An iterative order determination method for time-series modeling in structural health monitoring

Abstract

Statistical time-series modeling has recently emerged as a promising and applicable methodology to structural health monitoring. In this methodology, an important step is to choose robust and optimal orders of time-series models for extracting damage-sensitive features. In this study, an iterative order determination method is proposed to determine optimal orders based on residual analysis. The proposed technique consists of identifying the best time-series model, determining the maximum orders, and selecting the optimal orders that enable the model to extract uncorrelated residuals. The application of low-pass signal filters to the process of order determination is also evaluated. In a comparative study, the influence of optimal orders on damage is assessed to perceive whether features extracted from optimal models, with and without using low-pass filters, are sensitive to damage. Experimental data of a three-story laboratory frame and a large-scale bridge are applied to demonstrate the performance and capability of the proposed method. Results show that the proposed iterative method is an efficient tool for the determination of optimal orders along with the extraction of uncorrelated residuals.