Higher‐order Markov chain models for categorical data sequences*

In this paper we study higher‐order Markov chain models for analyzing categorical data sequences. We propose an efficient estimation method for the model parameters. Data sequences such as DNA and sales demand are used to illustrate the predicting power of our proposed models. In particular, we apply the developed higher‐order Markov chain model to the server logs data. The objective here is to model the users' behavior in accessing information and to predict their behavior in the future. Our tests are based on a realistic web log and our model shows an improvement in prediction. © 2004 Wiley Periodicals, Inc. Naval Research Logistics, 2004     

基于DAC5686的线性调频信号产生方法研究

研究了基于DAC5686的线性调频信号产生方法。分析了线性调频信号及其产生原理,研究了DAC5686工作原理,设计了信号产生电路,给出了线性调频信号的实现实例．结果表明,该方法可以灵活地产生所需线性调频信号,从而满足某型地空导弹制导雷达中频接收机性能测试的需要．与传统的线性调频信号产生方法相比,该方法降低了系统设计难度,缩短了开发周期,提高了设计的可靠性,具有较高的实用价值,对于其它场合频线性调频信号的产生也具有一定的借鉴意义．     

基于循环移位和异或运算的对合线性变换研究

在对称密码算法的设计中,为达到良好的扩散作用,设计者一般均选择分支数较大的线性变换.基于循环移位和异或运算的线性变换由于其实现效率较高,已经在很多密码算法中被采用,比如分组密码SMS4、HIGHT,Hash函数SHA -2、MD6等.此外,如果线性变换是对合的,还为解密带来了方便.研究了基于循环移位和异或运算设计的对合线性变换,给出了这类线性变换的计数公式,指出它们的分支数上界为4,并讨论了循环移位的参数与分支数之间的关系,从而为基于这类运算设计的线性变换提供了理论依据.     

基于改进多模滤波算法的控制系统故障诊断

应用分层多模自适应滤波算法对控制系统的故障进行诊断时,只能识别出故障的类型,如识别出是传感器还是执行器发生故障,并不能判定出故障的大小.提出一种改进分层多模自适应滤波算法,应用此算法可使分层多模自适应滤波算法不仅可以检测出控制系统的故障类型,而且能够确定发生故障的执行器局部故障程度.将此算法应用于某无人机控制系统的故障诊断,仿真结果验证了该方法的有效性.     

A branch and bound algorithm for the minimum storage‐time sequencing problem

The minimum storage‐time sequencing problem generalizes many well‐known problems in combinatorial optimization, such as the directed linear arrangement and the problem of minimizing the weighted sum of completion times, subject to precedence constraints on a single processor. In this paper we propose a new lower bound, based on a Lagrangian relaxation, which can be computed very efficiently. To improve upon this lower bound, we employ a bundle optimization algorithm. We also show that the best bound obtainable by this approach equals the one obtainable from the linear relaxation computed on a formulation whose first Chvàtal closure equals the convex hull of all the integer solutions of the problem. © 2001 John Wiley & Sons, Inc. Naval Research Logistics 48: 313–331, 2001     

稳健局部线性嵌入方法

针对局部线性嵌入方法对于噪声的敏感性,从分析噪声对数据集局部特性的影响入手,提出了稳健局部线性嵌入方法。通过与局部线性嵌入方法的理论分析和实例对比,表明稳健局部线性嵌入方法不仅对噪声影响不敏感,而且对邻域的选择有较好的适应性,可更好地挖掘数据集的本征特性,具有更强的数据可视化能力。     

非线性干扰观测器的高超声速飞行器自适应反演控制

针对高超声速飞行器参数不确定弹性体模型,提出了一种基于非线性干扰观测器的自适应反演控制器设计方法。将曲线拟合模型表示为严格反馈形式,采用反演方法设计控制器。采用动态面方法获取虚拟控制量的导数,避免了传统反演控制"微分项膨胀"问题。为了增强控制器的鲁棒性,基于二阶跟踪-微分器设计了一种新型非线性干扰观测器,以此对模型不确定项进行自适应估计和补偿。仿真结果表明,控制器对模型不确定性和气动弹性影响具有强鲁棒性,且能实现对速度和高度参考指令的稳定跟踪。     

动圈式永磁直线直流电机的精英保留多种群遗传优化算法

为了实现陆基无人机电磁弹射器高机动性及其直线弹射电机的高功率密度,针对动圈式永磁直线直流电机,提出精英保留的多种群遗传算法(Multi-Population Genetic Algorithm with Elite Retention, MPGAER)的电机最大功率密度优化方法。以磁通密度和电流密度为约束条件,利用其搜索能力强、收敛速度快的特点优化电机的结构参数,并与磁路法初始设计结果和传统遗传算法优化结果进行比较。结果表明:与磁路法初始设计相比,MPGAER能使电机质量减少6.25%,功率密度提高10%,电机动态性能得到提高;MPGAER优化设计的电机功率密度高于遗传算法设计结果,所提方法有效地解决了在优化过程中出现易收敛于局部最优点和寻优效果差的问题。     

An optimal recursive method for various inventory replenishment models with increasing demand and shortages

We establish various inventory replenishment policies to solve the problem of determining the timing and number of replenishments. We then analytically compare various models, and identify the best alternative among them based on minimizing total relevant costs. Furthermore, we propose a simple and computationally efficient optimal method in a recursive fashion, and provide two examples for illustration. © 1997 John Wiley & Sons, Inc. Naval Research Logistics 44: 791–806, 1997     

一种新的Kronecker扩频码在盲多用户检测中的应用

当直接序列(DS-CDMA)系统中的多址干扰非常强时,自适应的盲多用户检测的性能将会严重下降.为了解决这一问题,一般的做法是增加系统的扩频增益,但是其取得的效果是有限的.本文将一种新的克罗内克(Kronecker)扩频序列应用到盲多用户检测中,该序列通过普通的扩频序列对自身作Kronecker乘积而生成.理论分析和仿真...