自适应Kalman滤波器及其应用

对于带未知噪声统计的单输出系统,本文提出了一种新的自适应Kalman滤波器.应用 现代时间序列分析方法,基于ARMA新息模型的滑动平均(MA)参数的在线辨识,提出了 稳态最优Kalman滤波器增益估计的一种新算法,比Mehra的算法简单.同时还提出了辨 识滑动平均(MA)模型参数的一种新的自适应Kalman滤波算法.此外,给出了在雷达跟 踪系统中的应用,且仿真结果说明了本文算法的有效性.     

噪声背景下的盲源分离算法

分析了当存在高斯背景噪声时一类盲分离算法的性能，指出此时盲分离算法仍可用于估计解混矩阵，而输出信号为分离的源信号与高斯噪声的叠加。利用现代时间序列分析方法（MTSSAM）建立了输出信号的自回归移动平均（ARMA）新息模型，并给出了一种基于多维线性最小二乘法的信号滤渡算法。仿真试验表明，该算法稳定且收敛，可以在背景噪声存在时有效地恢复源信号的波形。     

Wiener状态去卷滤波器

应用现代时间序列分析方法,基于ARMA新息模型提出了一类带多重观测滞后和带滑动平均（MA）有色观测噪声系统的Wiener状态去卷滤波器,它具有渐近稳定性和ARMA递推形式,可统一处理滤波、平滑和预报问题,且可用于解决带ARMA有色观测噪声系统状态估计和信号Wiener滤波与反卷积问题,二个仿真例子说明了其有效性。     

ARMA序列的版参数预报*

在关于ARMA序列新息定理的基础上,本文给出了ARMA序列的一种半参数预报方法,该方法避开对ARMA模型中MA参数作估计这一计算复杂的工作,在只须知道AR参数的情况下直接得到序列的预报值,从而使计算量大为简化同时又保证有一定的精度,本文还介绍了半参数预报方法在城市自来水负荷预报中的成功应用。     

稳态Kalman滤波器增益新算法

应用现代时间序列分析方法,基于ARMA新息模型,提出了稳态Kalman滤波器增 益的两种简单的新算法,并证明了它们的等价性.应用ARMA新息模型参数的递推辨识器 伴随新算法,可实现自校正Kalman滤波器.仿真例子说明了其有效性.     

不带Diophantine方程的多通道最优去卷滤波器

用时域上的现代时间序列分析方法,基于ARMA新息模型和白噪声估值器,分别提出 了在ARMA新息滤波器形式下和在Wiener滤波器形式下的新的渐近稳定的多通道最优去卷 滤波器.它们避免了求解Diophantine方程,可统一处理去卷滤波、平滑和预报问题.还给出了 ARMA新息滤波器和Wiener去卷滤波器之间的关系.仿真例子说明了它们的有效性.     

残差初值的最小二乘估计

本文给出了一种简便的残差初值算法。该法在小样本情况下，对改善最小二乘法估计参数的精度特别有效，它不但适用于ARMA模型，而且也适用于CARMA模型和MA模型。     

MISO系统辅助模型多新息增广随机梯度算法

对于有色噪声干扰的输出误差多输入单输出（MISO）系统,常规的递推最小二乘辨识方法给出的参数估计是有偏的。为了提高随机梯度辨识方法的收敛精度和速度,用辅助模型的输出代替辨识模型信息向量中的未知不可测变量,推导出其辅助模型增广随机梯度辨识算法;再引入新息长度扩展标量新息为新息向量,提出了基于辅助模型的MISO系统多新息增广随机梯度辨识算法。所得算法在每一次的迭代中不仅使用了当前数据和新息,而且使用了过去数据和新息,提高了参数估计精度和收敛速度。仿真例子验证了算法的有效性。     

慢时变系统：指数稳定性和稳健适应控制

本文首先给出线性慢时变系统ｘ（ｔ）＝Ａ（ｔ）ｘ（ｔ）指数稳定的一个新的充分条件，进而考虑带有未建模动态和外部干扰的连续时间适应控制闭环系统的一般形式，给出了系统稳定的一些充分条件，这一结果可作为研究各种连续时间适应控制算法稳健稳定性问题的有力工具。     

稳态Kalman去卷滤波器及其应用

应用现代时间序列分析方法,基于非递推状态估计理论和ARMA新息模型,提出了含多重观测滞后系统的稳态Kalman去卷滤波器,并给出了它在跟踪系统中的仿真应用例子。     

基于变权重迁移学习的BN参数学习算法

针对小数据集条件下的贝叶斯网络(Bayesian network,BN)参数估计困难问题,提出了一种基于变权重迁移学习(DWTL)的BN参数学习算法。首先,利用MAP和MLE方法学习得到目标域初始参数和各源域参数;然后根据不同源域数据样本贡献的不同计算源权重因子;接着基于目标域样本统计量与小数据集样本阈值的关系设计了目标域初始参数和源域参数的平衡系数;最后,基于上述参数、源权重因子和平衡系数计算得到新的目标参数。在实验研究中,通过对经典BN模型的参数学习问题验证了DWTL算法的有效性;针对小数据集下的轴承故障诊断问题,相较于传统迁移学习(LP)算法,DWTL算法学习精度提高了10%。实验结果表明:所提出的算法能够较好地解决样本数据集在相对稀缺条件下的目标参数建模问题。     

一个多维数据搜索算法

本文提出了一种使用二叉树组织多维数据的数据结构,在这种结构下提出了一个区域搜索算法,确定空间中给定点的区域内所有在给定数据集中的点,搜索效率与维数无关,算法的平均时间复杂性为O(logn),为了保证算法的效率,提出了一种平衡树操作算法。     

An algebraic approach to strong stabilizability of linear nD MIMO systems

Although some necessary conditions for the strong stabilizability of linear multidimensional (nD) multiple-input-multiple-output (MIMO) systems have been available recently, very little is known about sufficient conditions for the same problem. This note presents two sufficient conditions for strong stabilizability of some classes of linear nD MIMO systems obtained using an algebraic approach. A simple necessary and sufficient condition is also given for the strong stabilizability of a special class of linear nD MIMO systems. An advantage of the proposed algebraic approach is that a stable stabilizing compensator can be constructed for an nD plant satisfying the sufficient conditions for the strong stabilizability presented in this note.     

A method for adaptive estimation of ARMA processes

When the noise process in adaptive identification of linear stochastic systems is correlated, and can be represented by a moving average model, extended least squares algorithms are commonly used, and converge under a strictly positive real (SPR) condition on the noise model. In this paper, we present an adaptive algorithm for the estimation of autoregressive moving average (ARMA) processes, and show that it is convergent without any SPR condition, and has a convergence rate of O({loglog t)/t}^1/2).     

时空谱点源目标自适应滤波检测算法

针对复杂背景下的点源弱目标检测问题,根据Wiener-Hopf方程在自适应滤波算法中的应用原理,提出了一种新的利用时间/空间/谱段的多维信息融合自适应滤波算法(ASTS filter).该方法的研究主要有3个步骤:首先研究时域、空域突出和多谱段融合的性质,然后构造出针对运动弱点目标的滤波模板,最后将自适应RLS滤波器应用于有缓动背景下的多谱红外图像检测中.由于普通的RLS滤波器应用于图像处理采用的是像素点信息作为输入参数,其造成矩阵运算计算量过大、处理时间长等缺点,而将点目标进行空间、时间、谱段特征提取后的信息作为输入参数,不仅避免了大型矩阵的运算,还可获得更高的信杂比增益.通过大量实验数据,证明本算法具有优良的滤波性能,同时突破了点目标运动的轨迹限制.与其它算法的效果和计算量进行比较,证明文中算法更为快捷、有效和灵活.     

On multivariate polynomial matrix factorization problems

This paper studies the multivariate polynomial matrix factorization problems which have applications to multidimensional systems theory and signal processing. We first extract an algorithm from Pommaret's proof of the Lin-Bose conjecture. Then we simplify our algorithm, and prove a theorem which gives a sufficient and necessary condition for a multivariate polynomial matrix to have an minor left prime (MLP) factorization. Examples are given to illustrate the effectiveness of this algorithm. Our results hold for any coefficient field and thus have a wide range of applications. This work was supported by grants from the Research Grants Council of Hong Kong (Project CUHK4185/01E) and 973 projects(G1999035802 and 2004CB318004)     

Design of closed-loop systems with bounded transmission or bounded sensitivity

This paper considers the design, in the frequency domain, of controllers for SISO plants, so that the closed-loop system is asymptotically stable, has a sensitivity function with zeros at given points in Re (s) ?0, and has a transmission or a sensitivity function bounded by a given function. The design requirements are reduced to an interpolation in Re (s) ?0, and a necessary and sufficient condition for its solution is presented. An algorithm is given for the construction of the required controllers.     

多机器人编队离散模型及队形控制稳定性分析

针对包含绕心运动情况下的多机器人编队进行离散建模,并利用该模型解决保持队形期望前端始终朝着编队前进方向的控制问题.以控制多机器人编队收敛到期望的队形并镇定到预设运动规律上为目标,定义了一类通信拓扑图,基于该类图提出了一种分布式协同控制算法.给出了该控制算法下编队系统渐进稳定的充分必要条件及反馈控制参数的收敛域.证明了在该充分必要条件下可实现编队收敛到期望的队形和预设运动规律上的目标.仿真实验表明,在该算法控制下多机器人编队较好地收敛到期望队形并按预设规律运动,且过程中始终保持队形期望前端朝着编队前进方向,进而验证了该算法的有效性和正确性.     

Moving‐image‐sticking phenomenon induced by an outside force in liquid‐crystal displays

Abstract— Image deformation caused by an outside force is observed to remain for hours at high gray levels for liquid‐crystal displays (LCDs) in the multi‐domain (MD) vertical‐alignment (VA) mode. This so‐called moving‐image‐sticking phenomenon demonstrated a non‐symmetric luminance profile for the left and right viewing direction for MDVA‐mode LCDs which have original symmetric viewing‐angle characteristics. The generation of a stable reverse‐tilt domain by an outside force was assumed to be the cause of this phenomenon, and the stability of a reverse‐tilt domain under an electric fringe field was calculated by changing the electric‐fringe‐field distribution which determines the LC tilt direction. The domain of a given tilt direction is calculated to change to other tilt direction induced by a fringe field at a low gray condition, but to remain unchanged at a high gray condition. This agrees with the observed trends of duration time of the moving‐image‐sticking phenomenon.     

Aggregation and systematic sampling of periodic ARMA processes

The aim of this work is to investigate the effects of temporal aggregation and systematic sampling on periodic autoregressive moving average (PARMA) time series. Firstly, it is shown that the class of weak PARMA processes, i.e. with uncorrelated but possibly dependent errors, is closed under a particular class of linear transformations that include both temporal aggregation and systematic sampling. This extends a similar result for autoregressive moving average processes; see [Wei, W.W.S., 2006. Time Series Analysis: Univariate and Multivariate Methods, second ed. Addison-Wesley, New York (Chapter 20)] for a review on the subject. Secondly, the properties of the noise of the transformed process are investigated. A sufficient condition is given under which aggregation and systematic sampling of a strong PARMA process, i.e. with independent errors, give rise in general to a weak PARMA process. Under that condition, the noise of the transformed process is neither strong nor a martingale difference. This result points out that the assumption of strong PARMA should not be used without careful considerations when analyzing aggregated time series that naturally occur in many scientific fields. The sufficient condition for non-independent errors is illustrated with the PARMA(1,1) model. A simulation study underlines the practical relevance of our findings and the importance of taking into account the dependence of the errors when fitting a PARMA model to an aggregated time series.