基于QPSO算法的支持向量机参数优化研究

应用具有量子行为的粒子群优化算法,对支持向量（SVM）进行参数优化研究．根据支持向量机的分类准确率和泛化能力之间的关系,应用QPSO算法选取比较优秀的参数模型,比较参数模型的各项性能,选取最适合实际需要的参数模型．仿真表明,QPSO算法的SVM模型与PSO算法相比在分类准确率和泛化能力上均获得更好的效果,经QPSO优化后的SVM整体性能明显提高．     

两种解相关算法的DOA估计性能研究

MUSIC算法能对独立信号的波达方向（DOA）进行有效估计,但该算法对相干信号或强相关信号进行DOA估计时,算法性能会随着相关系数的增加而急剧恶化甚至失效．针对该问题,利用前后向空间平滑技术与修正MU—SIC算法进行去相关,研究了它们去相关的基本原理及优缺点;利用MUSIC算法通过实验仿真对相关信号的波达方向估计性能进行了研究,分析了信号间相关系数对前后向空间平滑算法与修正MUSIC算法的测向性能的影响,并验证了算法去相关的有效性．     

空战截击引导航线自动生成算法研究

以等角航线作为截击引导航线计算的基础,研究了满足战术要求的截击引导航线自动生成方法,提出了基于前置点滑动搜索的截击引导航线优化生成算法（LPMSOA,lead-point moving search optimal algorithm)。LPMSOA算法采用二分搜索思想,以到达时间差为优化准则,通过对预定敌机前置点的滑动搜索来寻找最优前置点,通过飞行航迹长度最小化获得最短截击时间,在此基础上对最优截击引导航线进行解算。仿真实验表明,LPMSOA能有效解决空战截击引导航线自动生成问题,算法实时性强,计算精度高。     

固-液旋流分离器结构优化模拟研究

采用计算流体力学方法与流体动力学分析软件Fluent,探讨了固-液旋流分离器的溢流口直径、锥角、圆柱段长度和入口直径等主要结构参数对其颗粒溢流率的影响,并在此基础上进行结构参数的优化。结果表明,锥角、圆柱段长度和入口直径过大或过小都不利于旋流分离器的固液分离,均存在一个最佳值。对于主直径为75 mm的单锥双入口固-液旋流分离器,最佳圆柱段长度为87.0 mm,最佳入口直径为16.0 mm,最佳溢流口直径为16.5 mm,最佳锥角为6.0°。     

装备体系结构优化可行方案空间构建方法

针对装备体系结构方案数量规模较大及传统构建方法效率较低的问题,以单一费用约束条件下的装备体系结构优化问题为例,提出了一种可行空间构建的新方法,试图缩小体系成员的遍历范围,减少运算量,提高体系结构可行方案空间的构建效率。最后,利用Matlab软件对新算法进行数值模拟与仿真,并与传统方法进行了比较,结果表明:新方法的计算效率得到了明显提高。     

基于变异离散粒子群的协同空战攻击决策算法

为了提高智能协同空战攻击决策算法性能,将变异策略引入到DPSO(Discrete Particle Swarm Optimization)协同空战攻击决策算法中,提出了一种新的基于变异离散粒子群(Mutation Discrete Particle Swarm Optimization,MDPSO)的协同空战攻击决策算法。基于典型空战想定背景,仿真验证了算法的有效性。采用对比实验方法,基于准确性、可靠性和快速性等关键性能指标,分析比较了基于MDPSO协同空战攻击决策算法与多种智能决策算法,验证了基于MDPSO的协同空战攻击决策算法有着较好的综合性能。     

基于遗传算法的涡轮增压器叶轮优化设计

提出了一种基于遗传优化理论的涡轮增压器叶轮的优化设计方法,论述了以涡轮增压器叶轮能量损失最小为目标函数,以叶轮叶片进口角、进口直径、进口宽度、出口直径、叶片数、出口角为设计变量的涡轮增压器叶轮的优化设计模型及优化计算的方法,数值计算表明,这种算法可以方便地求得具有最小涡轮损失的涡轮叶形参数.     

多级可修备件库存的生灭过程建模与优化

针对VARI-METRIC模型在低可用度下结果不准确的问题,建立基于生灭过程的任意等级、任意层级可修件库存优化模型。通过对各级站点、各类备件需求率与到达率的预测,对每个部件建立其生灭过程模型,并提出基于生灭过程的装备可用度计算方法。以整个保障系统的装备可用度为约束指标,以备件总购置费最低为目标,利用边际算法得到最优备件配置方案,并建立仿真模型对所得优化方案进行评估与调整。结合算例,以仿真结果作为检验标准,选取权威的VMETRIC软件与该解析模型在优化性能、计算精度及适用性上进行对比和说明。结果表明,无论是解析模型还是VMETRIC软件,均存在一定的适用范围,而采用解析与仿真相结合的方法无疑具有更强的适应性。     

Optimal service and arrival rates in Jackson queueing networks

In this paper we present an algorithm for solving a class of queueing network design problems. Specifically, we focus on determining both service and arrival rates in an open Jackson network of queueing stations. This class of problems has been widely studied and used in a variety of applications, but not well solved due to the difficulty of the resulting optimization problems. As an example, consider the classic application in computer network design which involves determining the minimum cost line capacities and flow assignments while satisfying a queueing performance measure such as an upper limit on transmission delay. Other application areas requiring the selection of both service and arrival rates in a network of queues include the design of communication, manufacturing, and health care systems. These applications yield optimization problems that are difficult to solve because typically they are nonconvex, which means they may have many locally optimal solutions that are not necessarily globally optimal. Therefore, to obtain a globally optimal solution, we develop an efficient branch and bound algorithm that takes advantage of the problem structure. Computational testing on randomly generated problems and actual problems from a health care organization indicate that the algorithm is able to solve realistic sized problems in reasonable computing time on a laptop computer. © 2000 John Wiley & Sons, Inc. Naval Research Logistics 47: 1–17, 2000     

Optimal (τ, T) opportunistic maintenance of a k‐out‐of‐n:G system with imperfect PM and partial failure

The opportunistic maintenance of a k‐out‐of‐n:G system with imperfect preventive maintenance (PM) is studied in this paper, where partial failure is allowed. In many applications, the optimal maintenance actions for one component often depend on the states of the other components and system reliability requirements. Two new (τ, T) opportunistic maintenance models with the consideration of reliability requirements are proposed. In these two models, only minimal repairs are performed on failed components before time τ and the corrective maintenance (CM) of all failed components are combined with PM of all functioning but deteriorated components after τ; if the system survives to time T without perfect maintenance, it will be subject to PM at time T. Considering maintenance time, asymptotic system cost rate and availability are derived. The results obtained generalize and unify some previous research in this area. Application to aircraft engine maintenance is presented. © 2000 John Wiley & Sons;, Inc. Naval Research Logistics 47: 223–239, 2000