遥控武器站总体结构参数优化研究

为减小遥控武器站炮口扰动以提高射击精度,建立了遥控武器站部分机构参数化三维模型、有限元模型和刚柔耦合动力学模型。基于多学科集成优化软件ModelCenter进行了系统集成,以减小炮口扰动为目标,建立了遥控武器站总体结构参数优化模型。采用多目标遗传算法对总体结构参数进行了优化,优化后炮口振动状况明显改善,与位移相关的起始撼动和与速度相关的起始扰动分别较原方案降低了17.05%和19.04%。     

基于GA-SVDD的轴承性能退化评估

为解决因机械设备轴承损伤导致机械故障而无法正常工作的问题,提出了一种基于GA-SVDD的轴承性能退化定量评估方法。该方法采用遗传算法优化选择特征参量,并建立SVDD超球体模型,运用SVDD距离评估轴承的性能退化程度。实验分析表明：该方法能够有效地对轴承性能退化过程的细节进行描述,实现对待测样本退化程度的定量评估。     

Are non‐lethal weapons a viable military option to strengthen the hearts and minds approach in Afghanistan?

Commanders of the International Security Assistance Force (ISAF) have repeatedly stressed the hearts and minds approach in Afghanistan, in saying that the human terrain is decisive for a successful outcome of the mission. Avoidance of civilian casualties is considered of strategic importance, and by nature highly dependent on the management of tactical level Escalation of Force (EoF) situations. Non‐lethal weapons (NLWs) are expected to enable tactical commanders to avoid innocent civilian casualties in such situations. This article considers a selected NLW on its potential to accomplish this requirement. It uses a defence technology assessment approach to analyse EoF situations experienced by Dutch ISAF forces in which the NLW is inserted. The analysis demonstrates that a range of contextual factors in the Afghanistan high‐risk environment tend to narrow down the window of opportunity for the NLW to help defuse the risk of unintended civil casualties.     

抢险救灾非战争军事行动中应急资源调度网络的优化方法

抢险救灾非战争军事行动包括道路抢修和物资运输等任务,而这两类任务在灾后应急资源调度中存在关联性的影响,且面临路网结构可变及需求随机模糊等挑战,对此,提出了一种非确定性应急资源调度网络双层规划模型,设计了基于蒙特卡洛方法与遗传算法耦合的智能启发式求解策略.通过对典型情境下应急资源调度案例进行分析建模和数值求解,说明了该模型和算法的合理性和有效性.     

多特征的UAV快速目标识别算法仿真

针对UAV(Unmanned Aerial Vehicle)侦察图像快速目标识别问题,重点展开基于多特征的UAV快速目标识别算法的仿真研究。算法结合图像的不变矩特征和SIFT特征,首先用不变矩特征构造适应度函数并利用遗传算法的全局搜索能力,在侦察图像中进行搜索,快速提取出可能包含目标的感兴趣区域(ROI,Region of Interest);然后采用尺度不变特征变换算法(SIFT,Scale Invariant Feature Transform)在ROI区域中进行匹配识别,从而确定目标的精确位置。仿真结果表明:算法具有较强的鲁棒性,能有效地识别飞机目标并显著减少识别时间,为UAV系统提供了一种近实时的目标识别方法。     

改进的前向信息修补算法及其应用

前向信息修补算法可以对离散动态贝叶斯网络的缺失数据进行预测,该算法只适用于所有观测节点是相互独立的网络,却不能处理观测节点有依赖关系网络的缺失数据。针对该算法的这一缺陷,提出了改进的前向信息修补算法,在分析离散动态贝叶斯网络的缺失数据具有二种基本形式的基础上,推导出了每种形式的相应预测公式。继而构建了用于识别威胁源离散动态贝叶斯网络的模型。仿真实验验证了改进的前向信息修补算法的有效性。     

拓展TOPSIS的地面目标关联算法

地面战场复杂的背景环境和目标的强机动性,使得传统关联方法所必需的先验信息不易获得,且传统关联方法仅利用状态信息进行关联,导致关联信息量不足,从而关联正确率不高。针对上述问题,采用无需任何先验假设的TOPS IS,在状态信息的基础上引入属性信息,作为拓展TOPS IS的评价指标,利用熵权确定各指标权重,最后用相对贴近度确定关联排序。仿真结果表明,该算法有效地提高了关联正确率,且能够满足实时性要求。     

Technical note: Finite-time regret analysis of Kiefer-Wolfowitz stochastic approximation algorithm and nonparametric multi-product dynamic pricing with unknown demand

We consider the problem of nonparametric multi-product dynamic pricing with unknown demand and show that the problem may be formulated as an online model-free stochastic program, which can be solved by the classical Kiefer-Wolfowitz stochastic approximation (KWSA) algorithm. We prove that the expected cumulative regret of the KWSA algorithm is bounded above by where κ₁, κ₂ are positive constants and T is the number of periods for any T = 1, 2, … . Therefore, the regret of the KWSA algorithm grows in the order of , which achieves the lower bounds known for parametric dynamic pricing problems and shows that the nonparametric problems are not necessarily more difficult to solve than the parametric ones. Numerical experiments further demonstrate the effectiveness and efficiency of our proposed KW pricing policy by comparing with some pricing policies in the literature.     

目标定位和跟踪的卡尔曼滤波加 BP 神经网络的方法

首先分析了卡尔曼滤波应用于单目标定位与跟踪时需要校正的因素,接着用具有反向传播（ＢＰ）学习算法的前向网络,建立校正原理和校正网络体系结构,最后分别给出了它对第１类和第２类火控系统应用的数学模型。     

基于小波分形理论的快速图象编码算法

小波和分形理论应用于图象压缩领域是当今研究的前沿。提出了一种快速图象编码算法,它将加权小波变换与基于二叉树和双向链表搜索的分形编码相结合,在高压缩比、高信噪比前提下,使编码时间大大缩短。在ＰｅｎｔｉｕｍＰｒｏ２００个人机上对一２５６×２５６,８ｂｐｐ图象进行实验,编码时间仅需８秒,而图象失真很小。