��Ϊ\wt{\varphi}�������������м�Ȩ�͵ļ�����Ϊ

在本文中, 令为一列行为混合随机变量阵列. 本文研究了行为混合随机变量阵列加权和的极限行为, 并且一些新的完全收敛性结果被取得, 这些结果推广和改进了相应的已有定理.     

广义Cox模型下的逐步扩大域流相关问题研究

在本文中, 我们主要讨论了广义Cox模型的信息流扩大问题. 假设在市场中有两类投资者, 第一类投资者拥有市场信息, 这里由一个维的布朗运动和一个可积随机 测度驱动; 而第二类投资者具有扩大的信息流, 这里假设是由信息流和广义Cox的模型刻画的违约信息流生成. 我们建立和刻画了广义Cox模型并且求给出它的主要性质包括生存过程和违约条件密度. 与Cox模型显著区别的是, 如果违约由广义Cox模型模型刻画, 与Cox模型平凡的结果不同的是, 鞅的分解更复杂和具有一般性.     

ij������ֵ����ʱCopula���Ž��Ⱥ�ṹ�Ϳ�խ��

本文证明了copula , 生存copula , 对偶copula 和伴随copula 关于copula的复合运算构成一个四元群, 给出了当某个单点值给定时它们的最优上下界. 计算了, 时copula最优上下界的宽窄度, 并与时的宽窄度进行了比较.     

SLEk(k>4)��Cardy��ʽ

Cardy给出临界渝流族横穿一个长方形 而不碰到长方形的上边和下边的概率估计公式; Lawler, Schramm和Werner给出了参数的通弦随机Loewner演 变穿过长方形的类似的概率估计公式. 在本文, 我们将后者的结果推广到的情形.     

��Ԫ�ع���ѡ���Ա�����һ�ּ򵥷���

在线性回归模型建模中, 回归自变量选择是一个受到广泛关注、文献众多, 具有很强的理论和实际意义的问题. 回归自变量选择子集的相合性是其中一个重要问题, 如果某种自变量选择方法选择的子集在样本量趋于无穷时是相合的, 而且预测均方误差较小, 则这种方法是可取的. 利用BIC准则可以挑选相合的自变量子集, 但是在自变量个数很多时计算量过大; 适应lasso方法具有较高计算效率, 也能找到相合的自变量子集; 本文提出一种更简单的自变量选择方法, 只需要计算两次普通线性回归: 第一次进行全集回归, 得到全集的回归系数估计, 然后利用这些回归系数估计挑选子集, 然后只要在挑选的自变量子集上再进行一次普通线性回归就得到了回归结果. 考虑如下的回归模型: 其中回归系数中非零分量下标的集合为, 设是本文方法选择的自变量子集下标集合, 是本文方法估计的回归系数(未选中的自变量对应的系数为零), 本文证明了, 在适当条件下, 其中表示的 分量下标在中的元素的组成的向量, 是误差方差, 是与 矩阵极限有关的矩阵和常数. 数值模拟结果表明本文方法具有很好的中小样本性质.     

关于两两NQD随机序列的一个极限定理

设为两两NQD随机序列, 且, 是一列严格单调递增的凸序列. 本文将 Feller (1946)关于独立同分布期望不存在随机序列的极限定理推广到两两NQD随机 序列的情形.     

一类混合序列下分位数估计的一致渐近正态性

本文在混合序列下, 研究了分位数估计的一致渐近正态性. 在一定条件下其收敛速度达到. 所得结果可以应用到风险度量VaR分位数估计.     

����ʼ�Ȩ���������ģ������Ӧ������λ������ľ�����Ȼͳ���ƶ�

本文对两个样本数据不完全的线性模型展开讨论, 其中线性模型协变量的观测值不缺失, 响应变量的观测值随机缺失(MAR). 我们采用逆概率加权填补方法对响应变量的缺失值进行补足, 得到两个线性回归模型``完全'样本数据, 在``完全'样本数据的基础上构造了响应变量分位数差异的对数经验似然比统计量. 与以往研究结果不同的是本文在一定条件下证明了该统计量的极限分布为标准, 降低了由于权系数估计带来的误差, 进一步构造出了精度更高的分位数差异的经验似然置信区间.     

逐步增加首失效截尾样本下参数估计的优良性

在对称平方损失函数下, 利用逐步增加首失效截尾样本, 研究两参数Pareto分布族参数的一致最小方差无偏估计(UMVUE), Bayes估计和参数型经验Bayes(PEB)估计. 按照均方误差(MSE)准则, 比较UMVUE与PEB估计的优良性. 根据风险函数导出Bayes估计与PEB估计的渐近性, 并获得它们的收敛速度. 在相同的置信水平下, 研究参数分别在经典统计和Bayes统计中的区间估计, 并利用数值模拟说明Bayes区间估计的精度高于经典统计区间估计.     

From Multifractal Measures to Multifractal Wavelet Series

Given a positive locally finite Borel measure μ on R, a natural way to construct multifractal wavelet series is to set , where . Indeed, under suitable conditions, it is shown that the function F_μ inherits the multifractal properties of μ. The transposition of multifractal properties works with many classes of statistically selfsimilar multifractal measures, enlarging the class of processes which have self-similarity properties and controlled multifractal behaviors. Several perturbations of the wavelet coefficients and their impact on the multifractal nature of F_μ are studied. As an application, multifractal Gaussian processes associated with F_μ are created. We obtain results for the multifractal spectrum of the so-called W-cascades introduced by Arnéodo et al.     

Damage and Failure of Metal/Fibre-Reinforced Polymer Tensile Specimens with Inelastic Interface

Hybrid specimens of metal and fibre-reinforced polymer are applied in automotive and aerospace industry. The simulation and analysis of damage of such engineering structures is the focus of this research. The investigation includes a computation of the extension of single lap tensile specimen, produced by ultrasonic metal welding. The specimen is manufactured from CF-PA66 - fibre-reinforced polymer and AlMg3 (AA5754), which is used as a metallic joining partner. The aluminium substrate is treated as an elastoplastic material. The polymer composite generally shows an orthotropic elastic behaviour. The interface material has been numerically modeled as an elastoplastic material with linear hardening, coupled with Lemaitre-type damage. The finite element method is used for the investigation of so-called interface elements. The geometry of the interface is a consequence of the welding sonotrode geometry. The behaviour of specimens with square and ring interface geometry are analysed. The influence of the interface geometry on the mechanical properties of the joint is shown. The increase of the damage parameter and the development of failure are described for both cases. (© 2010 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim)     

Supercomputer simulation of viscous noncompressible flow past bodies of complex shape

The article reports the results of numerical analysis of viscous thermally conducting noncompressible flow past bodies of complex shape. The effect of physico-chemical processes is ignored. Flow past bodies with various nose cone designs is examined. The process is described using a system of Navier–Stokes equations augmented with the energy equation. The continuity equation is used to control the numerical accuracy. The simulation results are reported in the form of vector fields and surface components of the velocity vector in various channel sections. The results are analyzed for various body configurations.     

Nonaxisymmetric Free Convection Flow over a Rotating Disk in a Viscoelastic fluid with Magnetic Field

The non axisymmetric motion produced by a buoyancy-induced secondary flow of a viscoelastic fluid over an infinite rotating disk in a verticalplane with a magnetic field applied normal to the disk has been studied.The governing Navier Stokes equations and the energy equation admit a self similar solution. The system of ordinary differential equations has been solved numerically using Runge-Kutta Gill subroutine.The turning moment for the viscoelastic fluid is found to be less than that of the Newtonian fluid but the turning moment is increased due to the magnetic parameter. The resultant force due to the buoyancy-induced secondary flow increases with the magnetic parameter but reduces as the viscoelastic parameter increases. The quantity of fluid, which is pumped outwards due to the centrifuging action of the disk, for the viscoelastic fluid is more than that of the Newtonian fluid. The buoyancy-induced secondary flow boundary layer is much thicker than the primary boundary layer thickness. The thermal boundary layer due to the primary flow increases with the magnetic parameter decreases as the viscoelastic parameter increases. The heat transfer increases with the viscoelastic parameter but decreases as the magnetic parameter increases. The effect of the viscoelastic parameter is more pronounced on the secondary flow than on the primary flow.     

空泡起始和溃灭阶段的噪声

本文对孤立空气-水蒸汽空泡,在起始和溃灭阶段的噪声进行了分析.导出了噪声声压及振速的表达式,并进行了具体的计算.计算结果表明:从自由气核发育的起始时刻到空泡溃灭的整个过程中均伴有噪声.空泡噪声主要发生在溃灭阶段的晚期,其声压的数量级可以达到100分贝以上. 在基本声学假定下[1],考虑理想、不可压流体中,孤立空气-水蒸汽空泡在起始和溃灭阶段的噪声,并计及液体的表面张力的影响.     

Parallel multi-frontal solver for p adaptive finite element modeling of multi-physics computational problems

The paper presents a parallel direct solver for multi-physics problems. The solver is dedicated for solving problems resulting from adaptive finite element method computations. The concept of finite element is actually replaced by the concept of the node. The computational mesh consists of several nodes, related to element vertices, edges, faces and interiors. The ordering of unknowns in the solver is performed on the level of nodes. The concept of the node can be efficiently utilized in order to recognize unknowns that can be eliminated at a given node of the elimination tree. The solver is tested on the exemplary three-dimensional multi-physics problem involving the computations of the linear acoustics coupled with linear elasticity. The three-dimensional tetrahedral mesh generation and the solver algorithm are modeled by using graph grammar formalism. The execution time and the memory usage of the solver are compared with the MUMPS solver.     

车路耦合非线性振动高阶Galerkin截断研究

将移动车辆模型化为运动的两自由度质量-弹簧-阻尼系统,道路模型化为立方非线性黏弹性地基上的弹性梁,并将路面不平度设定为简谐函数．通过受力分析,建立车路非线性耦合振动高阶偏微分方程．采用高阶Galerkin截断结合数值方法求解耦合系统的动态响应．首次研究不同截断阶数对车路耦合非线性振动动态响应的影响,确定Galerkin截断研究车路耦合振动的收敛性．研究结果表明,对于软土地基的沥青路面,耦合振动的动态响应,需要150阶以上的截断才能达到收敛效果．并通过高阶收敛的Galerkin截断研究了系统参数对车路耦合非线性振动动态响应的影响.     

The uniform heating and bending of a two-layer plate

The problem of the uniform heating of a two-layer plate is solved. The transversely isotropic layer considered (a soft plate) is in ideal contact with a rigid isotropic thin elastically deformed layer. The ends of the plate are load-free. A boundary layer of the soft plate (a thin contact layer) is introduced, which enables the boundary conditions on the ends of the plate to be formulated in such a way that the problem has a bounded smooth solution [1]. The two-layer plate, generally speaking, is bounded along the axis perpendicular to the axes directed along the length and thickness of the plate. The resultant force and the resultant moment, applied to the end transverse sections, are equal to zero. The exact solution of the temperature problem is sought using the equations of the theory of elasticity. The plane problem of the bending of a two-layer plate acted upon by a uniformly distributed pressure applied to the side surface of an anisotropic layer is solved by a similar method. The ends of the rigid isotropic layer are clamped.     

Nonlinear electrohydrodynamic Kelvin-Helmholtz and Marangoni instabilities near the marginal state

The effects of surface tension and adsorption on the electrohydrodynamic Kelvin-Helmholtz instability are studied. The system is stressed by a normal electric field such that it allows for the presence of surface charges at the interface. The method used is that of multiple scales. The nonlinear Schrödinger equation describing the behavior of the disturbed system is derived. The stability of the perturbed system is discussed both analytically and numerically and the stability diagrams are obtained. At the critical point, a generalized formulation of the evolution equation is developed, which leads to the nonlinear Klein-Gordon equation. The various stability criteria are derived from this equation.     

Nonlinear positional differential game in the class of mixed strategies

The feedback control problem is considered for a nonlinear dynamic system under lack of information on disturbances. The problem on minmax-maxmin of the guaranteed result for a given positional quality index is formalized as an antagonistic two-player differential game in the framework of the concept developed in the Sverdlovsk (now Yekaterinburg) school on the theory of differential games. The problem is solved in the class of mixed strategies. The existence of the value of the game and a saddle point is established. The solution to the problem is based on the application of appropriate leader models, the method of extremal shift to the accompanying points and the method of upper convex hulls. The results of the study are applied to a realistic control model. The simulation outputs are presented.     

The linearization method in the inverse problem of determination of low-permeability zones in an oil-bearing layer

The possibility of determination of low-permeability zones in an oil-bearing layer from bore-pressure measurements is studied. The formulation of the problem on the pressure distribution in the layer is considered in the case when the pressure is invariable across the layer. The problem is reduced to an integral equation. The linearization of the inverse problem of determination of low-permeability zones is considered. An iterative technique is proposed for solution of this problem. The technique involves reduction of the inverse problem to an operator equation.