基于PCA-SVM算法对稀土元素与稀土判别指标耦合数据集的铀矿床分类

不同类型铀矿床的沥青铀矿/晶质铀矿具有不同的稀土元素组成,其组成可作为判别铀矿床类型的重要指标。采用基于Python语言的主成分分析（principal component analysis,PCA）与支持向量机（support vector machines,SVM）结合的分类模型,对收集到的全球已知6种类型铀矿床的216组沥青铀矿/晶质铀矿稀土元素数据进行研究。以216组数据为训练集,通过数据清洗、特征缩放、PCA特征提取、网格搜索和交叉验证参数寻优构建SVM分类模型,对24组同变质型胡家峪晶质铀矿进行智能识别。研究结果显示：仅使用稀土元素的14维训练集最优模型判定胡家峪晶质铀矿类型的测试准确率为0.4%;由稀土元素、稀土总量、轻重稀土比、铕异常组成的17维训练集最优模型的测试准确率为75.0%,较14维训练集提高74.6%,模型泛化能力强;而通过传统稀土元素配分曲线、w（ΣREE）-（LREE/HREE）_N图解不能有效判定胡家峪晶质铀矿类型。本次研究表明,PCA-SVM算法对增有传统稀土判别指标数据集进行挖掘可有效厘定铀氧化物成因类型,效果明显优于单纯的稀土元素数据集以及传统的稀土配分曲线、w（ΣREE）-（LREE/HREE）_N图解。     

固城电灌站厂房减压仰斜式挡土墙实例力学分析

20世纪60年代,某地修建提灌工程,采用了"减压仰斜式"挡土墙这种结构型式,至今仍在安全运行。由于结构新颖、合理、经济、安全,在当地逐步得到推广。但在力的计算方面存在许多不明确之处,依据库伦、朗肯基本理论,提出了各种力的解析计算。     

岩体演化的非线性动力学模型与稳定性分析

以时间序列为基础,应用支持向量机建立岩体演化的非线性动力学模型,依据Lyapunov指数给出最长可预报时间,并通过函数拟合、变量代换将其化为标准的尖点突变模型,利用突变理论对其进行稳定性分析。结果表明,该模型预测效果理想,并具有良好的推广能力。     

Critical review on shear strength models for soil-infilled joints

An infilled rock joint is likely to be the weakest plane in a rock mass. The presence of infill material within the joint significantly reduces the friction of the discontinuity boundaries (i.e. rock to rock contact of the joint walls). The thicker the infill, the smaller the shear strength of the rock joint. Once the infill reaches a critical thickness, the infill material governs the overall shear strength, and the joint walls (rock) play no significant role. Several models have been proposed to predict the peak shear strength of soil-infilled joints under both constant normal load (CNL) and constant normal stiffness (CNS) boundary conditions, taking into account the ratio of infill thickness (t) to the height of the joint wall asperity (a). CNS models provide a more realistic picture of the soil-infilled joint behaviour in the field. This paper presents a critical review on the existing mathematical models for predicting the shear strength of soil-infilled rock joint and verifies the normalised peak shear stress model with further laboratory investigations carried out on idealised saw-tooth rock joints at the University of Wollongong. Based on the prediction of the experimental data, the normalised peak shear stress model is slightly modified by the authors. A simplified approach for using this model in practice is presented and a new expression for prediction of dilatation at peak shear stress is suggested.     

盆地三维构造-地层格架的矢量剪切原理及方法

三维矢量剪切功能的强弱, 是衡量所建立的盆地三维数字体质量的重要标志.在阐述了基于B-Rep模型的盆地三维数字体矢量剪切原理之后, 探讨了在计算机上实现矢量剪切的技术途径与方法.以线条、填充多边形、曲面和注释4种图元的剪切为基础, 建立了一个较为完善的盆地三维数字构造-地层体的矢量剪切模型, 并且编制了相应的软件.使用这一技术方法和软件系统, 对珠三凹陷进行了实际的矢量剪切分析, 取得了良好的效果.      

岩矿石电磁频散规律的实验研究

通过大量的实测资料，总结了岩矿石频散现象的普遍性及其规律性。对产生频散的原因进行了机理上的解释。同时，结合电磁波在地质勘探中的实际应用问题，阐述了频散对多预测量的结果所产生的影响，进而提出了在实际工作中进行频散校正的必要性。     

基于聚类和支持向量回归的短期负荷预测方法

提出了一种基于自组织特征映射(SOFM)的聚类分析和支持向量回归(SVR)的电力系统短期负荷预测方法。该方法首先利用自组织特征映射网络,通过无监督学习策略,对训练样本集进行聚类分析,将其分为若干相似子类;再针对每一子类构造一个支持向量回归(SVR)模型,以对应子类的样本集训练SVR模型。由于聚类后的每一子类的样本具有相似性,同时子类样本数较少,因此,该方法能够缩短训练时间,提高预测精度。基于某电网提供的历史负荷数据进行的不同方法对比实验说明了该方法的有效性。     

低温热液成矿作用中铊有机络合物搬运形式的研究

文章依据等库伦反应外推原理,计算了铊的醋酸(TlAc0)、柠檬酸(TlCit2-)、苹果酸(TlMal-)、草酸(TlOx-)及琥珀酸(TlSuc-)络合物在25～100℃之间的稳定常数。将这些稳定常数输入EQ3/6的DATA0.SUP热力学数据库后,在75℃和100℃温度条件下,对铊的诸物种于低温热液中在不同pH值条件下的分配进行了计算。计算表明,在中性及偏碱性条件下,在75℃还原环境中,自由铊离子(Tl+)所占比例约为55%,TlHS0约占10%,而其余则为铊的有机络合物,并以铊的柠檬酸络合物占绝对优势。在75℃氧化环境中,自由铊离子约占55%,而铊的有机络合物则为45%左右。在100℃还原环境中,自由铊离子所占比例约为20%,TlHS0约占20%,其余则为铊的有机络合物。在100℃氧化环境中,自由铊离子所占比例约为30%,其余则为铊的有机络合物。因而笔者认为,铊的有机络合物,尤其是铊的柠檬酸络合物,在低温热液中对于铊的溶解及搬运起着重要的作用。     

Modeling tunneling-induced ground surface settlement development using a wavelet smooth relevance vector machine

Accurate prediction of ground surface settlement is necessary for effectively controlling the settlement that develops during tunneling. Many models have been established for this purpose by extracting the relationship between the settlement and the factors that influence it. However, most of the models focused on the maximum ground surface settlement and do not involve dynamic and real-time predictions. This paper investigated how tunneling-induced ground surface settlement developed using a smooth relevance vector machine with a wavelet kernel (wsRVM). Various factors that affect this settlement, including geometrical, geological and shield operational parameters were considered. The model was applied to earth pressure balance (EPB) shield-driven tunnels. The results indicate that the prediction model performs well and that the distribution of the predictions can provide a measure of the prediction uncertainty. Unlike conventional methods that requireadditional efforts to determine relevant model parameters, the proposed method can optimize the parameters in the training process. The results of the parametric study conducted show that the model performance can be improved by the optimization and that the method can serve as a simple tool for practitioners to use in estimating ground surface settlement development during tunneling.     

滑坡位移的多模态支持向量机模型预测

将支持向量机（support vector machine,SVM）方法与信号分析中的经验模态分解（empirical mode decomposition, EMD）方法相匹配,提出了一种通过多模态支持向量机函数回归分析建模预测滑坡位移的理论方法。以边坡位移历史观测数据为基础,应用EMD方法获得滑坡形成过程中位移演化的几个特征时间模态,构成了多模态信息统计学习样本,确定了边坡位移演化的自适应多尺度变化信息。对应于每个经验模态的位移变化信息,引入了多模态SVM建模方法,然后合成不同经验模态下边坡位移的计算结果,得到滑坡位移的预测值。以卧龙寺新滑坡和新滩滑坡的监测数据为基础的理论预测结果表明,与采用遗传算法的神经网络方法的预测结果相比,支持向量机经验模态方法具有更强的预测能力,理论预测结果与实际监测值具有很好的一致性