Improving the Ability of a Laser Ultrasonic Wave-Based Detection of Damage on the Curved Surface of a Pipe Using a Deep Learning Technique

With the advent of the Fourth Industrial Revolution, the economic, social, and technological demands for pipe maintenance are increasing due to the aging of the infrastructure caused by the increase in industrial development and the expansion of cities. Owing to this, an automatic pipe damage detect...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Byoungjoon Yu, Kassahun Demissie Tola, Changgil Lee, Seunghee Park
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	plumbing maintenance deep learning ultrasonic wave propagation imaging CNN external damage Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/1678e8e1e49a4dfe955cb848085663b3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1678e8e1e49a4dfe955cb848085663b3
record_format	dspace
spelling	oai:doaj.org-article:1678e8e1e49a4dfe955cb848085663b32021-11-11T19:06:55ZImproving the Ability of a Laser Ultrasonic Wave-Based Detection of Damage on the Curved Surface of a Pipe Using a Deep Learning Technique10.3390/s212171051424-8220https://doaj.org/article/1678e8e1e49a4dfe955cb848085663b32021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7105https://doaj.org/toc/1424-8220With the advent of the Fourth Industrial Revolution, the economic, social, and technological demands for pipe maintenance are increasing due to the aging of the infrastructure caused by the increase in industrial development and the expansion of cities. Owing to this, an automatic pipe damage detection system was built using a laser-scanned pipe’s ultrasonic wave propagation imaging (UWPI) data and conventional neural network (CNN)-based object detection algorithms. The algorithm used in this study was EfficientDet-d0, a CNN-based object detection algorithm which uses the transfer learning method. As a result, the mean average precision (mAP) was measured to be 0.39. The result found was higher than COCO EfficientDet-d0 mAP, which is expected to enable the efficient maintenance of piping used in construction and many industries.Byoungjoon YuKassahun Demissie TolaChanggil LeeSeunghee ParkMDPI AGarticleplumbing maintenancedeep learningultrasonic wave propagation imagingCNNexternal damageChemical technologyTP1-1185ENSensors, Vol 21, Iss 7105, p 7105 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	plumbing maintenance deep learning ultrasonic wave propagation imaging CNN external damage Chemical technology TP1-1185
spellingShingle	plumbing maintenance deep learning ultrasonic wave propagation imaging CNN external damage Chemical technology TP1-1185 Byoungjoon Yu Kassahun Demissie Tola Changgil Lee Seunghee Park Improving the Ability of a Laser Ultrasonic Wave-Based Detection of Damage on the Curved Surface of a Pipe Using a Deep Learning Technique
description	With the advent of the Fourth Industrial Revolution, the economic, social, and technological demands for pipe maintenance are increasing due to the aging of the infrastructure caused by the increase in industrial development and the expansion of cities. Owing to this, an automatic pipe damage detection system was built using a laser-scanned pipe’s ultrasonic wave propagation imaging (UWPI) data and conventional neural network (CNN)-based object detection algorithms. The algorithm used in this study was EfficientDet-d0, a CNN-based object detection algorithm which uses the transfer learning method. As a result, the mean average precision (mAP) was measured to be 0.39. The result found was higher than COCO EfficientDet-d0 mAP, which is expected to enable the efficient maintenance of piping used in construction and many industries.
format	article
author	Byoungjoon Yu Kassahun Demissie Tola Changgil Lee Seunghee Park
author_facet	Byoungjoon Yu Kassahun Demissie Tola Changgil Lee Seunghee Park
author_sort	Byoungjoon Yu
title	Improving the Ability of a Laser Ultrasonic Wave-Based Detection of Damage on the Curved Surface of a Pipe Using a Deep Learning Technique
title_short	Improving the Ability of a Laser Ultrasonic Wave-Based Detection of Damage on the Curved Surface of a Pipe Using a Deep Learning Technique
title_full	Improving the Ability of a Laser Ultrasonic Wave-Based Detection of Damage on the Curved Surface of a Pipe Using a Deep Learning Technique
title_fullStr	Improving the Ability of a Laser Ultrasonic Wave-Based Detection of Damage on the Curved Surface of a Pipe Using a Deep Learning Technique
title_full_unstemmed	Improving the Ability of a Laser Ultrasonic Wave-Based Detection of Damage on the Curved Surface of a Pipe Using a Deep Learning Technique
title_sort	improving the ability of a laser ultrasonic wave-based detection of damage on the curved surface of a pipe using a deep learning technique
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/1678e8e1e49a4dfe955cb848085663b3
work_keys_str_mv	AT byoungjoonyu improvingtheabilityofalaserultrasonicwavebaseddetectionofdamageonthecurvedsurfaceofapipeusingadeeplearningtechnique AT kassahundemissietola improvingtheabilityofalaserultrasonicwavebaseddetectionofdamageonthecurvedsurfaceofapipeusingadeeplearningtechnique AT changgillee improvingtheabilityofalaserultrasonicwavebaseddetectionofdamageonthecurvedsurfaceofapipeusingadeeplearningtechnique AT seungheepark improvingtheabilityofalaserultrasonicwavebaseddetectionofdamageonthecurvedsurfaceofapipeusingadeeplearningtechnique
_version_	1718431570093670400

Improving the Ability of a Laser Ultrasonic Wave-Based Detection of Damage on the Curved Surface of a Pipe Using a Deep Learning Technique

Ejemplares similares