基于区间数TOPSIS法优选空军战役作战计划

针对战役作战计划优选中的不确定性,运用区间分析和TOPSIS(Technique for Order Preference by Similarity to Ideal Solution)法探索空军战役作战计划优选问题.通过引进区间数乘法运算,将区间数多指标决策问题转变为指标为区间数的多指标决策问题,进而给出区间数多指标决策问题的TOPSIS法,对空军战役作战计划进行排序选优.与传统方法相比较,该方法较好地解决了评价指标为不确定值时的多指标决策问题.     

基于敌后侦察与诱骗博弈的远程火力打击战法*

对敌后侦察反军事诱骗的远程火力打击战法的定量分析是战役研究中尚未解决的关键问题之一,根据信息作战原理,运用仿真和统计学分析的混合方法,建立基于概率的二人非零和(TPNZS)非合作博弈模型,设计基于侦察与诱骗博弈的远程火力打击战法,定量分析我方的敌后侦察和敌方的军事诱骗对远程信息与火力联合打击能力的影响,并对一个典型实例的初步试验及分析结果表明:与敌后侦察和军事诱骗有关的正确识别目标和错误识别目标的概率以及远程火力命中目标的概率是评估远程信息与火力联合打击能力的关键,而对评估结果进行博弈分析则是远程火力打击战法设计的关键,用识别正确目标和错误目标能力以及远程火力命中目标能力描述的基于敌后侦察与诱骗博弈的远程火力最优打击战法为Δ*=(0,Δ2*,1-Δ2*)=(0.0000,0.7727,0.2273),被打击方对远程火力打击的最优战法为π*=(π1*,0,1-π1*)=(0.8511,0.0000,0.1489)。     

基于模糊综合评判法的敌空袭主攻方向预测研究

针对主攻方向预测的主要特点,运用模糊理论探索解决其主观推理、决策问题。应用隶属函数及变权重模糊综合评判方法分析,建立了评估模型,得到了类似人主观判断的结果,最后通过示例说明应用模糊综合评判法预测主攻方向的可行性。     

Aggregating courier deliveries

We consider the problem of efficiently scheduling deliveries by an uncapacitated courier from a central location under online arrivals. We consider both adversary‐controlled and Poisson arrival processes. In the adversarial setting we provide a randomized (3βΔ/2δ ? 1) ‐competitive algorithm, where β is the approximation ratio of the traveling salesman problem, δ is the minimum distance between the central location and any customer, and Δ is the length of the optimal traveling salesman tour overall customer locations and the central location. We provide instances showing that this analysis is tight. We also prove a 1 + 0.271Δ/δ lower‐bound on the competitive ratio of any algorithm in this setting. In the Poisson setting, we relax our assumption of deterministic travel times by assuming that travel times are distributed with a mean equal to the excursion length. We prove that optimal policies in this setting follow a threshold structure and describe this structure. For the half‐line metric space we bound the performance of the randomized algorithm in the Poisson setting, and show through numerical experiments that the performance of the algorithm is often much better than this bound.     

基于大数据的战区联合作战装备保障决策

大数据技术在决策领域的不断应用,将给装备保障决策方式带来重大变革。本文研究基于大数据的战区联合作战装备保障决策问题,提升信息化条件下装备保障准确、高效的决策方式等方面发挥重大作用。阐述了大数据的基本内涵,在决策领域的应用价值。通过系统推理的方法对战区联合作战装备保障决策的分析,提出基于大数据的战区联合作战装备保障决策基本构想,画出科学决策过程示意图,构建大数据战区联合作战装备保障辅助决策系统。结合研究大数据在战区联合作战装备保障决策领域的现实情况,提出相对应的措施建议。     

混合多属性决策投影算法的装甲分队目标价值评估

科学评价混合多属性目标价值是装甲分队作战决策的基础,为提高信息化装甲分队作战辅助决策水平,建立了混合多属性评估矩阵并运用投影算法完成目标价值评估与排序。实例分析表明,基于混合多属性决策投影算法可合理有效地评估多目标价值,为分队指挥员科学决策提供重要数据支持。     

基于可视化交互的国动指挥所设计

国防动员的指挥控制中大量的信息数据(如部队需求、地方资源)和错综复杂的多方关系,使得指挥员难以在短时间内从浩如烟海的信息中提取有用的决策信息和作出快速准确地指挥协调。为此,着眼未来指挥所的发展趋势,提出基于可视化交互的国动指挥所设计方法:通过分析国动指挥任务的关键路径,提取重要的决策信息,利用可视化交互技术,实现对国动任务的信息化指挥控制。以某部演习的国防动员指挥为例,验证了方法的可行性和有效性。     

准则权重信息不完全的证据推理多属性决策算法

针对准则权重信息不完全情况下的多属性决策问题,提出了一种新的证据推理多属性决策算法,它通过建立基于证据信息熵的决策模型来求解准则的最优权重系数,利用求解得到的权重系数和递归ER算法求出各方案的效用值,进而得到各方案的优劣次序。最后,通过算例分析验证了该方法的有效性和合理性。     

针对无人机集群对抗的规则与智能耦合约束训练方法

基于无人机集群智能攻防对抗构想,建立了无人机集群智能攻防对抗仿真环境。针对传统强化学习算法中难以通过奖励信号精准控制对抗过程中无人机的速度和攻击角度等问题,提出一种规则与智能耦合约束训练的多智能体深度确定性策略梯度(rule and intelligence coupling constrained multi-agent deep deterministic policy gradient, RIC-MADDPG)算法,该算法采用规则对强化学习中无人机的动作进行约束。实验结果显示,基于RIC-MADDPG方法训练的无人机集群对抗模型能使得红方无人机集群在对抗中的胜率从53%提高至79%,表明采用“智能体训练—发现问题—编写规则—再次智能体训练—再次发现问题—再次编写规则”的方式对优化智能体对抗策略是有效的。研究结果对建立无人机集群智能攻防策略训练体系、开展规则与智能相耦合的集群战法研究具有一定参考意义。     

Scheduling combat logistics force replenishments at sea for the US Navy

The Replenishment at Sea Planner (RASP) is saving the U.S. Navy millions of dollars a year by reducing fuel consumption of its Combat Logistics Force (CLF). CLF shuttle supply ships deploy from ports to rendezvous with underway U.S. combatants and those of coalition partners. The overwhelming commodity transferred is fuel, ship‐to‐ship by hoses, while other important packaged goods and spare parts are high‐lined, or helicoptered between ships. The U.S. Navy is organized in large areas of responsibility called numbered fleets, and within each of these a scheduler must promulgate a daily forecast of CLF shuttle operations. The operational planning horizon extends out several weeks, or as far into the future as we can forecast demand. We solve RASP with integer linear optimization and a purpose‐built heuristic. RASP plans Replenishment‐at‐Sea (RAS) events with 4‐hour (Navy watch) time fidelity. For five years, RASP has served two purposes: (1) it helps schedulers generate a daily schedule and animates it using Google Earth, and (2) it automates reports command‐to‐ship messages that are essential to keep this complex logistics system operating.