ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Variance-Reduced Particle Filters for Structural System Identification Problems

Chowdhury, Roy S and Roy, D and Vasu, RM (2013) Variance-Reduced Particle Filters for Structural System Identification Problems. In: JOURNAL OF ENGINEERING MECHANICS-ASCE, 139 (2). pp. 210-218.

[img] PDF
jl_eng_mec_asc_139_2_210_2013.pdf - Published Version
Restricted to Registered users only

Download (965Kb) | Request a copy
Official URL: http://dx.doi.org/10.1061/(ASCE)EM.1943-7889.00004...

Abstract

A few variance reduction schemes are proposed within the broad framework of a particle filter as applied to the problem of structural system identification. Whereas the first scheme uses a directional descent step, possibly of the Newton or quasi-Newton type, within the prediction stage of the filter, the second relies on replacing the more conventional Monte Carlo simulation involving pseudorandom sequence with one using quasi-random sequences along with a Brownian bridge discretization while representing the process noise terms. As evidenced through the derivations and subsequent numerical work on the identification of a shear frame, the combined effect of the proposed approaches in yielding variance-reduced estimates of the model parameters appears to be quite noticeable. DOI: 10.1061/(ASCE)EM.1943-7889.0000480. (C) 2013 American Society of Civil Engineers.

Item Type: Journal Article
Related URLs:
Additional Information: Copyright for this article belongs to the ASCE-AMER SOC CIVIL ENGINEERS, USA.
Keywords: Directed bootstrap filter; Gain-based direction; Quasi-Newton direction; Quasi-Monte Carlo simulations; Structural system identification
Department/Centre: Division of Mechanical Sciences > Civil Engineering
Division of Physical & Mathematical Sciences > Instrumentation and Applied Physics (Formally ISU)
Date Deposited: 29 Apr 2013 09:06
Last Modified: 29 Apr 2013 09:06
URI: http://eprints.iisc.ernet.in/id/eprint/46467

Actions (login required)

View Item View Item