Recursive identification of Hammerstein systems with dead-zone nonlinearity in the presence of bounded noise

The existing identification algorithms for Hammerstein systems with dead-zone nonlinearity are restricted by the noise-free condition or the stochastic noise assumption. Inspired by the practical bounded noise assumption, an improved recursive identification algorithm for Hammerstein systems with dead-zone nonlinearity is proposed. Based on the system parametric model, the algorithm is derived by minimising the feasible parameter membership set. The convergence conditions are analysed, and the adaptive weighting factor and the adaptive covariance matrix are introduced to improve the convergence. The validity of this algorithm is demonstrated by two numerical examples, including a practical DC motor case.     

Convergence Analysis of Weighted Stochastic Gradient Identification Algorithms Based on Latest‐Estimation for ARX Models

In this paper, weighted stochastic gradient (WSG) algorithms for ARX models are proposed by modifying the standard stochastic gradient identification algorithms. In the proposed algorithms, the correction term is a weighting combination of the correction terms of the standard stochastic gradient (SG) algorithm in the current and last recursive steps. In addition, a latest estimation based WSG (LE‐WSG) algorithm is also established. The convergence performance of the proposed LE‐WSG algorithm is then analyzed. It is shown by a numerical example that both the WSG and LE‐WSG algorithms can possess faster convergence speed and higher convergence precision compared with the standard SG algorithms if the weighting factor is appropriately chosen.     

Almost sure convergence of stochastic approximation algorithms with non-additive noise

Stochastic approximation algorithms with non-additive noise are discussed. In studying strong convergence of such algorithms, traditionally one assumes that the iterates return to a bounded or compact set infinitely often, or that the function under consideration grows with certain rate. The usual projection algorithms require that the bounded projection region is known beforehand. It is desirable to weaken these ‘boundedness’ conditions. By introducing randomly varying truncations, Chen and Zhu (1986) achieved this for stochastic approximation algorithms with additive noise. Here, we extend their result to a more general setting.     

WMF self-tuning Kalman estimators for multisensor singular system

For the multisensor linear stochastic singular system with unknown noise variances, the weighted measurement fusion (WMF) self-tuning Kalman estimation problem is solved in this paper. The consistent estimates of these unknown noise variances are obtained based on the correlation method. Applying the WMF method and the singular value decomposition (SVD) method yields the WMF reduced-order subsystems. Based on these consistent estimates of unknown noise variances and the new non-singular systems, the WMF self-tuning Kalman estimators of the state components and white noise deconvolution estimators are presented. Then the WMF self-tuning Kalman estimators of the original state are presented, and their convergence has been proved by dynamic error system analysis (DESA) method and dynamic variance error system analysis (DVESA) method. A simulation example of 3-sensors circuits systems verifies the effectiveness, the accuracy relationship and the convergence.     

Performance analysis of multi-innovation gradient type identification methods

It is well-known that the stochastic gradient (SG) identification algorithm has poor convergence rate. In order to improve the convergence rate, we extend the SG algorithm from the viewpoint of innovation modification and present multi-innovation gradient type identification algorithms, including a multi-innovation stochastic gradient (MISG) algorithm and a multi-innovation forgetting gradient (MIFG) algorithm. Because the multi-innovation gradient type algorithms use not only the current data but also the past data at each iteration, parameter estimation accuracy can be improved. Finally, the performance analysis and simulation results show that the proposed MISG and MIFG algorithms have faster convergence rates and better tracking performance than their corresponding SG algorithms.     

Parameter identification of wiener models by multi-innovation algorithms

An output nonlinear Wiener system is rewritten as a standard least squares form by reconstructing the input-output items of its difference equation. Multi-innovation based stochastic gradient (MISG) algorithm and its derivate algorithms are introduced to formulate identification methods of Wiener models. In order to increase the convergence performance of stochastic gradient (SG) algorithm, the scalar innovation in SG algorithm is expanded to an innovation vector which contains more information about input-output data. Furthermore, a proper forgetting factor for SG algorithm is introduced to get a faster convergence rates. The comparisons of convergence performance and estimation errors of proposed algorithms are illustrated by two numerical simulation examples.     

On convergence of the unscented Kalman–Bucy filter using contraction theory

Contraction theory entails a theoretical framework in which convergence of a nonlinear system can be analysed differentially in an appropriate contraction metric. This paper is concerned with utilising stochastic contraction theory to conclude on exponential convergence of the unscented Kalman–Bucy filter. The underlying process and measurement models of interest are Itô-type stochastic differential equations. In particular, statistical linearisation techniques are employed in a virtual–actual systems framework to establish deterministic contraction of the estimated expected mean of process values. Under mild conditions of bounded process noise, we extend the results on deterministic contraction to stochastic contraction of the estimated expected mean of the process state. It follows that for the regions of contraction, a result on convergence, and thereby incremental stability, is concluded for the unscented Kalman–Bucy filter. The theoretical concepts are illustrated in two case studies.     

Consistency of the extended gradient identification algorithm for multi-input multi-output systems with moving average noises

The consistency of identification algorithms for systems with colored noises is a main topic in system identification. This paper focuses on the extended stochastic gradient (ESG) identification algorithm for the multivariable linear systems with moving average noises. By integrating the noise regression terms and the noise model parameters into the information matrix and the parameter vector, and based on the gradient search principle, the ESG algorithm is presented. The unknown noise terms in the information matrix are replaced with their estimates. The convergence analysis shows that the parameter estimation error converges to zero under a persistent excitation condition. Two simulation examples are given to illustrate the effectiveness of the algorithm.     

OBE算法对误差界低估的鲁棒性

研究了具有未知但有界(UBB)误差系统辨识的最优定界椭球(OBE)算法对误差界 低估的鲁棒性.证明了在一定的条件下,即使误差界低估,任何OBE算法都能保持其收敛性. 这一结论可用于具有UBB误差的实际系统参数估计中,以期获得不太保守的结果.     

Development of multivariable PID controller gains in presence of measurement noise

This paper examines the ability of a multivariable PID controller rejecting measurement noise without the use of any external filter. The work first provides a framework for the design of the PID gains comprising of necessary and sufficient conditions for boundedness of trajectories and zero-error convergence in presence of measurement noise. It turns out that such convergence requires time-varying gains. Subsequently, novel recursive algorithms providing optimal and sub-optimal time-varying PID gains are proposed for discrete-time varying linear multiple-input multiple-output (MIMO) systems. The development of the proposed optimal algorithm is based on minimising a stochastic performance index in presence of erroneous initial conditions, white measurement noise, and white process noise. The proposed algorithms are shown to reject measurement noise provided that the system is asymptotically stable and the product of the input–output coupling matrices is full-column rank. In addition, convergence results are presented for discretised continuous-time plants. Simulation results are included to illustrate the performance capabilities of the proposed algorithms.     

Worst-case analysis of the least-squares method and related identification methods

We consider worst-case analysis of system identification under less restrictive assumptions on the noise than the l_∞ bounded error condition. It is shown that the least-squares method has a robust convergence property in l₂ identification, but lacks a corresponding property in l₁ identification (as well as in all other non-Hilbert space settings). The latter result is in stark contrast with typical results in asymptotic stochastic analysis of the least-squares method. Furthermore, it is shown that the Khintchine inequality is useful in the analysis of least l^p identification methods.     

Iterative Learning Control for Nonlinear Systems: A Bounded‐Error Algorithm

This paper presents a nonlinear iterative learning control (NILC) for nonlinear time‐varying systems. An algorithm of a new strategy for the NILC implementation is proposed. This algorithm ensures that trajectory‐tracking errors of the proposed NILC, when implemented, are bounded by a given error norm bound. A special feature of the algorithm is that the trial‐time interval is finite but not fixed as it is for the other iterative learning algorithms. A sufficient condition for convergence and robustness of the bounded‐error learning procedure is derived. With respect to the bounded‐error and standard learning processes applied to a virtual robot, simulation results are presented in order to verify maximal tracking errors, convergence and applicability of the proposed learning control.     

Weighted averaging and stochastic approximation

We explore the relationship between weighted averaging and stochastic approximation algorithms, and study their convergence via a sample-path analysis. We prove that the convergence of a stochastic approximation algorithm is equivalent to the convergence of the weighted average of the associated noise sequence. We also present necessary and sufficient noise conditions for convergence of the average of the output of a stochastic approximation algorithm in the linear case. We show that the averaged stochastic approximation algorithms can tolerate a larger class of noise sequences than the stand-alone stochastic approximation algorithms.This research was supported by the National Science Foundation through Grants ECS-9410313 and ECS-9501652.This research was supported by the National Science Foundation through NYI Grant IRI-9457645.     

On the stability and convergence of self-tuning control–virtual equivalent system approach

This article presents a unified understanding and judgement of the stability and convergence of a general self-tuning control (STC) system, which consists of arbitrary control strategy, arbitrary parameter estimation algorithm and a deterministic/stochastic linear time-invariant (LTI) plant. The necessary conditions required for the global stability and convergence of a general STC system are relaxed, i.e. the convergence of parameter estimates is removed for both deterministic and stochastic STC schemes. To reach this goal, ‘virtual equivalent system (VES)’ concept and methodology is adopted. With the help of VES, the original nonlinear dominant (nonlinear in structure) problem is converted to a linear dominant (linear in structure) problem. The results developed in this article show that STC systems are stable and convergent for the abundance of control strategies and parameter estimation algorithms, which will provide great flexibility in the applications of STC.     

Fast smooth second-order sliding mode control for stochastic systems with enumerable coloured noises

A fast smooth second-order sliding mode control is presented for a class of stochastic systems driven by enumerable Ornstein–Uhlenbeck coloured noises with time-varying coefficients. Instead of treating the noise as bounded disturbance, the stochastic control techniques are incorporated into the design of the control. The finite-time mean-square practical stability and finite-time mean-square practical reachability are first introduced. Then the prescribed sliding variable dynamic is presented. The sufficient condition guaranteeing its finite-time convergence is given and proved using stochastic Lyapunov-like techniques. The proposed sliding mode controller is applied to a second-order nonlinear stochastic system. Simulation results are given comparing with smooth second-order sliding mode control to validate the analysis.     

Approximate adjoint-based iterative learning control

This paper characterises stochastic convergence properties of adjoint-based (gradient-based) iterative learning control (ILC) applied to systems with load disturbances, when provided only with approximate gradient information and noisy measurements. Specifically, conditions are discussed under which the approximations will result in a scheme which converges to an optimal control input. Both the cases of time-invariant step sizes and cases of decreasing step sizes (as in stochastic approximation) are discussed. These theoretical results are supplemented with an application on a sequencing batch reactor for wastewater treatment plants, where approximate gradient information is available. It is found that for such case adjoint-based ILC outperforms inverse-based ILC and model-free P-type ILC, both in terms of convergence rate and measurement noise tolerance.     

Several multi-innovation identification methods

This paper considers connections between the cost functions of some parameter identification methods for system modelling, including the well known projection algorithm, stochastic gradient (SG) algorithm and recursive least squares (RLS) algorithm, and presents a modified SG algorithm by introducing the convergence index and a multi-innovation projection algorithm, a multi-innovation SG algorithm and a multi-innovation RLS algorithm by introducing the innovation length, aiming at improving the convergence rate of the SG and RLS algorithms. Furthermore, this paper derives an interval-varying multi-innovation SG and an interval-varying multi-innovation RLS algorithm in order to deal with missing data cases.     

含未知参数的自校正融合Kalman滤波器及其收敛性

对于带未知模型参数和噪声方差的多传感器系统,基于分量按标量加权最优融合准则,提出了自校正解耦融合Kalman滤波器,并应用动态误差系统分析(Dynamic error system analysis,DESA)方法证明了它的收敛性.作为在信号处理中的应用,对带有色和白色观测噪声的多传感器多维自回归(Autoregressive,AR)信号,分别提出了AR信号模型参数估计的多维和多重偏差补偿递推最小二乘(Bias compensated recursive least-squares,BCRLS)算法,证明了两种算法的等价性,并且用DESA方法证明了它们的收敛性.在此基础上提出了AR信号的自校正融合Kalman滤波器,它具有渐近最优性.仿真例子说明了其有效性.     

基于随机牛顿算法的离散系统自适应参数估计

针对一类离散系统,提出一种基于随机牛顿算法的自适应参数估计新框架,相较于已有的参数估计算法,所提出方法仅要求系统满足有限激励条件,而非传统的持续激励条件.所提出算法的核心思想在于通过对原始代价函数的修正,在使用当前时刻误差信息的基础上融入历史误差信息,进而通过对历史信息和历史激励的复用使得持续激励条件转化为有限激励条件;然后,为了解决传统算法收敛速度慢的问题并避免潜在的病态问题,采用随机牛顿算法推导出参数自适应律,并引入含有历史信息的海森矩阵作为时变学习增益,保证参数估计误差指数收敛;最后,基于李雅普诺夫稳定性理论给出不同激励条件下所提出算法的收敛性结论和证明,并通过对比仿真验证所提出算法的有效性和优越性.