样本分布

Stochastic variables included driven accelerations, driven time, torques, frictions and damps were considered basically. In the first, Monte Carlo method was applied to generate stochastic variables and dynamical responds of mechanism. Secondly, the application of Artificial Neural Network was motivated by the approximate concepts inherent in reliability analysis and time consuming repeated analyses required for MC.

将驱动加速度、驱动时间、摩擦和阻尼力等作为随机变量，应用蒙特卡罗方法，取得动态参数样本，再利用人工神经网络方法，根据抽取的样本对网络进行训练，统计网络输出得到动态应力分布，进而求出机构动态强度可靠度。

The main findings include:(1) the time series of sample returns are not normative;(2) the sample returns follow a Frechet extreme value distribution;(3) The EVT approach provides a more accurate static margin level while the EWMA approach is more suitable for setting dynamic margin level.

主要发现有：（1）样本收益率时间序列不符合正态性假设；（2）样本收益率时间序列服从 Frechet 极值分布；（3）我国国债期货保证金的静态设定应当采用 EVT 理论，动态设定应当采用 EWMA 方法。

The laminar flamelet model in combination with joint probability density function transport equation of mixture fraction and turbulence frequency is used to simulate fluctuating behavior of radiative source term in turbulent jet diffusion flames of hydrogen.

采用κ-ε湍流模型、标量联合的概率密度函数输运方程和层流火焰面模型相结合，模拟氢气自由扩散火焰中辐射源项湍流脉动特征。给出了主燃区内辐射源项湍流脉动的频率图。辐射源项的样本点分布集中，大约95%以上的样本落在其系综的±3倍方差以内，频谱图为单峰

Fourth, the method of real-time data disposal and the generalized distributing distance rule and algorithm of samples are presented by which few can be selected from plenty of measuring data.

提出过程数据预处理办法及样本点广义距离均匀分布规则和算法，解决了从海量过程测量数据中撷取少量样本数据的问题。

The premise of the superiority of the conventional statistical STAP is to have ample training samples with interference that are independently and identically distributed with interference in the test sample, in order to estimate the covariance matrix.

常规的统计STAP方法性能最优的前提条件是具有足够的与待检测样本中的干扰独立同分布的训练样本，以便估计协方差矩阵。

ABSTRACT In the nonhomogeneous environments, the performance of space time adaptive processing proposed by Brennan often declines sharply due to the fact that it is lack of independent identically distributed train samples.

在非均匀环境下，由于缺乏足够的与待检测样本中干扰独立同分布的训练样本，常规统计空时自适应处理方法的性能往往会急剧下降，因此能。。。

This project also obtained several limit theorems for some important dependent random variables and stochastic processes, such as the Strassen law of the iterated logarithm for negatively dependent random variables, strong limit theorems for mixing random vectors in Banach spaces, sample path properties for two-parameter fractional Wiener processes, and so on.

随机环境中的随机变量与随机过程的研究在国内外相当活跃，本项目主要研究它们的极限性质，着重研究了随机风景中随机变量与随机过程的极限性质，主要取得了以下几个结果：首先对简单对称的Kesten-Spitzer随机游动在低阶矩的条件下给出了强逼近，大大减弱了前人要求任意阶矩的条件，然后对独立风景中的一般随机变量给出了强逼近的一般性结果，由此导出在风景和随机变量都只具有低阶矩的条件下的独立但不同分布、混合相依变量的强逼近，在只有弱高于二阶矩的条件下得到了重相对数律和弱收敛；给出了连续时间参数的Brown风景中Brown运动和稳定风景中稳定过程的滞后增量和连续模等精确样本轨道性质；同时给出了一些重要的相依随机变量和过程的若干极限定理，如负相关随机变量的Strassen重对数律、抽象空间上混合相依变量的一些强极限定理成立的充分必要条件、两参数分数Wiener过程的样本轨道性质等。

Among them, the algorithm of Eigenface, the most widely-used method of linear map based on PCA, has become the mainstream criterion to test the performance of various FV systems.

目前，已经提出了许多特征提取的方法，其中基于主成分分析(PCA Principle Component Analysis)的Eigenface算法及其变形已经成为测试人脸识别系统性能的基准算法，该方法是模式识别判别分析中最常用的一种线性映射方法，是根据样本点在多维模式空间的位置分布，以样本点在空间中变化最大方向，即方差最大的方向，作为判别矢量来实现数据的特征提取与数据压缩的。

Through analyzing the influence of the learning samples' location in the spectral space on the accuracy of multi spectral remote sensing image classification using BP neural network, a method for learning samples selection based on x 2 distribution was presented and used in TM image classification.

通过分析多光谱遥感图像学习样本在光谱空间不同位置对BP神经网络分类器分类精度的影响，提出基于x2 分布的学习样本选取方法，并应用于TM 图像分类。

In each period, without the knowledge of the distribution function of the time between failures and the repair time, the PA estimate of gradient of performance function is put into the stochastic approximation algorithm which recursively optimize the threshold value of the flow control model in a manufacturing system.

在分析过程中，对故障时间和工作时间的分布不做任何假设，利用自适应控制的思想，将整个样本路径依据一定的规则分成有限长的时间段，在每一段时间内用扰动分析估计目标函数的样本导数，然后用随机逼近算法渐进地估计流程控制问题中的最优阈值，从而实现了阈值的自适应控制。

However, as the name（read－only memory）implies, CD disks cannot be written onorchanged in any way.

然而，正如其名字所指出的那样，CD盘不能写，也不能用任何方式改变其内容。

Galvanizes steel pallet is mainly export which suits standard packing of European Union, the North America. galvanizes steel pallet is suitable to heavy rack. Pallet surface can design plate type, corrugated and the gap form, satisfies the different requirements.

镀锌钢托盘多用于出口，替代木托盘，免薰蒸，符合欧盟、北美各国对出口货物包装材料的法令要求；喷涂钢托盘适用于重载上货架之用，托盘表面根据需要制作成平板状、波纹状及间隔形式，满足不同的使用要求。