关于判断抽样审计的几个问题

审计中的判断抽样是审计人员根据被审单位的实际情况,对被审项目总体进行判断,并根据判断结果有目的、有重点地抽取样本进行审查的方法。本文对判断抽样审计中存在的问题如总体的确定、基本要求和抽样选择等进行探讨,以期对实际工作有一定的指导意义。     

含有正态相关变量的多设计点/多失效模式情况下的方向抽样可靠性灵敏度分析

针对含有正态相关变量的多设计点/多失效模式系统的可靠性问题,提出了两种有效的基于方向抽样的可靠性灵敏度分析方法。可靠性灵敏度分析方法的基本思路是首先将正态相关变量进行等价独立标准正态变换,利用改进的方向抽样可靠性灵敏度分析方法得到独立标准正态空间的可靠性及灵敏度结果;通过复合求导法则,将独立标准正态空间的可靠性及灵敏度结果转化到正态相关空间,得到失效概率对相关正态变量分布参数(均值、标准差和相关系数)的偏导数,并对所推导的可靠性及灵敏度估计值进行了方差分析。与经典的MonteCarlo数字模拟法相比较,文中所列的数值算例和简单工程算例的分析结果验证了所提方法的可行性与有效性。     

改进 K-均值算法在雷达辐射源信号预分选中的应用

雷达辐射源信号分选是电子对抗领域一个关键技术,随着电子技术的发展,电磁环境日趋复杂,信号分选的难度越来越大,在这样的条件下,我们应该寻求新的解决问题的方法.本文首先概述了雷达辐射源信号分选意义、系统组成和分选流程,然后介绍了改进 K-均值算法.为了有效实现信号分选,提出了基于改进K-均值算法的信号分选方法,该方法可对到达角、载频和脉宽参数进行分选.最后进行了仿真实验,结果表明该方法实现简单,分选效果较好     

民机结构维修大纲抽样检查原则与方法研究

民机结构维修中的抽样检查是保证飞机持续适航的关键措施。结构抽样检查是为了掌握同一时期下线飞机的结构损伤情况,以便更好地修订维修计划。针对民机结构维修的抽样是非随机抽样的特点,本文研究了结构维修抽样的原则,结合空客A320抽样经验,给出了我国自主设计大飞机结构维修抽样准则和抽样的具体步骤。     

面向机翼气动外形优化的二级优化方法

针对飞机气动外形优化问题,提出了一种流程简单,可同时优化总体外形和剖面形状的二级优化方法.这种方法将优化流程分为总体外形级和剖面形状级两个层次:总体外形级优化任务是将外形参数传递给剖面形状级,并对总体外形进行优化;剖面形状级优化任务是对剖面形状进行优化,并将目标函数和约束值返回总体外形级.二级优化的最终结果可获得最优的总体外形和剖面形状.文章以一个通用航空飞机的机翼为算例,验证了这种二级优化方法的可行性和有效性.     

自助法在小样本数据均值估计中的应用

自助法（Bootstrap）是较好的处理小样本数据的方法,其无先验性及计算过程中只需要实际观测数据的优越性,使其广泛地应用于小样本数据处理。针对方法自身存在的缺陷,文章比较了目前自助法常用的两种抽样方式的优劣性,并采用改进的样本经验分布函数来解决这个问题,通过对均值的估计证实了方法的有效性。     

正态分布置信检验方法

正态母体特征值(母体均值、百分位值、百分率、标准差和变异系数等)的检验是工程中常见的问题。本文根据置信检验理论,建立了正态母体特征值的置信检验方法,包括母体均值、百分位值、百分率、标准差和变异系数的强检验、弱检验和弱强检验,可以满足不同的实际需求。置信检验克服了显著性假设检验在接受原假设时缺乏说服力的弱点,能够以高概率判断正态母体特征值是否满足工程中规定的条件。不但比传统的正态分布假设检验和抽样检验具有更高的精度,而且更加便于应用,许多假设检验和抽样检验难以处理的问题(如母体百分率和百分位值的检验),采用置信检验可以容易地得到解决。      

涡轮盘概率风险的评估方法

针对CCAR33.70条款对涡轮盘开展概率风险评估的要求,研究了响应面法在定义重点采样区间以及计算裂纹扩展寿命中的应用,给出了在蒙特卡洛模拟过程中应用响应面法定义失效域,缩短样本方差、提高抽样效率的方法.分析结果表明应用重点采样法可以极大地提高抽样效率.采用重点采样法获得的失效样本数与总样本数的比例高达94%,远大于传统的直接抽样法获得的失效样本数与总样本数的比例（仅为33%）.该方法可以在保证分析精度的条件下减少样本的数量.另外,应用响应面法拟合寿命近似方程,可以极大地缩减裂纹扩展寿命的计算时间:利用寿命近似方程开展104次随机抽样所花费的时间仅有2min,远低于应用传统寿命计算方法所花费的时间（288 min）.通过对寿命近似方程的寿命计算误差分析可以看出:最大计算误差仅有1.0%,计算结果与传统裂纹扩展寿命模型的计算结果吻合度高.该研究成果可以提高涡轮盘概率风险评估的效率.      

三向碳／碳复合材料拉伸性能测试方法研究

本文简要介绍三向碳／碳复合材料拉伸性能测试方法，研究了试样形状、夹持方式、变形测量方法对复合材料拉伸性能的影响，并用总体参数的统计检验对总体均值进行了显著性检验，用数理统计方法提出了合理的试样数量，从而比较严格、正确、合理地确定了测定三向碳／碳拉伸性能的试验参数。     

计量序贯抽检方案在固体火箭发动机批生产验收中的应用

计量序贯抽样方案与计数抽样及计量一次、二次抽样相比存在着明显的优点.对同样的检验要求,计量序贯抽样所需的平均抽样量最小.本文建议对服从正态分布的固体发动机性能参数采用计量序贯抽样方案进行批生产验收.文中给出了确定计量序贯方案的公式及实例.     

Instantaneous Frequency Estimation Using Adaptive Linear Predictor Weights

A computationally efficient scheme for estimating the digital instantaneous frequencies of narrowband inputs is introduced. The frequency estimates are obtained by searching for minima of the inverse input power spectrum. This spectrum is estimated at each input sample from the weights of an adaptive linear predictor which uses the LMS (least mean square) algorithm to update its weights. The related minima are sought via an iterative search algorithm, referred to as the iterative frequency estimator. This algorithm is computationally more efficient than available methods, and also provides a higher resolution. Simulation results are included; these include tracking of random message sequences in FM signals, and the formant frequency estimation of speech.     

Reliability Sensitivity Algorithm Based on Stratified Importance Sampling Method for Multiple Failure Modes Systems

 Combining the advantages of the stratified sampling and the importance sampling, a stratified importance sampling method (SISM) is presented to analyze the reliability sensitivity for structure with multiple failure modes. In the presented method, the variable space is divided into several disjoint subspace by n-dimensional coordinate planes at the mean point of the random vector, and the importance sampling functions in the subspaces are constructed by keeping the sampling center at the mean point and augmenting the standard deviation by a factor of l. The sample size generated from the importance sampling function in each subspace is determined by the contribution of the subspace to the reliability sensitivity, which can be estimated by it-erative simulation in the sampling process. The formulae of the reliability sensitivity estimation, the variance and the coeffi-cient of variation are derived for the presented SISM. Comparing with the Monte Carlo method, the stratified sampling method and the importance sampling method, the presented SISM has wider applicability and higher calculation efficiency, which is demonstrated by numerical examples. Finally, the reliability sensitivity analysis of flap structure is illustrated that the SISM can be applied to engineering structure.     

Linear Minimum Variance Estimation with Complex Phase Errors

The linear minimum variance estimator of a random signal, received multiplied by a complex Gaussian phase error and added to random noise, is investigated. The results apply to the propagation of images through the turbulent atmosphere, fading channels, and synthetic-aperture radar. Among others, a result is that the multiplicative error can be replaced by an additive error, usually white. The best signal modulation is found in two important special cases.     

Tracking targets using adaptive Kalman filtering

A simple algorithm for estimating the unknown process noise variance of an otherwise known linear plant, using a Kalman filter is suggested. The process noise variance estimator is essentially dead beat, using the difference between the expected prediction error variance, computed in the Kalman filter, and the measured prediction error variance. The estimate is used to adapt the Kalman filter. The use of the adaptive filter is demonstrated in a simulated example in which a wildly maneuvering target is tracked     

宽带信号近似最大似然方位估计快速算法

 针对短采样宽带信号近似最大似然方位估计（AML）计算量大的问题,将马尔可夫蒙特卡罗(MCMC)方法与近似最大似然方位估计相结合,提出一种基于完美抽样的近似最大似然方位估计快速算法（PAML）。该算法将AML算法的空间谱函数作为信号的概率分布函数,并利用完美抽样方法从该概率分布函数中抽样。与AML和遗传算法的对比实验研究表明,两目标情况下PAML算法在中低信噪比条件下的估计性能与AML和遗传算法性能相当,而计算量分别是二者的1/24和1/3。随着目标个数的增加,PAML算法的计算量优势将更加明显。     

Performance of a Square Law Pseudonoise Ranging Time-of-Arrival Estimator

The performance of a square law time-of-arrival (TOA) estimator that has been proposed for use in ASTRO-DABS, part of a possible satellite-based fourth generation air traffic control system is considered. The transmitted message consists of a pulse amplitude modulated (PAM) ranging sequence that, due to transmitter characteristics, is corrupted by an unknown frequency offset. The optimum TOA estimator, for the case of no frequency uncertainty, is first presented, together with a lower bound on the variance of the estimate generated. This is followed by the consideration of a suboptimum TOA estimator for which a high signal-to-noise ratio (SNR) performance analysis is carried out; here, the effects of frequency uncertainty are included. Next, the zero-crossing properties of the derivative of the (suboptimum) estimation statistic are presented and the results used to derive an upper bound to the TOA estimate variance that is valid for all SNR values. This latter result is significant because it displays the system threshold effect and complements performance lower bounds that may be derived via other methods. In addition, the method presented here may be applied to other optimum and suboptimum systems where a discrete set of parameters is to be estimated.     

The Estimation of the "Center of Gravity" of a Photon Density Profile in Noise

A model for an optical position estimation system is developed employing the photon Poisson process theory. The position estimate is based upon the definition of a center of gravity (CG) of the power density profile of the optical source on the focal plane. An estimator structure is derived using maximum likelihood estimates of the image profile. The resulting estimate of the CG is shown to be unbiased and its variance is obtained. The variance is shown to depend upon the signal energy and noise level as well as upon the distance of the center from the initial counting point. Thus, a composite estimation system is presented which reduces the variance and yet yields a simple structure. Studies on star estimation have yielded position accuracies better than 0.1 seconds of arc for a 2.5 visual magnitude star in a background of equivalent intensity.     

相关系数ARMA(p,q)序列分析方法

本文提出相关系数ARMA(p,q)序列分析方法。相关系数ARMA(p,q)序列是从非平稳序列中分离出的一类工程上常见且便于研究的时间序列,在模式识别、故障诊断、信号处理、自动控制和结构响应分析等领域有着广泛的应用。传统的相关函数ARMA(p,q)序列仅是它的一个特例。文中建立了相关系数ARMA(p,q)序列的条件极大似然估计和精确极大似然估计,前者在样本较大时简单便于工程应用,后者则在样本较小时仍具有较高的精度,它们通过时域的全程分析,充分利用样本信息确定相关系数ARMA(p,q)序列的均值函数、方差函数和相关系数函数。在此基础上可进行高精度的频谱分析。     

Reducing geometric dilution of precision using ridge regression

A signal processing technique is proposed for improving position-fix navigation system accuracy performance when the geometry of the navigation landmarks (e.g. sensors) are nearly collinear. In the navigation literature, the accuracy degradation associated with a nearly collinear measure geometry is termed the geometric dilution of precision (GDOP). Its presence causes not only the variance of the position estimates to be highly inflated but also any bias terms which may be present in the model. Since a nearly collinear predictor matrix is mathematically equivalent to GDOP, it is proposed to use the ridge regression technique in a navigation signal processor. A position-fix algorithm based on ridge regression reduces the bias and variance inflation caused by GDOP and the overall mean-squared position error as well. Ridge regression contains the GDOP-sensitive least-mean-square (LMS) estimator as a special case. Even with a matched model, GDOP can inflate the mean-square error (MSE) of the ordinary least-squares estimator, whereas the ridge regression technique chooses a suitable biased estimator that will reduce the MSE, which is the main goal. The ridge concept is extended to include GDOP-amplified bias errors. A simple range/range navigation system is analyzed to illustrate the underlying principles of ridge regression     

Efficient particle filtering for road-constrained target tracking

The variable-structure multiple-model particle filtering approach for state estimation of road-constrained targets is addressed. The multiple models are designed to account for target maneuvers including "move-stop-move" and motion ambiguity at an intersection; the time-varying active model sets are adaptively selected based on target state and local terrain condition. The hybrid state space is partitioned into the mode subspace and the target subspace. The mode state is estimated based on random sampling; the target state as well as the relevant likelihood function associated with a mode sample sequence is approximated as Gaussian distribution, of which the conditional mean and covariance are deterministically computed using a nonlinear Kalman filter which accounts for road constraints in its update. The importance function for the sampling of the mode state approximates the optimal importance function under the same Gaussian assumption of the target state.