基于递归神经网络的C3I系统故障预报系统

阐述了C3I系统故障预测系统的设计要求,分析了带有偏差单元的递归神经网络的相关原理,建立了C3I系统故障的神经网络预测模型并提出了相应的训练算法.提出了把神经网络、预测理论和专家系统有机地结合起来建立故障预报系统的初步设想.并以防空C3I系统的典型故障为例,实现了故障的预测.预测结果证明,给出的神经网络预测模型和训练算法是可行的,且具有较高的精度.     

基于分布式排队网络的防空战术协同模型

分析了多个防空火力单元的作战过程,将战术BM/C3的控制协调决策抽象为决策策略。建立了多个火力单元协同作战的排队网络模型,并运用SPN理论对排队网络的运行机制进行了强有力的描述,有效地体现了防空作战过程中的威胁评估、目标分配等战术决策过程。这将为建立大型复杂排队网络,模拟仿真战役层面防空作战过程奠定基础。     

神经网络模型预测函数控制方法

在建立基于神经网络模型的非线性预测函数控制系统结构和基于BP网络非线性预测模型的基础上,提出了基于神经网络模型的非线性预测函数控制方法,并对其优化法等进行了讨论。通过与PID方法的仿真比较表明,预测函数控制方法具有抑制干扰能力强、跟踪性能好的特点,能够满足一些非线性系统的控制要求。     

基于BP神经网络的机载航炮故障诊断方法

机载航炮是战斗机的一个重要作战武器,其工作情况的好坏直接影响到战机的攻击和自卫能力,因此,对机载航炮的故障诊断受到航空兵部队普遍关注。通过对机载航炮大量故障现象、故障原因、故障样本的收集、分析和整理,利用BP神经网络建立了机载航炮智能诊断模型。该网络采用了三层结构、17个输入量、10个输出量的故障诊断系统,较完善地反映了机载航炮的故障类型。经故障诊断实例检验,该系统诊断结果正确,有良好的实用价值。     

GSPN的分析方法及其应用

随着计算机和信息技术的发展,广义随机Petri网(G SPN)作为一种图形化的建模工具,不仅可以对系统进行形式化的描述和快速原型开发,而且由于其具有坚实的数学理论基础,可以对系统进行正确性验证和性能评价,因此在系统的设计过程中,得到了广泛的应用。基于结构分析方法、可达图分析和数值分析方法讨论分析了G SPN,并给出了具体的算例,最后讨论了G SPN的应用领域。     

A model of supply-chain decisions for resource sharing with an application to ventilator allocation to combat COVID-19

We present a stochastic optimization model for allocating and sharing a critical resource in the case of a pandemic. The demand for different entities peaks at different times, and an initial inventory for a central agency are to be allocated. The entities (states) may share the critical resource with a different state under a risk-averse condition. The model is applied to study the allocation of ventilator inventory in the COVID-19 pandemic by FEMA to different U.S. states. Findings suggest that if less than 60% of the ventilator inventory is available for non-COVID-19 patients, FEMA's stockpile of 20 000 ventilators (as of March 23, 2020) would be nearly adequate to meet the projected needs in slightly above average demand scenarios. However, when more than 75% of the available ventilator inventory must be reserved for non-COVID-19 patients, various degrees of shortfall are expected. In a severe case, where the demand is concentrated in the top-most quartile of the forecast confidence interval and states are not willing to share their stockpile of ventilators, the total shortfall over the planning horizon (until May 31, 2020) is about 232 000 ventilator days, with a peak shortfall of 17 200 ventilators on April 19, 2020. Results are also reported for a worst-case where the demand is at the upper limit of the 95% confidence interval. An important finding of this study is that a central agency (FEMA) can act as a coordinator for sharing critical resources that are in short supply over time to add efficiency in the system. Moreover, through properly managing risk-aversion of different entities (states) additional efficiency can be gained. An additional implication is that ramping up production early in the planning cycle allows to reduce shortfall significantly. An optimal timing of this production ramp-up consideration can be based on a cost-benefit analysis.     

基于灰度关联和神经网络的装备价格第三方服务机构评价模型

为了科学合理选择装备价格第三方服务机构,研究以灰度关联分析和神经网络方法构建评价模型。研究数据采用问卷调研形式获取,针对样本数据采用灰度关联法分析评价指标与综合评分之间的关联性,发现服务态度和制度建设情况两个评价指标与综合评分关联度达0.74以上,较为重要。采用有效二级指标和综合评分作为输入和输出数据,构建基于神经网络的装备价格第三方服务机构评价模型。通过实际数据验证分析,发现神经网络模型预测精准的概率为75%,预测满足要求的概率为25%,满足实际应用需求,能够为主管部门遴选机构建言献策。     

Pricing and inventory management during new product introduction when shortage creates hype

In this study, we analyze the joint pricing and inventory management during new product introduction when product shortage creates additional demand due to hype. We develop a two‐period model in which a firm launches its product at the beginning of the first period, before it observes sales in the two periods. The product is successful with an exogenous probability, or unsuccessful with the complementary probability. The hype in the second period is observed only when the product is successful. The firm learns the actual status of the product only after observing the first‐period demand. The firm must decide the stocking level and price of the product jointly at the beginning of each of the two periods. In this article, we derive some structural properties of the optimal prices and inventory levels, and show that (i) firms do not always exploit hype, (ii) firms do not always increase the price of a successful product in the second period, (iii) firms may price out an unsuccessful product in the first period if the success probability is above a threshold, and (iv) such a threshold probability is decreasing in the first‐period market potential of the successful product. © 2015 Wiley Periodicals, Inc. Naval Research Logistics 62: 304–320, 2015     

Chance‐constrained multi‐terminal network design problems

We consider a reliable network design problem under uncertain edge failures. Our goal is to select a minimum‐cost subset of edges in the network to connect multiple terminals together with high probability. This problem can be seen as a stochastic variant of the Steiner tree problem. We propose two scenario‐based Steiner cut formulations, study the strength of the proposed valid inequalities, and develop a branch‐and‐cut solution method. We also propose an LP‐based separation for the scenario‐based directed Steiner cut inequalities using Benders feasibility cuts, leveraging the success of the directed Steiner cuts for the deterministic Steiner tree problem. In our computational study, we test our branch‐and‐cut method on instances adapted from graphs in SteinLib Testdata Library with up to 100 nodes, 200 edges, and 17 terminals. The performance of our branch‐and‐cut method demonstrates the strength of the scenario‐based formulations and the benefit from adding the additional valid inequalities that we propose. © 2015 Wiley Periodicals, Inc. Naval Research Logistics 62: 321–334, 2015     

地理社交网络位置推荐

地理社交网络将地理位置信息融合进传统社交网络,将人们的现实生活和虚拟世界的生活连接在一起。作为地理社交网络的一个重要应用,位置推荐可以向人们推荐其可能感兴趣的位置,为人们的出行提供参考,极大地便利了人们的生活。在此背景下,论文研究了地理社交网络位置推荐的基本概念,分析了位置推荐常用的方法,描述了典型的数据集及推荐效果的评估方法,指出了位置推荐面临的主要问题,并展望了未来可能的研究方向,为相关领域的研究提供参考。