Simultaneous tunnel defects and lining thickness identification based on multi-tasks deep neural network from ground penetrating radar images

被引：29

作者：

Liu, Bin ^{[1
,2
,3
]}

Zhang, Jiaqi ^{[4
,5
]}

Lei, Ming ^{[4
]}

Yang, Senlin ^{[1
]}

Wang, Zhangfang ^{[4
]}

机构：

[1] Shandong Univ, Geotech & Struct Engn Res Ctr, 17923 Jingshi Rd, Jinan 250061, Shandong, Peoples R China

[2] Shandong Univ, Sch Civil Engn, Jinan, Shandong, Peoples R China

[3] Shandong Univ, Data Sci Inst, Jinan, Shandong, Peoples R China

[4] Shandong Univ, Sch Control Sci & Engn, Jinan, Shandong, Peoples R China

[5] Chinese Acad Sci, Inst Microelect, Beijing 100029, Peoples R China

来源：

AUTOMATION IN CONSTRUCTION | 2023年 / 145卷

基金：

中国国家自然科学基金;

关键词：

Tunnel automatic inspection; Ground penetrating radar; Multi-task deep learning; Defect identification; Tunnel lining thickness; GPR; RECOGNITION;

D O I：

10.1016/j.autcon.2022.104633

中图分类号：

TU [建筑科学];

学科分类号：

0813 ;

摘要：

The overall assessment of tunnel lining, including shapes, categories, and depths of tunnel internal defects as well as the thickness of tunnel linings is vital to the safe operation of tunnels. We proposed a method comprising a multi-task deep neural network and curve fitting post-processing operation for simultaneously identifying the shapes, categories, and depths of tunnel defects as well as lining thicknesses from ground penetrating radar (GPR) images. The multi-task deep neural network, denoted as M-YOLACT, was designed to identify defects, lining profiles, and hyperbola shapes simultaneously. We introduced a curve-fitting post-processing operation to calculate the dielectric constant automatically based on the hyperbola shapes and evaluated the defect depths and lining thicknesses. The method was validated by numerical simulations, sandbox, and field tests. The method effectively identified the shapes and classes of tunnel defects as well as the thickness profiles from GPR B-Scan images.

引用

页数：17