Parallel architectures for RLS with directional forgetting

Efficient parallel architectures for recursive least squares with directional forgetting are presented. Two different arrays are proposed. The first employs O(n) processors and exhibits a 1/(2n + 3) throughput rate, n being the number of parameters to be estimated. The second can achieve a 1/(n + 2) throughput rate at the expense of an O(n²) processor complexity. Both architectures make use of the UD algorithm, here properly modified so as to embody the directional-forgetting variant.     

Convergence analysis of the RLS identification algorithm with exponential forgetting in stationary ARX‐structures

The recursive least‐squares (RLS) identification algorithm is often extended with exponential forgetting as a tool for parameter estimation in time‐varying stochastic systems. The statistical properties of the parameter estimates obtained from such an extended RLS‐algorithm depend in a non‐linear way on the time‐varying characteristics and on the forgetting factor. In this paper, the RLS‐estimator with exponential forgetting is applied to time‐invariant Gaussian autoregressions with second‐order stationary external inputs, i.e.to Gaussian ARX‐processes. Approximate expressions for the asymptotic bias and covariance of the parameter estimates when the forgetting factor tends to one and time to infinity are given, showing that the bias is non‐zero and that the covariance function decays exponentially with a rate that is given by the forgetting factor. The orders of magnitude of the errors in the asymptotic expressions are also derived. Copyright © 1999 John Wiley & Sons, Ltd.     

Remarks on the mean square tracking error

The purpose of this paper is to extend recent results of Ljung and Priouret to a more general class of regressors.     

A result on the mean square error obtained using general tracking algorithms

Tracking time-varying properties is of crucial importance in all adaptive algorithms. In this contribution we study a fairly general algorithm for tracking properties of model parameters that can be described in a linear regression form (including AR models and the like). An explicit expression for the mean square error between the estimated and the true (time-varying) parameter is established. For slow adaptation this expression can be arbitrarily well approximated by a much simpler expression. The treatment differs from other related studies using weak convergence theory, averaging, etc. in that the results are not asymptotic in nature and are applicable also to the transient phase as well as over unbounded time intervals.     

基于VFFRLS算法的锂电池参数辨识

动力电池性能是影响电动汽车综合性能的关键因素,因此准确辨识锂离子电池模型的参数对后续电池系统的荷电状态估计和健康状态预测至关重要。为了提高锂离子电池模型参数辨识算法的精度,以磷酸铁锂电池作为研究对象,建立电池二阶RC等效电路模型,并采用基于变量遗忘因子的最小二乘算法对锂离子电池模型进行在线参数辨识。通过搭建测试平台进行充放电实验,基于2种不同工况的实验数据,分别用文中算法、递推最小二乘算法和传统的带遗忘因子的最小二乘算法进行参数辨识,根据辨识结果估计出的端口电压与实验测试得到的实际值的误差比较来描述文中算法辨识结果的准确度。实验结果表明,基于变量遗忘因子的最小二乘算法在锂电池参数辨识方面表现出快速的收敛性和较高的估计精度。     

基于可变遗忘因子广义RLS算法的频率估计

传统的递推最小二乘(RLS)算法有良好的抑制噪声的能力,但在非稳态环境下跟踪能力弱,导致误差大.RLS和Kalman滤波之间存在一一对应的关系,引入Kalman滤波的一步预测估计和新的状态转移矩阵,可以得到广义的RLS算法,该算法改进了跟踪能力.同时,考虑到加权遗忘因子对算法的收敛速度和跟踪能力也有很大影响,故在广义RLS算法中再引入可变的遗忘因子,以确保对时变参数的快速跟踪能力和小的参数估计误差.对基于可变遗忘因子的广义RLS自适应算法和按指数加权的传统RLS算法进行了仿真比较,分析了在稳态下加入谐波、输入幅值变化、输入频率变化等情况下,2种方法所得的频率估计值和均方误差,结果显示所提方法在精度和收敛速度上都更优越.     

Blind adaptive identification of 2‐channel systems using bias‐compensated RLS algorithm

This paper studies the problem of blind adaptive identification, which focuses on how to obtain the consistent estimation of channel characteristics when only the output signal of each transmission channel is available. To solve this problem, traditional algorithms usually construct a single‐input–multiple‐output system resorting to the technique of antenna array or time oversampling. However, they simply suppose that the noise of each channel is known a priori or balanced, which cannot always be satisfied in practice. Therefore, considering the practical situation where the noise of each transmission channel is both unknown and unbalanced, a bias‐compensated recursive least‐squares algorithm is proposed, which can estimate the unbalanced noises in real time and obtain the consistent estimation of channel characteristics. Simulation results illustrate the good performance of the proposed algorithm under different signal‐to‐noise‐ratio conditions.     

基于正交投影与多新息RLS的PMSM参数辨识

针对永磁同步电机参数辨识过程中收敛速度慢的问题,提出基于正交投影与多新息递推最小二乘相结合的算法来估计永磁同步电机参数。选择永磁同步电机四阶非线性状态空间模型的数学方程,将此模型改写为线性回归模型的形式,省略线性化过程。在仿真过程中加入噪声到电机的运行系统中,来模拟真实的电机运行环境,然后将正交投影与多新息递推最小二乘的结合算法分阶段配合应用于永磁同步电机的线性回归模型中进行参数辨识。辨识结果显示出了该结合算法的有效性。     

Some asymptotic results in recursive identification using laguerre models

This paper deals with recursive identification of time-varying systems using Laguerre models. Laguerre models generalize finite impulse response (FIR) models by using a priori information about the dominating time constants of the system to be identified. Three recursive algorithms are considered: the stochastic gradient algorithm, the recursive least squares algorithm and a Kalman-filter-like recursive identification algorithm. Simple and explicit expressions for the model quality are derived under the assumptions that the system varies slowly, that the model is updated slowly and that the model order is high. The derived expressions show how the use of Laguerre models affects the model quality with respect to tracking capability and disturbance rejection.     

The research of superheated steam temperature control based on generalized predictive control algorithm and adaptive forgetting factor

The superheated steam temperature system of the thermal power plant has the characteristics of large inertia, nonlinearity, and strong time variation, which make it difficult to be controlled. To address these problems, this paper proposes a generalized predictive control algorithm with an adaptive forgetting factor. First, based on a fuzzy algorithm and a recursive least squares algorithm, the controlled object's model can be quickly and accurately obtained with the adaptive forgetting factor in real time. It overcomes the nonlinear and time-varying problems of the controlled object in the control progress. Meanwhile, it also solves the problem of data saturation and the weight assignment of the “new and old” data during online identification. Second, an adaptive generalized predictive controller algorithm has been developed with the controlled object. It solves the large inertia problem of the controlled object. Finally, through establishing simulation model of the superheated steam temperature system and simulating, the results show that the proposed method has better control performance, antidisturbance ability, adaptability, and robustness. Moreover, it has a certain reference significance for the design of a practical control system.     

基于RLS的永磁同步电机离线参数辨识研究

为了获取准确的电机参数以提高电机驱动系统的控制性能,针对面贴式永磁同步电机,通过直流注入的方式,采用递推最小二乘法(RLS)对定子电阻和电感进行离线辨识。辨识方法为在α轴注入阶跃激励电压在稳态阶段辨识电阻,在阶跃过渡过程中辨识电感。辨识中通过补偿驱动器因死区时间及IGBT、续流二极管导通压降造成的电压误差来提高电阻辨识结果的准确性。并通过加入基值电压的方式消除这些因素对电感辨识的影响。最后,通过仿真和实验验证了所提方法的正确性和实用性。     

Harmonic estimation using RLS algorithm and elimination with improved current control technique based SAPF in a distribution network

This paper presents the application of well known recursive least square (RLS) harmonic estimation technique and its elimination with improved current control technique based shunt active power filter (SAPF) in a distorted power network. The estimation of amplitude and phase angle of fundamental and harmonics is performed using RLS algorithm, known for their simplicity of computation, accuracy and good convergence properties. The estimates are updated recursively as samples of the harmonic signals are received. In order to eliminate harmonics produced by the nonlinear load connected in the distribution network, a three-phase SAPF with modified current control technique is employed. In this paper, based on the analysis and modeling of SAPF with closed-loop control, a feed forward compensation path of load current and a new pulse width modulation (PWM) control scheme is proposed to improve the dynamic performance of the SAPF. In this case the amplitude and phase angle of the converter AC voltage should be adjusted using PWM, thus producing either leading or lagging reactive power. Harmonic contented in the signal is estimated at the point of common coupling (PCC) with and without SAPF. The comparative results of amplitude and phase angle of fundamental and selected harmonics are determined considering installation of SAPF in the distribution network. The system is studied using MATLAB environment to justify the effectiveness of proposed control technique in comparison to the other techniques discussed in the recent literature.     

On-line identification of continuous time-delay systems using the genetic algorithm

This paper proposes a new kind of on-line identification method of continuous time-delay systems from sampled input-output data. In order to track the time-varying system parameters as well as time-delay, the recursive linear least squares (RLS) method is combined in a bootstrap manner with the genetic algorithm (GA) which has a high potential for global optimization. The time-delay is coded into binary bit strings and searched by the GA, while the system parameters are updated by the RLS method. Furthermore, this method (GALS method) is hybridized with the sequential nonlinear least squares method to improve the speed of convergence. Simulation results show that both the GALS and hybrid methods are efficient in the case that the system changes abruptly, and among them the hybrid method has superior convergence property to the GALs method and yields excellent estimation results in the case that the system changes with time continuously.     

MUSIC算法的性能分析与改进

使用均匀线性天线阵列雷达,在MUSIC小波预处理方法的基础上对其进行改进,将小波预处理MUSIC算法改进成小波包预处理MUSIC算法,并将其与旋转不变子空间算法(ESP RIT)算法、最大似然估计法(MLE)算法和小波预处理MUSIC算法进行仿真比较,通过计算机仿真结果证明,改进后的小波包预处理MUSIC法比小波预处理MUSIC方法具有更高的精确度和更好的稳定性.     

Box-Jenkins模型阶次与参数同时估计的递推算法

研究了Box—Jenkins模型阶次与参数的同时估计问题．基于信息压缩阵的UD分解技术和广义增广最小二乘原理，提出Box-Jenkins模型阶次与参数同时估计的一种递推算法，减少了辨识计算量，改善数值稳定性，提高了辨识精度．仿真结果表明该算法的有效性。     

基于PSO优化最小二乘支持向量机的热工系统辨识

在用最小二乘支持向量机(LS-SVM)辨识大迟延对象时,正则化参数、核宽度以及模型类中的迟延时间多是根据经验估测的,而不同的参数值对最小二乘支持向量机辨识的精度就会不同.针对上述问题,采用粒子群优化(PSO)算法对热工辨识系统中的相关参数进行优化.对电厂一次风量数据和平均床温数据进行的仿真实验结果表明,在用LS-SVM对大迟延对象进行辨识时,通过PSO算法进一步确定其最佳参数及迟延时间,能够有效地提高辨识精度.     

基于RLS法的锂离子电池离线参数辨识

提出一种基于递推型最小二乘法(RLS)算法改进的离线参数识别方法,采用RLS法作为离线参数辨识的初值,以解决离线辨识初值选择的限制,并能保证辨识结果的精度。采用RLS算法辨识参数,获取模型参数,仿真电压和实验电压最大误差达100 m V,但耗时仅120 s。采用Simscape模型的离线参数辨识方法,最大误差58 m V,耗时1. 8 h;利用RLS算法获取初值,用离线参数辨识方法,最大误差为31 m V,平均误差15 m V,耗时0. 5 h。辨识精度与辨识速度都有明显的提升。     

Harmonic estimation in a power system using a novel hybrid Least Squares-Adaline algorithm

Nowadays many algorithms have been proposed for harmonic estimation in a power system. Most of them deal with this estimation as a totally nonlinear problem. Consequently, these methods either converge slowly, like GA algorithm [U. Qidwai, M. Bettayeb, GA based nonlinear harmonic estimation, IEEE Trans. Power Delivery (December) 1998], or need accurate parameter adjustment to track dynamic and abrupt changes of harmonics amplitudes, like adaptive Kalman filter (KF) [Steven Liu, An adaptive Kalman filter for dynamic estimation of harmonic signals, in: 8th International Conference On Harmonics and Quality of Power, ICHQP’98, Athens, Greece, October 14–16, 1998]. In this paper a novel hybrid approach, based on the decomposition of the problem into a linear and a nonlinear problem, is proposed. A linear estimator, i.e., Least Squares (LS), which is simple, fast and does not need any parameter tuning to follow harmonics amplitude changes, is used for amplitude estimation and an adaptive linear combiner called ‘Adaline’, which is very fast and very simple is used to estimate phases of harmonics. An improvement in convergence and processing time is achieved using this algorithm. Moreover, better performance in online tracking of dynamic and abrupt changes of signals is the result of applying this method.     

基于DSP自动准同期装置可靠捕捉合闸时机的研究

利用DSP快速计算能力,实时采集、计算系统侧和待并侧频差、压差及角差,对待并侧电压量实现自适应采样,利用外部中断来快速响应角差变化,采用最小二乘拟合曲线的方法来计算角差变化率以及采用特定的机制来保证同期合闸的快速性及准确性。