Authors: None

Abstract:

Keywords:

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.90001

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: ---

Authors: None

Abstract:

Keywords:

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.90002

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: ---

Authors: None

Abstract:

Keywords:

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.90003

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: ---

Authors: None

Abstract:

Keywords:

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.90004

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: ---

Authors: None

Abstract:

Keywords:

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.90005

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: ---

Authors: Ninness, Brett

Abstract: The field of control-oriented system identification is mature. Nevertheless, it is still very active. This is because there are many important unsolved challenges. Of these, this paper considers a selection. This involves considering the estimation of general nonlinear model structures, together with accurate error bounds, using methods that scale well to models of high dimension. A particular strength of the system identification field is that it has always actively sought to understand, embrace and develop ideas from other fields, such as statistics, mathematics and econometrics. This paper proposes a continuation of this successful strategy by proposing and profiling the adoption of new ideas originating in statistics, signal processing and statistical mechanics.

Keywords: Multivariable System Identification; Error Quantification; Particle Filtering/Monte Carlo Methods

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00001

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 1-20

Authors: Nemcova, Jana; van Schuppen, Jan H.

Abstract: The aim of this tutorial paper is to provide an overview of system identification of polynomial and of rational systems. It is an introduction to a session included in the program of the IFAC Symposium System Identification (SYSID.2009). Polynomial and rational systems arise in systems biology where there is a great need to have algorithms and methods for obtaining realistic models. The paper presents a system identification procedure for these classes of systems consisting of: (1) Modeling; (2) Experiment design and data processing; (3) Identifiability; (4) Approximation; and (5) Evaluation. Major open problems include the approximation problem and formulation of computer-algebra algorithms for checking identifiability.

Keywords: Nonlinear System Identification; Biological Systems

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00002

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 21-26

Authors: Ropers, Delphine; Baldazzi, Valentina; de Jong, Hidde

Abstract: A large and complex network of biochemical reactions, involving genes, mRNAs, proteins, metabolites, and signalling molecules, controls the adaptation of the bacterium Escherichia coli to environmental changes. In order to better understand the functioning of this network, we develop a kinetic model, which takes the form of a large system of nonlinear ODEs, including different time scales. We reduce the system dimension by making a quasi-steady-state assumption, and further approximate the reduced model into a piecewise-linear model. This allows us to qualitatively analyze the response of E. coli to carbon-source availability.

Keywords: Biological Systems

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00003

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 27-32

Authors: Boulier, François; Lemaire, François

Abstract: Differential algebra is an algebraic theory for differential equations (ordinary or with partial derivatives, linear or non linear). It involves an elimination theory which is completely algorithmic since the mid 1990s. In addition to the numerous applications which have been developed in control theory for more than twenty years, it was recently shown that differential elimination makes algorithmic a rigorous quasi-steady state approximation method for generalized chemical reaction systems. This result was recently succesfully applied to model reduction problems in cellular modeling. This paper presents this recent advance in connection with a new MAPLE package (with new functionalities). This package is built over the BLAD libraries, which are LGPL-licensed open source, written in the C programming language.

Keywords: Toolboxes; Biological Systems; Nonlinear System Identification

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00004

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 33-38

Authors: Laubenbacher, Reinhard; Jarrah, Abdul Salam; Dimitrova, Elena; Stigler, Brandilyn; Vera-Licona, Paola

Abstract: This paper gives a review of tools for the system identification of dynamic models for gene regulatory networks, using the modeling framework of polynomial dynamical systems over finite fields.

Keywords:

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00005

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 39-41

Authors: Nemcova, Jana

Abstract: The properties of a parametrized system such as structural and global identifiability provide information whether the parameters of the system can be determined uniquely. Therefore, verifying at least one of these properties preceeds determination of numerical values of the parameters. In this paper we derive necessary and sufficient conditions for a parametrized rational system to be structurally or globally identifiable. We also formulate the corresponding conditions for parametrized polynomial systems. The results are applied to study the identifiability properties of the system modeling a chain of two enzyme-catalyzed irreversible reactions.

Keywords: Identifiability; Biological Systems; Nonlinear System Identification

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00006

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 42-47

Authors: Saccomani, Maria Pia; D'angiò, Leontina

Abstract: DAISY (Differential Algebra for Identifiability of SYstems) is a recently developed computer algebra software tool which can be used to automatically check global identifiability of (linear and) nonlinear dynamic models described by differential equations involving polynomial or rational functions. Global identifiability is a fundamental prerequisite for model identification which is important not only for biological or medical systems but also for many physical and engineering systems derived from first principles. The software does not require understanding of the underlying mathematical principles and can be used by researchers in applied fields with a minimum of mathematical background. We demonstrate the DAISY software by checking the a priori global identifiability of two benchmark nonlinear models taken from the literature. The analysis of these two examples includes comparison with other methods and demonstrates how identifiability analysis is simplified by this tool. It includes discussion of some specific aspects related for example to the role of observability and knowledge of initial conditions in testing identifiability. The main focus of this paper is not on the description of the mathematical background of the algorithm, which has been presented elsewhere, but on illustrating its use and on some of its more interesting features. DAISY is available on the web site http://www.dei.unipd.it~pia.

Keywords: Identifiability; Biological Systems; Nonlinear System Identification

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00007

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 48-53

Authors: Casini, Marco; Garulli, Andrea; Vicino, Antonio

Abstract: Optimal input design for system identification with quantized sensors is tackled in a worst-case setting. Under the assumption of uniformly quantized measurements, the paper addresses the one-step input design problem for static gains. Results are provided for both noise-free and noisy data and are instrumental for designing suboptimal inputs for FIR systems of arbitrary order. The input design problem over a time horizon of length N is also investigated, in order to characterize the time complexity of the considered identification problem.

Keywords: Input and Excitation Design; Bounded Error Identification; Other

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00008

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 54-59

Authors: Zhao, Yanlong; Wang, Le Yi; Zhang, Ji-Feng; Yin, George

Abstract: In this paper, identification of systems with binary-valued observations is investigated. Rather than estimating parameters under deterministic and stochastic frameworks separately, we introduce a joint framework in which the two frameworks play complementary roles in improving identification accuracy. It is shown that when uncertainty on the unknown parameter is large, the stochastic method may fail, but the worst-case method is effective in uncertainty reduction. On the other hand, the worst-case method becomes ineffective when the uncertainty becomes small, in fact it leaves an irreducible error and hence consistency is lost. This is where the stochastic framework becomes effective in achieving consistency and efficiency. This paper fully utilizes the strength of each framework to overcome shortcomings. Input design, threshold selection, and criteria for switching from one framework to another are developed.

Keywords: Nonlinear System Identification; Identifiability

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00009

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 60-65

Authors: Aguero, Juan C; Godoy, Boris I; Goodwin, Graham C.; Wigren, Torbjörn

Abstract: In this paper we describe a novel algorithm for estimating the parameters of a linear system when the observed output signal is quantized. This question has relevance to many areas including sensor networks and telecommunications. The algorithm utilizes a set of pre-computed scenarios to reduce the computational complexity of EM type algorithms that are typically deployed for this kind of problem. More generally, the idea of utilizing scenarios seems to have widespread potential in system identification.

Keywords: Maximum Likelihood Methods

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00010

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 66-71

Authors: Juillard, Jerome; Jafaridinani, Kian; Colinet, Eric

Abstract: In this paper, we present a new weighted least-squares (WLS) approach for parameter estimation based on binary data. Two WLS criteria are studied. We show that these two criteria do not have the same asymptotical behavior although they are closely related. Particularly, in the presence of noise, one of the criteria used for determining the system parameters provides an appropriate estimation, whereas the other one leads to an underestimation of the system parameters. These asymptotical results are illustrated by simulations in Gaussian and non-Gaussian contexts.

Keywords: Nonlinear System Identification; Identification for Control

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00011

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 72-77

Authors: Gustafsson, Fredrik; Karlsson, Rickard

Abstract: System identification based on quantized observations requires either approximations of the quantization noise, leading to suboptimal algorithms, or dedicated algorithms taylored to the quantization noise properties. This contribution studies fundamental issues in estimation that relate directly to the core methods in system identification. As a first contribution, results from statistical quantization theory are surveyed and applied to both moment calculations (mean, variance etc) and the likelihood function of the measured signal. In particular, the role of adding dithering noise at the sensor is studied. The overall message is that taylored dithering noise can considerably simplify the derivation of optimal estimators. The price for this is a decreased signal to noise ratio, and a second contribution is a detailed study of these effects in terms of the Cram'er-Rao lower bound. The common additive uniform noise approximation of quantization is discussed, compared, and interpreted in light of the suggested approaches.

Keywords: Maximum Likelihood Methods; Error Quantification; Nonparametric Methods

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00012

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 78-83

Authors: Wang, Le Yi; Li, Chanying; Yin, George; Guo, Lei; Xu, Cheng-Zhong

Abstract: This paper introduces an observer for linear time invariant systems in continuous time whose outputs are measured only by binary-valued sensors. The traditional observers will fail in general, even if the system has a full-rank observability matrix. It is shown that by controlling the sensor threshold, it is always possible to cause the output to cross the sensor threshold within a designated time interval. Information on the time instants of threshold crossing is then used to develop state estimates. Convergence properties of the state observer are established. It is shown that by generating appropriate switching time sequences, state observers are convergent in the mean squares sense, with probability one, and exponentially. Combined with a state feedback using the state estimates, this state estimator leads to a stabilizing output feedback.

Keywords: Nonlinear System Identification; Identification for Control

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00013

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 84-89

Authors: Lyzell, Christian; Enqvist, Martin; Ljung, Lennart

Abstract: The prediction-error approach to parameter estimation of linear models often involves solving a non-convex optimization problem. In some cases, it is therefore difficult to guarantee that the global optimum will be found. A common way to handle this problem is to find an initial estimate, hopefully lying in the region of attraction of the global optimum, using some other method. The prediction-error estimate can then be obtained by a local search starting at the initial estimate. In this paper, a new approach for finding an initial estimate of certain linear models utilizing structure and the subspace method is presented. The polynomial models are first written on the observer canonical state-space form, where the specific structure is later utilized, rendering least-squares estimation problems with linear equality constraints.

Keywords: Subspace Methods; Multivariable System Identification

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00014

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 90-95

Authors: Houtzager, Ivo; Wingerden, van, Jan-Willem; Verhaegen, Michel

Abstract: In this paper a subspace model identification algorithm is presented that can be implemented recursively to track slowly time-varying linear systems operating in open loop and closed loop. Particular attention is paid to the computational cost and tracking performance of the developed identification algorithm. The identification problem is described by only two linear problems. The computational complexity is reduced by using array algorithms to solve these linear problems and exploiting the structure in the vectors. This results in a fast implementation of the developed recursive identification algorithm. The effectiveness of the proposed algorithm in comparison with existing methods is emphasized with a simulation study on a time-varying closed-loop system.

Keywords: Subspace Methods; Recursive Identification; Closed Loop Identification

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00015

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 96-101

Authors: de Callafon, Raymond; Miller, Daniel

Abstract: Subspace identification techniques are reinterpreted via classical realization theory to formulate a wide class of subspace identification methods. Re-formulating subspace identification in terms of a low rank decomposition of a weighted Hankel matrix allows special cases such as impulse-based and step-based input signals, but also realization based on arbitrary input signals and correlation functions. Ideas are illustrated with a simulation example.

Keywords: Subspace Methods; Multivariable System Identification

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00016

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 102-107

Authors: Tanaka, Hideyuki

Abstract: This paper studies a realization algorithm for modeling dynamical systems subject to a bounded error. An iterative algorithm is developed based on ``indefinite realization'', which is a generalization of stochastic realization. A Riccati difference equation for indefinite realization is derived, and it is shown that the Riccati recursion converges to the stabilizing solution to the steady state Riccati equation under certain assumptions. Numerical simulation results are also included.

Keywords: Subspace Methods; Multivariable System Identification; Bounded Error Identification

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00017

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 108-113

Authors: Markovsky, Ivan

Abstract: Closed-loop data-driven simulation refers to the problem of constructing trajectories of a closed-loop system directly from data of the plant and a representation of the controller. Conditions under which the problem has a solution are given and an algorithm for computing the solution is presented. The problem formulation and its solution are in the spirit of the deterministic identification algorithms, i.e., in the theoretical analysis of the method, the data is assumed exact (noise free).

Keywords: Subspace Methods; Identifiability; Identification for Control

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00018

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 114-115

Authors: Jiang, Yueping; Fang, Haitao

Abstract: A recursive subspace identification algorithm is proposed for the closed-loop stochastic systems in state-space form. Each recursion step consists of two-stages: first, the innovation of the stochastic system is estimated by the extended least squares (ELS) algorithm; then, a basis of the extended observability matrix is estimated by the stochastic approximation based principal component analysis (SABPCA) method by using the estimated innovation to replace the true one. Under reasonable conditions the recursively estimated observability matrix a.s converges to the true one up to a similarity transformation. The performance of the proposed algorithm is illustrated via a simulation example.

Keywords: Subspace Methods; Recursive Identification; Closed Loop Identification

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00019

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 116-121

Authors: Sjoberg, Jonas E.; Schoukens, Johan

Abstract: An approach to estimate the plausible number of parameters in a nonlinear model in an identification problem is considered. By suggesting a series of experiments using periodic input signal, estimates of the disturbance variance and the nonlinear distortion can be formulated. With these estimates an expression for a reasonable number of parameters is obtained. This is useful help when a user has to choose between different types of nonlinear model structure which differ largely in their number of parameters.

Keywords: Nonlinear System Identification; Input and Excitation Design; Error Quantification

Digital Object Identifier (DOI): 10.3182/20090706-3-FR-2004.00020

Conference: 15th IFAC Symposium on System Identification, 2009

Location: Saint-Malo Convention Center, Saint-Malo, France

Start Date: Mon Jul 06 2009 - End Date: Wed Jul 08 2009

Page Numbers: 122-125