Artificial Intelligence and Data Science
Online ISSN : 2435-9262
A STUDY ON QUANTIFICATION OF IMPACT-ECHO MONITORING WITH MACHINE LEARNING
SHIMBO HiroshiMIZOBUCHI ToshiakiOZEKI TomokoNOJIMA Jun-ichiro
Author information
JOURNAL OPEN ACCESS

2020 Volume 1 Issue J1 Pages 522-529

Details
Abstract

Impact-Echo monitoring is widely used as a method to find the flaking or cracking caused by deterioration of concrete structures. However, the accuracy of the monitoring depends on the skill and experience of the engineer. In this paper, we investigated the possibility of machine learning to quantify the Impact-Echo monitoring. Specifically, the impact sounds were imaged by spectrogram conversion and classified by a convolutional neural network. This method was tested on concrete test specimens with simulated defects and also salt-damaged real structures. It was possible to diagnose concrete defects with the same accuracy as a skilled engineer by using small image data. It was shown that the obtained neural network has a certain generalization performance.

Content from these authors
© 2020 Japan Society of Civil Engineers
Previous article Next article
feedback
Top