一种新的变步长LMS自适应滤波算法性能分析

在简单介绍了基本的LMS,NLMS自适应滤波算法的基础上,介绍了一种新的可变步长LMS自适应滤波算法,并将该算法应用于自适应噪声对消系统的仿真中.通过计算机仿真,给出了LMS、NLMS和新的可变步长LMS自适应滤波三种算法的性能对比,结果表明该算法具有较快的收敛速度和较小的稳态误差.     

基于多尺度小波变换的变步长LMS滤波算法

对LMS自适应算法、基于抽样函数的变步长LMS算法和基于多尺度小波变换的自适应滤波算法进行了研究,在此基础上把变步长LMS算法与多尺度小波变换相结合,产生了新算法。该算法一方面可以克服固定步长LMS算法在收敛速度与收敛精度方面与步长因子的矛盾;另一方面,小波变换的引入减少了输入向量自相关矩阵的条件数,提高了收敛速度、跟踪性能和稳定性。最后对算法的性能进行了计算机仿真比较,仿真结果表明:基于多尺度小波变换的变步长LMS滤波算法具有较快的收敛速度和更强的抑噪能力。     

基于分式函数的新变步长LMS算法

为了解决传统LMS算法在稳态误差和收敛速度之间的矛盾,提出了一种基于分式函数的新型变步长LMS算法(简称VXLMS算法)。因为新型变步长函数不包含指数运算,所以降低了运算量,加快了算法的收敛速度,同时也提高了数据跳变时的跟踪性能。在VXLMS算法收敛的条件下,通过理论推导确定了该变步长函数的参数取值范围,然后通过取不同参数值分析对算法性能的影响,选出最优参数值进行仿真分析。仿真结果表明:相同仿真条件下提出的VXLMS算法相对于VSSLMS算法和SVSLMS算法稳态误差更低、收敛速度更快,即说明提出的小计算量新变步长函数,通过调整步长因子使权向量快速达到最优,进而使VXLMS算法具有更好的收敛性、稳定性以及鲁棒性。     

一种新的变步长LMS自适应滤波算法研究及其应用

变步长LMS自适应滤波算法克服了传统自适应滤波算法的不足,通过构造合适的变步长因子,在提高收敛速度的同时保证了较小的稳态误差,在实际中得到了广泛应用。为进一步改善算法性能,首先对传统的和现有改进的变步长LMS算法机理进行了深入分析,在此基础上,提出了一种新的变步长LMS自适应滤波算法。该算法通过建立一个新的步长因子与误差的非线性函数模型,使得算法在不失精度的情况下,具有较快的收敛速度。论文对新算法的机理进行了较为详尽的阐述,对算法中关键参数的选取对滤波性能的影响进行了深入分析,并给出了算法中关键参数的自适应确定方法。仿真实验表明,相对于其他自适应滤波算法,该算法在收敛速度方面有了很大的提高。将新算法应用于对实际龙口水位监测数据的滤波中,取得了良好效果。     

限幅的变步长BP算法

针对BP算法学习速度慢和易陷入局部最优等缺陷,提出了一种新的变步长算法--限幅的变步长算法CVLBP.这种算法根据误差来调整下次的学习步长,同时把步长限制在一定范围内,这样在计算量增加很少的情况下,使学习时间大为缩短的同时,也避免了过多的振荡,防止了系统的发散.仿真结果表明,该算法具有跳出局部最优的能力,同时对初始权值和闻值具有一定的鲁棒性.     

基于变步长自适应陷波器的在线检重抗振方法研究

针对检重秤运动部件与外壳之间的相对运动以及机械固有频率点在外力作用下发生的共振对称量信号造成干扰,提出一种基于箕舌线改进的变步长最小均方(LMS)自适应陷波(ANF)的检重秤抗振动方法。通过分析检重秤振动来源与振动特性,并在共振状态下与滑窗滤波、巴特沃斯低通、巴特沃斯陷波以及固定步长LMS陷波等传统抗振方式进行仿真和实验对比,证明变步长LMS自适应陷波器对振动干扰滤除具有准确性与优越性。同时,在多种速度下运用该方法并结合滑窗与非对称切尾均值滤波在实际检重平台对检重结果进行最终处理,实现平均误差≤0. 171 g,标准偏差≤0. 240%,满足XIII(1)等级。     

一种新的LMS算法及其在明渠流量计中的应用

针对变步长LMS(least mean square)自适应滤波算法存在收敛速度慢和稳态误差比较大的问题,根据变步长滤波算法步长调整原理,提出了一种新的基于多项式的非线性变步长LMS算法,通过MATLAB仿真分析研究新算法中各参数对收敛速度和稳态误差的影响,并和已有的变步长LMS算法进行对比,结果表明该算法比已有的算法...     

一种改进变步长LMS算法及其在系统辨识中的应用

在分析传统LMS算法及变步长LMS的基础上，本文提出了一种改进的变步长LMS算法并应用于系统辨识。新算法利用瞬时误差的四次方和遗忘因子共同来调整步长，进一步解决了收敛时间和稳态误差的矛盾。将新算法应用到系统辨识中时，与传统LMS算法和变步长LMS算法相比，仿真表明新算法有更快的收敛速率。     

改进变步长自适应分布式滤波算法

为提高传统LMS算法在分布式传感器网络自适应滤波中的收敛速度并保持较小的稳态误差,在扩散LMS算法基础上,提出一种基于Sigmoid函数改进变步长的分布式扩散LMS自适应滤波算法,算法通过Sigmoid函数变换构建步长因子与迭代误差之间非线性模型,并通过设置控制因子合理调整模型的步长曲线波型,使得算法在初期使用较大的步长以加快收敛速度,而在后期则采用平稳变化步长以保持较低的稳态误差,从而在在不失传统算法稳态精度的情况下,实现较快的收敛速度。实验结果表明:相比于已有算法,所提算法的估计性能更优。     

一种改进的变步长LMS算法及其DSP实现

固定步长LMS(least mean square)算法自适应滤波器在收敛速度、时变跟踪能力与稳态误差上对步长因子的要求存在矛盾.变步长LMS算法的步长因子是变化的,能够有效地避免此矛盾.在分析了2种变步长LMS算法的基础上,提出了全新的变步长算法,并在MATLAB环境中进行仿真,之后应用SZ-EPP5402评估板对其进行了DSP实现.仿真结果与DSP实现都表明:变步长LMS算法在一定程度上改善了收敛速度与稳态误差间矛盾,具有更快收敛速度与更小稳态误差.     

Simulation and experimental design of a new advanced variable step size Incremental Conductance MPPT algorithm for PV systems

Improvement of the efficiency of photovoltaic system based on new maximum power point tracking (MPPT) algorithms is the most promising solution due to its low cost and its easy implementation without equipment updating. Many MPPT methods with fixed step size have been developed. However, when atmospheric conditions change rapidly , the performance of conventional algorithms is reduced. In this paper, a new variable step size Incremental Conductance IC MPPT algorithm has been proposed. Modeling and simulation of different operational conditions of conventional Incremental Conductance IC and proposed methods are presented. The proposed method was developed and tested successfully on a photovoltaic system based on Flyback converter and control circuit using dsPIC30F4011. Both, simulation and experimental design are provided in several aspects. A comparative study between the proposed variable step size and fixed step size IC MPPT method under similar operating conditions is presented. The obtained results demonstrate the efficiency of the proposed MPPT algorithm in terms of speed in MPP tracking and accuracy.     

LMS algorithm for active noise control with improved gradient estimate

Most existed LMS algorithms have noisy gradient estimate since they use instantaneous square error to estimate ensemble average of the square errors. In this paper, a new type of LMS algorithm is developed for active noise control. The gradient estimate in the proposed algorithm is improved by using the weighted time average instead of the instantaneous value to approximate the ensemble average. Compared to the filtered-x LMS algorithm, the proposed algorithm is shown to have many improved convergence properties. Computer simulations are given to support the theoretical analysis.     

Adaptive filter design based on the LMS algorithm for delay elimination in TCR/FC compensators

Thyristor controlled reactor with fixed capacitor (TCR/FC) compensators have the capability of compensating reactive power and improving power quality phenomena. Delay in the response of such compensators degrades their performance. In this paper, a new method based on adaptive filters (AF) is proposed in order to eliminate delay and increase the response of the TCR compensator. The algorithm designed for the adaptive filters is performed based on the least mean square (LMS) algorithm. In this design, instead of fixed capacitors, band-pass LC filters are used. To evaluate the filter, a TCR/FC compensator was used for nonlinear and time varying loads of electric arc furnaces (EAFs). These loads caused occurrence of power quality phenomena in the supplying system, such as voltage fluctuation and flicker, odd and even harmonics and unbalancing in voltage and current. The above design was implemented in a realistic system model of a steel complex. The simulation results show that applying the proposed control in the TCR/FC compensator efficiently eliminated delay in the response and improved the performance of the compensator in the power system.     

电子分析天平温度漂移补偿算法研究

基于电磁力平衡传感器的电子分析天平温度漂移影响复杂,尚无理想的解决方案。现有天平的温度漂移补偿主要依靠基于晶体管的硬件电路实现,适用温度范围窄、精度低、灵活性差。依据电磁力平衡传感器的工作机理,深入研究与天平称量结果密切相关的各元件参数温度特性,建立了电子分析天平温度漂移数学模型,对该模型进行了称量精度要求内的合理简化。通过对温度敏感元件的温度测量及测量滞后分析,提出了温度漂移的分段线性加权补偿算法,实现了温度漂移快速准确地自动补偿。检验结果表明,采用该补偿算法,量程200 g、分辨力0.1 mg的电子分析天平在18~23℃的工作温度范围内,满载示值误差的绝对值≤0.3 mg,优于国家标准《GB/T 26497-2011电子天平》规定的I级天平温度漂移对示值的影响指标。     

A new interpolation method of variable period and step size in micro-EDM milling based on square constraint

In certain applications of statistical process control, it is possible to model quality of a product or process using a multiple linear regression profile. Some methods exist in the literature which could be used for monitoring multiple linear regression profiles. However, the performance of most of these methods deteriorates as the number of regression parameters increases. In this paper, we specifically concentrate on phase II monitoring of multiple linear regression profiles and propose a new dimension reduction method to overcome the dimensionality problem of some of the existing methods. The robustness, effectiveness, and limitations of the proposed method are also discussed. Simulation results show that in term of average run length criterion, the proposed method outperforms the traditional methods and has comparable performance with another dimension reduction method in the literature.     

基于STM32的高精度电子天平

为了解决目前市面上的电子天平成本高、精度低、称量速度慢的问题,将目前工作频率高、功能强大的STM32芯片应用到电子天平的设计中,用其作为主控制器设计了一款高精度的电子天平。该设计采用内部集成24位A/D转换器和放大器的称重传感器专用芯片HX711对称重传感器输出的小信号进行处理,提高了电路的稳定性;采用数字滤波算法进行滤波,降低了电路复杂度,使性能更可靠;将A/D转换器输出的模拟信号直接数字化,然后,采用滑动均值滤波法进行了滤波;最后,进行了检定实验,开展了误差分析,分析了真实值与测量值之间的关系,并在误差分析的基础上,对天平测量准确性进行了评估。实测结果表明,该电子天平设计量程为300 g,精度为0.01 g,重复性误差和示值误差均≤0.02 g,而且称量速度快,10 s左右即可达到稳定读数。