土的轻型与重型击实试验结果的统计分析

通过对土的轻型与重型击实试验结果（最大干密度和最优含水率）的统计分析,建立了轻、重两种击实试验方法所确定参数之间的线性关系式,可利用轻型击实试验结果推导出重型击实试验结果。     

Analysis of Swelling and Shrinkage Behavior of Compacted Clays

The impact of the variation in compaction condition on the swelling and shrinkage behavior of three soils has been examined. Two natural soils, namely red soil and black cotton soil, and one artificially mixed soil sample of commercial bentonite with well-graded sand, were studied. Compaction curve for Standard Proctor conditions were plotted and four compaction conditions were selected. Experimental results showed that clay mineralogy dominates over compaction conditions in influencing the swelling and shrinkage behavior of the tested soils. Monitoring of void ratio (e)−water content (w) relations during shrinkage showed that soil specimens generally shrunk in three distinct linear stages. A small reduction in void ratio occurred on reduction in water content during the first shrinkage stage and was termed as initial shrinkage. In second stage, void ratio decreased rapidly with reduction in water content and was termed as primary shrinkage. In third and final stage, reduction in water content is accompanied by a marginal change in void ratio and it’s called residual shrinkage. Irrespective of initial compaction conditions studied, the transition from primary to residual shrinkage for all the specimens occurred within a narrow range of water content (10–15%).     

融沉系数的人工神经网络预测方法

分析了前人关于融沉系数经验方法的研究结果,结果显示,与融沉系数关系最为密切的物性参数为液塑限、粉黏粒含量、干密度和含水量（含冰量）．为了能够综合描述诸因素与融沉系数的经验关系,以兰州黄土和青藏黏土为试验对象,得到了两种具有不同物性参数的土在不同含水量和干密度条件下的融沉系数．采用BP神经网络算法对试验数据进行学习训练,...     

石油污染土的击实特性

为了解石油污染对土的压实特性的影响,利用室内击实试验,以原油、柴油和水为介质,得到了单一液体介质和油水混合介质时土的击实曲线。结果表明:石油代替水作为壤粘土孔隙流体,其击实曲线无明显峰值,干密度随含油率增加略有增大但远小于无污染土的最大干密度。油水混合作为孔隙流体,随含油率的增加,原油污染土壤的击实曲线由钟型、双峰型转向无明显峰值曲线,出现类似高液限粘土压实特性;柴油污染土的击实曲线由尖锐型转变为无峰值型;最优含水率均减小,最大干密度随含油率变化规律与油品性质有关。提出了"油膜润滑"的新观点,可较好地解释石油污染壤粘土击实曲线的变化规律。     

软基沉降的BP神经网络和灰色系统联合预测

使用BP神经网络插值方法对灰色数据进行了预处理,进而建立了预测软基沉降量的BP神经网络和灰色系统联合模型.实例分析表明,该模型短期沉降预测结果的最大相对误差小于2%,最终沉降预测结果的相对偏差小于5%,且灰色预测时取后期沉降瘦导颇算结果准确度高于取前期沉降数据的计算结果准确度.     

基于BP神经网络的土壤冰结温度及未冰水含量预测模型

土壤冻结温度与未冻水含量是冻土的重要物理参数，影响因素多，关系复杂，利用BP网络模型来描述冻结温度与未冻水含量及其与主要影响因素之间的关系，效果良好，该模型直接根据试验数据通过神经网络的自学习能力寻求输出变量与输入变量间的内在非线性规律，其优点在于可利用一个神经网络同时描述多个因素对冻结温度及未冻水含量的影响。     

基于神经网络理论的河道水情预报模型

河道水流运动过程特别是洪水演进过程是一个复杂的非线性动力学过程,鉴于神经网络具有很强的处理大规模复杂非线性动力学系统的能力,本文将神经网络理论用于河道水情预报的研究,以期识别水流运动变化过程与其影响因子之间的复杂非线性关系,为河道水情预报提供了一条新的途径。在此基础上建立了螺山站洪水预报的非线性动力学模型,通过分析研究得出近年来特别是1998年长江中游出现的小流量高水位现象与螺山汉口河段累计淤积有关并得到螺山站水位变化与河床淤积之间的定量关系。     

冻结方式对冻土试样制备的影响

冻土试样的制备是进行冻土试验最为基础而重要的工作,其中土样在冻结过程中受到的影响直接关系到试样内部状况.为研究冻结方式对粉质粘土含水量和干密度分布的影响,采取不同的冻结方式即单向冻结和多向冻结方法,对比分析不同状态下兰州黄土和北麓河粘土冻结试样各部位含水量与干密度的分布状况.结果表明:试样内含水量和干密度的分布程度取决于土的类型、饱和状态和冻结方式,具体为:非饱和兰州黄土在多向冻结情况下,可以取得比单向冻结更加均匀的冻结试样;饱和兰州黄土冻结试样无论是单向冻结还是多向冻结都较为均匀;北麓河粘土无论饱和与否,均以单向冻结为好.     

Using and Improving Neural Network Models for Ground Settlement Prediction

Earth-fill structures such as embankments, which are constructed for the preservation of land and infrastructure, show significant amount of settlement during and after construction in lowland areas with soft grounds. Settlements are often still predicted with large uncertainty and frequently observational methods are applied using settlement monitoring results in the early stage after construction to predict the long term settlement. Most of these methods require a significant amount of measurements to enable accurate predictions. In this paper, an artificial neural network model for settlement prediction is evaluated and improved using measurement records from a test embankment in The Netherlands. Based on a learning pattern that focuses on convergence of the settlement rate, the basic model predicted settlements which were in good agreement with the measurements, when the amount of measured data used as teach data for the model exceeded a degree of consolidation of 69 %. For lower amounts of teach data the accuracy of settlement prediction was limited. To improve the accuracy of settlement prediction, it is proposed to add short-term predicted values that satisfy predefined statistical criteria of low coefficient of variance or low standard deviation to the teach data, after which the model is allowed to relearn and repredict the settlement. This procedure is repeated until all predicted values satisfy the criterion. Using the improved network model resulted in significantly better predictions. Predicted settlements were in good agreement with the measurements, even when only the measurements up to a consolidation stage of 35 % were used as initial teach data.     

盾构施工地面长期沉降的神经网络预测

基于逆传播人工神经网络方法，建立了盾构施工地面长期沉降的非线性预测模型，建立了沉降与诸多影响因素：所处位置、时间、上覆土性参数及盾构施工参数等的关系模型。通过在上海地铁2号线龙东路一中央公园站区间资料的验证，发现与实际比较吻合。     

Assessment and Prediction of Liquefaction Potential Using Different Artificial Neural Network Models: A Case Study

Soil liquefaction as a transformation of granular material from solid to liquid state is a type of ground failure commonly associated with moderate to large earthquakes and refers to the loss of strength in saturated, cohesionless soils due to the build-up of pore water pressures and reduction of the effective stress during dynamic loading. In this paper, assessment and prediction of liquefaction potential of soils subjected to earthquake using two different artificial neural network models based on mechanical and geotechnical related parameters (model A) and earthquake related parameters (model B) have been proposed. In model A the depth, unit weight, SPT-N value, shear wave velocity, soil type and fine contents and in model B the depth, stress reduction factor, cyclic stress ratio, cyclic resistance ratio, pore pressure, total and effective vertical stress were considered as network inputs. Among the numerous tested models, the 6-4-4-2-1 structure correspond to model A and 7-5-4-6-1 for model B due to minimum network root mean square errors were selected as optimized network architecture models in this study. The performance of the network models were controlled approved and evaluated using several statistical criteria, regression analysis as well as detailed comparison with known accepted procedures. The results represented that the model A satisfied almost all the employed criteria and showed better performance than model B. The sensitivity analysis in this study showed that depth, shear wave velocity and SPT-N value for model A and cyclic resistance ratio, cyclic stress ratio and effective vertical stress for model B are the three most effective parameters on liquefaction potential analysis. Moreover, the calculated absolute error for model A represented better performance than model B. The reasonable agreement of network output in comparison with the results from previously accepted methods indicate satisfactory network performance for prediction of liquefaction potential analysis.     

径向基人工神经网络法在土壤盐渍化调查中的应用

土壤盐渍化是一个世界性的生态问题，同时也是资源开发和利用问题。对于盐渍化土壤的调查是合理利用土壤的前提条件。文章应用径向基（RBF）人工神经网络，结合多源遥感影像对北方某地区耕地土壤盐渍化状况进行调查研究，取得了满意的效果。     

人工神经网络在盐渍土盐胀特性研究中的应用

利用人工神经网络处理非线性体系的优势性,对盐渍土膨胀规律多影响因素试验数据进行了建模方法分析,提出了盐渍土盐胀率随含水量、氯化钠含量、硫酸钠含量、初始干容重和上覆荷载5因素变化的计算公式,计算结论比常规二次回归法更加符合目前对盐渍土盐胀规律的定性认识.     

重复利用土击实试验对比及其准确性探讨

土的最大干密度和最优含水率是土方工程中抗压、抗剪、抗渗等性能的关键性指标。基于泾阳地区的马兰黄土,通过室内标准击实试验,对土重复使用和不重复使用的击实曲线进行对比分析,并利用三点二次插值函数的方法建立土的干密度和含水量的函数关系,验证击实试验结果的可靠性。研究表明：泾阳地区马兰黄土的最大干密度为1.735gcm-3,最优含水率为17.07%;重复利用土的最大干密度为1.762gcm-3,最优含水率为16.69%,相对非重复利用土,最大干密度增大1.56%,最优含水量减小2.23%。利用插值函数得到的最优含水率与最大干密度与击实试验的结论基本一致,表明击实试验的准确性。三点二次插值法思路明确、计算简便,为求解最大干密度和最优含水量提供了理论依据,具有较高的适用性。     

水库群优化调度函数的人工神经网络方法研究

提出了研究水库群优化调度函数的人工神经网络方法,并探讨了神经网络的训练参数、训练方法和训练样本的改变对网络训练和应用效果的影响。实例研究表明,模型及其算法是可行的、有效的。     

人工神经网络在水文水资源中的应用

人工神经网络理论被广泛地应用于水文水资源领域中各种问题的研究,依问题性质不同将其划分为4大类:(1)分类和识别问题;(2)预测预报问题;(3)优化计算问题;(4)基于神经网络的专家系统研制与开发问题,对人工神经网络在水文水资源中的应用现状作了较全面的介绍。还指出了目前应用中存在的主要问题以及今后的研究方向。     

BP神经网络在测井数据预测原煤灰分中的应用

测井曲线能敏感反应原煤灰分,为了利用测井数据分析原煤灰分,采用BP神经网络建立测井数据预测原煤灰分模型,用以研究利用自然伽马、密度和视电阻率等测井参数估测原煤灰分的方法。通过网络训练与测试,实验预测结果与期望结果吻合性好、误差小,因而BP神经网络可以用于测井数据预测原煤灰分。     

基于人工神经网络的边坡稳定性工程地质评价方法

针对边坡稳定性工程地质评价方法过分强调经验和难以定量的缺点，提出了一种基于人工神经网络的边坡稳定性工程地质评价方法（ＡＮ２Ｓ２ＥＧＥＭ），详细介绍了它的建模方法和应用实例．结果表明该方法不仅有效，而且有定量、简便、实时、自适应等优点，具有广阔的应用前景。     

基于RBF神经网络的地下水动态模拟与预测

RBF网络具有结构自适应确定、输出与初始权值无关的优良特性.以matlab为平台将该网络应用于某地的地下水动态模拟与预测,较为系统地研究了训练样本集与检测样本集的构建、原始数据的预处理、神经网络的构建、训练、检测及结果评价整个过程,取得了良好效果.同时,还与BP网进行了对比,认为,RBF网络是一种值得推广的地下水动态模拟与预测神经网络模型.     

基于季节冻土微观结构特征的神经网络冻胀率仿真预测

为了寻求基于宏观-微观物理参数间接得到季节冻土冻胀率的途径, 根据现有技术手段容易测试到土的性质参数, 利用BP神经网络法对季节冻土冻胀率进行预测. 选取微观孔隙参数及结构单元体参数各4个、 外部条件参数3个共11个参数, 建立季节冻土冻胀率神经网络预测模型. 结果表明: 在33个检验样本中, 误差最大为0.19, 最小为0.00, 有4个样本的误差在0.1~0.19之间, 其他样本误差都在0.05以下, 占总样本数的88%, 说明模型能反映冻胀变化的基本趋势. 因此, 文中建立的基于11个宏观微观物理参数的BP神经网络冻胀率预测模型是可行的.