Online damage detection using recursive principal component analysis

Tools

Bhowmik, B. and Krishnan, M. and Hazra, B. and Pakrashi, V. (2017) Online damage detection using recursive principal component analysis. Procedia Engineering, 199. pp. 2108-2113. ISSN 1877-7058 (https://doi.org/10.1016/j.proeng.2017.09.067)

[thumbnail of Bhowmik-etal-PE-2017-Online-damage-detection-using-recursive-principal-component]
Preview
 Text. Filename: Bhowmik-etal-PE-2017-Online-damage-detection-using-recursive-principal-component.pdf
Final Published Version
License: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 logo
Download (2MB)| Preview

Abstract

In this paper, a novel baseline free approach for continuous online damage detection of multi degree of freedom vibrating structures using Recursive Principle Component Analysis (RPCA) in conjunction with online damage indicators is proposed. The RPCA algorithm iterates the eigenvector and eigenvalue estimates for sample covariance matrices and new data point at each successive time instants, to obtain recursive proper orthogonal modes online using the rank-one perturbation method. The proposed method when applied to streaming data, eliminates the need for offline post processing. Numerical simulations performed on 5-DOF nonlinear system under white noise excitations, with different levels of damage demonstrate the robustness and efficacy of the proposed methodology as an ideal candidate for real-time, reference free structural health monitoring.

ORCID iDs

Bhowmik, B. ORCID logoORCID: https://orcid.org/0000-0001-7782-513X, Krishnan, M., Hazra, B. and Pakrashi, V.;
CORE (COnnecting REpositories)