Structural Damage Detection using Deep Convolutional Neural Network and Transfer Learning

During the long-term operation of hydro-junction infrastructure, water flow erosion causes concrete surfaces to crack, resulting in seepage, spalling, and rebar exposure. To ensure infrastructure safety, detecting such damage is critical. We propose a highly accurate damage detection method using a...

Full description

Saved in:
Bibliographic Details
Published in:KSCE Journal of Civil Engineering Vol. 23; no. 10; pp. 4493 - 4502
Main Authors: Feng, Chuncheng, Zhang, Hua, Wang, Shuang, Li, Yonglong, Wang, Haoran, Yan, Fei
Format: Journal Article
Language:English
Published: Seoul Korean Society of Civil Engineers 01.10.2019
Springer Nature B.V
대한토목학회
Subjects:
Accuracy
Artificial neural networks
Asphalt pavements
Cameras
Civil Engineering
Concrete
Cracks
Damage detection
Datasets
Deep learning
Detection
Engineering
Erosion
Erosion mechanisms
Geotechnical Engineering & Applied Earth Sciences
Global positioning systems
GPS
High definition
Hydroelectric power
Industrial Pollution Prevention
Infrastructure
Internet
Learning
Machine learning
Methods
Neural networks
Rebar
Reinforcing steels
Research centers
Science
Seepage
Spalling
Structural damage
Structural Engineering
Students
Support vector machines
Transfer learning
Unmanned aerial vehicles
Water flow
토목공학
hydro-junction infrastructure
damage detection
transfer learning
structural health monitoring
concrete surface defect
deep convolutional neural network
ISSN:1226-7988, 1976-3808
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:During the long-term operation of hydro-junction infrastructure, water flow erosion causes concrete surfaces to crack, resulting in seepage, spalling, and rebar exposure. To ensure infrastructure safety, detecting such damage is critical. We propose a highly accurate damage detection method using a deep convolutional neural network with transfer learning. First, we collected images from hydro-junction infrastructure using a high-definition camera. Second, we preprocessed the images using an image expansion method. Finally, we modified the structure of Inception-v3 and trained the network using transfer learning to detect damage. The experiments show that the accuracy of the proposed damage detection method is 96.8%, considerably higher than the accuracy of a support vector machine. The results demonstrate that our damage detection method achieves better damage detection performance.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1226-7988
1976-3808
DOI:10.1007/s12205-019-0437-z