Open Access

Applied Sciences (Switzerland)

, volume 9 , issue 16 , pages 3312

Deep Learning-Based Classification of Weld Surface Defects

Zhu ^{1, 2}

Ge ^{1, 2}

. Liu ^{1, 2, 3}

Hide authors affiliations Show authors affiliations: 3 affiliations

Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control, School of Mechanical Engineering, Tianjin University of Technology, Tianjin 300384, China |

National Demonstration Center for Experimental Mechanical and Electrical Engineering Education, School of Mechanical Engineering, Tianjin University of Technology, Tianjin 300384, China |

State Key Lab of Digital Manufacturing Equipment & Technology, School of Mechanical Science & Engineering, Huazhong University of Science & Technology, Wuhan 430074, China |

Publication type: Journal Article

Publication date: 2019-08-12

MDPI

Applied Sciences (Switzerland)

scimago Q2

wos Q2

SJR: 0.521

CiteScore: 5.5

Impact factor: 2.5

ISSN: 20763417

DOI: 10.3390/app9163312

Copy DOI

Computer Science Applications

Process Chemistry and Technology

General Materials Science

Instrumentation

General Engineering

Fluid Flow and Transfer Processes

Abstract

In order to realize the non-destructive intelligent identification of weld surface defects, an intelligent recognition method based on deep learning is proposed, which is mainly formed by convolutional neural network (CNN) and forest random. First, the high-level features are automatically learned through the CNN. Random forest is trained with extracted high-level features to predict the classification results. Secondly, the weld surface defects images are collected and preprocessed by image enhancement and threshold segmentation. A database of weld surface defects is established using pre-processed images. Finally, comparative experiments are performed on the weld surface defects database. The results show that the accuracy of the method combined with CNN and random forest can reach 0.9875, and it also demonstrates the method is effective and practical.

Found

1 citation

Soldatov Alexander

600 publications, 11 304 citations

h-index: 52

Southern Federal University

Top-30

Journals

	1 2 3 4 5
Sensors	Sensors, 5, 7.35% Sensors 5 publications, 7.35%
Journal of Manufacturing Processes	Journal of Manufacturing Processes, 5, 7.35% Journal of Manufacturing Processes 5 publications, 7.35%
IEEE Access	IEEE Access, 4, 5.88% IEEE Access 4 publications, 5.88%
International Journal of Advanced Manufacturing Technology	International Journal of Advanced Manufacturing Technology, 3, 4.41% International Journal of Advanced Manufacturing Technology 3 publications, 4.41%
Metals	Metals, 2, 2.94% Metals 2 publications, 2.94%
Journal of Manufacturing Systems	Journal of Manufacturing Systems, 2, 2.94% Journal of Manufacturing Systems 2 publications, 2.94%
Journal of Intelligent Manufacturing	Journal of Intelligent Manufacturing, 2, 2.94% Journal of Intelligent Manufacturing 2 publications, 2.94%
Measurement and Control	Measurement and Control, 1, 1.47% Measurement and Control 1 publication, 1.47%
Applied Sciences (Switzerland)	Applied Sciences (Switzerland), 1, 1.47% Applied Sciences (Switzerland) 1 publication, 1.47%
Nanomaterials	Nanomaterials, 1, 1.47% Nanomaterials 1 publication, 1.47%
Catalysts	Catalysts, 1, 1.47% Catalysts 1 publication, 1.47%
Ultrasonics	Ultrasonics, 1, 1.47% Ultrasonics 1 publication, 1.47%
Process Safety and Environmental Protection	Process Safety and Environmental Protection, 1, 1.47% Process Safety and Environmental Protection 1 publication, 1.47%
IOP Conference Series: Materials Science and Engineering	IOP Conference Series: Materials Science and Engineering, 1, 1.47% IOP Conference Series: Materials Science and Engineering 1 publication, 1.47%
IEEE Transactions on Industrial Informatics	IEEE Transactions on Industrial Informatics, 1, 1.47% IEEE Transactions on Industrial Informatics 1 publication, 1.47%
Security and Communication Networks	Security and Communication Networks, 1, 1.47% Security and Communication Networks 1 publication, 1.47%
International Journal of Engineering Research in Africa	International Journal of Engineering Research in Africa, 1, 1.47% International Journal of Engineering Research in Africa 1 publication, 1.47%
Frontiers in Physics	Frontiers in Physics, 1, 1.47% Frontiers in Physics 1 publication, 1.47%
Artificial Intelligence in Data and Big Data Processing	Artificial Intelligence in Data and Big Data Processing, 1, 1.47% Artificial Intelligence in Data and Big Data Processing 1 publication, 1.47%
Lecture Notes in Networks and Systems	Lecture Notes in Networks and Systems, 1, 1.47% Lecture Notes in Networks and Systems 1 publication, 1.47%
Advances in Intelligent Systems and Computing	Advances in Intelligent Systems and Computing, 1, 1.47% Advances in Intelligent Systems and Computing 1 publication, 1.47%
Engineering Research Express	Engineering Research Express, 1, 1.47% Engineering Research Express 1 publication, 1.47%
Herald of the Bauman Moscow State Technical University Series Instrument Engineering	Herald of the Bauman Moscow State Technical University Series Instrument Engineering, 1, 1.47% Herald of the Bauman Moscow State Technical University Series Instrument Engineering 1 publication, 1.47%
Kinetics and Catalysis	Kinetics and Catalysis, 1, 1.47% Kinetics and Catalysis 1 publication, 1.47%
Journal of Nondestructive Evaluation	Journal of Nondestructive Evaluation, 1, 1.47% Journal of Nondestructive Evaluation 1 publication, 1.47%
AIP Conference Proceedings	AIP Conference Proceedings, 1, 1.47% AIP Conference Proceedings 1 publication, 1.47%
Processes	Processes, 1, 1.47% Processes 1 publication, 1.47%
Measurement: Journal of the International Measurement Confederation	Measurement: Journal of the International Measurement Confederation, 1, 1.47% Measurement: Journal of the International Measurement Confederation 1 publication, 1.47%
Handbook of Research on Diverse Applications of Nanotechnology in Biomedicine, Chemistry, and Engineering	Handbook of Research on Diverse Applications of Nanotechnology in Biomedicine, Chemistry, and Engineering, 1, 1.47% Handbook of Research on Diverse Applications of Nanotechnology in Biomedicine, Chemistry, and Engineering 1 publication, 1.47%
	1 2 3 4 5

Publishers

	2 4 6 8 10 12 14 16 18
Institute of Electrical and Electronics Engineers (IEEE)	Institute of Electrical and Electronics Engineers (IEEE), 18, 26.47% Institute of Electrical and Electronics Engineers (IEEE) 18 publications, 26.47%
MDPI	MDPI, 11, 16.18% MDPI 11 publications, 16.18%
Elsevier	Elsevier, 11, 16.18% Elsevier 11 publications, 16.18%
Springer Nature	Springer Nature, 10, 14.71% Springer Nature 10 publications, 14.71%
Taylor & Francis	Taylor & Francis, 3, 4.41% Taylor & Francis 3 publications, 4.41%
IOP Publishing	IOP Publishing, 2, 2.94% IOP Publishing 2 publications, 2.94%
Pleiades Publishing	Pleiades Publishing, 2, 2.94% Pleiades Publishing 2 publications, 2.94%
SAGE	SAGE, 1, 1.47% SAGE 1 publication, 1.47%
Hindawi Limited	Hindawi Limited, 1, 1.47% Hindawi Limited 1 publication, 1.47%
Trans Tech Publications	Trans Tech Publications, 1, 1.47% Trans Tech Publications 1 publication, 1.47%
Frontiers Media S.A.	Frontiers Media S.A., 1, 1.47% Frontiers Media S.A. 1 publication, 1.47%
Bauman Moscow State Technical University	Bauman Moscow State Technical University, 1, 1.47% Bauman Moscow State Technical University 1 publication, 1.47%
AIP Publishing	AIP Publishing, 1, 1.47% AIP Publishing 1 publication, 1.47%
IGI Global	IGI Global, 1, 1.47% IGI Global 1 publication, 1.47%
OOO Zhurnal "Mendeleevskie Soobshcheniya"	OOO Zhurnal "Mendeleevskie Soobshcheniya", 1, 1.47% OOO Zhurnal "Mendeleevskie Soobshcheniya" 1 publication, 1.47%
Wiley	Wiley, 1, 1.47% Wiley 1 publication, 1.47%
	2 4 6 8 10 12 14 16 18

We do not take into account publications without a DOI.
Statistics recalculated weekly.

Are you a researcher?

Create a profile to get free access to personal recommendations for colleagues and new articles.

PDF

Metrics

Cite this

GOST |

Cite this

GOST Copy

Zhu et al. Deep Learning-Based Classification of Weld Surface Defects // Applied Sciences (Switzerland). 2019. Vol. 9. No. 16. p. 3312.

GOST all authors (up to 50) Copy

Zhu, Ge, Liu . Deep Learning-Based Classification of Weld Surface Defects // Applied Sciences (Switzerland). 2019. Vol. 9. No. 16. p. 3312.

RIS |

Cite this

RIS Copy

TY - JOUR

DO - 10.3390/app9163312

UR - https://doi.org/10.3390/app9163312

TI - Deep Learning-Based Classification of Weld Surface Defects

T2 - Applied Sciences (Switzerland)

AU - Zhu

AU - Ge

AU - Liu, .

PY - 2019

DA - 2019/08/12

PB - MDPI

SP - 3312

IS - 16

VL - 9

SN - 2076-3417

ER -

BibTex |

Cite this

BibTex (up to 50 authors) Copy

@article{2019_Zhu,

author = {Zhu and Ge and . Liu},

title = {Deep Learning-Based Classification of Weld Surface Defects},

journal = {Applied Sciences (Switzerland)},

year = {2019},

volume = {9},

publisher = {MDPI},

month = {aug},

url = {https://doi.org/10.3390/app9163312},

number = {16},

pages = {3312},

doi = {10.3390/app9163312}

}

MLA

Cite this

MLA Copy

Zhu, et al. “Deep Learning-Based Classification of Weld Surface Defects.” Applied Sciences (Switzerland), vol. 9, no. 16, Aug. 2019, p. 3312. https://doi.org/10.3390/app9163312.

Publisher

MDPI

Journal

Applied Sciences (Switzerland)

scimago Q2

wos Q2

SJR

0.521

CiteScore

5.5

Impact factor

2.5

ISSN

20763417 (Electronic)