检索结果-内蒙古大学图书馆

recursive Subspace Identification Based on Projector Tracking

IFAC Proceedings Volumes 2003年第16期36卷 1579-1584页

作者： Marco Lovera Dipartimento di Elettronica e Informazione Politecnico di Milano Piazza Leonardo da Vinci 32 20133 Milano Italy

The problem of MIMO state space recursive identification is considered and analyzed using subspace model identification (SMI) techniques. In this paper the use of projection tracking techniques for the update of the observability subspace is proposed: existing results are used for the output error case and a novel instrumental variable (IV) projection tracking approach is proposed, to accommodate for arbitrary correlation of the disturbances. Simulation results show the performance achievable with the given algorithms.

关键词： Subspace methods recursive algorithms Identification algorithms State space models Tracking systems

来源：评论

学校读者我要写书评

暂无评论

Convergence analysis of a recursive prediction error method.

引用

IFAC Proceedings Volumes 2012年第16期45卷 1496-1501页

作者： Soma Tayamon Torbjörn Wigren Uppsala University Department of Information Technology Division of System and Control Uppsala Sweden

A convergence analysis is performed for a recursive prediction error algorithm discretised using the midpoint integration method. Several conditions are formulated such that the stability of an associated differential equation can be tied to the local and global convergence properties of the algorithm. This shows that convergence to the true parameters is possible. The theoretical analysis of this paper is complemented by numerical example.

关键词： Nonlinear systems system identification prediction error methods recursive algorithms convergence analysis

来源：评论

学校读者我要写书评

暂无评论

Consistency and Minimality for the Prewindowed Prediction Problem

引用

IFAC Proceedings Volumes 1992年第14期25卷 471-476页

作者： P.A. Regalia Département Electronique et Communications Institut National des Télécommunications 9 rue Charles Fourier 91011 Evry Cedex France

The issues of consistency and minimal parametrization of the prewindowed prediction problem are presented in detail. The paper establishes an equivalence class between the set of p × p symmetric, positive definite matrices P and the set of 2 × 1 stable causal allpass functions η p (z) or McMillan degree p. The minimal parametrization of such matrices P is obtained by parametrizing η p (z) resulting in an inherently consistent parametrization. The application to numerically stable fast least-squares filtering is highlighted.

关键词： Least-squares estimation stability of numerical methods adaptive systems prediction theory recursive algorithms

来源：评论

学校读者我要写书评

暂无评论

The Lepschy stability test and its application to fractional-order systems

引用

ARCHIVES OF CONTROL SCIENCES 2021年第1期31卷 145-163页

作者： Casagrande, Daniele Krajewski, Wieslaw Viaro, Umberto Univ Udine Polytech Dept Engn & Architecture Via Sci 206 I-33100 Udine Italy Polish Acad Sci Syst Res Inst Ul Newelska 6 PL-01447 Warsaw Poland

It is shown how a stability test, alternative to the classical Routh test, can profitably be applied to check the presence of polynomial roots inside half-planes or even sectors of the complex plane. This result is obtained by exploiting the peculiar symmetries of the root locus in which the basic recursion of the test can be embedded. As is expected, the suggested approach proves useful for testing the stability of fractional-order systems. A pair of examples show how the method operates. It is believed that the suggested geometric approach can also be of some didactic value in introducing basic control-system tools to engineering students.

关键词： fractional-order systems D-stability recursive algorithms complex polynomials root locus symmetries control-theory didactics

来源：评论

学校读者我要写书评

暂无评论

Inverse-Free Incremental Learning algorithms With Reduced Complexity for Regularized Extreme Learning Machine

引用

IEEE ACCESS 2020年 8卷 177318-177328页

作者： Zhu, Hufei Wu, Yanpeng Hunan First Normal Univ Dept Informat Sci & Engn Changsha 410205 Peoples R China Shenzhen Univ Coll Comp Sci & Software Shenzhen 518060 Peoples R China

The existing inverse-free incremental learning algorithm for the regularized extreme learning machine (ELM) was based on an inverse-free algorithm to update the regularized pseudo-inverse, which was deduced from an inverse-free recursive algorithm to update the inverse of a Hermitian matrix. Before that recursive algorithm was applied in the existing inverse-free ELM, its improved version had been utilized in previous literatures. Then from the improved recursive algorithm to update the inverse, we deduce a more efficient inverse-free algorithm to update the regularized pseudo-inverse, from which we propose the inversefree incremental ELM algorithm based on regularized pseudo-inverse. Usually the above-mentioned inverse is smaller than the pseudo-inverse, while in the processor units with limited precision, the recursive algorithm to update the inverse may introduce numerical instabilities. Then to further reduce the computational complexity, we also propose the inverse-free incremental ELM algorithm based on the LDLT factors of the inverse, where the LDLT factors are updated iteratively by the inverse LDLT factorization. With respect to the existing inverse-free ELM, the proposed ELM based on regularized pseudo-inverse and that based on LDLT factors are expected to require only 3/8+M and 1/8+M of complexities, respectively, where M is the output node number. The numerical experiments show that both the proposed ELM algorithms significantly accelerate the existing inverse-free ELM, and the speedup in training time is not less than 1.41. On the Modified National Institute of Standards and Technology (MNIST) Dataset, usually the proposed algorithm based on LDLT factors is much faster than that based on regularized pseudo-inverse. On the other hand, in the numerical experiments, the original ELM, the existing inverse-free ELM and the proposed two ELM algorithms achieve the same performance in regression and classification, and result in the same solutions, which includ

关键词： Training Licenses Kernel Fault tolerance Fault tolerant systems Complexity theory Information science Extreme learning machine (ELM) recursive algorithms inverse-free inverse LDLT factorization regularized pseudo-inverse incremental learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Dynamic Simulation of an Integrated Robot/Forge Near Net-Shape Processing Center

引用

IFAC Proceedings Volumes 1992年第28期25卷 347-351页

作者： K.W. Lilly A.S. Melligeri Department of Mechanical Engineering The Pennsylvania State University University Park PA 16802

Automation of forging processes is important both for reasons of safety and to improve manufacturing capabilities. Development of an integrated robot/forge processing cell and its efficient dynamic simulation are discussed in this paper. Dynamic simulation of the closed-chain industrial robot is implemented using an O (N) recursive algorithm, while material flow in the workpiece is represented using a finite-element model. Integration of the two models along with process control is discussed. Timing results for a specific open die forging example are presented.

关键词： automation computer simulation finite element method forging industrial robots manufacturing processes metallurgical industries recursive algorithms

来源：评论

学校读者我要写书评

暂无评论

Identification of Structure and Parameters of the Multivariable Systems

引用

IFAC Proceedings Volumes 1993年第2期26卷 327-329页

作者： D.W. Hu Department of Automatic Control Changsha Institute of Technology Changsha Hunan 410073 PRC

The identification of the ARMAX model and the state space model of the multivariable system is investigated in the presence of coloured noise. Firstly. the optimal input vector design is introduced to identify the Markov parameter matrices. Secondly. in the description of the multi-dimensional ARMAX model. an order recursive algorithm is presented for estimating the order and the parameter matrices of the ARMAX model using the estimated Markov matrices. The aymptotic biases are compensated to achieve higher identification precision. Furthermore. the autocorrelation function matrices of the observation noise are estimated. Finally. the recursive algorithm of the identification of the Kronecker structure invariants and the parameters of the state space model of the multivariable system is suggested.

关键词： Identificatoin multivariable systems canonical forms parameter estimation recursive algorithms Kronecker invariants Markov parameter matrices

来源：评论

学校读者我要写书评

暂无评论

Identification by the Stochastic Variant of the Steepest Descent Method

引用

IFAC Proceedings Volumes 1982年第4期15卷 1247-1251页

作者： F.Ζ. Unton Systems Research Institute Polish Academy of Sciences ul. Newelska 6 01-447 Warsaw Poland

The main problem considered is on-line identification by the stochastic approximation methods. Some modifications of the algorithms are introduced. The modified methods increases the efficiency of the algorithms with respect to number of observations of the system. Convergence with probability one to the true parameters is also obtained. Efficiency of the algorithms is tested on two fourth-order discrete-time systems.

关键词： Identification parameter estimation linear systems recursive algorithms

来源：评论

学校读者我要写书评

暂无评论

On a Robustified Adaptive Clark-Gawthrop's Controller

引用

IFAC Proceedings Volumes 1990年第8期23卷 357-361页

作者： V.Ž. Filipović B.D. Kovačević Faculty of Eleclncal Engineering University of Belgrade Belgrade Yugoslavia

An adaptive regulator of the Clark-Gawthrop's type in the presence of disturbance uncertainty is considered in the paper. Supposing a linear ARMAX model with delay of the single input-output system, a robustified direct adaptive control algorithm is derived using the well known statistical approach called M-estimation. The derived algorithm differes from the least-squares method by the insertion of a sui table chosen nonlinear transformation of the prediction error, which has to cut off the large noise realizations, called outliers. The global stability of the proposed control system and the asymptotic optimality of the adaptive regulator is established theoretically using the martingale theory.

关键词： Adaptive systems robust identification recursive algorithms convergence analysis

来源：评论

学校读者我要写书评

暂无评论

On-Line Probability Estimation for Bayesian Distributed Detection Systems in Non-Stationary Environments

引用

IFAC Proceedings Volumes 1991年第5期24卷 215-219页

作者： M. Kam A. Naim Wei Cheng Department of Electrical and Computer Engineering Drexel University Philadelphia PA 19104 USA Reshet Inc. 314 North 32nd Street Philadelphia PA 19104 USA

In order to synthesize a binary target/no target decision, Bayesian distributed detection systems need the target probabilities and the local-detector performance probabilities. In this paper we discuss the use of three possible approaches to estimating these probabilities online, when they are not available a priori or when they change during an experiment. These techniques are: (i) decreasing-gain stochastic approximation, (ii) constant- gain stochastic approximation-like estimation, and (iii) decreasing-gain stochastic approximation enhanced by a disruption-detection algorithm. We demonstrate the operation of the algorithms in numerical simulations and conclude that both (ii) and (iii) can be useful for practical distributed detection systems which encounter jump-changes in the estimated probabilities.

关键词： Distributed Detection Sensor Fusion Self-adjusting Systems recursive algorithms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：