大庆徐家围子地区深部致密砂砾岩气层识别

大庆徐家圈子地区深部致密砂砾岩储层的骨架成分除了含有石英、长石外，还含有许多酸性喷发岩，而且各种骨架成分的含量随深度变化比较大；复杂的岩性使得气的影响被岩性的影响所淹没，从而造成常规气层识别方法失效。针对这一问题，应用神经网络方法准确求取地层颗粒密度和泥质含量，然后对中子和密度测井值进行岩性影响校正和泥质影响校正，使得求出的中子和密度孔隙度仅受地层气的影响，最后将得到的中子和密度孔隙度进行对比，应用中子和密度孔隙度的差异识别气层。     

测井资料在碳酸盐岩洞—裂缝型储层产能评价中的应用

介绍了一种基于测井资料来预测双孔结构碳酸盐岩储层产能的新方法。首先根据碳酸盐岩剖面中双孔结构储层的地质和测井特征,提取与储层产能密切相关的多个测井和地质参数,考虑到这些参数与产能的非线性相关关系以及产能数据的变化特点,采用BP神经网络技术建立其储层产能的预测模型,由此处理了轮南地区的多口井测井资料。所预测的储层段产能与试油产能较为一致,效果良好。     

Prediction of creep characteristic of rock under varying environment

The strain developed due to creep is mainly proportional to the logarithm of the time under load, and is mostly proportional to the stress and temperature. At higher temperature the creep rate falls slowly with respect to time, and the creep strain is proportional to a fractional power of time, with the exponent increasing as the temperature increases and reaching a value approximately one-third at temperatures of about 0.5°C. At these temperatures, the creep increases with stress according to a power greater than unity and possibly exponentially. It increases with temperature as (−U/kT), where U is an activation energy and k is Boltzman’s constant. There are different methods to determine the creep strain and the energy of Jog (B) including experimental methods, multivariate regression analysis, and by numerical simulation. These methods are less cumbersome and time consuming. In the present investigation, artificial neural network technique has been used for prediction of the creep strain and energy of Jog (B). Two different networks have been tested and validated. Both the networks have four input neurons and one hidden layer with five neurons, and one output neuron. The data for different rocks at temperatures up to 750°C under conditions of compressive or tortional stress are taken from the literatures. The training and testing data sets used were 163 and 14, respectively. To deal with the problem of overfitting of data, Bayesian regulation has been used and network is trained with suitable training epochs. The coefficients of correlation among the predicted and observed values are found high and they improve the confidence of the users. The mean absolute percentage error obtained are also very low.     

沪蓉西马水河大桥岸坡稳定性评价

马水河大桥是沪蓉国道主干线关键性工程,大桥桥头边坡地质条件复杂,构造发育,边坡整体稳定性对大桥施工和安全运行影响很大,但其整体稳定性非常难以判断。如何在计算中反映马水河大桥岸坡的地质结构、岩体结构特征及岩体结构面网络以及变形破坏模式,是决定岸坡稳定性分析结果客观性的重要因素。基于岸坡地质条件、地质结构和岩体结构面网络模拟的有限差分数值分析方法和数值分析模型,分别模拟了边坡在天然状态下、桥荷载作用下及水位升高50 m情况下的应力状态和变形大小。研究结果表明,在桥荷载作用下,斜坡应力场局部影响较大,深度达50 m,因此建议桩基设计时应加大桩基断面尺寸以改善桩体承载力。     

基于改进BP网络算法的隧洞围岩分类

围岩分类对指导地下工程的设计和施工具有非常重要的意义.引入人工神经网络的方法, 进行隧洞围岩分类, 在传统BP算法的基础上, 通过改进学习算法、优化传递函数和网络结构进行神经网络方法优化.采用附加动量法和学习速率自适应调整的策略改进学习算法, 使得当误差大于上临界值时, 则降低学习率, 当误差小于下临界值时, 则适当提高学习率, 这样可加快网络的训练速度, 确保网络的稳定性; 通过引入调整学习率参数, 使得传递过程更加敏感, 加快了传递函数的收敛速度, 提高了训练函数的计算精度; 通过给定隐含层节点模型的取值范围, 对网络结构进行优化, 提高了泛化精度.将改进的BP网络模型应用于广东省东深供水改造工程的隧洞围岩分类中, 分类结果与根据《水工隧洞设计规范(SL279-2002) 》的分类结果完全一致, 表明该方法具有良好的工程实用性.      

陕西渭北东部区新生代伸展构造网络系统对奥灰水的控制作用

本文以新活动论构造观和系统论为指导,建立了渭北东部区新生代伸展构造系统模式,并以岩体结构控制论为基础,系统地讨论了本区构造网络系统对奥陶系灰岩的空间分布、奥陶系灰岩地下水水文地质单元的边界条件、奥灰水单元的补、径、排特征及其富集等方面的控制作用以及宏观指导意义。最后,系统地提出了导水构造网络系统控水的实质。      

热传导有限元的神经计算原理及应用

根据热传导有限元分析方法的特点，把有限元计算问题转化为带约束的非线性优化问题，并给出求解该问题的改进Hopfield(TH）网络，最后对一个简单温度场神经计算进行数值仿真，仿真结果表明，神经网络能完成有限元模型的求解。     

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。     

空三加密在数字摄影测量中的精度分析

该文结合章丘市1∶2000地形图绘制项目的具体实践,认为航空摄影测量产品误差来源主要为空三加密这一重要工序,影响空三加密精度的因素主要为：影像质量（分辨率、清晰度、重叠度）、像控点选取及精度、加密点的选取及加密解算方法、加密人员的经验等。找出影响空三加密精度的主要因素及解决办法,结合生产实践解决了1∶2000地形图绘制空三加密精度问题。     

Strain rate of the South American lithospheric plate by SIRGAS-CON geodetic observations

A multiyear solution of the SIRGAS-CON network was used to estimate the strain rates of the earth surface from the changing directions of the velocity vectors of 140 geodetic points located in the South American plate. The strain rate was determined by the finite element method using Delaunay triangulation points that formed sub-networks; each sub-network was considered a solid and homogeneous body. The results showed that strain rates vary along the South American plate and are more significant on the western portion of the plate, as expected, since this region is close to the subduction zone of the Nazca plate beneath the South American plate. After using Euler vectors to infer Nazca plate movement and to orient the velocity vectors of the South American plate, it was possible to estimate the convergence and accommodation rates of the Nazca and South American plates, respectively. Strain rate estimates permitted determination of predominant contraction and/or extension regions and to establish that contraction regions coincide with locations with most of the high magnitude seismic events. Some areas with extension and contraction strains were found to the east within the stable South American plate, which may result from different stresses associated with different geological characteristics. These results suggest that major movements detected on the surface near the Nazca plate occur in regions with more heterogeneous geological structures and multiple rupture events. Most seismic events in the South American plate are concentrated in areas with predominant contraction strain rates oriented northeast-southwest; significant amounts of elastic strain can be accumulated on geological structures away from the plate boundary faults; and, behavior of contractions and extensions is similar to what has been found in seismological studies.