Zero‐attracting variable‐step‐size least mean square algorithms for adaptive sparse channel estimation

Recently, sparsity‐aware least mean square (LMS) algorithms have been proposed to improve the performance of the standard LMS algorithm for various sparse signals, such as the well‐known zero‐attracting LMS (ZA‐LMS) algorithm and its reweighted ZA‐LMS (RZA‐LMS) algorithm. To utilize the sparsity of the channels in wireless communication and one of the inherent advantages of the RZA‐LMS algorithm, we propose an adaptive reweighted zero‐attracting sigmoid functioned variable‐step‐size LMS (ARZA‐SVSS‐LMS) algorithm by the use of variable‐step‐size techniques and parameter adjustment method. As a result, the proposed ARZA‐SVSS‐LMS algorithm can achieve faster convergence speed and better steady‐state performance, which are verified in a sparse channel and compared with those of other popular LMS algorithms. The simulation results show that the proposed ARZA‐SVSS‐LMS algorithm outperforms the standard LMS algorithm and the previously proposed sparsity‐aware algorithms for dealing with sparse signals. Copyright © 2015 John Wiley & Sons, Ltd.     

自适应滤波器的新型变步长算法及其应用

针对变步长算法的选取对自适应滤波器的性能有重大的影响,而常见变步长算法的步长与误差或输入信号有关,在自适应调节过程中步长存在较大的波动,影响自适应滤波器的滤波效果等问题,通过分析和比较常见的变步长算法,提出一种新型变步长算法.该算法先将误差信号取绝对值,然后再求其均值,以该均值决定步长的变化,克服步长波动的不足.采用新...     

一种改进的变步长LMS自适应算法

为了得到一种抗干扰性能强、收敛速度快、稳态误差小的变步长LMS算法,本文分析了传统LMS算法、变步长LMS算法及其改进算法,并对现有变步长LMS算法进行分类归纳,在列出几种具有代表性算法的基础上,提出了一种改进的变步长LMS算法.新方法引入修正系数,通过当前和过去估计误差以及误差的时域均值来调节自适应算法的步长,具有收敛速度快,稳态误差小的优点,并且提高了LMS算法的抗干扰性能.文中最后给出了仿真结果,仿真结果与理论分析一致.     

Novel combination schemes of individual weighting factors sign subband adaptive filter algorithm

To improve the performance of the recently presented individual weighting factors sign subband adaptive filter (IWF‐SSAF) algorithm, its 2 combination algorithms using different step sizes are proposed. The first algorithm is to convexly combine the weight vectors of a large step‐size IWF‐SSAF filter and a small step‐size one; and the second algorithm is to obtain a time‐varying step size for the IWF‐SSAF by combining a large step size and a small one. The minimization of the sum of the l₁‐norm of subband errors is used to indirectly update the mixing parameters in these 2 algorithms through a modified sigmoidal function. Moreover, in the first algorithm, to implement a smooth transition from the large step‐size IWF‐SSAF filter to the small step‐size one, the component filters receive a cyclic feedback of the combined weight vector. Both proposed algorithms have almost the same convergence performance, but the second algorithm saves computational cost. Simulation results in impulsive noise scenarios demonstrate the superiority of our proposed algorithms.     

基于自适应变步长最小均方的谐波检测算法的研究

从数字信号处理中的自适应噪声对消原理出发,介绍了一种改进的变步长最小均方(LMS)算法,该算法根据基波电流和谐波电流的不相关性,利用误差信号和参考输入的互相关估计来控制迭代步长,使得步长的更新不受谐波电流的影响。该算法原理简单,运算量小,易于实现,仿真结果表明了该谐波电流检测算法的有效性。     

一种改进的自适应谐波检测方法及其应用

提出了一种改进的变步长自适应算法,将其运用于有源电力滤波器中的谐波电流检测中,取得了很好的效果。在常见的变步长自适应算法中,步长与误差或者输入信号有关,而在自适应的调节过程中,步长存在较大的波动,影响谐波电流检测的准确性。改进的自适应算法首先对误差信号加绝对值,接着对其求均值并以该均值来控制步长的变化,从而克服了步长波动的不足。该算法不但具有较快的动态响应,而且提高了谐波检测的精度。通过MATLAB仿真验证了该算法的可行性和有效性。     

Set‐theoretic adaptive filtering based on data‐driven sparsification

In this article, we propose a fast and efficient algorithm named the adaptive parallel Krylov‐metric projection algorithm. The proposed algorithm is derived from the variable‐metric adaptive projected subgradient method, which has recently been presented as a unified analytic tool for various adaptive filtering algorithms. The proposed algorithm features parallel projection—in a variable‐metric sense—onto multiple closed convex sets containing the optimal filter with high probability. The metric is designed based on (i) sparsification by means of a certain data‐dependent Krylov subspace and (ii) maximal use of the obtained sparse structure for fast convergence. The numerical examples show the advantages of the proposed algorithm over the existing ones in stationary/nonstationary environments. Copyright © 2011 John Wiley & Sons, Ltd.     

基于自适应滤波算法的谐波仿真分析

为改善自适应滤波算法的滤波效果,减小稳态误差,提高跟踪响应速度,并验证改进的变步长LMS滤波算法的有效性和优越性,利用电磁暂态仿真软件PSCAD/EMTDC,构建电网谐波仿真计算模型,并与传统的基于瞬时无功功率理论的p-q算法以及定步长LMS算法进行仿真比较,根据不同系统条件下的滤波仿真波形,进行快速傅里叶分析,验证了此改进变步长LMS算法在计算量增加不多的前提下,可以同时获得较好的跟踪速度和较小的稳态误差,证实了该算法的有效性。     

改进变步长LMS算法在软起动谐波检测中的应用

针对现有自适应变步长最小均方(LMS)谐波电流检测算法在低信噪比环境中易受干扰影响,提出一种改进自适应变步长LMS算法。该算法将误差信号与前一工频周期误差信号的差值作为反馈量,结合箕舌线函数构造出随动的动态因子,将此动态因子也作为调节权值的动量因子,利用自相干估计误差控制步长。该算法折中考虑收敛速度和稳态精度,并有效降低噪声信号的干扰。通过对电机软起动器工作过程中产生的周期重复性谐波进行检测和分析,证明了该谐波电流检测算法的可行性。     

Extension of LMS stability condition over a wide set of signals

A sufficient condition for least mean squares (LMS) algorithm stability with a small set of assumptions is derived in this paper. The derivation is not, contrary to the majority of currently known conditions, based on the independence assumption or other statistic properties of the input signals. Moreover, it does not make use of the small‐step‐size assumption, neither does it assume the input signals are stationary. Instead, it uses a theory of discrete systems and properties of a discrete state‐space matrix. Therefore, the result can be applied to a wide set of signals, including deterministic and nonstationary signals. The location of all eigenvalues of the matrix responsible for the LMS algorithm stability has been calculated. Simulation experiments, where the step size reaches a couple of hundreds without loss of stability, are shown to support the theory. On the other hand, simulation where the calculations based on the small‐step‐size theory provide a too large estimation of the upper bound for the step size, while the new condition gives a proper solution, is also presented. Therefore, the new condition may be used in cases where fast adaptation is necessary and when the independence theory or the small‐step‐size assumptions do not hold. Copyright © 2014 John Wiley & Sons, Ltd.     

一种改进的自适应谐波电流检测方法

针对现有的基于双曲正切函数变步长LMS算法的谐波电流检测仍存在稳态误差和收敛速度不能同时满足要求的问题,分析了一种在基于双曲正切函数变步长LMS算法的基础上改进的变步长算法,利用误差的时间均值估计建立步长与误差之间的新型双曲正切函数关系以控制步长的更新,降低稳态误差,提高算法的检测精度。并且同时对权值采用两次迭代更新,将两次迭代的结果作为新的权值,以加快权值的更新速度,提高算法的收敛速度。该算法具有较高的检测精度的同时还有较快的响应速度。Matlab/Simulink的仿真结果证明了该算法用于谐波电流检测具有很好的效果。     

基于自适应算法的谐波检测方法研究

由于低通滤波器的影响,传统的ip-iq算法有检测速度慢的缺点,针对此缺点,本文提出了一种基于变步长LMS/LMF算法自适应滤波器来代替低通滤波器的作用,针对输入信号的特点相应的改变自适应滤波器的步长因子,同时改变最小均方算法(LMS)和最小四阶矩算法(LMF)的比例,充分发挥了LMF和LMS检测精度和检测速度的优势。仿真结果表明,提出的算法检测速度和精度具有明显的优势,具有一定的工程应用价值。     

Audio source separation: solutions and problems

The problem of separating out a number of audio sources observed from an array of microphones in a real room environment has received a great deal of attention in the past decade. While there are now a number of workable methods that can even deal with relatively high reverberation (IEEE Trans Audio Speech Process, 2003; 11 :489–497), a number of interesting problems still remain. In this paper, the authors review the methods based around independent component analysis, discussing the various choices available in algorithm design. We then explore the issue of sensitivity to speaker movement which appears to impose fundamental limitations on BSS performance. Copyright © 2004 John Wiley & Sons, Ltd.     

自适应变步长MPPT算法

为减小光伏电池因环境变化造成的功率损失,提高系统的光电转换效率及跟踪响应速度,在传统电导增量法的基础上结合自适应变步长最小均方差LMS(least mean squre)算法,提出了一种自适应变步长最大功率跟踪算法,并在Matlab环境下利用SimPowerSystem功能模块建立了光伏电池的数学模型及自适应变步长算法...     

基于声传感器阵的舰船被动定向研究

在被动声探测设备中声传感器阵对舰船目标宽带噪声源的精确定向取决于时延估计的精度,针对这一问题,将自适应参量模型算法与变步长的 LMS算法相结合,提出了一种可高精度估计任意时延,且收敛速度快的时延估计算法.结合舰船辐射宽带噪声,以正四面体声传感器定向阵列为例进行了计算机仿真,仿真结果表明：该方法估计所得的方位角误差小于0.1°,俯仰角误差小于1°,实现了对舰船目标宽带噪声源的精确定向,具有很好的工程实用价值.     

Transient analysis of diffusion least‐mean squares adaptive networks with noisy channels

In this paper, we study the effect of noisy channels on the transient performance of diffusion adaptive network with least‐mean squares (LMS) learning rule. We first drive the update equation of diffusion LMS which incorporates the effects of noisy channels. Then, using the framework of fundamental weighted energy conservation relation, we derive closed‐form expressions for learning curves in terms of mean‐square deviation and excess mean‐square error. We also find the mean and mean‐square stability bounds of step‐size for diffusion LMS with noisy channels. We show that although noisy channels affect the performance of the diffusion LMS network, the stability bounds of the step‐size are the same form as in the ideal channels case. The derived closed‐form expressions are shown to provide a good match with values found by simulation. Copyright © 2011 John Wiley & Sons, Ltd.     

On complete stability of linear and quadratic programming neural networks

The paper addresses complete stability (CS) of the important class of neural networks to solve linear and quadratic programming problems introduced by Kennedy and Chua (IEEE Trans. Circuits Syst., 1988; 35 : 554). By CS it is meant that each trajectory converges to a stationary state, i.e. an equilibrium point of the neural network. It is shown that the neural networks in (IEEE Trans. Circuits Syst., 1988; 35 : 554) enjoy the property of CS even in the most general case where there are infinite non‐isolated equilibrium points. This result, which is proved by exploiting a new method to analyse CS (Int. J. Bifurcation Chaos 2001; 11 : 655), extends the stability analysis by Kennedy and Chua (IEEE Trans. Circuits Syst., 1988; 35 : 554) to situations of interest where the optimization problems have infinite solutions. Copyright © 2002 John Wiley & Sons, Ltd.     

基于系数估值约束的改进LMS自适应滤波算法

为提高扩散LMS自适应滤波算法的收敛速度和保持较低的稳态误差,在扩散LMS算法基础上,提出一种基于参数估计值约束的分布式自适应网络滤波算法,算法在迭代收敛过程中,根据相邻迭代过程参数估计值差值约束实现自适应的调整步长大小,从而使得算法在估计初期采用较大步长以加速收敛,而在估计后期自适应的调整步长以保持较低的稳态误差。对比实验结果表明:相比于现有其他算法,所提算法在进行分布式估计时性能更优。     

基于变步长LMS自适应陷波算法的电气信号频率测量

提出一种基于二阶无限冲击响应(IIR)变步长自适应数字陷波滤波器的电气信号频率跟踪测量算法。论述了陷波滤波器能够滤除信号中特定的频率,而其他的频率成分不受影响的原理;最小均方LMS(LeastMeanSquare)自适应陷波算法是将被谐波和随机噪声污染的电气信号通过基波陷波器,根据陷波器输出误差采用变步长因子的递推LMS自适应修正陷波器参数和跟踪频率的变化。实例中,给出了给定变步长迭代公式的常数以计算出频率,并采用频率稳定时的测量、频率波动时的测量、电机运行频率测量的3种仿真结果表明所提出的频率跟踪测量算法效果良好。     

A unified framework for gradient algorithms used for filter adaptation and neural network training

In this paper we present in a unified framework the gradient algorithms employed in the adaptation of linear time filters (TF) and the supervised training of (non-linear) neural networks (NN). the optimality criteria used to optimize the parameters H of the filter or network are the least squares (LS) and least mean squares (LMS) in both contexts. They respectively minimize the total or the mean squares of the error e(k) between an (output) reference sequence d(k) and the actual system output y(k) corresponding to the input X(k). Minimization is performed iteratively by a gradient algorithm. the index k in (TF) is time and it runs indefinitely. Thus iterations start as soon as reception of X(k) begins. the recursive algorithm for the adaptation H(k – 1) → H(k) of the parameters is implemented each time a new input X(k) is observed. When training a (NN) with a finite number of examples, the index k denotes the example and it is upper-bounded. Iterative (block) algorithms wait until all K examples are received to begin the network updating. However, K being frequently very large, recursive algorithms are also often preferred in (NN) training, but they raise the question of ordering the examples X(k). Except in the specific case of a transversal filter, there is no general recursive technique for optimizing the LS criterion. However, X(k) is normally a random stationary sequence; thus LS and LMS are equivalent when k becomes large. Moreover, the LMS criterion can always be minimized recursively with the help of the stochastic LMS gradient algorithm, which has low computational complexity. In (TF), X(k) is a sliding window of (time) samples, whereas in the supervised training of (NN) with arbitrarily ordered examples, X(k – 1) and X(k) have nothing to do with each other. When this (major) difference is rubbed out by plugging a time signal at the network input, the recursive algorithms recently developed for (NN) training become similar to those of adaptive filtering. In this context the present paper displays the similarities between adaptive cascaded linear filters and trained multilayer networks. It is also shown that there is a close similarity between adaptive recursive filters and neural networks including feedback loops. The classical filtering approach is to evaluate the gradient by ‘forward propagation’, whereas the most popular (NN) training method uses a gradient backward propagation method. We show that when a linear (TF) problem is implemented by an (NN), the two approaches are equivalent. However, the backward method can be used for more general (non-linear) filtering problems. Conversely, new insights can be drawn in the (NN) context by the use of a gradient forward computation. The advantage of the (NN) framework, and in particular of the gradient backward propagation approach, is evidently to have a much larger spectrum of applications than (TF), since (i) the inputs are arbitrary and (ii) the (NN) can perform non-linear (TF).