Deterioration and damage identification in building structures using a novel feature selection method

Identifying structural defects in complex structures is one of the main objectives in real-world structural health monitoring (SHM) applications. In this article, a signal-based supervised methodology is proposed for detecting deterioration and damage in building structures. This method benefits from a novel feature selection method called signal simulation-based feature selection (SSFS) algorithm, which only relies on baseline signals to extract the most sensitive features from any type of structure. The results showed that the offered methodology is capable of identifying damage and deterioration precisely, and therefore, can be a viable alternative to conventional techniques that require additional information.

Automated summary

The article introduces a signal-based supervised methodology for detecting deterioration and damage in building structures, utilizing a novel feature selection method called signal simulation-based feature selection algorithm. The results demonstrate the capability of the proposed methodology in accurately identifying damage and deterioration, offering a viable alternative to conventional techniques that require additional information.