Frequency domain sample maximum likelihood estimation for spatially dependent parameter estimation in PDEs

The identification of the spatially dependent parameters in Partial Differential Equations (PDEs) is important in both physics and control problems. A methodology is presented to identify spatially dependent parameters from spatio-temporal measurements. Local non-rational transfer functions are derived based on three local measurements allowing for a local estimate of the parameters. A sample Maximum Likelihood Estimator (SMLE) in the frequency domain is used, because it takes noise properties into account and allows for high accuracy consistent parameter estimation. Confidence bounds on the parameters are estimated based on the noise properties of the measurements. This method is successfully applied to the simulations of a finite difference model of a parabolic PDE with piecewise constant parameters.

[1]  Yves Rolain,et al.  Uncertainty of transfer function modelling using prior estimated noise models , 2003, Autom..

[2]  Thierry Poinot,et al.  Fractional modelling and identification of thermal systems , 2011, Signal Process..

[3]  Torsten Söderström,et al.  Reduced order models for diffusion systems , 2001 .

[4]  Graham C. Goodwin,et al.  Robust optimal experiment design for system identification , 2007, Autom..

[5]  A. Polyanin,et al.  Handbook of Exact Solutions for Ordinary Differential Equations , 1995 .

[6]  Duarte Valério,et al.  Identification of Fractional Models from Frequency Data , 2007 .

[7]  Rik Pintelon,et al.  Identification of Linear Systems: A Practical Guideline to Accurate Modeling , 1991 .

[8]  J. Schoukens,et al.  Estimation of nonparametric noise and FRF models for multivariable systems—Part I: Theory , 2010 .

[9]  T. Söderström,et al.  Reduced order models for diffusion systems using singular perturbations , 2001 .

[10]  C. Kravaris,et al.  Identification of parameters in distributed parameter systems by regularization , 1983, The 22nd IEEE Conference on Decision and Control.

[11]  H. Banks,et al.  Estimation of variable coefficients in parabolic distributed systems , 1985 .

[12]  G. Smith,et al.  Numerical Solution of Partial Differential Equations: Finite Difference Methods , 1978 .

[13]  N. J. Lopes Cardozo,et al.  A model for electron transport barriers in tokamaks, tested against experimental data from RTP , 1998 .

[14]  Gerd Vandersteen,et al.  Frequency-domain system identification using non-parametric noise models estimated from a small number of data sets , 1997, Autom..

[15]  D. Ucinski.  Optimal measurement methods for distributed parameter system identification , 2004 .

[16]  Kazufumi Ito,et al.  Lagrange multiplier approach to variational problems and applications , 2008, Advances in design and control.

[17]  Graham C. Goodwin,et al.  Dynamic System Identification: Experiment Design and Data Analysis , 2012 .

[18]  Lennart Ljung,et al.  Some results on identifying linear systems using frequency domain data , 1993, Proceedings of 32nd IEEE Conference on Decision and Control.

[19]  E. Rafajłowicz.  Optimal experiment design for identification of linear distributed-parameter systems: Frequency domain approach , 1983 .

[20]  T Söderström,et al.  Parameter Estimation for Diffusion Models , 1999 .

[21]  D.G. Dudley,et al.  Dynamic system identification experiment design and data analysis , 1979, Proceedings of the IEEE.

[22]  Rik Pintelon,et al.  System Identification: A Frequency Domain Approach , 2012 .

[23]  Karl Kunisch,et al.  Cubic spline approximation techniques for parameter estimation in distributed systems , 1983 .

[24]  Karl Johan Åström.  Maximum likelihood and prediction error methods , 1980, Autom..

[25]  Umberto Soverini,et al.  Maximum likelihood identification of noisy input-output models , 2007, Autom..

[26]  Torsten Söderström,et al.  Errors-in-variables methods in system identification , 2018, Autom..

[27]  Torsten Söderström,et al.  Accuracy analysis of time domain maximum likelihood method and sample maximum likelihood method for errors-in-variables and output error identification , 2010, Autom..

[28]  Kenneth W Gentle,et al.  Dependence of heat pulse propagation on transport mechanisms: Consequences of nonconstant transport coefficients , 1988 .

[29]  T. A. Zang,et al.  Spectral methods for fluid dynamics , 1987 .

[30]  Patricia K. Lamm,et al.  Estimation of discontinuous coefficients in parabolic systems: applications to reservoir simulation , 1987 .

[31]  C. Vogel.  Computational Methods for Inverse Problems , 1987 .

[32]  N. R. Goodman.  Statistical analysis based on a certain multivariate complex Gaussian distribution , 1963 .

[33]  Ivan P. Gavrilyuk,et al.  Lagrange multiplier approach to variational problems and applications , 2010, Math. Comput..

[34]  Michael T. Heath,et al.  Scientific Computing , 2018 .

[35]  Rik Pintelon,et al.  Diffusion systems: stability, modeling, and identification , 2005, IEEE Transactions on Instrumentation and Measurement.

[36]  Hans Zwart,et al.  An Introduction to Infinite-Dimensional Linear Systems Theory , 1995, Texts in Applied Mathematics.

[37]  Graziella Pacelli,et al.  Inverse Problem for a Class of Two-Dimensional Diffusion Equations with Piecewise Constant Coefficients , 1999 .

[38]  Ruth F. Curtain,et al.  Survey paper: Transfer functions of distributed parameter systems: A tutorial , 2009 .

[39]  Karl Kunisch,et al.  Estimation of a temporally and spatially varying diffusion coefficient in a parabolic system by an augmented Lagrangian technique , 1991 .

[40]  Sabine Fenstermacher,et al.  Estimation Techniques For Distributed Parameter Systems , 2016 .

[41]  Khaled Jelassi,et al.  Comparison of identification techniques for fractional models , 2011, Eighth International Multi-Conference on Systems, Signals & Devices.