LEACH—DRT算法中基于神经网络的数据预测算法

为了保证无线传感器网络中数据的完整性,针对基于LEACH路由协议的动态轮时间算法存在的问题,提出一种基于人工神经网络的数据预测算法。该动态轮时间算法中,部分簇因调整后的轮时间不足以完成数据的采集而丢失数据。数据预测算法结合传感器节点数据具有时空相关性的特点,将时空延迟算子引入神经网络模型,并通过建立的神经网络模型对数据进行预测。仿真时采用伯克利英特尔实验室的传感器数据,通过Mafl软件对模型进行测试并分析仿真结果。实验结果表明：该算法对连续多个数据的预测效果理想,预测误差始终保持在较低水平。     

遗传神经网络在保障资源需求预测中的应用

针对现代战争条件下装备保障资源需求变化快,保障资源预测困难的问题,首先分析了影响装备保障资源需求的因素,根据实际情况选取了平均维修间隔时间(MTBM)、平均修复时间(MTBR)等8项影响装备保障资源需求的关键指标,然后将基于遗传算法(GA)优化的反向传播(BP)神经网络应用于保障资源需求预测中,构建了基于遗传神经网络的需求预测模型,最后利用1980年～2010年实际保障资源需求数据对模型进行了验证.验证结果表明,基于GA优化的BP神经网络预测模型有较快的收敛速度、较强的适应性和较高的预测精度,适用于装备保障资源需求预测.     

基于云理论的装备技术状态预测

通过分析装备技术状态变化的模糊性和不确定性等特性,提出了基于云理论的装备技术状态预测模型.根据装备技术状态劣化趋势,给出了基于云模型的时间序列状态预测方法,有效地运用了装备状态评估中的主观预测知识.将历史趋势与当前趋势相结合,实现了基于时间序列的状态预测.最后以某装备的发动机为研究对象,对发动机状态的动态评估值进行了预测,验证了该状态预测方法的有效性.     

天基预警卫星弹道预报能力仿真分析

天基预警卫星对导弹位置和速度的预测误差是引导信息中的重要组成部分,直接影响到远程预警雷达和跟踪制导雷达的搜索性能.根据天基预警卫星视线角误差和导弹目标经验数据,设计导弹预报误差估计模型,计算预报误差带半径.仿真结果表明:通过对理想弹道目标进行观测误差协方差分析,可以获得预警卫星观测的水平及垂直平面预测误差带.     

Waypoint analysis for command and control

Command and Control (C2) in a military setting can be epitomized in battles‐of‐old when commanders would seek high ground to gain superior spatial‐temporal information; from this vantage point, decisions were made and relayed to units in the field. Although the fundamentals remain, technology has changed the practice of C2; for example, enemy units may be observed remotely, with instruments of varying positional accuracy. A basic problem in C2 is the ability to track an enemy object in the battlespace and to forecast its future position; the (extended) Kalman filter provides a straightforward solution. The problem changes fundamentally if one assumes that the moving object is headed for an (unknown) location, or waypoint. This article is concerned with the new problem of estimation of such a waypoint, for which we use Bayesian statistical prediction. The computational burden is greater than an ad hoc regression‐based estimate, which we also develop, but the Bayesian approach has a big advantage in that it yields both a predictor and a measure of its variability. © 2004 Wiley Periodicals, Inc. Naval Research Logistics, 2004     

基于马尔可夫预测的低消耗弹药库存仿真建模分析

应用马尔可夫方法的无后效性原理,建立了低消耗弹药库存的预测模型,为该类弹药的年度供应提供依据。在模型建立的基础上,对其仿真算法进行了描述,并应用计算机进行了仿真实现。     

On the median residual lifetime and its aging properties: A characterization theorem and applications

This paper is devoted to study several aspects of the median residual life function (MERLF). In reliability studies, it is well known that, although the MERLF have several advantages over the mean residual life function (MRLF), the MRLF has the good property of uniquely determine a life distribution whereas either the median residual life function (MERLF) or an α‐percentile residual life do not have such good property. We shall give a characterization result where knowledge of both the MERLF and the survival function on an interval does uniquely determine the distribution. Moreover, in order to apply this characterization in practical situations, we propose a method to estimate the necessary information of the survival function. Relationships between analytical properties of the survival function and its associated MERLF are also obtained. Bryson and Siddiqui [J Am Statist Assoc 64 (1969), 1472–1483] proved relationships among seven criteria for aging, out of which two contained the MRLF (decreasing MRLF and net decreasing MRLF). In this paper, we prove that the same pattern of relationships holds if the MRLF is replaced by the MERLF. We also examine the aging criteria corresponding to an increasing MERLF and show that there is no relation between the behavior (increasing or decreasing) of the MERLF and of the MRLF. © 2005 Wiley Periodicals, Inc. Naval Research Logistics, 2005     

凝结水泵三维流场数值模拟与分析

为深入理解和分析电站凝结水泵性能,采用计算流体力学方法(CFD)对其内部复杂的三维流场进行了数值模拟与分析.首先,建立了某三级凝结水泵各部件几何模型,并对其进行网格划分.通过求解RANS方程对凝结水泵内部三维流场进行数值求解,湍流流动采用SST模型进行模拟.计算得到该泵若干工况下的扬程和功率等性能参数和泵内部流动特征,计算结果与试验数据吻合很好.模拟结果及分析表明:采用CFD方法模拟结构复杂的凝结水泵内部流动和进行性能预报是可行的.通过内流场分析还发现导叶体等部件的设计有可改进之处.     

回归型支持向量机的机翼结冰冰型预测

飞机结冰严重威胁着飞行安全。针对机翼结冰冰型预测时不确定性因素较多、难以准确预测的问题,提出了一种基于回归型支持向量机的机翼结冰冰型预测方法。在建立冰型模型的基础上,利用回归型支持向量机(Support Vector Regression,SVR)获得冰型多项式系数,从而预测出相关飞行条件和大气条件下的冰型。仿真结果表明,该方法具有较好的预测能力,可以及时提供可靠的结冰信息,为保证结冰条件下的飞行安全提供了保障。     

海洋移动目标多模型运动预测方法

分析海洋移动目标的运动特征,提出了预测前插值的灰色预测方法,改进了航迹变更预测和潜在区域预测模型。通过集成匀速运动预测、航迹变更预测、基于航迹的预测和潜在区域预测,提出多模型运动预测方法及其模型参数配置依据,根据滑动时间窗口中的观测数据与预测值的统计比较,评价不同预测方法的近期预测效果,决策下阶段适宜选择的预测方法。仿真实验表明多模型运动预测比使用单一运动预测方法降低预测风险,提高了预测精度。