基于自监督信息增强的图表示学习

针对图表示学习模型依赖具体任务进行特征保留以及节点表示的泛化性有限等问题,本文提出一种基于自监督信息增强的图表示学习模型(Self-Variational Graph Auto Encoder,Self-VGAE)。Self-VGAE首先使用图卷积编码器和节点表示内积解码器构建变分图自编码器(Variational Graph Auto Encoder,VGAE),并对原始图进行特征提取和编码;然后,使用拓扑结构和节点属性生成自监督信息,在模型训练过程中约束节点表示的生成。在多个图分析任务中,Self-VGAE的实验表现均优于当前较为先进的基线模型,表明引入自监督信息能够增强对节点特征相似性和差异性的保留能力以及对拓扑结构的保持、推断能力,并且Self-VGAE具有较强的泛化能力。     

基于学习进化的机器人同时定位与地图创建

利用学习与进化结合的思想,改善基于粒子滤波的SLAM算法。在对学习与进化的关系深入分析的基础上,针对基于粒子滤波的SLAM算法,提出将滤波过程分成学习和进化两个阶段,分别给出相应算法解决粒子有效性与多样性的问题,缓解二者之间的矛盾,改善了SLAM算法的效果,增强了算法的鲁棒性,也验证了学习与进化的关系。最后,通过多次Monte-Carlo仿真实验结果表明了该算法的有效性。     

陕西省水资源承载力动态研究

面临严重的水资源短缺问题,以及对可持续发展造成的制约,运用主成分分析法,从影响陕西省水资源承载力动态变化的15个指标中选出3个指标作为主成分,并用熵值法对其赋权,计算出1999～2004年陕西省水资源承载力的综合得分.结果表明,陕西省的人口和经济发展的持续增长,导致了水资源承载力呈现出恶化的趋势.图2,表4,参10.     

Non-fragile decentralized H∞ controller design for uncertain linear systems

Considering the design problem of non-fragile decentralized H∞ controller with gain variations, the dynamic feedback controller by measurement feedback for uncertain linear systems is constructed and studied. The parameter uncertainties are considered to be unknown but norm bounded. The design procedures are investigated in terms of positive definite solutions to modify algebraic Riccati inequalities. Using information exchange among local controllers, the designed non-fragile decentralized H∞ controllers guarantee that the uncertain closed-loop linear systems are stable and with H∞ -norm bound on disturbance attenuation. A sufficient condition that there are such non-fragile H∞ controllers is obtained by algebraic Riccati inequalities. The approaches to solve modified algebraic Riccati inequalities are carried out preliminarily. Finally, a numerical example to show the validity of the proposed approach is given.     

基于混沌差分进化算法的飞机等效系统拟配研究

提出了基于Tent映射的混沌差分进化算法。以某飞机纵向短周期系统为例,首次研究了基于混沌差分进化算法的飞机等效系统的拟配,克服了一些传统的拟配算法存在的一些缺点。仿真结果表明,基于混沌差分进化算法拟配得到的等效系统满足等效系统拟配的各项要求和一级飞行品质的要求,取得了更好的拟配效果。证明该算法在飞机等效系统拟配中的有效性和高效性。

Abstract：

Chaotic differential evolution algorithm based on Tent map was introduced. Taking aircraft longitudinal short period system as an example,the analog-matching of the aircraft longitudinal equivalent system based on chaotic differential evolution algorithm was studied firstly and overcome the disadvantages of the conventional algorithms in the analog-matching of equivalent system. The simulation results show that the equivalent system by chaotic differential evolution algorithm is satisfied the various requirements in the analog-matching of equivalent system and the requirement of level 1 flight qualities,and has obtained better analog-matching results. The usefulness and high effectiveness of the chaotic differential evolution algorithm in the analog-matching of aircraft equivalent system is proved.     

基于复杂网络的指挥控制信息协同模型研究

网络化作战的时代特征迫切需要新的仿真模型和评价方法,以预测信息优势对作战效果的影响。在描述网络化指挥控制活动特点的基础之上,从复杂网络角度出发建立起指挥控制信息协同模型,并就不同规则演化下的网络特征变化进行了定量分析,从而为评估信息协同对作战效果的影响提供了新的研究思路和方法。     

基于微分进化算子的量子粒子群优化算法及应用

分析了量子粒子群优化算法(Quantum-behaved Particle Swarm Optimization,QPSO)的进化方程,指出其存在的局部收敛问题,通过将微分进化(Differential Evolution,DE)的基本操作思想引入到QPSO中,提出了改进的QPSO算法(QPSO-DE);算法改进的方法是在粒子搜索过程中,以一定的概率对粒子的每一维执行微分进化操作,以增加粒子的随机性,从而减少了粒子群体因多样性缺失而易于陷入局部最优或停滞的情况,增强了粒子群体的搜索能力,提高了算法的优化性能;对多个标准测试函数及在IIR数字滤波器优化设计中的仿真实验结果表明,与PSO算法和QPSO算法相比,QPSO-DE算法能够取得更好的优化结果。     

Delay-dependent state feedback robust stabilization for uncertain singular time-delay systems

The problem of robust stabilization for uncertain singular time-delay systems is studied.First,a new delay-dependent asymptotic stability criteria for normal singular time-delay systems is given,which is less conservative.Using this result,the problem of state feedback robust stabilization for uncertain singular time-delay systems is discussed.Finally,two examples are given to illustrate the effectiveness of the results.     

Non-fragile decentralized H∞ controller design for uncertain linear systems

Considering the design problem of non-fragile decentralized H∞ controller with gain variations, the dynamic feedback controller by measurement feedback for uncertain linear systems is constructed and studied. The parameter uncertainties are considered to be unknown but norm bounded. The design procedures are investigated in terms of positive definite solutions to modify algebraic Riccati inequalities. Using information exchange among local controllers, the designed non-fragile decentralized H∞ controllers guarantee that the uncertain closed-loop linear systems are stable and with H∞ -norm bound on disturbance attenuation. A sufficient condition that there are such non-fragile H∞ controllers is obtained by algebraic Riccati inequalities. The approaches to solve modified algebraic Riccati inequalities are carried out preliminarily. Finally, a numerical example to show the validity of the proposed approach is given.