Initial estimates for Wiener-Hammerstein models using phase-coupled multisines

Block-oriented models are often used to model nonlinear systems. These models consist of linear dynamic (L) and nonlinear static (N) sub-blocks. This paper addresses the generation of initial estimates for a Wiener-Hammerstein model (LNL cascade). While it is easy to measure the product of the two linear blocks using a Gaussian excitation and linear identification methods, it is difficult to split the global dynamics over the individual blocks. This paper first proposes a well-designed multisine excitation with pairwise coupled random phases. Next, a modified best linear approximation is estimated on a shifted frequency grid. It is shown that this procedure creates a shift of the input dynamics with a known frequency offset, while the output dynamics do not shift. The resulting transfer function, which has complex coefficients due to the frequency shift, is estimated with a modified frequency domain estimation method. The identified poles and zeros can be assigned to either the input or output dynamics. Once this is done, it is shown in the literature that the remaining initialization problem can be solved much easier than the original one. The method is illustrated on experimental data obtained from the Wiener-Hammerstein benchmark system.

[1]  Yves Rolain,et al.  Structure discrimination in block-oriented models using linear approximations: A theoretic framework , 2015, Autom..

[2]  David Rees,et al.  Identification of nonlinear cascade systems using paired multisine signals , 1998, IEEE Trans. Instrum. Meas..

[3]  Er-Wei Bai,et al.  Identification of a modified Wiener-Hammerstein system and its application in electrically stimulated paralyzed skeletal muscle modeling , 2009, Autom..

[5]  C. H. Chen,et al.  Maximum likelihood identification of stochastic Weiner-Hammerstein-type non-linear systems , 1992 .

[6]  M. J. Korenberg,et al.  The identification of nonlinear biological systems: LNL cascade models , 1986, Biological Cybernetics.

[7]  S. Paszkowski,et al.  On the Weierstrass approximation theorem , 1957 .

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

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

[10]  Brett Ninness,et al.  Generalised Hammerstein–Wiener system estimation and a benchmark application , 2012 .

[11]  Stephen A. Billings,et al.  Identification of systems containing linear dynamic and static nonlinear elements , 1982, Autom..

[12]  Yves Rolain,et al.  Identification of Wiener-Hammerstein systems by a nonparametric separation of the best linear approximation , 2014, Autom..

[13]  Yves Rolain,et al.  Non-parametric Estimation of the Frequency-response Functions of the Linear Blocks of a Wiener-Hammerstein Model , 1997, Autom..

[14]  Yves Rolain,et al.  Identification of linear systems with nonlinear distortions , 2003, Autom..

[15]  Johan Schoukens,et al.  Identification of Wiener–Hammerstein models: Two algorithms based on the best split of a linear model applied to the SYSID'09 benchmark problem , 2012 .

[16]  Johan Schoukens,et al.  Initializing Wiener-Hammerstein models based on partitioning of the best linear approximation , 2012, Autom..

[17]  E. Bai,et al.  Block Oriented Nonlinear System Identification , 2010 .

[18]  Yves Rolain,et al.  IDENTIFICATION OF ROTOR-BEARING SYSTEMS IN THE FREQUENCY DOMAIN PART II: ESTIMATION OF MODAL PARAMETERS , 2001 .

[19]  D. Ridley,et al.  Cape Town, South Africa , 1986, Journal of clinical ultrasound : JCU.

[20]  Yves Rolain,et al.  Mastering System Identification in 100 Exercises , 2012 .

[21]  Johan Schoukens,et al.  Generating initial estimates for Wiener-Hammerstein systems using phase coupled multisines , 2014 .

[22]  Johan Schoukens,et al.  Initial estimates of the linear subsystems of Wiener-Hammerstein models , 2012, Autom..

[23]  Johan Schoukens,et al.  Computing an initial estimate of a Wiener-Hammerstein system with a random phase multisine excitation , 2005, IEEE Transactions on Instrumentation and Measurement.

[24]  M. Isaksson,et al.  A comparative analysis of behavioral models for RF power amplifiers , 2006, IEEE Transactions on Microwave Theory and Techniques.

[25]  David M. Simpson,et al.  Wiener-Hammerstein Parameter Estimation using Differential Evolution - Application to Limb Reflex Dynamics , 2010, BIOSIGNALS.

[26]  Han-Fu Chen,et al.  Recursive identification of errors-in-variables Wiener-Hammerstein systems , 2014, Eur. J. Control.

[27]  Julian J. Bussgang,et al.  Crosscorrelation functions of amplitude-distorted gaussian signals , 1952 .