Some applications of a backpropagation neural network in geo-engineering

A MATLAB based backpropagation neural network (BPNN) model has been developed. Two major geo-engineering applications, namely, earth slope movement and ground movement around tunnels, are identified. Data obtained from case studies are used to train and test the developed model and the ground movement is predicted with the help of input variables that have direct physical significance. A new approach is adopted by introducing an infiltration coefficient in the network architecture apart from antecedent rainfall, slope profile, groundwater level and strength parameters to predict the slope movement. The input variables for settlement around underground excavations are taken from literature. The neural network models demonstrate a promising result predicting fairly successfully the ground behavior in both cases. If input variables influencing output goals are clearly identified and if a decent number of quality data are available, backpropagation neural network can be successfully applied as mapping and prediction tools in geotechnical investigations.     

Prediction of pile settlement using artificial neural networks based on standard penetration test data

In recent years artificial neural networks (ANNs) have been applied to many geotechnical engineering problems with some degree of success. With respect to the design of pile foundations, accurate prediction of pile settlement is necessary to ensure appropriate structural and serviceability performance. In this paper, an ANN model is developed for predicting pile settlement based on standard penetration test (SPT) data. Approximately 1000 data sets, obtained from the published literature, are used to develop the ANN model. In addition, the paper discusses the choice of input and internal network parameters which were examined to obtain the optimum model. Finally, the paper compares the predictions obtained by the ANN with those given by a number of traditional methods. It is demonstrated that the ANN model outperforms the traditional methods and provides accurate pile settlement predictions.     

Prediction of slope stability using artificial neural network (case study: Noabad, Mazandaran, Iran)

Investigations of failures of soil masses are subjects touching both geology and engineering. These investigations call the joint efforts of engineering geologists and geotechnical engineers. Geotechnical engineers have to pay particular attention to geology, ground water, and shear strength of soils in assessing slope stability. Artificial neural networks (ANNs) are very sophisticated modeling techniques, capable of modeling extremely complex functions. In particular, neural networks are nonlinear. In this research, with respect to the above advantages, ANN systems consisting of multilayer perceptron networks are developed to predict slope stability in a specified location, based on the available site investigation data from Noabad, Mazandaran, Iran. Several important parameters, including total stress, effective stress, angle of slope, coefficient of cohesion, internal friction angle, and horizontal coefficient of earthquake, were used as the input parameters, while the slope stability was the output parameter. The results are compared with the classical methods of limit equilibrium to check the ANN model’s validity.     

Multi-sensor approach to settlement analysis of earth dams

In this paper, a fusion method for the settlement study of the earth dams based on geodetic and geotechnical data is developed. The developed method can be algorithmically explained as follows: (a) interpolation of the geotechnical data to the epoch of geodetic observations by four degree polynomial fitting, which serves as a low-pass filter. (b) Conversion of the initial observations into time series of the dam heights at the geodetic and geotechnical stations. (c) Fusion of the data from the two sources at different fusion levels. (d) Final decision based on the deformation parameters derived from fused data. The significant innovation of the proposed method centered upon its ability to incorporate geodetic and geotechnical observation types into a one integrated solution through fusion. The method is numerically tested for the Karkhe earth dam by using geodetic and geotechnical data from 1997 till 2009. The numerical evaluation at 229 check points indicates more than 70% improvement in the settlementmodeling based on the fusion of the geodetic and geotechnical data, as compared to the settlement modeling based on geotechnical data alone.     

Modeling soil collapse by artificial neural networks

The feasibility of using neural networks to model the complex relationship between soil parameters, loading conditions, and the collapse potential is investigated in this paper. A back propagation neural network process was used in this study. The neural network was trained using experimental data. The experimental program involved the assessment of the collapse potential using the one-dimensional oedometer apparatus. To cover the broadest possible scope of data, a total of eight types of soils were selected covering a wide range of gradation. Various conditions of water content, unit weights and applied pressures were imposed on the soils. For each placement condition, three samples were prepared and tested with the measured collapse potential values averaged to obtain a representative data point. This resulted in 414 collapse tests with 138 average test values, which were divided into two groups. Group I, consisting of 82 data points, was used to train the neural networks for a specific paradigm. Training was carried out until the mean sum squared error (MSSE) was minimized. The model consisting of eight hidden nodes and six variables was the most successful. These variables were: soil coefficient of uniformity, initial water content, compaction unit weight, applied pressure at wetting, percent sand and percent clay. Once the neural networks have been deemed fully trained its accuracy in predicting collapse potential was tested using group II of the experimental data. The model was further validated using information available in the literature. The data used in both the testing and validation phases were not included in the training phase. The results proved that neural networks are very efficient in assessing the complex behavior of collapsible soils using minimal processing of data. This revised version was published online in July 2006 with corrections to the Cover Date.     

水位升降对粗砂地基承载力和沉降影响的试验研究

随着城市地下空间的开发和利用,地下水位埋深较浅的地区,例如沈阳市,在施工过程中需要降水,工程完毕后停止降水又使水位恢复。水位的变化可能会导致地基土抗剪强度的变化、地基的回弹或沉降、渗透破坏引起地表塌陷等岩土问题,尤其是地基承载能力和既有建筑物的沉降是工程设计中必须考虑的岩土问题。对于辽沈地区,大多数文献只给出定性的回答,但工程设计需要的是定量回答,这是本文的研究目的。本文通过模型试验模拟粗砂地基上的浅基础,通过静载荷试验、水位观测、水压力和土压力传感器测试等方法测试地下水位升降时,粗砂地基的承载力、土中应力及基础沉降等的变化规律,并对试验结果进行分析和数值仿真分析,提出了利用拟合公式的方法弥补数值仿真分析与模型试验误差的思路。研究结果表明,对于密实的粗砂土地基,其地基承载力特征值在地下水位上升前后会降低,降低幅度达26%,主要原因是地基土抗剪强度降低导致承载力减小;在基础上施加一定荷载后,无论地下水位升和降,基础都会产生附加沉降。水位升高4.3m,沉降为0.565mm,主要原因是地基土的承载能力降低。水位下降4.3m,沉降0.315mm,主要原因是地下水位下降导致土中有效应力增大;数值仿真分析结果表明FLAC3D 可以较好地模拟试验过程,可用拟合公式的方法修正饱和砂土出现的误差。     

统一强度理论在边坡稳定性分析中的应用

基于统一强度理论,以某高速公路路基边坡的典型断面为例,运用刚体极限平衡理论中的毕肖普简化法进行计算,得到不同的统一强度理论参数、不同的双剪应力状态参数与边坡稳定系数之间的关系。在此基础上,讨论了边坡问题的强度理论效应。通过分析可知,中间主应力在边坡稳定性分析中不容忽视。实际工程中,应根据具体边坡的岩土特征及应力状态确定统一强度理论参数和双剪应力状态参数,确切地反映岩土强度特性,界定稳定系数的上下限范围,有效地发挥材料的强度潜能,节约工程费用。      

南京地铁应用人工地层冻结法的可行性研究

人工地层冻结技术用于采矿凿井在国外有100余年的历史,在中国也有40余年,然而,它在其它岩土工程中的应用尚处于起步阶段。本文以南京地铁珠江路—鼓楼区间为例,探讨了冻结法施工的可行性、设计方法、技术要点及其可能遇到的环境岩土工程问题。     

Consolidation behavior of soil–cement column improved ground

Columnar inclusion is one of the effective and widely used methods for improving the engineering properties of soft clay ground. This article investigates the consolidation behavior of composite soft clay ground using both physical model tests under an axial-symmetry condition and finite element simulations using the PLAXIS 2D program. It was determined that the final settlement and the rate of consolidation of the composite ground depended on the stress state. For an applied stress that is much lower than the failure stress, the final settlement of the composite ground was lower, and the consolidation was rapid. When the soil–cement column failed, the stress on the column suddenly decreased (due to strain-softening); meanwhile, the stress on the soil increased to maintain the force equilibrium. Consequently, the excess pore pressure in the surrounding clay increased immediately. The cracked soil–cement column acted as a drain, which accelerated the dissipation of the excess pore pressure. The consolidation of the composite ground was mainly observed in the vertical direction and was controlled by the area ratio, which is the ratio of the diameter of the soil–cement column to the diameter of the composite ground, a. The stress on the column was shown to be low for a composite ground with a high value of a, which resulted in less settlement and fast consolidation. For a long soil–cement column, the excess pore pressures in the surrounding clay and the column were essentially the same at a given consolidation time throughout the improvement depth. It is proposed that the soil–cement column and surrounding clay form a compressible ground, and the consolidation occurs in the vertical direction. The composite coefficient of consolidation (c_v(com₎) that was obtained from the physical model test on the composite ground can be used to approximate the rate of consolidation. This approximation was validated via a finite element simulation. The proposed method is highly useful to geotechnical engineers because of its simplicity and reliable prediction.     

三轴试验抗剪强度指标线性回归方法的讨论

利用线性回归统计抗剪强度指标是岩土工程中的常用手段。对于常规三轴试验,可以通过线性拟合p-q曲线或者拟合大小主应力的方法来求解抗剪强度参数,并给出了这两种方法的完整计算公式,同时应用矩法和线性回归方法统计了小浪底64组320个固结排水三轴试验和多个水利工程大坝填筑料的试验资料,发现对于常规三轴试验,拟合p-q曲线求解抗剪强度参数存在高估摩擦系数、低估粘聚力的问题;利用概率理论对两种方法进行了对比分析也发现了同样的趋势。因此,根据常规三轴试验统计抗剪强度参数时采用直接拟合大小主应力更为合理。     

高填方下覆结构性黄土次固结特性研究

研究结构性黄土的次固结特性及机制,已成为黄土高填方地基工后沉降计算和控制的有效手段。本文通过对结构性黄土的压缩试验,研究了其次固结特性及变形机制,建立了描述次固结系数时间效应的关系式。试验结果表明,结构性黄土存在明显的次固结效应;荷载-次固结系数曲线（P-C_α）表现出先增加后减小,最终趋于稳定;C_α峰值对应荷载大于P_c,且高荷载将不是次固结系数的主要控制因素;在岩土破损力学框架内,分析了荷载、含水率对次固结系数影响的机制;水对土颗粒胶结作用的弱化使得高含水率结构性黄土的P-C_α曲线只呈现下降段和稳定段;建立了一种描述次固结系数时间效应的关系式,可对计算高填方下覆原有黄土地基的工后沉降提供帮助。     

Integration of Information Technology into Geotechnical Engineering Practice: Concept and Development

Information Technology (IT) has been extensively used to predict, visualize, and analyze physical parameters in order to expedite routine geotechnical design procedures. This paper presents an example of the combined technique of IT and numerical analysis for routine geotechnical design projects. The proposed approach involves the development of ANN(s) using a calibrated finite element model(s) for use as a prediction tool and implementation of the developed ANN(s) into a GIS platform for visualization and analysis of spatial distribution of predicted results. A novel feature of the proposed approach is an ability to expedite a routine geotechnical design process that otherwise requires significant time and effort in performing numerical analyses for different design scenarios. A knowledge-based underground excavation design system that utilizes artificial neural networks (ANNs) as prediction tools is also introduced. Practical implications of the use of IT in geotechnical design are discussed in great detail.     

相关型岩土参数分析和选用

岩土参数与应力环境、沉积条件、风化程度和埋藏条件等因素相关,其统计值具有空间变异性和相关性,采用非相关型岩土统计参数进行岩土工程设计具有不经济性。通过分析岩土参数的变化规律及与其相关的主要因素,说明岩土参数可用深度或参数与地层顶面或底面的距离作为相关参数进行相关型判别,论述相关型参数的判定标准和相关型标准值的计算方法,采用图解法分析相关型参数多种取值方法的可靠性。以华南某核电厂常规岛地基和某变电站边坡为例,介绍了相关型岩土参数标准值经验公式在岩土设计优化中的应用。分析表明：具有规律性变化的岩土参数宜选择恰当的相关参数划分为相关型,相关参数可取参数与地层顶面或底面的距离,相关型岩土参数标准值可使岩土设计方案更具合理性和经济性。     

喜马拉雅中段冰湖终碛坝体溃决过程实验研究

终碛坝广泛分布于世界各地的高山和极高山区。为了探究终碛坝的溃决过程,了解溃口的演变特征,文章以嘉龙错终碛坝的原位实验,模拟了终碛湖漫顶溃决过程。通过分析实验结果发现:（1）根据观察,将终碛坝溃决过程划分为坝体下游坡面冲刷、“溯源侵蚀”、出水口下切和溃口拓宽四个阶段。（2）上游湖区崩塌体激发的涌浪会造成溃口内的瞬时流量增加数倍,从而使得在有涌浪和无涌浪的条件下,“溯源侵蚀”过程出现陡坎和斜坡两种下切型。（3）通过分析溃口下切侵蚀过程,发现溃口的下切侵蚀发展过程主要受到坝体孔隙比和细粒含量的影响,并且溃口中点侵蚀率与水流剪应力存在一定的线性关系,符合线性侵蚀模型。通过分析发现,嘉龙错终碛坝的侵蚀系数为0.051,临界启动应力为237.64 Pa。与堰塞坝相比,可侵蚀系数比更小,而临界启动应力更大。     

Probabilistic analysis of collapsing soil by indicator kriging

Collapsing soils, which undergo a large decrease in bulk volume virtually instantaneously upon saturation and/or load application, are found in arid and semi-arid regions of the world. In the western and midwestern U.S., problems resulting from collapsing soils are being recognized due to rapid industrial and urban developments. A probabilistic analysis of the distribution of such soils would be a rational approach for quantifying risk involved for a project in an area where such soils are found. Indicator kriging was applied to seven sets of collapse and collapse-related soil parameters to obtain the probability that a certain parameter is more or less than a predefined critical value for low, medium, and high collapse susceptibility. Results are presented in the form of probability contour plots with known variance of estimation of the probability. The ability to predict the probability of occurrence of collapse and collapse-related soil parameters for different critical values with a known degree of certainty is invaluable to planners, developers, and geotechnical engineers.     

地基沉降大变形计算方法的关键问题研究

针对大、小变形法地基沉降量结果的差异问题,从大变形应力和应变度量、本构关系以及本构参数等概念的角度进行探讨。在连续介质力学有关原理基础上,先后研究了基于Green应变、Almansi应变和自然应变的地基大变形沉降量计算式。基于欧拉应力--Almansi应变对、欧拉应力--自然应变对的大变形法压缩本构关系整理方法,以及大、小变形法切线体积压缩系数之间的转换方法等。理论分析和算例分析结果表明,遵循该转换关系的条件下,同一问题所得的大、小变形法最终沉降量结果是相同的,忽略该转换关系将导致大变形法沉降量计算结果偏大或偏小于小变形法的结果,这也为合理确定大变形法本构参数提供新的参考。     

Reservoir parameters determination using artificial neural networks: Ras Fanar field, Gulf of Suez, Egypt

Ras Fanar field is one of the largest oil-bearing carbonate reservoirs in the Gulf of Suez. The field produces from the Middle Miocene Nullipore carbonate reservoir, which consists mainly of algal-rich dolomite and dolomitic limestone rocks, and range in thickness between 400 and 980 ft. All porosity types within the Nullipore rocks have been modified by diagenetic processes such as dolomitization, leaching, and cementation; hence, the difficulty arise in the accurate determination of certain petrophysical parameters, such as porosity and permeability, using logging data only. In this study, artificial neural networks (ANN) are used to estimate and predict the most important petrophysical parameters of Nullipore reservoir based on well logging data and available core plug analyses. The different petrophysical parameters are first calculated from conventional logging and measured core analyses. It is found that pore spaces are uniform all over the reservoirs (17–23%), while hydrocarbon content constitutes more than 55% and represented mainly by oil with little saturations of secondary gasses. A regular regression analysis is carried out over the calculated and measured parameters, especially porosity and permeability. Fair to good correlation (R <65%) is recognized between both types of datasets. A predictive ANN module is applied using a simple forward backpropagation technique using the information gathered from the conventional and measured analyses. The predicted petrophysical parameters are found to be much more accurate if compared with the parameters calculated from conventional logging analyses. The statistics of the predicted parameters relative to the measured data, show lower sum error (<0.17%) and higher correlation coefficient (R >80%) indicating that good matching and correlation is achieved between the measured and predicted parameters. This well-learned artificial neural network can be further applied as a predictive module in other wells in Ras Fanar field where core data are unavailable.     

Earthquake early warning for earth dams: concepts and objectives

In the geotechnical field, the risk related to slope instabilities or collapse of geotechnical structures are increasingly being faced by early warning systems, capable of: (1) predicting the incipient collapse based on the interpretation of a continuous monitoring of the structure and (2) spreading alarm promptly to reduce people exposure. Compared with structural approaches, early warning systems have two important advantages: a faster, simpler and less expensive implementation and environmental compatibility. Past experience indicates that vulnerability of earth dams is generally low under both static and seismic loading conditions. In spite of this, earth dams are characterized by a high-risk level, due to the high exposure factor. Nowadays, the application of early warning systems to dams is fully supported by the technological progress achieved in the telecommunication field, since it is possible to install and automate recordings and transmission of all physical variables significant to check dam safety: accelerations, displacements, pore-water pressures, total stresses, seepage flows. A considerable lack still arises in the predictive models for interpreting monitoring data and providing indicators on dam safety soon after a strong earthquake. The present work illustrates the basic concepts of an earthquake early warning (EEW) system for earth dams and the main features that should characterize a predictive model to such a scope. An application to a real case is finally provided, enhancing the role played by each monitored physical variable for the aims of EEW.     

One-Dimensional Consolidation of Sedimented Stowed Pond Ash

Use of fly ash locked in the ash ponds in geotechnical applications such as stowing or backfilling of the mines is an attractive alternative to solve the disposal problem. Before it is used as a stowing or backfilling material, the response of the fly ash?to imposed load must be determined in order to assess its load taking ability. The present study examines the effect of time and incremental load on the consolidation characteristics of the sedimented stowed pond ash using a fixed ring consolidometer. The important parameters, viz. rate of settlement, consolidation coefficients and void ratio, etc. of the hydraulically stowed pond ash collected after 7, 14, 21, 28 and 35?days of stowing under step incremental loads are determined. The study revealed that 60.42–84.87% settlement of the sedimented stowed pond ash takes place in the initial 1?min of the loading. In addition, it is observed that the coefficient of consolidation of the sedimented stowed pond ash, which varies in the range of 0.0195–0.1882?cm²/min, is comparatively low and decreases with the increment of applied load and time. This indicates that the structures lying above the stowed pond ash mass will undergo gradual settling and not suffer large deformation.     

基于三角形滑移面的地基松动土压力研究

由岩溶塌陷、隧道开挖等方面引起的土体变形往往会对基础建设和基础结构等造成不均匀沉降、地面塌陷及开裂等危害,确定土体结构顶部松动土压力的分布情况并准确地分析土体变形与土拱效应间关系显得尤为重要。为了揭示土体变形和沉降对结构顶部松动土压力的变化规律,进行了一系列不同H/B的活动门试验（H为地基高度,B为活动门宽度）。基于试验结果,提出以三角形作为力学模型分析不同滑移面时松动土压力的数学模型,考虑了滑移面角度与土体变形及主应力偏转三者之间的关系,分析了滑移面内任意水平微分土条的主应力偏转情况并建立受力平衡微分方程,根据不同滑移面形态下的边界条件求解松动土压力理论公式,与已有试验结果对比验证了理论公式的合理性。通过对滑移面角度、侧向土压力系数和内摩擦角等主要参数进行分析,结果表明：在较小相对位移下（1%～3%）土体应力迅速发生转移和重分布,初始滑移面角度略小于π/4+φ/2（φ为内摩擦角）,随着H/B增大土体应力比缓慢增长最终趋于稳定;地基内封闭三角形滑移面的松动土压力与相对位移及内摩擦角相关;内摩擦角的增加使得土拱效应得到充分发挥,加强了应力转移,降低了土拱应力比;内摩擦角的增大减小了水平向...