Transition Moving Horizon Estimation Using Multiple Linear Models

By transition estimation, it is meant a type of estimation method that is employed when the plant transitions from one operating state to another as a result of a set point change. This paper proposes an intelligent multiple model approach called moving horizon Bayesian estimation (MHBE) that can estimate the states of a nonlinear plant effectively. The nonlinear plant operates in multiple regimes and makes transitions between them. It is often difficult to obtain a single nonlinear model that accurately describes the plant in all regimes. An alternative approach is presented where local linear models are identified at each different operating point, and moving horizon estimation is performed by tracking the transitions from one regime to another. In this paper, simulation results for a numerical example and comparison results with the Kalman estimator are given, the result indicate that the method of MHBE is more effective than Kalman filter for constrained system.

[1]  C. Striebel.  Sufficient statistics in the optimum control of stochastic systems , 1965 .

[2]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[3]  S. Verdú,et al.  Abstract dynamic programming models under commutativity conditions , 1987 .

[4]  M. Morari,et al.  Moving horizon estimation for hybrid systems , 2002, Proceedings of the 2000 American Control Conference. ACC (IEEE Cat. No.00CH36334).

[5]  Jay H. Lee,et al.  A moving horizon‐based approach for least‐squares estimation , 1996 .

[6]  Thomas F. Edgar,et al.  Nonlinear state estimation , 1997 .

[7]  Eckhard Arnold,et al.  Nonlinear Moving Horizon State Estimation of an Activated Sludge Model , 2001 .

[8]  Jay H. Lee,et al.  Constrained linear state estimation - a moving horizon approach , 2001, Autom..

[9]  R. E. Kalman,et al.  New Results in Linear Filtering and Prediction Theory , 1961 .

[10]  L. Boillereaux,et al.  Moving Horizon State Estimation for a bioprocesses modelled by a neural network , 1997 .

[11]  M. Iri,et al.  An algorithm for diagnosis of system failures in the chemical process , 1979 .

[12]  C. V. Rao,et al.  Stability of constrained linear moving horizon estimation , 1999, Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251).

[13]  Arthur Gelb,et al.  Applied Optimal Estimation , 1974 .

[14]  T. Johansen,et al.  Constructing NARMAX models using ARMAX models , 1993 .

[15]  James B. Rawlings,et al.  Critical Evaluation of Extended Kalman Filtering and Moving-Horizon Estimation , 2005 .

[16]  Francis J. Doyle,et al.  Use of multiple models and qualitative knowledge for on-line moving horizon disturbance estimation and fault diagnosis , 2002 .

[17]  A. Rueda,et al.  Approximation of nonlinear systems by dynamic selection of linear models , 1996, Proceedings of 1996 Canadian Conference on Electrical and Computer Engineering.

[18]  Tor Arne Johansen,et al.  Nonlinear Predictive Control Using Local Models -Applied to a Batch Process , 1994 .