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...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	KSCE Journal of Civil Engineering Ročník 23; číslo 10; s. 4493 - 4502
Hlavní autoři:	Feng, Chuncheng, Zhang, Hua, Wang, Shuang, Li, Yonglong, Wang, Haoran, Yan, Fei
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Seoul Korean Society of Civil Engineers 01.10.2019 Springer Nature B.V 대한토목학회
Témata:	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
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	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.
Bibliografie:	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