一种计算二维图象矩的神经网络方法

提出一种计算二维图象矩的神经网络方法,首先,导出一维信号矩与一维Ｈａｄａｍａｒｄ变换之间的关系。通过２Ｎ－一维Ｈａｄａｍａｒｄ变换和极少量加法,移位及乘法运行可计算二维图象矩。然后给出用Ｔａｎｋ－Ｈｏｐｆｉｅｌｄ神经网络实现Ｈａｄａｍａｒｄ变换的方法,并对该网络作了改进。     

Median filtering algorithms for multichannel detectors

Particle detectors of worldwide networks are continuously measuring various secondary particle fluxes incident on Earth surface. At the Aragats Space Environmental Center (ASEC), the data of 12 cosmic ray particle detectors with a total of ∼280 measuring channels (count rates of electrons, muons and neutrons channels) are sent each minute via wireless bridges to a MySQL database. These time series are used for the different tasks of off-line physical analysis and for online forewarning services. Usually long time series contain several types of errors (gaps due to failures of high or low voltage power supply, spurious spikes due to radio interferences, abrupt changes of mean values of several channels or/and slowly trends in mean values due to aging of electronics components, etc.). To avoid erroneous physical inference and false alarms of alerting systems we introduce offline and online filters to “purify” multiple time-series. In the presented paper we classify possible mistakes in time series and introduce median filtering algorithms for online and off-line “purification” of multiple time-series.     

带权优化约束Delaunay三角化算法

Delaunay细化算法是目前大多数约束Delaunay三角化算法的主要思想,针对其要求输入的约束条件中不能包含夹角较小的尖角的问题,给出了Delaunay细化算法收敛的充分条件,并通过在尖角点和尖角边处引入带权点和带权Delaunay空圆/球准则的方法提出了一种带权优化约束Delaunay三角化算法,解决了经典的细化算法在尖角处算法不收敛时需引入辅助控制区域以及过多辅助点的问题,对算法的收敛性进行了分析,给出了相应的算法应用实例,可以应用于复杂几何对象的科学计算和工程分析.     

超声速低声爆布局分层优化方法

声爆抑制是发展新一代超声速民机必须突破的关键技术。总体布局参数的合理设计可以使飞行器具有良好的声爆特性。为了提高全局进化算法在布局设计中的优化效率,提出一种基于数据挖掘的分层优化方法,利用数据挖掘中的决策树算法提取设计知识,获得设计变量分层信息,指导低声爆布局分层优化;针对某超声速低声爆飞行器,选取后掠角、上反角、展弦比、梢根比、长细比五个总体布局参数作为设计变量,开展分层优化数值实验,并与一体化优化形成对比验证。结果表明：分层优化方法能够搜索到与一体化优化高度吻合的最优解,分层优化的收敛速度显著高于一体化优化,且对随机寻优历程的表现更稳健。     

三焦点张量的最小代数误差非迭代算法研究

通过普通数码相机获得的3幅未标定图像,采用RANSAC算法进行两两匹配获得3幅图像的一组兴趣点对,利用最小代数误差非迭代算法在MATLAB中计算出三焦点张量,提出一种最小代数误差非迭代算法。实验结果表明,该方法是一种有效的三焦点张量计算方法,计算复杂度小、实现效率高。能够得到较准确的三焦点张量,为下一步相机自动标定以及三维场景的自动重建和量测奠定了基础。     

An equilibrium multi-objective optimum design for non-circular clearance hole of disk with discrete variables

An Equilibrium Multi-objective Optimization Model(EMOM) with self-regulated weighting factors has been proposed for the optimum design of non-circular clearance hole on the front flange of turbine disk. In the ‘‘equilibrium design, both the stress decrease around the hole and the least hole's profile variation are considered, which balances two ambivalent design goals. Specific discrete variables are applied to realize the standardization design in the optimization process, in which a Surrogate Genetic Coding Algorithm(SGCA) is introduced, and a special check module is used to get rid of repeated fitness evaluation of the samples. The method offers an equilibrium design for the non-circular clearance hole of the turbine disk with great accuracy and efficiency.     

一种有效的软件结构图的布图算法

信息的可视化表示是帮助理解软件结构的重要手段.结构化软件中的复杂的模块调用为软件结构的分析和理解带来不便,为此提出一种以模块连接度(扇入扇出系数和)为特征的广义张量平衡算法,以图形方式直观地表现出模块之间复杂的调用关系.具体讨论了算法应遵循的原则,给出了算法的可操作规则集.实践证明,该算法布出的图形具有高度的对称性和紧耦合性,且层次分明,线间交叉少,同时符合图形语义要求和协调性原则.     

地形纹理分割技术在雷达图像仿真中的应用

文章阐述了将图像分割技术应用于雷达地形纹理分割中,用基于 FCM 图像分割方法对可见光纹理进行区域自动识别,形成互不相交的纹理区域,并借助建立的雷达材质库对区域材质进行指定,有效解决了海量地形纹理数据处理的难题,并提高了处理的准确性.     

Improved NSGA-II Multi-objective Genetic Algorithm Based on Hybridization-encouraged Mechanism

To improve performances of multi-objective optimization algorithms, such as convergence and diversity, a hybridization- encouraged mechanism is proposed and realized in elitist nondominated sorting genetic algorithm （NSGA-Ⅱ）. This mechanism uses the normalized distance to evaluate the difference among genes in a population. Three possible modes of crossover operators--＂Max Distance＂, ＂Min-Max Distance＂, and ＂Neighboring-Max＂--are suggested and analyzed. The mode of ＂Neighboring-Max＂, which not only takes advantage of hybridization but also improves the distribution of the population near Pareto optimal front, is chosen and used in NSGA-Ⅱ on the basis of hybridization-encouraged mechanism （short for HEM-based NSGA-Ⅱ）. To prove the HEM-based algorithm, several problems are studied by using standard NSGA-Ⅱ and the presented method. Different evaluation criteria are also used to judge these algorithms in terms of distribution of solutions, convergence, diversity, and quality of solutions. The numerical results indicate that the application of hybridization-encouraged mechanism could effectively improve the performances of genetic algorithm. Finally, as an example in engineering practices, the presented method is used to design a longitudinal flight control system, which demonstrates the obtainability of a reasonable and correct Pareto front.     

基于模糊机会约束规划的机会阵雷达方向图综合

针对机会阵雷达方向图综合的不确定问题,提出了一种基于模糊机会约束规划的方向图综合规划模型。该模型基于可信性理论,综合考虑天线单元分布的随机性以及激励状态的不确定性,将参与方向图综合时激励打开的天线数目看做一个梯形模糊变量,用以描述综合时的复杂不确定环境。随后,将规划模型转化为清晰等价形式,再结合遗传算法和灰关联综合评价法则设计了一种混合智能优化算法,用于求解该模型。以一维任意非均匀线阵为例,对主瓣宽度和最大副瓣电平进行了优化。仿真表明:优化后结果的可信性高于置信水平,验证了该算法的有效性。