Elsevier

Automatica

Volume 34, Issue 4, April 1998, Pages 469-475
Automatica

Brief Paper
A Multi-model Algorithm for Parameter Estimation of Time-varying Nonlinear Systems

https://doi.org/10.1016/S0005-1098(97)00203-3Get rights and content

Abstract

We present a new on-line multi-model algorithm for parameter estimation of time-varying nonlinear systems. The time variation is captured by assuming that the system parameters change according to a Markovian mechanism. The algorithm postulates a finite number of possible values of the system parameter and computes recursively the credit function of each parameter value, according to its predictive accuracy. A convergence analysis of the algorithm is presented which indicates that the algorithm estimates correctly the parameter value in the time intervals between source switchings. This conclusion is corroborated by numerical experiments.

References (0)

Cited by (33)

  • DeepMTT: A deep learning maneuvering target-tracking algorithm based on bidirectional LSTM network

    2020, Information Fusion
    Citation Excerpt :

    Many modified IMM algorithms [12–14] were proposed for specific scenarios of maneuvering-target tracking, such as nonlinear, non-Gaussian and multi-target tracking scenarios. On the other hand, model-set design algorithms were proposed to offer better model approximations in maneuvering-target tracking procedures, such as fixed structure MM (FSMM) [15,16] and variable structure MM (VSMM) [9,17] algorithms. Recently, advanced MM algorithms such as the MIE-BLUE-IMM [18] and hybrid grid MM (HGMM) [19] algorithms have been proposed, where more information, i.e., input estimation [18] and adaptive fine sub-models [19], is offered in the tracking processing.

  • An optimization approach to adaptive Kalman filtering

    2011, Automatica
    Citation Excerpt :

    Since MMAE operates under the assumption that one of the models in the model bank is the right one, it is an unsuitable method for systems with unknown dynamics. It has been shown in the series of papers Baram and Sandell (1978), Li (1994, 2000), Li and Bar-Shalom (1994, 1996), Li and Jilkov (2005), Li, Jilkov, and Ru (2005), Li and Zhang (2000), Li, Zhang, and Zhi (1999), Li, Zwi, and Zwang (1999), Petridis and Kehagias (1998) and that using too large a model bank actually decreases performance since, in that case, the true model gets too much competition from false models. Therefore safeguarding with a lot of plausible system models is not an option.

View all citing articles on Scopus

This paper was recommended for Publication in revised form by Associate Editor Brett Ninness under the direction of Editor Torsten Söderström.

View full text