A Modified Fully Convolutional Network for Crack Damage Identification Compared with Conventional Methods

Large-scale structural health monitoring and damage detection of concealed underwater structures are always the urgent and state-of-art problems to be solved in the field of civil engineering. With the development of artificial intelligence especially the combination of deep learning and computer vi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Meng Meng, Kun Zhu, Keqin Chen, Hang Qu
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi Limited 2021
Materias:	Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/d1dcb83a9cf44400ae6ab9deb7285889
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d1dcb83a9cf44400ae6ab9deb7285889
record_format	dspace
spelling	oai:doaj.org-article:d1dcb83a9cf44400ae6ab9deb72858892021-11-22T01:09:57ZA Modified Fully Convolutional Network for Crack Damage Identification Compared with Conventional Methods1687-560510.1155/2021/5298882https://doaj.org/article/d1dcb83a9cf44400ae6ab9deb72858892021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/5298882https://doaj.org/toc/1687-5605Large-scale structural health monitoring and damage detection of concealed underwater structures are always the urgent and state-of-art problems to be solved in the field of civil engineering. With the development of artificial intelligence especially the combination of deep learning and computer vision, greater advantages have been brought to the concrete crack detection based on convolutional neural network (CNN) over the traditional methods. However, these machine learning (ML) methods still have some defects, such as it being inaccurate or not strong, having poor generalization ability, or the accuracy still needs to be improved, and the running speed is slow. In this article, a modified fully convolutional network (FCN) with more robustness and more effectiveness is proposed, which makes it convenient and low cost for long-term structural monitoring and inspection compared with other methods. Meanwhile, to improve the accuracy of recognition and prediction, innovations were conducted in this study as follows. Moreover, differed from the common simple deconvolution, it also includes a subpixel convolution layer, which can greatly reduce the sampling time. Then, the proposed method was verified its practicability with the overall recognition accuracy reaching up to 97.92% and 12% efficiency improvement.Meng MengKun ZhuKeqin ChenHang QuHindawi LimitedarticleElectronic computers. Computer scienceQA75.5-76.95ENModelling and Simulation in Engineering, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Electronic computers. Computer science QA75.5-76.95
spellingShingle	Electronic computers. Computer science QA75.5-76.95 Meng Meng Kun Zhu Keqin Chen Hang Qu A Modified Fully Convolutional Network for Crack Damage Identification Compared with Conventional Methods
description	Large-scale structural health monitoring and damage detection of concealed underwater structures are always the urgent and state-of-art problems to be solved in the field of civil engineering. With the development of artificial intelligence especially the combination of deep learning and computer vision, greater advantages have been brought to the concrete crack detection based on convolutional neural network (CNN) over the traditional methods. However, these machine learning (ML) methods still have some defects, such as it being inaccurate or not strong, having poor generalization ability, or the accuracy still needs to be improved, and the running speed is slow. In this article, a modified fully convolutional network (FCN) with more robustness and more effectiveness is proposed, which makes it convenient and low cost for long-term structural monitoring and inspection compared with other methods. Meanwhile, to improve the accuracy of recognition and prediction, innovations were conducted in this study as follows. Moreover, differed from the common simple deconvolution, it also includes a subpixel convolution layer, which can greatly reduce the sampling time. Then, the proposed method was verified its practicability with the overall recognition accuracy reaching up to 97.92% and 12% efficiency improvement.
format	article
author	Meng Meng Kun Zhu Keqin Chen Hang Qu
author_facet	Meng Meng Kun Zhu Keqin Chen Hang Qu
author_sort	Meng Meng
title	A Modified Fully Convolutional Network for Crack Damage Identification Compared with Conventional Methods
title_short	A Modified Fully Convolutional Network for Crack Damage Identification Compared with Conventional Methods
title_full	A Modified Fully Convolutional Network for Crack Damage Identification Compared with Conventional Methods
title_fullStr	A Modified Fully Convolutional Network for Crack Damage Identification Compared with Conventional Methods
title_full_unstemmed	A Modified Fully Convolutional Network for Crack Damage Identification Compared with Conventional Methods
title_sort	modified fully convolutional network for crack damage identification compared with conventional methods
publisher	Hindawi Limited
publishDate	2021
url	https://doaj.org/article/d1dcb83a9cf44400ae6ab9deb7285889
work_keys_str_mv	AT mengmeng amodifiedfullyconvolutionalnetworkforcrackdamageidentificationcomparedwithconventionalmethods AT kunzhu amodifiedfullyconvolutionalnetworkforcrackdamageidentificationcomparedwithconventionalmethods AT keqinchen amodifiedfullyconvolutionalnetworkforcrackdamageidentificationcomparedwithconventionalmethods AT hangqu amodifiedfullyconvolutionalnetworkforcrackdamageidentificationcomparedwithconventionalmethods AT mengmeng modifiedfullyconvolutionalnetworkforcrackdamageidentificationcomparedwithconventionalmethods AT kunzhu modifiedfullyconvolutionalnetworkforcrackdamageidentificationcomparedwithconventionalmethods AT keqinchen modifiedfullyconvolutionalnetworkforcrackdamageidentificationcomparedwithconventionalmethods AT hangqu modifiedfullyconvolutionalnetworkforcrackdamageidentificationcomparedwithconventionalmethods
_version_	1718418428059975680

A Modified Fully Convolutional Network for Crack Damage Identification Compared with Conventional Methods

Ejemplares similares