A Convolutional Neural Network Based Framework for Health Monitoring of a Welded Joint Steel Frame Structure

Maloth Naresh; Shirsendu Sikdar; Joy Pal

doi:10.1007/978-3-031-05509-6_21

A Convolutional Neural Network Based Framework for Health Monitoring of a Welded Joint Steel Frame Structure

Maloth Naresh, Shirsendu Sikdar, Joy Pal

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

This study presents a Convolutional Neural Network (CNN) based Deep-learning framework for the health monitoring of a welded joint steel plane frame structure. The deep learning algorithm model is trained to extract local features from the vibration-based time-frequency scalogram images and using those features to distinguish the undamaged and two different damage cases of the steel plane frame structure. The performance and robustness of the framework are tested for an unseen image set corresponding to the training classes. The proposed deep learning framework can successfully classify the undamaged and damaged classes with high testing accuracy that signifies its efficiency as an automation tool for the health monitoring of steel plane frame structures subjected to damage near joints.

Original language	English
Title of host publication	Advances in Structural Mechanics and Applications
Subtitle of host publication	Proceedings of ASMA-2021
Editors	José António Fonseca de Oliveira Correia, Satyabrata Choudhury, Subhrajit Dutta
Publisher	Springer, Cham
Pages	251-262
Number of pages	12
Volume	26
Edition	1st
ISBN (Electronic)	9783030983352
ISBN (Print)	9783030983345, 9783030983376
DOIs	https://doi.org/10.1007/978-3-031-05509-6_21
Publication status	Published - 9 Jun 2022
Externally published	Yes
Event	International Conference on Advances in Structural Mechanics and Applications - Silchar, India Duration: 26 Mar 2021 → 28 Mar 2021

Publication series

Name	Structural Integrity
Publisher	Springer
Volume	26
ISSN (Print)	2522-560X
ISSN (Electronic)	2522-5618

Conference

Conference	International Conference on Advances in Structural Mechanics and Applications
Abbreviated title	ASMA 2021
Country/Territory	India
City	Silchar
Period	26/03/21 → 28/03/21

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Access to Document

10.1007/978-3-031-05509-6_21Licence: Unspecified

Cite this

Naresh, M., Sikdar, S., & Pal, J. (2022). A Convolutional Neural Network Based Framework for Health Monitoring of a Welded Joint Steel Frame Structure. In J. A. F. D. O. Correia, S. Choudhury, & S. Dutta (Eds.), Advances in Structural Mechanics and Applications: Proceedings of ASMA-2021 (1st ed., Vol. 26, pp. 251-262). (Structural Integrity; Vol. 26). Springer, Cham. https://doi.org/10.1007/978-3-031-05509-6_21

Naresh, Maloth ; Sikdar, Shirsendu ; Pal, Joy. / A Convolutional Neural Network Based Framework for Health Monitoring of a Welded Joint Steel Frame Structure. Advances in Structural Mechanics and Applications: Proceedings of ASMA-2021. editor / José António Fonseca de Oliveira Correia ; Satyabrata Choudhury ; Subhrajit Dutta. Vol. 26 1st. ed. Springer, Cham, 2022. pp. 251-262 (Structural Integrity).

@inproceedings{189603c2355349f5b00e4d01b80769d7,

title = "A Convolutional Neural Network Based Framework for Health Monitoring of a Welded Joint Steel Frame Structure",

abstract = "This study presents a Convolutional Neural Network (CNN) based Deep-learning framework for the health monitoring of a welded joint steel plane frame structure. The deep learning algorithm model is trained to extract local features from the vibration-based time-frequency scalogram images and using those features to distinguish the undamaged and two different damage cases of the steel plane frame structure. The performance and robustness of the framework are tested for an unseen image set corresponding to the training classes. The proposed deep learning framework can successfully classify the undamaged and damaged classes with high testing accuracy that signifies its efficiency as an automation tool for the health monitoring of steel plane frame structures subjected to damage near joints.",

keywords = "Convolution Neural Network, Deep learning, Steel plane frame, Structural health monitoring, Welded joint",

author = "Maloth Naresh and Shirsendu Sikdar and Joy Pal",

note = "Funding Information: Acknowledgements. Authors are thankful to the Experimental Laboratory staff of IIT Bombay for their support during the experiment. Shirsendu Sikdar wishes to acknowledge the support from the Research Foundation-Flanders (FWO) Belgium under grant agreement no. FWO.3E0.2019.0102.01. Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; International Conference on Advances in Structural Mechanics and Applications, ASMA 2021 ; Conference date: 26-03-2021 Through 28-03-2021",

year = "2022",

month = jun,

day = "9",

doi = "10.1007/978-3-031-05509-6\_21",

language = "English",

isbn = "9783030983345",

volume = "26",

series = "Structural Integrity",

publisher = "Springer, Cham",

pages = "251--262",

editor = "Correia, \{Jos{\'e} Ant{\'o}nio Fonseca de Oliveira \} and Choudhury, \{Satyabrata \} and Dutta, \{Subhrajit \}",

booktitle = "Advances in Structural Mechanics and Applications",

address = "Switzerland",

edition = "1st",

}

Naresh, M, Sikdar, S & Pal, J 2022, A Convolutional Neural Network Based Framework for Health Monitoring of a Welded Joint Steel Frame Structure. in JAFDO Correia, S Choudhury & S Dutta (eds), Advances in Structural Mechanics and Applications: Proceedings of ASMA-2021. 1st edn, vol. 26, Structural Integrity, vol. 26, Springer, Cham, pp. 251-262, International Conference on Advances in Structural Mechanics and Applications, Silchar, India, 26/03/21. https://doi.org/10.1007/978-3-031-05509-6_21

A Convolutional Neural Network Based Framework for Health Monitoring of a Welded Joint Steel Frame Structure. / Naresh, Maloth; Sikdar, Shirsendu; Pal, Joy.
Advances in Structural Mechanics and Applications: Proceedings of ASMA-2021. ed. / José António Fonseca de Oliveira Correia; Satyabrata Choudhury; Subhrajit Dutta. Vol. 26 1st. ed. Springer, Cham, 2022. p. 251-262 (Structural Integrity; Vol. 26).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Convolutional Neural Network Based Framework for Health Monitoring of a Welded Joint Steel Frame Structure

AU - Naresh, Maloth

AU - Sikdar, Shirsendu

AU - Pal, Joy

N1 - Funding Information: Acknowledgements. Authors are thankful to the Experimental Laboratory staff of IIT Bombay for their support during the experiment. Shirsendu Sikdar wishes to acknowledge the support from the Research Foundation-Flanders (FWO) Belgium under grant agreement no. FWO.3E0.2019.0102.01. Publisher Copyright: © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

PY - 2022/6/9

Y1 - 2022/6/9

N2 - This study presents a Convolutional Neural Network (CNN) based Deep-learning framework for the health monitoring of a welded joint steel plane frame structure. The deep learning algorithm model is trained to extract local features from the vibration-based time-frequency scalogram images and using those features to distinguish the undamaged and two different damage cases of the steel plane frame structure. The performance and robustness of the framework are tested for an unseen image set corresponding to the training classes. The proposed deep learning framework can successfully classify the undamaged and damaged classes with high testing accuracy that signifies its efficiency as an automation tool for the health monitoring of steel plane frame structures subjected to damage near joints.

AB - This study presents a Convolutional Neural Network (CNN) based Deep-learning framework for the health monitoring of a welded joint steel plane frame structure. The deep learning algorithm model is trained to extract local features from the vibration-based time-frequency scalogram images and using those features to distinguish the undamaged and two different damage cases of the steel plane frame structure. The performance and robustness of the framework are tested for an unseen image set corresponding to the training classes. The proposed deep learning framework can successfully classify the undamaged and damaged classes with high testing accuracy that signifies its efficiency as an automation tool for the health monitoring of steel plane frame structures subjected to damage near joints.

KW - Convolution Neural Network

KW - Deep learning

KW - Steel plane frame

KW - Structural health monitoring

KW - Welded joint

UR - https://www.scopus.com/pages/publications/85134591554

UR - https://doi.org/10.1007/978-3-030-98335-2

U2 - 10.1007/978-3-031-05509-6_21

DO - 10.1007/978-3-031-05509-6_21

M3 - Conference contribution

AN - SCOPUS:85134591554

SN - 9783030983345

SN - 9783030983376

VL - 26

T3 - Structural Integrity

SP - 251

EP - 262

BT - Advances in Structural Mechanics and Applications

A2 - Correia, José António Fonseca de Oliveira

A2 - Choudhury, Satyabrata

A2 - Dutta, Subhrajit

PB - Springer, Cham

T2 - International Conference on Advances in Structural Mechanics and Applications

Y2 - 26 March 2021 through 28 March 2021

ER -

Naresh M, Sikdar S, Pal J. A Convolutional Neural Network Based Framework for Health Monitoring of a Welded Joint Steel Frame Structure. In Correia JAFDO, Choudhury S, Dutta S, editors, Advances in Structural Mechanics and Applications: Proceedings of ASMA-2021. 1st ed. Vol. 26. Springer, Cham. 2022. p. 251-262. (Structural Integrity). Epub 2022 Jun 7. doi: 10.1007/978-3-031-05509-6_21

A Convolutional Neural Network Based Framework for Health Monitoring of a Welded Joint Steel Frame Structure

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this