一种RetinaNet与SE融合的航空取证目标检测算法

针对在开展航空侦察取证时缺乏自动化、智能化取证手段的情况,提出了一种基于Reti-naNet与SE融合的航空取证目标检测算法,解决目标尺度变化大、数据集中类别不均衡的问题,并通过SE (squeeze-excitations)模块引入注意力机制进一步改进性能.该改进算法中的特征金字塔网络FPN可有效应对目标尺寸变化较大...     

按保障度最大配置备件模型

考虑了备件资源有限,有多个需求单位的条件下,依据装备数量、零部件、元器件的故障率,单装用数、平均更换时间、各级维修机构领取备件的平均时间,建立了两级备件保障度的模型,并在备件总资源量一定的条件下,按保障度最大给出了两级备件配置的程序、方法和示例.模型举例说明了模型输出结果的特征和敏感性.模型应用可减少备件的积压,降低备件的短缺,提高备件的保障效果.     

Probabilistic resource pooling games

We study a setting with a single type of resource and with several players, each associated with a single resource (of this type). Unavailability of these resources comes unexpectedly and with player‐specific costs. Players can cooperate by reallocating the available resources to the ones that need the resources most and let those who suffer the least absorb all the costs. We address the cost savings allocation problem with concepts of cooperative game theory. In particular, we formulate a probabilistic resource pooling game and study them on various properties. We show that these games are not necessarily convex, do have non‐empty cores, and are totally balanced. The latter two are shown via an interesting relationship with Böhm‐Bawerk horse market games. Next, we present an intuitive class of allocation rules for which the resulting allocations are core members and study an allocation rule within this class of allocation rules with an appealing fairness property. Finally, we show that our results can be applied to a spare parts pooling situation.     

基于属性的舰载机航材备件品种确定方法

航材备件品种确定是舰载机供应保障工作的重要内容。基于属性对舰载机航材备件品种确定进行研究。基于粗糙集理论对属性集进行属性约简,确定航材备件品种确定的主要影响属性,然后基于属性约简进行航材备件品种确定。给出了单属性、顺次属性和多属性的品种决策方法。最后结合实例进行了应用分析。     

随舰备件动态管理及备件数量计算模型

针对精确化保障的需要,提出了一种新的随舰备件动态管理策略.基于不同型号装备中相同型号的部件可以相互替换,开发了一个能综合考虑同型号部件具有不同寿命分布、任务要求的不同工作时间等特点的随舰备件数量计算模型.并以寿命服从正态分布的部件为算例进行了备件数量计算,验证了模型的可行性.     

基于RUP的航空兵作战C~4ISR体系结构研究

本文分析了C4ISR系统的建模特点,对当前主流体系结构模型开发方法进行了比较,提出了运用Rational统一过程（RUP）开发DoDAF体系结构视图产品,并分析了其可行性。结合航空兵作战的特点,采用Rational ROSE建模工具开发了的相关视图产品,描述了航空兵作战过程,证明了RUP对体系结构的开发有着良好的支持作用。     

基于解析算法的声纳浮标搜潜系统定位精度分析

针对基于位置时间参数解析算法的声纳浮标阵搜潜系统的定位精度问题,采用定性和定量分析相结合的方法展开了研究。从解析定位模型出发,首先定性分析浮标自身的定位误差与传感器测时误差对航速及航向角计算的影响;然后选取评价指标,采用蒙特卡洛方法进行了仿真分析,得到了不同仿真条件下各个因素对定位精度具体的影响关系,这些结论为根据精度参数合理选择浮标阵的数量及布放阵型提供了依据。     

Limiting cyberwarfare: applying arms-control models to an emerging technology

ABSTRACT

An arms race in cyberspace is underway. US and Western government efforts to control this process have largely been limited to deterrence and norm development. This article examines an alternative policy option: arms control. To gauge whether arms-control models offer useful lessons for addressing cyber capabilities, this article compiles a new dataset of predominantly twentieth-century arms-control agreements. It also evaluates two case studies of negotiated agreements that regulate dual-use technologies, the 1928 Geneva Protocol prohibiting chemical- and biological-weapon use and the 1944 Chicago Convention on International Civil Aviation. The analysis underscores the limits of norm development for emerging technologies with both civilian and military applications. It finds lessons for developing verifiable, international cooperation mechanisms for cyberwarfare in the regulatory model of international aviation. Conventionally, arms-control agreements take advantage of transparent tests or estimates of arms. To restrict cyberwarfare activities, experts and policy makers must adapt arms-control models to a difficult-to-measure technology at an advanced stage of development and use. Further investigation of international regulatory schemes for dual-use technology of similar diffusion and development to the internet, such as international civil aviation, is needed.     

数据与知识双驱动的备件需求模糊预测模型

针对知识驱动型需求预测模型所需的专家知识稀缺、数据驱动型需求预测模型可解释性不足的问题,提出了数据与知识双驱动的备件需求模糊预测模型。该模型基于模糊聚类算法将数值型数据聚类为结构简单、可解释性强的规则库,运用模糊逻辑将领域专家知识表示为Mamdani型规则库。在此基础上,引入了一种新型智能计算理论——模糊网络理论对两类规则库进行合并运算,形成初始预测模型。采用遗传算法优化模型规则库的模糊集参数来提高模型预测准确性。通过与模糊聚类算法进行对比,提出的模型在可解释性以及准确性指标上均具有优势。     

舰船装备随行备件量需求规律分析

通过对舰船装备备件需求影响因素的分析 ,从理论上推导了备件需求的分布规律 ,在此基础上建立了舰船级备件典型需求模型 ,并且对典型的故障分布模型进行了推广