A kernel canonical correlation analysis approach for removing environmental and operational variations for structural damage identification

Vibration-based damage detection relies on the observation of changes in damage-sensitive dy-namic features. However, a major problem is that dynamic features are sensitive not only to structural damage but also to environmental and operational variations (EOVs), such as tem-perature, humidity, and operational loading. In addition, the influence of EOVs on damage -sensitive features is often nonlinear, which limits the application of many linear methods in the removal of environmental effects. To remove the nonlinear effects of EOVs on dynamic fea-tures, an improved method based on kernel canonical correlation analysis (KCCA) is proposed in this study. Using this method, the monitored data were divided into two groups. The two sets of data were then mapped into a higher-dimensional space through the kernel trick to determine their implicit linear relationship. Subsequently, two variables that share the co-occurrence in-formation of EOV effects were computed using canonical correlation analysis (CCA), and a sta-tionary residual insensitive to EOVs was obtained. Furthermore, the proposed approach was examined using a simulated 7-DOF example and then applied to real monitored data from the Z24 bridge, demonstrating that nonlinear EOV effects can be successfully removed and damage can be accurately identified.

Automated summary

Vibration-based damage detection relies on the observation of changes in damage-sensitive dynamic features. However, dynamic features are also sensitive to environmental and operational variations (EOVs), limiting the application of linear methods in removing environmental effects. This study proposes an improved method based on kernel canonical correlation analysis (KCCA) to remove the nonlinear effects of EOVs on dynamic features, demonstrating its success in accurately identifying damage.