KPLS-SVM在缺失飞参数据估计中的应用

飞行参数的缺失给飞行事故调查工作带来了很大困难.将核的偏最小二乘法与支持向量机耦合,建立基于状态匹配的飞行参数估计模型可以较好地解决缺失飞参数据的估计问题.首先将初始输入映射到高维特征空间,进而利用偏最小二乘法在特征空间中提取对缺失飞参数据影响较强的得分向量, 最后将提取的得分向量作为输入建立支持向量机模型.既克服了输入变量间的相关性问题, 又降低了支持向量机的输入维数.仿真也说明了使用该方法估计缺失飞行参数的可行性和有效性.     

炮兵作战决策方案优选的方法

炮兵作战方案的选择,是炮兵作战指挥决策的关键环节,其合理与否,直接关系到炮兵作战效能的发挥和作战的成败.根据炮兵作战的实际,阐述了炮兵作战方案优选的依据,给出了运用层次分析法确定影响作战方案选择的各因素权重的方法步骤,在对优选依据的建模要素进行分析的基础上,构建了每个要素的效用函数计算模型,并给出了评估方案的计算方法,提供了模型应用的一般步骤.     

一类多对二随机格斗中的最优射击策略

射击策略的选择在随机格斗中是一重要战术问题,当一方武器面临多个武器目标时,如何确定射击目标顺序的研究,显然是具有实际意义的。依据发射间隔服从负指数分布的多对一随机格斗中最优策略应满足的条件,推出求解此类多对一格斗最优策略的方法。进而研究了射击间隔服从此类分布的多对二随机格斗中处于劣势一方的射击策略选择问题,得出寻求最优射击策略的一般方法。     

导弹阵地空袭目标威胁评估

威胁评估是导弹作战决策中一个重要环节.针对导弹阵地作战中空袭目标的实时威胁评估问题,结合阵地实际,文中在分析威胁成因和指标相关性的基础上构建了威胁评估指标体系,利用模糊理论对威胁因素进行了量化处理,基于目标实时信息用组合加权平均模型进行了评估计算.仿真结果表明,该模型能根据实时的目标信息,准确灵敏地评估出目标威胁度,同时考虑了因素的相关性影响,结果更切实合理.     

利用詹森不等式推广几个数学问题

詹森（Jensen）不等式是解决不等式问题的一个重要方法,也是发现数学问题的重要手段。运用詹森不等式的关键是通过观察所给代数式的函数特征,构造一个凹或凸的函数,以利解题。     

基于Rogowski线圈的传感头研究

分析了Rogowski线圈的工作原理,建立了Rogowski线圈的等效电路模型,推导了Rogowski线圈的传递函数;设计了一种新型的精密积分器,采用Protel仿真验证了精密积分器的优越性;对所研制的基于PCB的Rogowski线圈传感头进行了实验分析.实验结果表明,传感头测量准确度达到0.5级,工作状况稳定,完全满足设计要求.     

失效概率函数求解的高效算法

结合基于分数矩约束的极大熵方法和替代模型法,发展了一种失效概率函数求解的高效算法。所提算法的基本思路是利用自主学习的迭代Kriging方法来构造失效概率函数,即采用较少的训练样本来构造粗糙的失效概率函数,在此基础上通过添加新的违反学习函数约束的样本来更新失效概率函数,直到达到精度要求。对于每一个分布参数的训练样本点,所提方法采用分数矩约束的极大熵法来求解相应的失效概率样本。由于分数矩的计算采用了高效的降维积分,并且由于分数矩约束下极大熵法中优化策略高效地逼近了响应的概率密度函数,从而使得失效概率样本能够被高效高精度地估计出来。为了检验所提方法的精度及效率,给出了两个算例,对比了所提方法与已有的失效概率函数求解的Bayes公式法及Monte Carlo法等,结果表明,所提方法适用于求解复杂的功能函数问题,且在满足精度要求的基础上大大降低了计算量。     

Statistical Analysis as an Adjunct to Historical Research: Identification of the Likely Manufacturers of British Pattern 1907 Bayonets Supplied by the Birmingham Small Arms Company to the Siamese Government in 1920

In 1920, the Birmingham Small Arms Company supplied 10,000 Pattern 1907 bayonets to the government of Siam to accompany an order for rifles. The original maker of these bayonets was unknown, but historical research indicates that the Wilkinson Sword Co. Ltd. was a primary maker. The weights of some surviving Pattern 1907 bayonets, including twelve bayonets from the 10,000 described above, produced by the six makers in the UK before and during the Great War (1914–1918) period were available. A statistical analysis of the data was performed to compare with the historical research. The results strongly supported that the Wilkinson Sword Co. Ltd. was a primary maker. They were also sufficient to exclude from this batch of twelve bayonets the Royal Small Arms Factory (Enfield) and Vickers Ltd. as manufacturers. The statistical evidence for the presence of bayonets made by J.A. Chapman Ltd., R. Mole & Sons and Sanderson Bros. was weaker than that for the Wilkinson Sword Co. Ltd., but was nevertheless supportive of that hypothesis. Overall, the analysis was consistent with the supply to Siam of commingled bayonets from British government stores. It was noted that the bayonets for the Siam contract fell into a relatively narrow weight range, but the reason for this could not be determined.     

对流层散射双向时间比对中对流层斜延迟估计

为精确估计对流层散射双向时间比对系统中对流层斜延迟,分析了估计卫星信号对流层斜延迟的Hopfield天顶延迟模型及CFA2.2映射函数模型并对其进行修正,从而适用于对流层散射斜延迟的精确估计。根据北纬35°~37°范围内的三个测站2010—2012三年的气象数据,验证Hopfield模型精度范围小于35 mm,并将三个测站按相互之间基线距离的不同分为三组比对站,利用2012年的气象数据,计算在不同入射角下一年的对流层散射斜延迟,并得出最大斜延迟对应的年积日和入射角。结果表明,三组比对站的最大单向散射斜延迟为21.82~35.45 m。在双向比对抵消90%的情况下,时间延迟为7.3 ns~11.7 ns;相互抵消95%时,时间延迟为3.6 ns~5.9 ns。     

Approximation algorithms for sequential batch‐testing of series systems

We introduce and study a generalization of the classic sequential testing problem, asking to identify the correct state of a given series system that consists of independent stochastic components. In this setting, costly tests are required to examine the state of individual components, which are sequentially tested until the correct system state can be uniquely identified. The goal is to propose a policy that minimizes the expected testing cost, given a‐priori probabilistic information on the stochastic nature of each individual component. Unlike the classic setting, where variables are tested one after the other, we allow multiple tests to be conducted simultaneously, at the expense of incurring an additional set‐up cost. The main contribution of this article consists in showing that the batch testing problem can be approximated in polynomial time within factor , for any fixed . In addition, we explain how, in spite of its highly nonlinear objective function, the batch testing problem can be formulated as an approximate integer program of polynomial size, while blowing up its expected cost by a factor of at most . Finally, we conduct extensive computational experiments, to demonstrate the practical effectiveness of these algorithms as well as to evaluate their limitations. © 2016 Wiley Periodicals, Inc. Naval Research Logistics 63: 275–286, 2016