Transfer Learning-Based Algorithms for the Detection of Fatigue Crack Initiation Sites: A Comparative Study

The identification of fatigue crack initiation sites (FCISs) is routinely performed in the field of engineering failure analyses; this process is not only time-consuming but also knowledge-intensive. The emergence of convolutional neural networks (CNNs) has inspired numerous innovative solutions for...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	S.Y. Wang, T. Guo
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	computer vision machine learning transfer learning fatigue crack initiation sites faster R-CNN Technology T
Acceso en línea:	https://doaj.org/article/dd2b81edad664600ba03a64c98db147b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:dd2b81edad664600ba03a64c98db147b
record_format	dspace
spelling	oai:doaj.org-article:dd2b81edad664600ba03a64c98db147b2021-11-30T11:45:00ZTransfer Learning-Based Algorithms for the Detection of Fatigue Crack Initiation Sites: A Comparative Study2296-801610.3389/fmats.2021.756798https://doaj.org/article/dd2b81edad664600ba03a64c98db147b2021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fmats.2021.756798/fullhttps://doaj.org/toc/2296-8016The identification of fatigue crack initiation sites (FCISs) is routinely performed in the field of engineering failure analyses; this process is not only time-consuming but also knowledge-intensive. The emergence of convolutional neural networks (CNNs) has inspired numerous innovative solutions for image analysis problems in interdisciplinary fields. As an explorative study, we trained models based on the principle of transfer learning using three state-of-the-art CNNs, namely VGG-16, ResNet-101, and feature pyramid network (FPN), as feature extractors, and a faster R-CNN as the backbone to establish models for FCISs detection. The models showed application-level detection performance, with the highest precision reaching up to 95.9% at a confidence threshold of 0.6. Among the three models, the ResNet model exhibited the highest accuracy and lowest training cost. The performance of the FPN model closely followed that of the ResNet model with an advantage in terms of the recall.S.Y. WangT. GuoFrontiers Media S.A.articlecomputer visionmachine learningtransfer learningfatigue crack initiation sitesfaster R-CNNTechnologyTENFrontiers in Materials, Vol 8 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	computer vision machine learning transfer learning fatigue crack initiation sites faster R-CNN Technology T
spellingShingle	computer vision machine learning transfer learning fatigue crack initiation sites faster R-CNN Technology T S.Y. Wang T. Guo Transfer Learning-Based Algorithms for the Detection of Fatigue Crack Initiation Sites: A Comparative Study
description	The identification of fatigue crack initiation sites (FCISs) is routinely performed in the field of engineering failure analyses; this process is not only time-consuming but also knowledge-intensive. The emergence of convolutional neural networks (CNNs) has inspired numerous innovative solutions for image analysis problems in interdisciplinary fields. As an explorative study, we trained models based on the principle of transfer learning using three state-of-the-art CNNs, namely VGG-16, ResNet-101, and feature pyramid network (FPN), as feature extractors, and a faster R-CNN as the backbone to establish models for FCISs detection. The models showed application-level detection performance, with the highest precision reaching up to 95.9% at a confidence threshold of 0.6. Among the three models, the ResNet model exhibited the highest accuracy and lowest training cost. The performance of the FPN model closely followed that of the ResNet model with an advantage in terms of the recall.
format	article
author	S.Y. Wang T. Guo
author_facet	S.Y. Wang T. Guo
author_sort	S.Y. Wang
title	Transfer Learning-Based Algorithms for the Detection of Fatigue Crack Initiation Sites: A Comparative Study
title_short	Transfer Learning-Based Algorithms for the Detection of Fatigue Crack Initiation Sites: A Comparative Study
title_full	Transfer Learning-Based Algorithms for the Detection of Fatigue Crack Initiation Sites: A Comparative Study
title_fullStr	Transfer Learning-Based Algorithms for the Detection of Fatigue Crack Initiation Sites: A Comparative Study
title_full_unstemmed	Transfer Learning-Based Algorithms for the Detection of Fatigue Crack Initiation Sites: A Comparative Study
title_sort	transfer learning-based algorithms for the detection of fatigue crack initiation sites: a comparative study
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/dd2b81edad664600ba03a64c98db147b
work_keys_str_mv	AT sywang transferlearningbasedalgorithmsforthedetectionoffatiguecrackinitiationsitesacomparativestudy AT tguo transferlearningbasedalgorithmsforthedetectionoffatiguecrackinitiationsitesacomparativestudy
_version_	1718406656476315648

Transfer Learning-Based Algorithms for the Detection of Fatigue Crack Initiation Sites: A Comparative Study

Ejemplares similares