Two Stage Identification of Linear Switched Systems

The aim of this paper is to propose an identification scheme for linear switched systems with state space description. The method consists of two stages: first, output matrix elements are identified by Kaczmarz Algorithm and then by k-means clustering algorithm, switching time is estimated; Second, by passing the estimated switching time to an adaptive observer in serial-parallel form, input and state matrices are estimated. Identification method is tested on numerical simulation.

[1]  Wilfrid Perruquetti,et al.  Real-time estimation of the switching signal for perturbed switched linear systems , 2009, ADHS.

[2]  Zhuo Wang,et al.  From model-based control to data-driven control: Survey, classification and perspective , 2013, Inf. Sci..

[3]  J. Ragot,et al.  Identification of switching systems using change detection technique in the subspace framework , 2004, 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601).

[4]  R. Sznajder.  Kaczmarz algorithm revisited , 2016 .

[5]  Martin Buss,et al.  Adaptive identification of continuous-time switched linear and piecewise linear systems , 2014, 2014 European Control Conference (ECC).

[6]  S. Sastry,et al.  An algebraic geometric approach to the identification of a class of linear hybrid systems , 2003, 42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475).

[7]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2008, Pattern Recognit. Lett..

[8]  Vincent Cocquempot,et al.  Switching Time Estimation and Fault Detection for Hybrid Systems Using Structured Parity Residuals , 2003 .

[9]  Wilfrid Perruquetti,et al.  Algebraic switching time identification for a class of linear hybrid systems , 2011, ADHS.

[10]  A. Garulli,et al.  A survey on switched and piecewise affine system identification , 2012 .

[11]  L. Ljung,et al.  Identification of Piecewise Affine Systems Using Sum-of-Norms Regularization , 2011 .

[12]  Bart De Schutter,et al.  Equivalence of hybrid dynamical models , 2001, Autom..