A hierarchical neural network for identification of multiple damage using modal parameters

S. J.S. Hakim; J. M. Irwan; M. H.W. Ibrahim; S. Shahidan; S. S. Ayop; N. Anting; T. N.T. Chik

doi:10.1063/5.0149295

A hierarchical neural network for identification of multiple damage using modal parameters

S. J.S. Hakim^*, J. M. Irwan, M. H.W. Ibrahim, S. Shahidan, S. S. Ayop, N. Anting, T. N.T. Chik

^*Corresponding author for this work

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

2 Scopus citations

Abstract

Artificial neural networks have been applied extensively in recent years due to their excellent performance in pattern recognition, which is useful for detecting damage in structural elements. The application of multiple damage cases by an ensemble neural network using dynamic parameters of structure is very limited. Therefore, in this paper, an ensemble neural network based on damage identification techniques was developed and applied for damage localization and severity identification of quad-point damage cases in I-beam structure. Experimental modal analysis and finite element simulation were carried out for I-beam with four-point damage cases to generate the modal parameters of the structure. Based on the results, it is found that the ensemble neural networks achieve a high detecting accuracy and good robustness of quad-point damage cases in I-beam structures.

Original language	English
Title of host publication	AIP Conference Proceedings
Editors	Shayfull Zamree Abd Rahim, Mohd Nasir Mat Saad, Irfan Abd Rahim, Mohd Khairul Fadzly Abu Bakar
Publisher	American Institute of Physics
Edition	1
ISBN (Electronic)	9780735448797
DOIs	https://doi.org/10.1063/5.0149295
State	Published - 21 Mar 2024
Externally published	Yes
Event	7th International Conference on Green Design and Manufacture 2021, IConGDM 2021 - Virtual, Online, Malaysia Duration: 8 Sep 2021 → 9 Sep 2021

Publication series

Name	AIP Conference Proceedings
Number	1
Volume	2750
ISSN (Print)	0094-243X
ISSN (Electronic)	1551-7616

Conference

Conference	7th International Conference on Green Design and Manufacture 2021, IConGDM 2021
Country/Territory	Malaysia
City	Virtual, Online
Period	8/09/21 → 9/09/21

Bibliographical note

Publisher Copyright:
© 2024 Author(s).

ASJC Scopus subject areas

General Physics and Astronomy

Access to Document

10.1063/5.0149295

Cite this

Hakim, S. J. S., Irwan, J. M., Ibrahim, M. H. W., Shahidan, S., Ayop, S. S., Anting, N., & Chik, T. N. T. (2024). A hierarchical neural network for identification of multiple damage using modal parameters. In S. Z. A. Rahim, M. N. M. Saad, I. A. Rahim, & M. K. F. Abu Bakar (Eds.), AIP Conference Proceedings (1 ed.). Article 040067 (AIP Conference Proceedings; Vol. 2750, No. 1). American Institute of Physics. https://doi.org/10.1063/5.0149295

@inproceedings{62bb41b4287749708639c6e9bed50427,

title = "A hierarchical neural network for identification of multiple damage using modal parameters",

abstract = "Artificial neural networks have been applied extensively in recent years due to their excellent performance in pattern recognition, which is useful for detecting damage in structural elements. The application of multiple damage cases by an ensemble neural network using dynamic parameters of structure is very limited. Therefore, in this paper, an ensemble neural network based on damage identification techniques was developed and applied for damage localization and severity identification of quad-point damage cases in I-beam structure. Experimental modal analysis and finite element simulation were carried out for I-beam with four-point damage cases to generate the modal parameters of the structure. Based on the results, it is found that the ensemble neural networks achieve a high detecting accuracy and good robustness of quad-point damage cases in I-beam structures.",

author = "Hakim, {S. J.S.} and Irwan, {J. M.} and Ibrahim, {M. H.W.} and S. Shahidan and Ayop, {S. S.} and N. Anting and Chik, {T. N.T.}",

note = "Publisher Copyright: {\textcopyright} 2024 Author(s).; 7th International Conference on Green Design and Manufacture 2021, IConGDM 2021 ; Conference date: 08-09-2021 Through 09-09-2021",

year = "2024",

month = mar,

day = "21",

doi = "10.1063/5.0149295",

language = "English",

series = "AIP Conference Proceedings",

publisher = "American Institute of Physics",

number = "1",

editor = "Rahim, {Shayfull Zamree Abd} and Saad, {Mohd Nasir Mat} and Rahim, {Irfan Abd} and {Abu Bakar}, {Mohd Khairul Fadzly}",

booktitle = "AIP Conference Proceedings",

address = "United States",

edition = "1",

}

Hakim, SJS, Irwan, JM, Ibrahim, MHW, Shahidan, S, Ayop, SS, Anting, N & Chik, TNT 2024, A hierarchical neural network for identification of multiple damage using modal parameters. in SZA Rahim, MNM Saad, IA Rahim & MKF Abu Bakar (eds), AIP Conference Proceedings. 1 edn, 040067, AIP Conference Proceedings, no. 1, vol. 2750, American Institute of Physics, 7th International Conference on Green Design and Manufacture 2021, IConGDM 2021, Virtual, Online, Malaysia, 8/09/21. https://doi.org/10.1063/5.0149295

A hierarchical neural network for identification of multiple damage using modal parameters. / Hakim, S. J.S.; Irwan, J. M.; Ibrahim, M. H.W. et al.
AIP Conference Proceedings. ed. / Shayfull Zamree Abd Rahim; Mohd Nasir Mat Saad; Irfan Abd Rahim; Mohd Khairul Fadzly Abu Bakar. 1. ed. American Institute of Physics, 2024. 040067 (AIP Conference Proceedings; Vol. 2750, No. 1).

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

TY - GEN

T1 - A hierarchical neural network for identification of multiple damage using modal parameters

AU - Hakim, S. J.S.

AU - Irwan, J. M.

AU - Ibrahim, M. H.W.

AU - Shahidan, S.

AU - Ayop, S. S.

AU - Anting, N.

AU - Chik, T. N.T.

PY - 2024/3/21

Y1 - 2024/3/21

N2 - Artificial neural networks have been applied extensively in recent years due to their excellent performance in pattern recognition, which is useful for detecting damage in structural elements. The application of multiple damage cases by an ensemble neural network using dynamic parameters of structure is very limited. Therefore, in this paper, an ensemble neural network based on damage identification techniques was developed and applied for damage localization and severity identification of quad-point damage cases in I-beam structure. Experimental modal analysis and finite element simulation were carried out for I-beam with four-point damage cases to generate the modal parameters of the structure. Based on the results, it is found that the ensemble neural networks achieve a high detecting accuracy and good robustness of quad-point damage cases in I-beam structures.

AB - Artificial neural networks have been applied extensively in recent years due to their excellent performance in pattern recognition, which is useful for detecting damage in structural elements. The application of multiple damage cases by an ensemble neural network using dynamic parameters of structure is very limited. Therefore, in this paper, an ensemble neural network based on damage identification techniques was developed and applied for damage localization and severity identification of quad-point damage cases in I-beam structure. Experimental modal analysis and finite element simulation were carried out for I-beam with four-point damage cases to generate the modal parameters of the structure. Based on the results, it is found that the ensemble neural networks achieve a high detecting accuracy and good robustness of quad-point damage cases in I-beam structures.

UR - http://www.scopus.com/inward/record.url?scp=85189320826&partnerID=8YFLogxK

U2 - 10.1063/5.0149295

DO - 10.1063/5.0149295

M3 - Conference contribution

AN - SCOPUS:85189320826

T3 - AIP Conference Proceedings

BT - AIP Conference Proceedings

A2 - Rahim, Shayfull Zamree Abd

A2 - Saad, Mohd Nasir Mat

A2 - Rahim, Irfan Abd

A2 - Abu Bakar, Mohd Khairul Fadzly

PB - American Institute of Physics

T2 - 7th International Conference on Green Design and Manufacture 2021, IConGDM 2021

Y2 - 8 September 2021 through 9 September 2021

ER -

A hierarchical neural network for identification of multiple damage using modal parameters

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this