Smart technique for identifying hybrid systems

The paper describes a system identification method for a nonlinear system based on a multi-point linear approximation. We show that under mild assumptions, the task can be transformed into a series of one-dimensional approximations, for which we propose an efficient solution method based on solving simple nonlinear programs (NLPs). The approach provides identification of nonlinear systems in a polynomial model structure (ARX, OE, BJ) from input-output data. The approximation is based on a neural network modelling procedure. The proposed modelling procedure is characterized by fast training, adjustable accuracy and reduced complexity of the final model. The modelling technique is widely applicable in automotive, power electronics, computer graphics, etc.

[1]  Bart De Schutter,et al.  Model predictive control for max-plus-linear discrete event systems , 2001, Autom..

[2]  P. Julián,et al.  High-level canonical piecewise linear representation using a simplicial partition , 1999 .

[3]  Michael S. Branicky,et al.  Studies in hybrid systems: modeling, analysis, and control , 1996 .

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

[5]  Satchidananda Dehuri,et al.  A Novel Learning Scheme for Chebyshev Functional Link Neural Networks , 2011, Adv. Artif. Neural Syst..

[6]  S. Kozák,et al.  Improved Piecewise Linear Approximation of Nonlinear Functions in Hybrid Control , 2011 .

[7]  Ton J.J. van den Boom,et al.  On model predictive control for max-min-plus-scaling discrete event systems , 2010 .

[8]  Christodoulos A. Floudas,et al.  A global optimization method, αBB, for process design , 1996 .

[9]  Ching-Shiow Tseng,et al.  Properties and performance of orthogonal neural network in function approximation , 2001, Int. J. Intell. Syst..

[10]  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).

[11]  Ching-Shiow Tseng,et al.  Performance comparison between the training method and the numerical method of the orthogonal neural network in function approximation , 2004 .

[12]  Alex ChiChung Kot,et al.  Nonlinear dynamic system identification using Chebyshev functional link artificial neural networks , 2002, IEEE Trans. Syst. Man Cybern. Part B.

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

[14]  F. W. Paul,et al.  A Fourier Series Neural Network and Its Application to System Identification , 1995 .

[15]  Deepak Shukla,et al.  Orthogonal functions for systems identification and control , 1998 .

[16]  Eduardo Sontag.  Nonlinear regulation: The piecewise linear approach , 1981 .

[17]  W. P. M. H. Heemels,et al.  Linear Complementarity Systems , 2000, SIAM J. Appl. Math..

[18]  Richard C. Larson,et al.  Model Building in Mathematical Programming , 1979 .

[19]  Alberto Bemporad,et al.  Control of systems integrating logic, dynamics, and constraints , 1999, Autom..

[20]  Alberto Bemporad,et al.  HYSDEL-a tool for generating computational hybrid models for analysis and synthesis problems , 2004, IEEE Transactions on Control Systems Technology.