Multivariate statistical process control-based hypothesis testing for damage detection in structural health monitoring systems

The objective of this paper is to propose a new damage detection technique based on multiscale partial least squares (MSPLS) and optimized exponentially weighted moving average (OEWMA) generalized likelihood ratio test (GLRT) to enhance monitoring of structural systems. The developed technique attempts to combine the advantages of the exponentially weighted moving average (EWMA) and GLRT charts with those of multiscale input-output model partial least square (PLS) and multi-objective optimization. The damage detection problem is addressed so that the data are first modeled using the MSPLS method and then the damages are detected using the OEWMA-GLRT chart. The idea behind the developed OEWMA-GLRT is to compute an optimal statistic that integrates current and previous data information in a decreasing exponential fashion giving more weight to the more recent data and selects the EWMA parameters that minimizes the (MDR), the false alarm rate (FAR) and the average run length (ARL(1)). This helps provide a more accurate estimation of the GLRT statistic and provide a stronger memory that enables better decision making with respect to damage detection. The performance of the developed technique is assessed and compared with PLS-based GLRT, PLS-based OEWMA, and PLS-based OEWMA-GLRT techniques using two illustrative examples, synthetic data and simulated International Association for Structural Control-American society of Civil engineers (IASC-ASCE) benchmark structure. The results demonstrate the effectiveness of the MSPLS-based OEWMA-GLRT technique over the PLS-based GLRT, PLS-based OEWMA, and PLS-based OEWMA-GLRT methods in terms of MDR, FAR, and ARL(1) values.