This study focuses on embeddable algorithms that operate within multi-scale wireless sensor networks for damage
detection in civil infrastructure systems, and in specific, the Bivariate Regressive Adaptive INdex (BRAIN) to detect
damage in structures by examining the changes in regressive coefficients of time series models. As its name suggests,
BRAIN exploits heterogeneous sensor arrays by a data-driven damage feature (DSF) to enhance detection capability
through the use of two types of response data, each with its own unique sensitivities to damage. While previous studies
have shown that BRAIN offers more reliable damage detection, a number of factors contributing to its performance are
explored herein, including observability, damage proximity/severity, and relative signal strength. These investigations
also include an experimental program to determine if performance is maintained when implementing the approaches in
physical systems. The results of these investigations will be used to further verify that the use of heterogeneous sensing
enhances overall detection capability of such data-driven damage metrics.
This study focuses on data-driven methods for structural health monitoring and introduces a Bivariate Regressive
Adaptive INdex (BRAIN) for damage detection in a decentralized, wireless sensor network. BRAIN utilizes a dynamic
damage sensitive feature (DSF) that automatically adapts to the data set, extracting the most damage sensitive model
features, which vary with location, damage severity, loading condition and model type. This data-driven feature is key to
providing the most flexible damage sensitive feature incorporating all available data for a given application to enhance
reliability by including heterogeneous sensor arrays. This study will first evaluate several regressive-type models used
for time-series damage detection, including common homogeneous formats and newly proposed heterogeneous
descriptors and then demonstrate the performance of the newly proposed dynamic DSF against a comparable static DSF.
Performance will be validated by documenting their damage success rates on repeated simulations of randomly-excited
thin beams with minor levels of damage. It will be shown that BRAIN dramatically increases the detection capabilities
over static, homogeneous damage detection frameworks.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.