Kernelized Identification of Linear Parameter-Varying Models with Linear Fractional Representation

The article presents a method for the identification of Linear Parameter-Varying (LPV) models in a Linear Fractional Representation (LFR), which corresponds to a Linear Time-Invariant (LTI) model connected to a scheduling variable dependency via a feedback path. A two-stage identification approach is proposed. In the first stage, Kernelized Canonical Correlation Analysis (KCCA) is formulated to estimate the state sequence of the underlying LPV model. In the second stage, a non-linear least squares cost function is minimized by employing a coordinate descent algorithm to estimate latent variables characterizing the LFR and the unknown model matrices of the LTI block by using the state estimates obtained at the first stage. Here, it is assumed that the structure of the scheduling variable dependent block in the feedback path is fixed. For a special case of affine dependence of the model on the feedback block, it is shown that the optimization problem in the second stage reduces to ordinary least-squares followed by a singular value decomposition.

[1]  R. Shah,et al.  Least Squares Support Vector Machines , 2022 .

[2]  Alberto Bemporad,et al.  A bias-correction method for closed-loop identification of Linear Parameter-Varying systems , 2018, Autom..

[3]  Marco Lovera,et al.  Identification of LPV State Space Models for Autonomic Web Service Systems , 2011, IEEE Transactions on Control Systems Technology.

[4]  K. Poolla,et al.  Identification of linear parameter-varying systems via LFTs , 1996, Proceedings of 35th IEEE Conference on Decision and Control.

[5]  Lawton H. Lee,et al.  Identification of Linear Parameter-Varying Systems Using Nonlinear Programming , 1999 .

[6]  B. Ninness,et al.  System identification of linear parameter varying state-space models , 2011 .

[7]  Roland Tóth,et al.  LPV system identification under noise corrupted scheduling and output signal observations , 2015, Autom..

[8]  Mario Sznaier,et al.  Identification of LPV systems with LFT parametric dependence via convex optimization , 2015, 2015 54th IEEE Conference on Decision and Control (CDC).

[9]  Vincent Verdult,et al.  Kernel methods for subspace identification of multivariable LPV and bilinear systems , 2005, Autom..

[10]  Javad Mohammadpour,et al.  State-space LPV model identification using kernelized machine learning , 2018, Autom..

[11]  Michael I. Jordan,et al.  Kernel independent component analysis , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[12]  R. Ravikanth,et al.  Identification of linear parametrically varying systems , 1995, Proceedings of 1995 34th IEEE Conference on Decision and Control.

[13]  Michel Verhaegen,et al.  Subspace identification of Bilinear and LPV systems for open- and closed-loop data , 2009, Autom..

[14]  C. Scherer.  Mixed H2/H∞ control for time‐varying and linear parametrically‐varying systems , 1996 .

[15]  Alireza Karimi,et al.  On the Consistency of Certain Identification Methods for Linear Parameter Varying Systems , 2008 .

[16]  J. Suykens,et al.  Least Squares Support Vector Machines for Kernel CCA in Nonlinear State-Space Identification , 2004 .

[17]  Alberto Bemporad,et al.  Regularized least square support vector machines for order and structure selection of LPV-ARX models , 2016, 2016 European Control Conference (ECC).

[18]  Paul M.J. Van den Hof,et al.  Prediction-Error Identification of LPV Systems: Present and Beyond , 2012 .

[19]  J. Doyle,et al.  Essentials of Robust Control , 1997 .

[20]  Roland Toth,et al.  Modeling and Identification of Linear Parameter-Varying Systems , 2010 .