Identification of power spectra by reweighted and regularized nuclear norm minimization

In this paper, we study model order choice in subspace identification algorithms using uniformly spaced spectrum measurements. In these algorithms, model order is determined by singular-value decomposition of a structured matrix constructed from spectrum measurements. This process requires splitting of the two invariant subspaces associated with the causal and the non-causal system poles presumed to be mirror image symmetric with respect to the unit circle. Due to noise, undermodelling, and insufficient amount of data, this symmetry is lost. Recently, a robust model order selection procedure based on the regularized nuclear norm optimization was proposed. We propose a reweighted version of this scheme. Numerical and real-life examples in this paper show that the reweighted nuclear norm minimization makes model order selection easier and results in more accurate models compared to the subspace approaches and the unweighted nuclear norm minimization, in particular at high signal-to-noise ratios.

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

[2]  Jan Swevers,et al.  A subspace algorithm for the identification of discrete time frequency domain power spectra , 1997, Autom..

[3]  M. Mesbahi.  On the rank minimization problem and its control applications , 1998 .

[4]  Susan A. Murphy,et al.  Linear fitted-Q iteration with multiple reward functions , 2013, J. Mach. Learn. Res..

[5]  Alexander J. Smola,et al.  Learning with kernels , 1998 .

[6]  Hüseyin Akçay,et al.  Nuclear Norm Spectrum Estimation From Uniformly Spaced Measurements , 2014, IEEE Transactions on Automatic Control.

[7]  Semiha Turkay,et al.  A study of random vibration characteristics of the quarter-car model , 2005 .

[8]  Michel Verhaegen,et al.  Optimal and robust feedback controller estimation for a vibrating plate , 2004 .

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

[10]  Huseyin Akcay,et al.  Subspace-Based Identification of Acoustic Noise Spectra in Induction Motors , 2015, IEEE Transactions on Energy Conversion.

[11]  M. Fazel,et al.  Reweighted nuclear norm minimization with application to system identification , 2010, Proceedings of the 2010 American Control Conference.

[12]  Hüseyin Akçay,et al.  Positive realness in stochastic subspace identification: A regularized and reweighted nuclear norm minimization approach , 2015, 2015 European Control Conference (ECC).

[13]  Hüseyin Akçay,et al.  Frequency domain subspace-based identification of discrete-time power spectra from nonuniformly spaced measurements , 2004, Autom..

[14]  Michael B. Wakin,et al.  An Introduction To Compressive Sampling [A sensing/sampling paradigm that goes against the common knowledge in data acquisition] , 2008 .

[15]  Stephen P. Boyd,et al.  Log-det heuristic for matrix rank minimization with applications to Hankel and Euclidean distance matrices , 2003, Proceedings of the 2003 American Control Conference, 2003..

[16]  E.J. Candes,et al.  An Introduction To Compressive Sampling , 2008, IEEE Signal Processing Magazine.

[17]  Jorge Mari,et al.  Modifications of rational transfer matrices to achieve positive realness , 2000, Signal Process..

[18]  Tohru Katayama,et al.  Subspace Methods for System Identification , 2005 .

[19]  Bart De Moor,et al.  Subspace Identification for Linear Systems: Theory ― Implementation ― Applications , 2011 .

[20]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..

[21]  Hüseyin Akçay,et al.  Subspace-based spectrum estimation in frequency-domain by regularized nuclear norm minimization , 2014, Signal Process..

[22]  Hüseyin Akçay,et al.  Frequency domain subspace-based identification of discrete-time singular power spectra from uniformly spaced measurements , 2012, 2012 American Control Conference (ACC).

[23]  W. Marsden.  I and J , 2012 .

[24]  Stephen P. Boyd,et al.  A rank minimization heuristic with application to minimum order system approximation , 2001, Proceedings of the 2001 American Control Conference. (Cat. No.01CH37148).

[25]  Hüseyin Akçay,et al.  Spectral estimation in frequency-domain by subspace techniques , 2014, Signal Process..

[26]  Zhang Liu,et al.  Nuclear norm system identification with missing inputs and outputs , 2013, Syst. Control. Lett..

[27]  Maryam Fazel,et al.  Iterative reweighted algorithms for matrix rank minimization , 2012, J. Mach. Learn. Res..

[28]  Sara van de Geer,et al.  Statistics for High-Dimensional Data , 2011 .