12 April 2017 A probabilistic model for visual inspection of concrete shear walls
Author Affiliations +
Abstract
This paper presents a probabilistic model, called Bayesian networks, to visually assess the state of damage in reinforced concrete shear walls. The goal of this research is to reduce the inspection time and decrease the chance of missing or underestimating the state of damage in such structures. To develop this model, we define six types of visible damage on concrete shear walls. The model describes the causal relationship of such damage signs with the design parameters and damage states of the walls. To train and test the model, a database of all visually documented experimental works on concrete shear walls was collected from the literature. The model is trained on ninety percent of the database, and its performance is successfully validated on the ten percent remaining unseen portion of the database. The results show that the model can classify the images of yielded and failed walls. Additionally, it can prognosticate the most probable failure scenario for a yielded wall.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Arvin Ebrahimkhanlou, Salvatore Salamone, "A probabilistic model for visual inspection of concrete shear walls", Proc. SPIE 10168, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2017, 101680Y (12 April 2017); doi: 10.1117/12.2258614; https://doi.org/10.1117/12.2258614
PROCEEDINGS
7 PAGES


SHARE
Back to Top