A randomized two-stage iterative method for switched nonlinear systems identification

Abstract This paper addresses the identification of discrete time switched nonlinear systems, which are collections of discrete time nonlinear continuous systems (modes) indexed by a finite-valued variable defining the current mode. In particular, we consider the class of Switched Nonlinear AutoRegressive eXogenous (Switched NARX, or SNARX) models, where the continuous dynamics are represented by NARX models. Given a set of input–output data, the identification of a SNARX model for the underlying system involves the simultaneous identification of the mode sequence and of the NARX model associated to each mode, configuring a mixed integer non-convex optimization problem, hardly solvable in practice due to the large combinatorial complexity. In this paper, we propose a black-box iterative identification method, where each iteration is characterized by two stages. In the first stage the identification problem is addressed assuming that mode switchings can occur only at predefined time instants, while in the second one the candidate mode switching locations are refined. This strategy allows to significantly reduce the combinatorial complexity of the problem, thus allowing an efficient solution of the optimization problem. The combinatorial optimization is addressed using a randomized method, whereby the sample-mode map and the SNARX model structure are characterized by a probability distribution, which is progressively tuned via a sample-and-evaluate strategy, until convergence to a limit distribution concentrated on the best SNARX model of the system generating the observed data.

[1]  L. Ljung,et al.  Segmentation of Time Series from Nonlinear Dynamical Systems , 2011 .

[2]  I. J. Leontaritis,et al.  Input-output parametric models for non-linear systems Part II: stochastic non-linear systems , 1985 .

[3]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[4]  Luigi Piroddi,et al.  A randomized algorithm for nonlinear model structure selection , 2015, Autom..

[5]  Gianluigi Pillonetto,et al.  A new kernel-based approach to hybrid system identification , 2016, Autom..

[6]  Alberto Bemporad,et al.  A bounded-error approach to piecewise affine system identification , 2005, IEEE Transactions on Automatic Control.

[7]  René Vidal,et al.  Identification of Hybrid Systems: A Tutorial , 2007, Eur. J. Control.

[8]  Manfred Morari,et al.  A clustering technique for the identification of piecewise affine systems , 2001, Autom..

[9]  Henrik Ohlsson,et al.  Identification of switched linear regression models using sum-of-norms regularization , 2013, Autom..

[10]  René Vidal,et al.  A continuous optimization framework for hybrid system identification , 2011, Autom..

[11]  Alberto Bemporad,et al.  Identification of piecewise affine systems via mixed-integer programming , 2004, Autom..

[12]  Gérard Bloch,et al.  Hybrid System Identification , 2019 .

[13]  Gérard Bloch,et al.  Reduced-Size Kernel Models for Nonlinear Hybrid System Identification , 2011, IEEE Transactions on Neural Networks.

[14]  A. Juloski,et al.  A Bayesian approach to identification of hybrid systems , 2004, CDC.

[15]  Laurent Bako,et al.  Identification of switched linear systems via sparse optimization , 2011, Autom..

[16]  S. Billings.  Nonlinear System Identification: NARMAX Methods in the Time, Frequency, and Spatio-Temporal Domains , 2013 .

[17]  Joao Xavier,et al.  Identification of switched ARX models via convex optimization and expectation maximization , 2015 .

[18]  D. Jacobson,et al.  Optimization of stochastic linear systems with additive measurement and process noise using exponential performance criteria , 1974 .

[19]  Constantino M. Lagoa,et al.  A Sparsification Approach to Set Membership Identification of Switched Affine Systems , 2012, IEEE Transactions on Automatic Control.