爆炸逻辑间隙零门实验研究

为了可靠实现爆炸逻辑间隙零门的原理功能,提出并验证了一种基于精细RDX和含能胶合剂的传爆药方案.通过实验探索了基于该传爆药的爆炸零门适用的间隙宽度范围,并设计了一种小尺寸爆炸逻辑间隙零门,为爆炸逻辑网络设计提供参考.     

美国陆军网络装备作战评估及启示

作战试验能有效地推动装备体系的建设发展，本文通过分析美国陆军网络集成评估与联合作战评估的作战试验特点，提出军队开展装备作战试验的几个建议。首先，总结了美国陆军网络集成评估到联合作战评估的发展演变，主要包括网络集成评估的地位和作用、网络集成评估的实施流程以及13次网络集成评估和3次作战评估的有关情况；其次，分析了网络集成评估的一系列作战试验特点，诸如实际作战需求牵引、逼真场景构建、试训一体化模式、部队战斗力的直接生成以及作战能力的军民融合式发展等；最后，提出了网络集成评估带来的若干启示，从满足实战能力需求开展作战试验、突出装备体系的互操作能力评估、探索试训结合的作战试验模式、组建专门的作战试验部队及鼓励工业部门参与作战试验等方面推动军队作战试验的发展。     

面向癫痫脑电的简化深度学习模型

针对脑电信号随机性强、动态变化迅速等特点,提出了一种简化深度学习模型研究癫痫脑电识别问题。提出的模型以一维卷积神经网络为基础,在结构方面简化了卷积层、池化层等以提高模型效率,在整体框架方面应用了Keras框架,在训练优化算法方面采用RMSProp算法作为模型优化算法,通过预定义的目标函数来进行损失估计,模型设计上加入了批标准化层和全局均值池化层。基于所提模型,从三个方面研究了癫痫脑电识别问题,即:利用经验模态分解,分别选取前三阶、前五阶、前七阶、前八阶的本征模态函数分量,在简化模型上进行对比分析；利用提出模型所具备的深度学习特点,直接识别原始脑电信号而无须特征提取环节；增加了三种不同方法分别提取7类特征,对相同的脑电数据进行对比分析。性能分析结果表明:对于五类不同的脑电信号,前三阶的本征模态函数分量的识别率达到92.1%,比其他几种处理方式识别率高；前八阶的本征模态分量识别率不及原始信号,表明人工数据处理时会给数据带来噪声; 所提出的简化深度学习模型能高效处理癫痫脑电识别问题,具备较高效率和较好性能。     

基于模糊灰关联分析的通信网运行可靠性评估

基于模糊灰关联度理论 ,提出了通信网运行可靠性评估的方法 .通过实例验证 ,该方法有效 .     

无标度网络理论在网络中心战中的应用

根据无标度网络理论对军事信息网络进行分析,认为军事信息网的逻辑层应为符合幂指数分布的无标度网络,传统的以泊松分布为理论基础的随机网络分析方法已不再适用,并通过构建随机网络和无标度网络的实例进行了对比分析,进一步论证了这个结论.根据无标度网络理论,对军事信息网的抗毁性特点进行了分析,得出了"对随机攻击鲁棒性强,对智能攻击脆弱性高"的结论,并提出了以网络连通性为标准,判定节点重要性的一般方法.参照国外的先进网络应用经验,针对军事信息网节点间非常不均衡的无标度特性,给出了"关键节点热备份"和"物理节点分散配置"的抗毁策略.     

An integrated electric power supply chain and fuel market network framework: Theoretical modeling with empirical analysis for New England

In this article, we develop a novel electric power supply chain network model with fuel supply markets that captures both the economic network transactions in energy supply markets and the physical network transmission constraints in the electric power network. The theoretical derivation and analysis are done using the theory of variational inequalities. We then apply the model to a specific case, the New England electric power supply chain, consisting of six states, five fuel types, 82 power generators, with a total of 573 generating units, and 10 demand market regions. The empirical case study demonstrates that the regional electric power prices simulated by our model match the actual electricity prices in New England very well. We also compute the electric power prices and the spark spread, an important measure of the power plant profitability, under natural gas and oil price variations. The empirical examples illustrate that in New England, the market/grid‐level fuel competition has become the major factor that affects the influence of the oil price on the natural gas price. Finally, we utilize the model to quantitatively investigate how changes in the demand for electricity influence the electric power and the fuel markets from a regional perspective. The theoretical model can be applied to other regions and multiple electricity markets under deregulation to quantify the interactions in electric power/energy supply chains and their effects on flows and prices. © 2009 Wiley Periodicals, Inc. Naval Research Logistics, 2009     

基于EMD和神经网络的气阀机构故障诊断研究

运用经验模态分解(EMD)对柴油机缸盖振动信号进行分析,求得各内禀模态函数(IMF)的能量百分比;将能量百分比作为神经网络的输入进行网络训练和故障识别,实现了气阀机构的故障诊断,取得了较好的效果。     

基于概率神经网络的设备故障诊断及仿真分析

针对某些难于建立准确数学模型的复杂系统,用神经网络的方法进行故障诊断有其独特的优越性.首先分析了概率神经网络(PNN)的基本结构及其训练算法,建立了某型航空发动机故障分类的概率神经网络模型,通过对该设备故障进行定性诊断,对比分析了概率神经网络与常用的误差反向传播神经网络(BPNN)分类模型对各类故障的分类效果.仿真表明,基于PNN模型的分类方法在分类速度、精度和泛化能力方面均优于基于BPNN的模型,是一种有效的故障分类方法.     

基于神经网络集成的传感器故障诊断研究

针对诊断传感器偏置故障及漂移故障的难点问题,提出了一种基于神经网络集成的传感器故障诊断方法。该方法将传感器输出看做时间序列,通过加噪声生成抖动数据,建立多组神经网络,以获得神经网络集成预测器输出。通过将预测器输出与传感器实际输出相比较获取残差序列,获得基于残差序列的传感器偏置故障和漂移故障的辨识策略,实现传感器故障在线诊断。应用结果表明该方法可以提高神经网络的运算精度,从而快速准确地检测和分离传感器故障,辨识传感器故障类型以及故障发生的时间。     

A novel facial emotion recognition scheme based on graph mining

Recent years have seen an explosion in graph data from a variety of scientific, social and technological fields. From these fields, emotion recognition is an interesting research area because it finds many applications in real life such as in effective social robotics to increase the interactivity of the robot with human, driver safety during driving, pain monitoring during surgery etc. A novel facial emotion recognition based on graph mining has been proposed in this paper to make a paradigm shift in the way of representing the face region, where the face region is represented as a graph of nodes and edges and the gSpan frequent sub-graphs mining algorithm is used to find the frequent sub-structures in the graph database of each emotion. To reduce the number of generated sub-graphs, overlap ratio metric is utilized for this purpose. After encoding the final selected sub-graphs, binary classification is then applied to classify the emotion of the queried input facial image using six levels of classification. Binary cat swarm intelligence is applied within each level of classification to select proper sub-graphs that give the highest accuracy in that level. Different experiments have been conducted using Surrey Audio-Visual Expressed Emotion (SAVEE) database and the final system accuracy was 90.00%. The results show significant accuracy improvements (about 2%) by the proposed system in comparison to current published works in SAVEE database.