KEYWORDS: Structural health monitoring, Bridges, Sensors, Mode shapes, Prior knowledge, Data transmission, Monte Carlo methods, Engineering, Decision trees, Decision making
Structural Health Monitoring (SHM) can provide valuable information for maintenance-related activities and post-disaster emergency management. However, as with any technological system, SHM systems can be susceptible to errors due to malfunctioning. Therefore, it is essential to assess the potential for malfunctions and the associated costs of maintenance and repair when evaluating the long-term benefits of SHM systems. In the last two decades, sensor validation tools (SVTs) have been proposed to support decisions by isolating and discarding abnormal data. Recently, the authors of this paper have proposed a framework based on the Value of Information (VoI) from Bayesian decision analysis to account for different states of an SHM system and assess the benefit of SVT information. By quantifying the additional value obtained from SVTs, decision-makers can make more informed decisions about investing in these systems. This framework is here demonstrated on a real case study, namely the S101 bridge in Austria, which has been artificially damaged for research purposes. The benefit of collecting SHM and SVT information is quantified by considering a simple decision problem related to the management of the bridge in the aftermath of a damaging event. Overall, the study highlights the potential benefits of using SVTs to improve the reliability of SHM data and inform decision-making in the management of structures.
The objective of this study was to implement a supervised machine learning method that utilizes the radial basis function neural network for 3D electrical impedance tomography conductivity distribution reconstruction of complex cellular lattice structures. This data-driven algorithm, which was trained by a variety of damaged cases, is significantly faster than conventional EIT while enabling greater accuracy of 3D conductivity distribution reconstruction. Both numerical simulations and experimental results are presented in this work, and the machine learning based EIT results are compared with those obtained using conventional EIT.
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.