Back to Search Start Over

Automatic elimination of invalid impact-echo signals for detecting delamination in concrete bridge decks based on deep learning

Authors :
Shibin Lin
Liang Meng
Guochen Zhao
Jiake Zhang
Jingzhou Xin
Yong Cheng
Shangwen Cheng
Changhai Zhai
Source :
Developments in the Built Environment, Vol 19, Iss , Pp 100521- (2024)
Publication Year :
2024
Publisher :
Elsevier, 2024.

Abstract

The impact-echo (IE) method is effective for evaluating invisible defects. However, it might return misleading results when its signals are invalid. This challenge aggravates when the tests are conducted using robotic devices that automatically collect massive data. This study proposes an automatic method to eliminate invalid signals based on the ResNet model. First, the signals are visualized into two-dimensional images as the input for ResNet. The input data can then be classified into valid and invalid data via the ResNet model, which is trained with 11,290 signals and tested with 5664 signals. Finally, defects can be detected using the dominant frequencies of the valid-class data. A case study with IE data from two concrete bridges was employed to validate the feasibility of the proposed approach. The results indicate that the method can achieve an average accuracy of 90.6% for eliminating invalid signals and significantly improve the IE test accuracy.

Details

Language :
English
ISSN :
26661659
Volume :
19
Issue :
100521-
Database :
Directory of Open Access Journals
Journal :
Developments in the Built Environment
Publication Type :
Academic Journal
Accession number :
edsdoj.1f7f5346dd9453197968e12569c6f38
Document Type :
article
Full Text :
https://doi.org/10.1016/j.dibe.2024.100521