多输入多输出非线性最小相位系统的自适应模糊控制

针对多输入多输出非线性最小相位系统,把自适应模糊控制和自适应模糊辨识结合起来,提出了一种自适应模糊控制方案.设计辨识器用来辨识系统的未知部分;然后由跟踪误差和辨识误差给出了参数调节规律,两种误差同时调节参数改善了系统性能.模糊逻辑系统用来估计未知函数.控制方案保证了系统的稳定性,实现了有界跟踪.仿真结果表明了该方案的可行性.     

二型模糊小波脑情感学习网络在非线性系统辨识中的研究

针对现有模糊神经网络在辨识具有时变的非线性系统存在辨识精度不高,收敛速度较慢等缺点,提出了一种二型小波模糊脑情感学习网络(T2FWBELN)模型,它结合了模糊逻辑和脑情感学习网络的优点,并在网络结构中使用了小波函数。与其他算法相比,该算法在非线性系统辨识中有着更高的逼近能力。同时,采用模糊C均值算法生成模糊规则,并使用梯度下降法对T2FWBELN的各种参数进行在线调整,降低了参数调整时间。为了进一步验证该模型的有效性和优越性,仿真了两个不确定非线性系统辨识的例子,一个是Mackey-Glass时间序列预测,一个是带有噪声的动态系统辨识。测试结果表明,所提出的模型在处理非线性系统辨识中拥有更高的精度。     

Hénon混沌系统的模糊广义预测控制与同步

针对Hénon混沌系统,本文给出了一种基于T-S模糊模型的混沌系统广义预测控制算法。该方法将模糊辨识和广义预测控制结合起来应用到Hénon混沌系统中。首先,应用T-S模糊模型对Hénon混沌系统进行辨识,模糊聚类法辨识模型的前件参数,递推最小二乘法辨识结论参数。基于辨识模型,采用广义预测控制算法对其进行控制,实现了系统的跟踪与同步。仿真结果表明,与其它算法相比,该算法能够保证系统输出快速、有效地跟踪设定值。     

模糊时滞系统的输出反馈控制器设计

利用模糊T-S模型对一类非线性时滞系统进行建模;在此基础上,设计出了模糊静态输出反馈控制器和模糊动态输出反馈控制器,并利用Lyapunov-Razumikhin引理和线性矩阵不等式证明了系统渐近稳定的充分条件,通过求解一系列线性矩阵不等式,得到了反馈增益矩阵。     

W-模型辨识及其统计特性

本文选用三位式伪随机序列作为输入 ,充分利用其激励信号的各种特性 ,辨识非线性系统 Wiener模型的线性子系统脉冲响应函数 ,对非线性增益环节 ,则由其奇数和偶数项多项式系数分别进行估计 .同时研究线性与非线性子系统辨识的统计特性 ,给出各部分参数估计的置信区间 .     

基于数据驱动的非完整移动机器人运动控制的研究

智能车辆驱动控制系统和转向控制系统是一个典型的多输入多输出的强耦合系统,当系统老化、轮胎磨损或是电池电压不稳定的情况模型难以精确建立.基于数据驱动原理,直接利用实测的速度以及舵机角度等信息,辨识控制器的参数,从而避开模型辨识的过程,简化控制器设计,提高控制精度.仿真结果表明,方法具有较好的控制效果和较强的扰动抑制能力.     

典型非线性模型的模糊辨识逼近精度分析

人们根据非线性系统的复杂特性归结了几种具有代表性的非线性模型.而模糊辨识方法是辨识非线性系统的有力工具,本文采用T-S模糊模型对三种常见的非线性模型:Hammerstein模型,Wiener模型和双线性模型进行逼近,并根据仿真数据研究不同的非线性结构对模糊模型逼近精度的影响.仿真实例是在训练和检验数据组数、模型阶数相同的情况下,采用三角形隶属函数,聚类型隶属函数和高斯型隶属函数分别对这三种非线性模型进行逼近能力的研究.     

基于广义最大熵的具有模糊输入输出的回归模型的参数估计

模糊回归是在模糊系统中建立因变量与一组自变量之间关系的重要工具,以评估模糊自变量如何影响模糊响应变量的过程。当系统中出现小样本或者非列满秩设计矩阵时,模糊最小二乘法可能得出偏误估计。本文基于文献[13]中的多元线性回归模型,利用广义最大熵方法,针对模糊输入模糊输出数据,给出线性回归模型的参数估计和算法步骤。当输入或输出数据退化为清晰值时,该估计退化为清晰输入模糊输出或者模糊输入清晰输出的回归模型参数估计。本文结合模拟数据和实例数据,将广义最大熵方法与模糊最小二乘方法、岭估计方法进行比较研究,结果显示广义最大熵方法的可行性和有效性。     

一类非线性动态系统的混合H2/H∞模糊输出反馈跟踪控制

讨论一类非线性动态系统的混合H2/H∞模糊输出反馈跟踪控制问题。首先利用T-S模糊模型对系统进行建模,然后设计基于观测器的控制器,使跟踪误差尽可能的小,并且对于任何有界参考输入,满足给定的H∞跟踪性能,以及在满足给定的H∞跟踪性能下,达到H2次优控制性能,最后将观测器与控制器的设计问题转化为EVP(特征值问题)。     

线性参数变化系统的子空间预测控制

为弥补线性系统与非线性系统间的差异,考虑非线性系统的近似模型-线性参数变化系统的子空间预测控制,此控制器能更贴切地控制非线性系统.采用数据驱动的子空间预测控制策略,构造输入-输出观测数据矩阵来辨识状态空间形式下的马尔科夫参数.利用矢量积算子的数据矩阵表示将来时刻的输出预测值,并以此预测值作用于代价函数.对带有不等式约束的二次代价函数采用并行分布算法来求解其最优值.针对直流电动机在质量分布因素下的线性参数变化系统,采用子空间预测控制器来控制直流电动机.     

球外部区域上一类椭圆边值问题的正径向解

研究了一类椭圆边值问题在球外部区域上正径向解的存在性,当非线性项f（u）关于u超线性或次线性增长的情形,获得了该问题正径向解的存在性.     

Classical model validation for control design purposes

Model Validation is at the heart of the System Identification process. Recently, much renewed interest has been expressed in so called "identification for control". This means that the design variables associated with the identification process are tailored to achieve models that are well suited for control design purposes. A separate, but closely related issue is to devise validation tests that give information about the model's quality and suitability for control design. This paper shows and discusses how a basic and classical residual test gives such information.     

Linear programming system identification

We define a version of the Inverse Linear Programming problem that we call Linear Programming System Identification. This version of the problem seeks to identify both the objective function coefficient vector and the constraint matrix of a linear programming problem that best fits a set of observed vector pairs. One vector is that of actual decisions that we call outputs. These are regarded as approximations of optimal decision vectors. The other vector consists of the inputs or resources actually used to produce the corresponding outputs. We propose an algorithm for approximating the maximum likelihood solution. The major limitation of the method is the computation of exact volumes of convex polytopes. A numerical illustration is given for simulated data.     

Stochastic optimization theory in Hilbert spaces—1

We study a class of stochastic optimization problems in which the state as well as the observation spaces are permitted to be (Hilbert spaces) of non-finite dimension. Although there have been previous attempts in the Hilbert space setting, our results, techniques, as well as applications, are totally different. We initiate the use of Gauss measure on a Hilbert space even though it is only finitely additive; and an associated theory of white noise, in contrast to the Wiener process theory, which is novel even in the finite dimensional case. We only treat time-invariant systems, but no strong ellipticity or coercivity conditions are used; we exploit the theory of semigroups of operators in contrast to the Lions-Magenes theory. A key result involves a far-reaching generalization of the Factorization theorem of Krein. We apply the results to the problem of boundary observation and control for partial differential equations. By the creation of a special state space, we can apply the theory to problems in which the state equations are finitedimensional but the noise does not have a rational spectrum. In a final section, we present a stochastic theory for inverse problems (System Identification) in the Hilbert space setting. The basic theoretical problem is the calculation of R-N derivatives for finitely additive measures. A fundamental result concerns Identifiability; in particular the identifiability of diffusion coefficients from boundary data is treated here for the first time.     

Approximate periodic solutions of a nonlinear parabolic system and an identification problem

This work continues our study in [L. Lei, Identification of parameters through the approximate periodic solutions of a linear parabolic system, preprint, 2005] on the identification problem for the coefficients for the lower order terms in a parabolic system, through its approximate periodic solutions. Different from the work in [L. Lei, Identification of parameters through the approximate periodic solutions of a linear parabolic system, preprint, 2005], our system now is nonlinear and the coefficients to be detected are from the first order term. From the application point of view, we now try to determine the diffusion coefficients for the system by the observation over a subregion of the physical domain. The existence and uniqueness problem of the approximate periodic solutions is studied in the first part of the paper.     

Invariant manifolds and the interplanetary superhighway

We propose a different model to study the Solar System by considering it as a series of Three Body Problems (Sun-Planet-Infinitesimal Body). The invariant manifolds of each Three Body System intersect in space to provide a transport mechanism spanning the entire Solar System which is popularly called the “Interplanetary Superhighway”. This concept is useful for designing space missions and for understanding the motions of minor bodies in the Solar System. (© 2008 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim)     

条件异方差双门限自回归模型的门限和延时的小波估计

本文讨论了条件异方差双门限自回归模型的门限和延时的识别问题,通过经验小波系数,给出了门限个数和门限以及延时的估计,在较弱的条例下,证明了所给的估计是相合的。     

Sequential analysis of organization design: A model and a case of Japanese firms

This paper deals with a design problem of an organization whose choice process of the task is formulated as a sequential decision process. This process incorporates the organization design as a combination of an organization structure anaa management system. Two organization structures, the pyramid organization and the matrix organization, are defined as the systems of task assignment. Two management systems, System 1 and System 2 are defined as the communication systems of the observation process on the environment.From a decision theoretic viewpoint, we analyze this organization design problem and obtain the results having the following managerial implications: The pyramid organization and System 1 are efficient under low uncertainty; the matrix organization and System 2 are efficient under high uncertainty; the pyramid organization is efficient if System 1 is efficient. Our empirical research on Japanese firms supports these implications.     

Robust synchronization of parametrized nonautonomous discrete systems with applications to communication systems

We study synchronization of a coupled discrete system consisting of a Master System and a Slave System. The Master System usually exhibits chaotic or complicated behavior and transmits a signal with a chaotic component to the Slave System. The Slave System then recovers the original signal and removes the chaotic component. To ensure secured communication, the Master and the Slave systems must synchronize independent of the variation of the systems parameters and initial conditions. Here we develop a general approach and obtain some general results for synchronization of such coupled systems naturally arising from discretization of well-know continuous systems, and we illustrate general results with two specific examples: the discretized Lorenz system and a discretized nonlinear oscillator. We also present some simulations using MatLab to illustrate our discussions.     

An experimental validation of the Stochastic Subspace Identification

In this contribution we derive and experimentally validate the Stochastic Subspace Identification. Additionally we compare the results with an updated finite element model. (© 2004 WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheim)