Gaussian mixture model for time series-based structural damage detection

Abstract

In this paper, a time series-based damage detection algorithm is proposed using Gaussian mixture model (GMM) and expectation maximization (EM) framework. The vibration time series from the structure are modelled as the autoregressive (AR) processes. The first AR coefficients are used as a feature vector for novelty detection. To test the efficacy of the damage detection algorithm, it has been tested on the pseudo-experimental data obtained from the FEM model of the ASCE benchmark frame structure. Results suggest that the presented approach is able to detect mainly major and moderate damage patterns.