基于遗传算法的红外图像增强研究

红外图像侦察是一种重要的航空侦察方式。遗传算法目前已在图像处理领域得到了很好的应用。本文将遗传算法引入红外图像增强,使用红外图像的参数模型将图像增强转化为参数的优化。实验结果表明,该方法是一种有效的图像增强方法。     

Estimating distribution functions from partially observed samples

Suppose that some components are initially operated in a certain condition and then switched to operating in a different condition. Working hours of the components in condition 1 and condition 2 are respectively observed. Of interest is the lifetime distribution F of the component in the second condition only, i.e., the distribution without the prior exposure to the first condition. In this paper, we propose a method to transform the lifetime obtained in condition 1 to an equivalent lifetime in condition 2 and then use the transformed data to estimate F. Both parametric and nonparametric approaches each with complete and censored data are discussed. Numerical studies are presented to investigate the performance of the method. © 2000 John Wiley & Sons, Inc. Naval Research Logistics 47: 521–530, 2000     

Investigation on the spatial distribution characteristics of behind-armor debris formed by the perforation of EFP through steel target

The behind-armor debris (BAD) formed by the perforation of an EFP is the main damage factor for the secondary destruction to the behind-armor components. Aiming at investigating the BAD caused by EFP, flash X-ray radiography combined with an experimental witness plate test method was used, and the FEM-SPH adaptive conversion algorithm in LS-DYNA software was employed to model the perforation process. The simulation results of the debris cloud shape and number of debris were in good agreement with the flash X-ray radiographs and perforated holes on the witness plate, respectively. Three-dimensional numerical simulations of EFP's penetration under various impact conditions were conducted. The results show that, an ellipsoidal debris cloud, with the major-to-minor axis radio (a/b) smaller than that caused by shaped charge jets, was formed behind the target. With the increase of target thickness (h) and decrease of impact velocity (v₀) and obliquity (θ), the value of a/b decreases. The number of debris ejected from target is significantly higher than that from EFP. Based on the statistical analysis of the spatial distribution of the BAD, An engineering calculation model was established considering the influence of h, v₀ and θ. The model can with reasonable accuracy predict the quantity and velocity distribution characteristics of BAD formed by EFP.     

强化学习框架下移动自组织网络分步路由算法

移动自组织网络是一种无基础设施、由移动通信节点组成的无线网络,具有高动态特性。传统的路由协议并不能适应节点移动性带来的频繁拓扑变化,简单的洪泛路由也会因开销过大降低网络的性能。针对如何在移动自组织网络中自适应地进行路由选择,提出强化学习框架下的分步路由选择算法。该算法以最小链路总往返时延为目标,基于强化学习进行路由搜寻,在筛选出符合目标需求节点集合的基础上,结合置信度选择路由。在链路变得不可靠时,数据包被广播给筛选出的邻居节点集以提升路由可靠性并降低开销。对提出的算法在分组到达率和路由开销等主要性能指标进行数值仿真分析。仿真结果表明,提出的分步路由算法相比于基于强化学习的智能鲁棒路由,在降低开销的同时,保持着相当的吞吐率。     

基于切比雪夫神经网络的软件定义卫星网络智能路由策略

针对现有的软件定义卫星网络中流表占用的三态内容寻址存储器空间不断增加,复杂的流表项查找、匹配过程导致路由转发效率降低,无法满足多样化应用需求的问题,提出基于神经网络的软件定义卫星网络智能路由架构。控制器通过训练神经网络获取数据流的传输模式,并用训练后的神经网络代替流表,在此基础上提出基于Chebyshev神经网络的智能路由策略,交换机根据数据流的业务类型预测其转发路径,以满足卫星网络应用的服务质量要求。仿真结果表明:所提路由策略显著减少了占用的三态内容寻址存储器存储空间,提高了路由效率。     

基于粒子群算法的宽带真延时平面阵列方向图综合

针对大阵元间距平面阵列方向图综合问题,提出基于粒子群算法的宽带真延时平面阵列方向图综合方法。该方法根据真延时条件下阵列方向图主瓣和栅瓣指向的特点,采用宽带真延时抑制阵列方向图的栅瓣;利用粒子群优化算法优化阵列结构,得到具有较高主副瓣比的平面阵列方向图。通过对8×8的矩形平面阵进行仿真,验证了所提方法的有效性,在此基础上,还仿真研究了该方法对栅瓣的抑制性能与信号带宽之间的关系。     

基于遗传算法的目标分配优化模型研究

结合现代防空作战的特点,给出了现代防空作战的目标分配模型,利用遗传算法给出了模型求解的方法及步骤;实践证明该方法解题速度快,结果的精度高,可以为决策者作出科学、准确的决策提供有力支持。     

自适应逆控制FXLMS算法有源噪声控制仿真研究

前馈有源噪声控制方法可在较宽的频带有效,使之获得了广泛的应用.在前馈有源噪声控制中,直接使用传统的FXLMS算法时,由于次级通道传递函数往往是非最小相位系统,导致系统的性能下降.文中提出一种基于非最小相位系统逆控制的自适应前馈有源噪声控制FXLMS算法,用带宽随机噪声信号和实测风机通风管道噪声信号进行仿真实验研究,结果表明,较传统的FXLMS算法有明显的改进.     

激光制导炸弹弹道拟合模型与算法

由于激光制导炸弹的弹道受控,其弹道复杂,采用传统炸弹弹道的拟合方法达不到精度要求。从抛物运动的角度提出了两种对激光制导炸弹弹道拟合的方法。第一种方法对一般的抛物运动标准解引入修正项实现对激光制导炸弹弹道的拟合。第二种方法对激光制导炸弹的攻击运动过程进行分析,然后,引入加速度修正项对激光制导炸弹弹道进行拟合。通过大量的仿真表明这两种方法的拟合精度均很高。相比较而言,第二种方法精度更高。     

单机攻击多目标逻辑的遗传优化求解

攻击逻辑的优化决策对于机载多目标攻击武器系统具有重要意义。本文建立了单机多目标攻击逻辑的解算模型 ,提出了解算要求 ,给出了采用遗传算法求解多目标攻击逻辑的应用方案。在此基础上 ,采用该方案进行大量的试探性仿真研究 ,对仿真结果进行了分析 ,并选择了合适的遗传算法参数。文章最后阐述了用遗传算法求解多目标攻击逻辑问题的发展前景