Void detection for tunnel lining backfill using impact-echo method based on continuous wavelet transform and convolutional neural network

Jiyun Lee , Kyuwon Kim , Meiyan Kang , Eun-Soo Hong , Suyoung Choi

Abstract

We propose a new method for detecting voids behind tunnel concrete linings using the impact-echo method that is based on continuous wavelet transform (CWT) and a convolutional neural network (CNN). We first collect experimental data using the impact-echo method and then convert them into time–frequency images via CWT. We provide a CNN model trained using the converted images and experimentally confirm that our proposed model is robust. Moreover, it exhibits outstanding performance in detecting backfill voids and their status.

Key Words

continuous wavelet transform; convolutional neural network; impact-echo method; lining backfill; nondestructive testing; void detection

Address

Jiyun Lee, Meiyan Kang and Suyoung Choi — Department of Mathematics, Ajou University, 206, World cup-ro, Yeongtong-gu, Suwon-si, Gyeonggi-do, Republic of Korea
Kyuwon Kim and Eun-Soo Hong — HBC, Inc., 138, Dunsanjung-ro, Seo-gu, Daejeon, Republic of Korea

PDF Viewer

Preview is limited to the first 3 pages. Sign in to access the full PDF.

← Back to Volume 36, No. 1