Genetic adaptive state estimation with missing input/output data

• Published in: Proceedings of the Institution of Mechanical Engineers. Part I, Journal of systems and control engineering Vol. 224; no. 5; pp. 611 - 617
• Main Authors: Fang, H, Wu, J, Shi, Y
• Format: Journal Article
• Language: English
• Published: London, England SAGE Publications 01.08.2010; SAGE PUBLICATIONS, INC
• Subjects: Adaptive algorithms; Autoregressive models; Autoregressive processes; Computer simulation; Genetic algorithms; Input output; Mathematical models; Mechanical engineering; Missing data; Parameter estimation; Preprocessing; Reconstruction; Simulation; State estimation; recursive algorithm; parameter estimation; genetic algorithms; missing input/output data
• ISSN: 0959-6518; 2041-3041
• DOI: 10.1243/09596518JSCE888

Abstract This paper presents the application of a genetic algorithm to state estimation for systems subject to randomly missing input/output data. By modelling the missing data in inputs and outputs with binomial processes, a modified Luenberger observer using the reconstructed data is employed for estimation. The proposed algorithm consists of two procedures: 1) Preprocessing the missing input/output data by reconstruction based on autoregressive (AR) modelling; and 2) implementing the genetic algorithm to perform on-line adaptive state estimation from reconstructed data. The effectiveness of the proposed algorithm is verified by numerical simulation.