A Method for Identification of Markovian Jump ARX Processes

Abstract In this paper, we address the problem of identification of Markovian jump ARX systems in the case where there is no a priori knowledge on the statistics of the process noise. The only assumptions made are the availability of known upper bounds on the subsystems order and noise level. The proposed method leverages available results to identify the subsystems models and provides a novel way to estimate the transition probability matrix of the switching in the presence of uncertainty. More precisely, since one cannot observe the exact switching sequence, the problem of estimating the transition probability matrix is formulated as a robust optimization problem, where one maximizes the minimum of the probability of all possible switching sequences. We show that this robust optimization problem can be efficiently solved by providing an equivalent convex formulation that can be solved using off-the-shelf software. Several academic examples are provided which illustrate the effectiveness of proposed approach.

[1]  Carlos E. de Souza,et al.  Robust stability and stabilization of uncertain discrete-time Markovian jump linear systems , 2006, IEEE Transactions on Automatic Control.

[2]  Yugang Niu,et al.  Adaptive sliding mode control for stochastic Markovian jumping systems with actuator degradation , 2013, Autom..

[3]  Jitendra Tugnait.  Detection and estimation for abruptly changing systems , 1981, CDC 1981.

[4]  Mübeccel Demirekler,et al.  Maximum Likelihood Estimation of Transition Probabilities of Jump Markov Linear Systems , 2008, IEEE Transactions on Signal Processing.

[5]  Fredrik Lindsten,et al.  Identification of jump Markov linear models using particle filters , 2014, 53rd IEEE Conference on Decision and Control.

[6]  Y. Sawaragi,et al.  Adaptive estimation for a linear system with interrupted observation , 1973 .

[7]  Lei Guo,et al.  Composite anti-disturbance control for Markovian jump nonlinear systems via disturbance observer , 2013, Autom..

[8]  S. Shankar Sastry,et al.  Generalized principal component analysis (GPCA) , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Li Li,et al.  Decentralized robust control of uncertain Markov jump parameter systems via output feedback , 2006, 2006 American Control Conference.

[10]  Jitendra K. Tugnait,et al.  A detection-estimation scheme for state estimation in switching environments , 1979, Autom..

[11]  Constantino M. Lagoa,et al.  Set membership identification of switched linear systems with known number of subsystems , 2015, Autom..

[12]  Peng Shi,et al.  A survey on Markovian jump systems: Modeling and design , 2015 .

[13]  M. Athans,et al.  State Estimation for Discrete Systems with Switching Parameters , 1978, IEEE Transactions on Aerospace and Electronic Systems.

[14]  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).

[15]  G. Wang.  ML Estimation of Transition Probabilities in Jump Markov Systems via Convex Optimization , 2010, IEEE Transactions on Aerospace and Electronic Systems.

[16]  Jitendra Tugnait,et al.  Adaptive estimation and identification for discrete systems with Markov jump parameters , 1981, 1981 20th IEEE Conference on Decision and Control including the Symposium on Adaptive Processes.

[17]  X. R. Li,et al.  Online Bayesian estimation of transition probabilities for Markovian jump systems , 2004, IEEE Transactions on Signal Processing.

[18]  Khashayar Khorasani,et al.  A Decentralized Markovian Jump ${\cal H}_{\infty}$ Control Routing Strategy for Mobile Multi-Agent Networked Systems , 2011, IEEE Transactions on Control Systems Technology.

[19]  James Lam,et al.  Stabilization of discrete-time Markovian jump linear systems via time-delayed controllers , 2006, Autom..

[20]  Sean B. Andersson,et al.  A Sequential Monte Carlo framework for the system identification of jump Markov state space models , 2014, 2014 American Control Conference.