Date of Award
Spring 2022
Document Type
Open Access Thesis
Department
Civil and Environmental Engineering
First Advisor
Paul Ziehl
Abstract
The average age of bridges in South Carolina is approaching 40 years, very close to the 50-year service life. Almost 11% of the bridges in South Carolina are rated as structurally deficient, greater than the national average of 7.5% (South 2021). Health monitoring is the concept that in-situ sensors can continuously monitor civil structures and send real time signals of damage. This process allows for automation and could save time and money on the inspection and load rating of bridges. Health monitoring requires sensors that provide uninterrupted data without sacrificing the functionality of the bridge. A prime candidate for this is acoustic emissions data which can gather information on an entire bridge with a few small sensors.
This study focuses on the classification of acoustic emission (AE) data using an artificial neural network (ANN) in hopes that it will contribute to the advancement in structural health monitoring (SHM) procedures for precast reinforced concrete flat slab superstructures. In addition, it will focus on the viability of acoustic emission data for health monitoring systems as well as the practicality of artificial neural networks on the classification of this data.
In addition, AE signals are analyzed and classified into load steps using statistical methods and an ANN. The statistical analysis provided slight differences between load steps, but classification proved difficult using a single feature of an AE waveform. The ANN was much more successful in classification of the AE data into 2 different load steps. The trained ANN was able to classify an unfamiliar data set. with 73.0% accuracy.
Rights
© 2022, Allen Ross
Recommended Citation
Ross, A.(2022). Classification of Acoustic Emission Data Into Load Steps Using An Artificial Neural Network. (Master's thesis). Retrieved from https://scholarcommons.sc.edu/etd/6582