Frequency Response Function Estimation in the Presence of Missing Output Data

Frequency response function (FRF) estimation is part of nonparametric system identification in the frequency domain. The FRF measurements give a quick but deep insight into the dynamics of complex systems. Data samples can get lost in some applications due to sensor failure and/or data transmission errors. We want to overcome this problem without having to repeat the measurement and/or the experiment because this can be either impossible or too expensive. In this paper, we propose a nonparametric method for estimating the FRF and its variance of a single-input single-output system from known input and noisy output measurements with missing output samples. No particular pattern of the missing data is assumed. Moreover, the proposed method provides an estimate of the missing data and its uncertainty.

[1]  P. Welch.  The use of fast Fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms , 1967 .

[2]  Soummya Kar,et al.  Distributed Consensus Algorithms in Sensor Networks With Imperfect Communication: Link Failures and Channel Noise , 2007, IEEE Transactions on Signal Processing.

[3]  J. W. Tukey,et al.  The Measurement of Power Spectra from the Point of View of Communications Engineering , 1958 .

[4]  J. Antoni.  Leakage-free identification of FRF's with the discrete time Fourier transform , 2006 .

[5]  Rik Pintelon,et al.  Identification of continuous-time systems with missing data , 1999, IEEE Trans. Instrum. Meas..

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

[7]  V. Hardman,et al.  A survey of packet loss recovery techniques for streaming audio , 1998, IEEE Network.

[8]  Alf Isaksson,et al.  Identification of ARX-models subject to missing data , 1993, IEEE Trans. Autom. Control..

[9]  Svante Gunnarsson,et al.  Estimation of Nonlinear Effects in Frequency Domain Identification of Industrial Robots , 2008, IEEE Transactions on Instrumentation and Measurement.

[10]  Yves Rolain,et al.  Frequency Response Function Measurements Using Concatenated Subrecords With Arbitrary Length , 2012, IEEE Transactions on Instrumentation and Measurement.

[11]  Roderick J. A. Little,et al.  Statistical Analysis with Missing Data: Little/Statistical Analysis with Missing Data , 2002 .

[12]  Piet M. T. Broersen,et al.  Autoregressive spectral analysis when observations are missing , 2004, Autom..

[13]  Wendy Van Moer,et al.  A Simple Nonparametric Preprocessing Technique to Correct for Nonstationary Effects in Measured Data , 2012, IEEE Transactions on Instrumentation and Measurement.

[14]  Taghi M. Khoshgoftaar,et al.  A comprehensive empirical evaluation of missing value imputation in noisy software measurement data , 2008, J. Syst. Softw..

[15]  Johan A. K. Suykens,et al.  Wiener-Hammerstein Benchmark , 2009 .

[16]  Ivan Markovsky,et al.  Structured Low-Rank Approximation with Missing Data , 2013, SIAM J. Matrix Anal. Appl..

[17]  J. Schoukens,et al.  Estimation of nonparametric noise and FRF models for multivariable systems—Part II: Extensions, applications , 2010 .

[18]  D. Rubin,et al.  Statistical Analysis with Missing Data , 1988 .

[19]  Gerd Vandersteen,et al.  Nonparametric preprocessing in system identification: A powerful tool , 2009, 2009 European Control Conference (ECC).

[20]  Yves Rolain,et al.  Bounding the Polynomial Approximation Errors of Frequency Response Functions , 2013, IEEE Transactions on Instrumentation and Measurement.

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

[22]  Jian Li,et al.  Missing Data Recovery Via a Nonparametric Iterative Adaptive Approach , 2009, IEEE Signal Processing Letters.

[23]  Graham C. Goodwin,et al.  Dual time-frequency domain system identification , 2012, Autom..

[24]  Gene H. Golub,et al.  Matrix computations (3rd ed.) , 1996 .

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

[26]  Yves Rolain,et al.  Improved (non-)parametric identification of dynamic systems excited by periodic signals—The multivariate case , 2011 .