Improving feature extraction via time series modeling for structural health monitoring based on unsupervised learning methods

Feature extraction by time series modeling based on statistical pattern recognition is a powerful approach to Structural Health Monitoring (SHM). Determination of an adequate order and identi cation of an appropriate model play prominent roles in extracting sensitive features to damage from time series representations. Early damage detection under statistical decision-making via high-dimensional features is another signi cant issue. The main objectives of this study were to improve a residual-based feature extraction method by time series modeling and to propose a multivariate data visualization approach to early damage detection. A simple graphical tool based on Box-Jenkins methodology was adopted to identify the most compatible time series model with vibration time-domain measurements. Furthermore, k-means and Gaussian Mixture Model (GMM) clustering techniques were utilized to examine the performance of the residuals of the identi ed model in damage detection. A numerical concrete beam and an experimental benchmark model were applied to verifying the improved and proposed methods along with comparative analyses. Results showed that the approaches were successful and superior to a state-of-the-art order determination technique in obtaining a sufficient order, generating uncorrelated residuals, extracting sensitive features to damage, and accurately detecting early damage by high-dimensional data.