Subspace-based Continuous-time Model Identification Using Nuclear Norm Minimization

Abstract This paper aims at finding a new way to implement subspace-based continuoustime model identification methods in noise corrupted case. A novel nuclear norm method for continuous-time model is first proposed. A connection between the noise constraint and optimization variables is solved during constructing the optimization problem. Finally, a simple numerical simulation is accomplished to show the efficacy of the proposed method.

[1]  Peter C. Young,et al.  The advantages of directly identifying continuous-time transfer function models in practical applications , 2014, Int. J. Control.

[2]  A. Swindlehurst,et al.  Subspace-based signal analysis using singular value decomposition , 1993, Proc. IEEE.

[3]  Roy S. Smith,et al.  Nuclear norm minimization methods for frequency domain subspace identification , 2012, 2012 American Control Conference (ACC).

[4]  Michel Verhaegen,et al.  Stochastic theory of continuous-time state-space identification , 1999, IEEE Trans. Signal Process..

[5]  Hugues Garnier,et al.  Parameter and differentiation order estimation in fractional models , 2013, Autom..

[6]  Roy S. Smith,et al.  Frequency Domain Subspace Identification Using Nuclear Norm Minimization and Hankel Matrix Realizations , 2014, IEEE Transactions on Automatic Control.

[7]  Lieven Vandenberghe,et al.  Interior-Point Method for Nuclear Norm Approximation with Application to System Identification , 2009, SIAM J. Matrix Anal. Appl..

[8]  F. Paganini.  A set-based approach for white noise modeling , 1996, IEEE Trans. Autom. Control..

[9]  Bart De Moor,et al.  The singular value decomposition and long and short spaces of noisy matrices , 1993, IEEE Trans. Signal Process..

[10]  H. Garnier,et al.  A PMF-based subspace method for continuous-time model identification. Application to a multivariable winding process , 2001 .

[11]  G. P. Rao,et al.  A general algorithm for parameter identification in lumped continuous systems--The Poisson moment functional approach , 1982 .

[12]  M. Gilson,et al.  Robust identification of continuous-time models with arbitrary time-delay from irregularly sampled data , 2015 .