Minimum order linear system identification and parameter estimation with application

Download
2014
Erdoğan, Onur Cem
Design, control, and investigation of complex systems require a tool to understand and model system behavior. This tool is the system identification, which convert the system response to a mathematical formulation. During the identification phase, the utilized model is important to convey system behavior. In this study, a number of minimum order and non-parametric system identification algorithms are implemented for the identification of linear time invariant mechanical systems. For this purpose, impulse response determination methods are investigated to obtain system behavior. State space modeling and special models used in the identification process of physical systems are investigated. Two system realization algorithms implementing minimum order non-parametric linear system identification are presented. A transformation based method for the extraction of physical system parameters from a real system model is represented. The suggested methods are implemented on both simulation and test data for different system models to investigate their effectiveness and performance.

Suggestions

Vester's Sensitivity Model for Genetic Networks with Time-Discrete Dynamics
Moreno, Liana Amaya; DEFTERLİ, ÖZLEM; Fuegenschuh, Armin; Weber, Gerhard Wilhelm (2014-07-03)
We propose a new method to explore the characteristics of genetic networks whose dynamics are described by a linear discrete dynamical model x(t+1) = Ax(t). The gene expression data x(t) is given for various time points and the matrix A of interactions among the genes is unknown. First we formulate and solve a parameter estimation problem by linear programming in order to obtain the entries of the matrix A. We then use ideas from Vester's Sensitivity Model, more precisely, the Impact Matrix, and the determi...
Evolution operator approach for solving linear ordinary differential equations and computation of EXP (A)
Azzam, Abdelnasser; Ergenç, Tanıl; Department of Mathematics (1991)
An Evolution Operator Approach which were developed to solve nonlinear O.D.E. systems, X=f(x), X(0)=£, is discussed for the linear systems X=AX where A is nxn symmetric matrix. In this approach, each component of the solution vector is represented as an action of evolution operator, exp(itL), on xj and then approximated by method of Moment using [N+1,N] Pade’ approximation. In applications, the most important part of this method is the computation of dynamical and spectral coefficients [6]. The recursive fo...
Analysis Window Length Selection For Linear Signal Models
Yazar, Alper; Candan, Çağatay (2015-05-19)
A method is presented for the selection of analysis window length, or the number of input samples, for linear signal modeling without compromising the model assumptions. It is assumed that the signal of interest lies in a known linear space and noisy samples of the signal is provided. The goal is to use as many signal samples as possible to mitigate the effect of noise without violating the assumptions on the model. An application example is provided to illustrate the suggested method.
Quantum systems and representation theorem
Dosi, Anar (2013-09-01)
In this paper we investigate quantum systems which are locally convex versions of abstract operator systems. Our approach is based on the duality theory for unital quantum cones. We prove the unital bipolar theorem and provide a representation theorem for a quantum system being represented as a quantum -system.
Presentation of a multi-tone model and its application to feedforward circuit analysis
Coskun, Hakan; Mutlu, Ahmet; Demir, Şimşek (2004-12-01)
Analytical tools that characterize nonlinear systems are essential and need to be developed for initial rapid optimizations and understanding of the system performance. Modeling of the input signal is a crucial part of this task. In this work, we present a multi-tone representation for an arbitrary, stochastically not well-defined signal and its application to a feedforward circuit which involve two nonlinear amplifiers, couplers, phase and delay units. Particularly, amplitude and phase aspects of the model...
Citation Formats
O. C. Erdoğan, “Minimum order linear system identification and parameter estimation with application,” M.S. - Master of Science, Middle East Technical University, 2014.