Fuzzy logic algorithm for runoff-induced sediment transport from bare soil surfaces   总被引：2，自引：0，他引：2  

Gokmen Tayfur  Serhan Ozdemir  Vijay P. Singh 《Advances in water resources》2003,26(12):1249

Utilizing the rainfall intensity, and slope data, a fuzzy logic algorithm was developed to estimate sediment loads from bare soil surfaces. Considering slope and rainfall as input variables, the variables were fuzzified into fuzzy subsets. The fuzzy subsets of the variables were considered to have triangular membership functions. The relations among rainfall intensity, slope, and sediment transport were represented by a set of fuzzy rules. The fuzzy rules relating input variables to the output variable of sediment discharge were laid out in the IF-THEN format. The commonly used weighted average method was employed for the defuzzification procedure.The sediment load predicted by the fuzzy model was in satisfactory agreement with the measured sediment load data. Predicting the mean sediment loads from experimental runs, the performance of the fuzzy model was compared with that of the artificial neural networks (ANNs) and the physics-based models. The results of showed revealed that the fuzzy model performed better under very high rainfall intensities over different slopes and over very steep slopes under different rainfall intensities. This is closely related to the selection of the shape and frequency of the fuzzy membership functions in the fuzzy model.  相似文献   

成像光谱数据建模与分类识别技术研究——以云南腾冲矿区为试验区   总被引：5，自引：0，他引：5       下载免费PDF全文

张杰林  岑长华牛铮陆书宁  曹代勇 《地质与勘探》2003,39(2):52-55

在系统分析成像光谱数据特征及岩石矿物具有诊断意义的吸收光谱特征形成机理的基础上，采用基于相关系数测度的光谱匹配技术、基于高斯改进型模型的光谱建模技术及人工神经网络分类算法，实现了岩石矿物光谱特征波形对比分析及诊断光谱信息提取与建模，提高了光谱分类识别算法的计算速度和分类精度。采用上述技术对云南腾冲铀矿区进行实验研究，取得良好效果。  相似文献   

融入先验知识的贝叶斯神经网络分类器     

唐云  鲍新毅 《物探化探计算技术》2003,25(1):83-87

提高神经网络模型推广性的关键是控制模型的复杂度，给出了一种基于贝叶斯推理的神经网络方法，它能自然地融入关于模型的先验知识，与观察到的数据样本相综合来控制神经网络模型中不同部分的复杂度。使用马尔可夫链蒙特卡罗模拟可获得模型参数的后验分布，预测分类是许多个以各自后验分布为权的马尔可夫链上的模型样本的平均。在二个实际分类问题应用中与常规神经网络方法进行了对比分析。  相似文献   

基于BP神经网络的手写数字识别   总被引：2，自引：0，他引：2  

杨勇  谢刚生 《华东地质学院学报》2003,26(4):383-386

介绍了光学字符识别的几种方法以及神经网络的特点，神经网络技术能够解决传统OCR方法所不能解决的问题，同时指出了手写数字识别存在的困难，论证了利用神经网络技术解决这种困难的可能性。本文实现了通过一个含有1个隐藏层的BP网络来识别手写数字，并取得了良好效果，论证了这种技术用于手写数字识别的可行性。  相似文献   

模糊优选神经网络在边坡稳定性分析中的应用     

方云  陈爱云  孙兵 《水文地质工程地质》2003,(Z1)

本文应用模糊优选神经网络理论,建立了边坡稳定性评价模型,综合分析了影响边坡稳定性的各种因素,根据它们作用程度的不同,赋予不同的权值,通过对收集到的边坡稳定性实例进行学习,提出了与优属度有关的函数关系式。可以看出:该方法具有精度高、收敛速度快、权值调整模型好等优点。  相似文献   

Open Stope Stability Using 3D Joint Networks     

M. Grenon  J. Hadjigeorgiou 《Rock Mechanics and Rock Engineering》2003,36(3):183-208

Summary The most popular exploitation method used in Canadian hard rock mines is open stope mining. Geomechanical design of open stopes relies on a range of analytical, numerical and empirical tools. This paper presents an engineering approach for the analysis and the design of reinforcement for open stopes in jointed rock. The proposed methodology, illustrated by three case studies, relies on developing 3D joint network models from field data. The 3D joint networks have been successfully linked to a 3D limit equilibrium software package. The models account for the finite length of joints as well as the influence of random joints. The integrated approach facilitates comparative analyses of different reinforcement strategies under different degrees of jointing in the hard rock environment. Received February 23, 2001; accepted October 11, 2002; Published online January 21, 2003 Acknowledgments The financial support of the National Science and Engineering Council of Canada and the Institut de Recherche en Santé et Sécurité au Travail of Quebec and Noranda Inc. is greatly appreciated. Authors' address: Prof. John Hadjigeorgiou, Université Laval, Department of Mining, Metallurgy and Materials Engineering, G1K 7P4 Quebec City, Quebec, Canada; e-mail: john.hadjigeorgiou@gmn.ulaval.ca  相似文献   

人工神经网络在隧道围岩稳定性识别中的应用   总被引：10，自引：0，他引：10  

刘贵应  陈建平  魏新颜  刘加龙 《地质科技情报》2002,21(1):95-98

在全面分析影响隧道围岩稳定性因素的基础上，结合人工神经网络方法的特点，提出了一种基于隧道围岩稳定性识别的B－P人工神经网络方法。通过实例分析对比表明，模型精度很高，识别结果可靠，且操作简洁方便，能有效地应用于隧道围岩稳定性的识别。  相似文献   

Modeling Conditional Distributions of Facies from Seismic Using Neural Nets   总被引：2，自引：0，他引：2  

Jef Caers  Xianlin Ma 《Mathematical Geology》2002,34(2):143-167

We present a general, flexible, and fast neural network approach to the modeling of a conditional distribution of a discrete random variable, given a continuous or discrete random vector. Although many more applications of the neural net technique could be envisioned, the aim is to apply the developed methodology to the integration of seismic data into reservoir models. Many geostatistical methods for integrating seismic data rely on a screening assumption of further away seismic events by the colocated seismic datum. Such assumption makes the task of modeling cross-covariances and local conditional distributions much easier. In many cases, however, the seismic data exhibit distinct and locally varying spatial patterns of continuity related to geological events such as channels, shale bodies, or fractures. The previous screening assumption prevents recognizing and hence utilizing these patterns of seismic data. In this paper we propose to relate seismic data to facies or petrophysical properties through a colocated window of seismic information instead of the single colocated seismic datum. The variation of seismic data from one window to another is accounted for. Several examples demonstrate that using such a window improves the predictive power of seismic data.  相似文献   

Scanline Method to Determine the Fractal Nature of 2-D Fracture Networks     

Tayfun Babadagli 《Mathematical Geology》2002,34(6):647-670

A previous method proposed to measure the fractal dimension of pore spaces is adapted and modified for 2-D fracture networks. The method relies on scanning a 2-D fracture network through successive straight lines from top to bottom and measuring the distance between two fractures. The fractal dimension is then obtained using the log–log plot of the feature size and the number of features for this particular size at different magnifications. It is shown in this study that the method proposed to measure the fractal dimension of porous structures can be applicable to 2-D fracture networks with some modifications after testing it on synthetic and natural fracture patterns. The method is simplified to be useful for practical applications in the fractal analysis of fracture networks. The results reveal that, on the basis of the direction of scanning lines, different fractal behavior and dimensions can be obtained indicating that 2-D fracture networks possess multifractal character. This approach takes into account the effect of fracture orientation on the fractal behavior and anisotropic nature of fracture networks as well as the fracture density, length, and spatial distribution.  相似文献   

基于神经网络方法的极化雷达地表参数反演   总被引：6，自引：1，他引：6  

杨虎  郭华东  王长林  李新武  岳焕印 《遥感学报》2002,6(6):451-455

人工神经网络（Artificial Neural Network)是一个由独立处理单元以一定拓扑结构高度连接而成的并行分布式信息处理结构，适于解决各种非线性问题，积分方程（Integrated Equation Model)单散射模型可模拟各种地表参数条件下裸露地表后向散射系数，以IEM为基础生成训练数据，用L波段的C波段SIR-CHH，VV极化单散射后向散射系数数据为神经网络输入，通过后向反馈（BP）神经网络模型可同时反演得到裸露地表条件下地表介电常数，地表相关长度和均方根高度等地表参数。  相似文献