface. It may be necessary to complement current evaluation practice with an evaluation of the deep groundwater response to earthquakes, especially if the deep groundwater is artesian and productive, with a relatively thin confining layer.

     

A simulation of earthquake induced undrained pore pressure changes with bearing on some soil liquefaction observations following the 2001 Bhuj earthquake

The Bhuj earthquake of January 26th, 2001, induced wide spread liquefaction within the Kachch peninsula. It has been pointed out that inundation due to soil liquefaction was short lived in some parts than in others in the affected region. Several geological, seismological and hydrological factors would have cumulatively contributed to these observed changes. We simulate in this article, undrained or short-term change in pore pressure in a poroelastic half space, in response to a simplified model of the Bhuj earthquake source. We find that the regions of relatively shorter lived inundation due to soil liquefaction may fall in the region where pore pressure responsible for soil liquefaction attributable to strong ground shaking was counteracted by pore pressure changes due to undrained poroelastic effect and vice versa.     

建筑物下砂土地震液化分区特征数值模拟研究

基于动力有限元反应分析,对存在于建筑物下的非自由场地的液化特性进行了研究。通过多种工况的计算,探讨了建筑物刚度、宽度和荷载大小对液化区分布的影响。以往一般认为建筑物下的砂土难于液化,而由计算结果及分析,可先实际情况并非这样简单。建筑物基底以下存在易于液化的“V”字型区域,该区域形态与建筑物的刚度、宽度和荷载大小都有密切关系。     

自适应BP网络在洛带气田测井解释中的应用

应用自适应算法对BP网络进行改进，可以提高BP网络的收敛速度和全局寻优性能。在此基础上，利用多种测井数据及岩心描述资料作为网络模型的学习样本，以测井解释渗透率的神经网络模型为例，通过网络的学习、训练，建立测井解释神经网络模型。并应用此模型，定量计算出多口井的渗透率值，与常规渗透率计算结果相比，BP的解释结果及精度均令人满意，同时还取得了良好的实际应用效果。