Damage identification in a ship's structure using neural networks

A. Zubaydi; M. R. Haddara; A. S.J. Swamidas

doi:10.1016/S0029-8018(01)00077-4

Damage identification in a ship's structure using neural networks

A. Zubaydi, M. R. Haddara^*, A. S.J. Swamidas

^*Corresponding author for this work

Memorial University of Newfoundland

Research output: Contribution to journal › Article › peer-review

75 Citations (Scopus)

Abstract

Visual inspection of large and complex structures such as a ship is difficult and costly due to problems of accessibility. In this paper, a neural network technique is developed for identifying the damage occurence in the side shell of a ship's structure. The side shell is modeled as a stiffened plate. The input to the network is the autocorrelation function of the vibration response of the structure. The response was obtained using a finite element model of the structure. The output is a single function G_r(z_r,ż_r), which was formed by adding together the damping and a part of the restoring forces. The function is used to identify not only the damage occurence in the model but also its extent and location. The results show that the method presented in this work is successful in identifying the occurence of damage. The detection of the extent and location of damage is promising, however, more work has to be done in this area.

Original language	English
Pages (from-to)	1187-1200
Number of pages	14
Journal	Ocean Engineering
Volume	29
Issue number	10
DOIs	https://doi.org/10.1016/S0029-8018(01)00077-4
Publication status	Published - 5 Apr 2002
Externally published	Yes

Keywords

Autocorrelation functions
Crack detection
Neural networks
Parametric identification
Vibration of stiffened plates

Access to Document

10.1016/S0029-8018(01)00077-4

Cite this

@article{526a5337c2ac445db79cb9f657299048,

title = "Damage identification in a ship's structure using neural networks",

abstract = "Visual inspection of large and complex structures such as a ship is difficult and costly due to problems of accessibility. In this paper, a neural network technique is developed for identifying the damage occurence in the side shell of a ship's structure. The side shell is modeled as a stiffened plate. The input to the network is the autocorrelation function of the vibration response of the structure. The response was obtained using a finite element model of the structure. The output is a single function Gr(zr,{\.z}r), which was formed by adding together the damping and a part of the restoring forces. The function is used to identify not only the damage occurence in the model but also its extent and location. The results show that the method presented in this work is successful in identifying the occurence of damage. The detection of the extent and location of damage is promising, however, more work has to be done in this area.",

keywords = "Autocorrelation functions, Crack detection, Neural networks, Parametric identification, Vibration of stiffened plates",

author = "A. Zubaydi and Haddara, {M. R.} and Swamidas, {A. S.J.}",

note = "Funding Information: The first author would like to acknowledge the financial support from the Government of Indonesia through the High Education Project (HEP), Ministry of Education and Culture, and the National Science and Engineering Research Council (NSERC) of Canada. The second and third authors would like to thank the National Science and Engineering Research Council (NSERC) of Canada for the financial support of this work.",

year = "2002",

month = apr,

day = "5",

doi = "10.1016/S0029-8018(01)00077-4",

language = "English",

volume = "29",

pages = "1187--1200",

journal = "Ocean Engineering",

issn = "0029-8018",

publisher = "Elsevier B.V.",

number = "10",

}

TY - JOUR

T1 - Damage identification in a ship's structure using neural networks

AU - Zubaydi, A.

AU - Haddara, M. R.

AU - Swamidas, A. S.J.

N1 - Funding Information: The first author would like to acknowledge the financial support from the Government of Indonesia through the High Education Project (HEP), Ministry of Education and Culture, and the National Science and Engineering Research Council (NSERC) of Canada. The second and third authors would like to thank the National Science and Engineering Research Council (NSERC) of Canada for the financial support of this work.

PY - 2002/4/5

Y1 - 2002/4/5

N2 - Visual inspection of large and complex structures such as a ship is difficult and costly due to problems of accessibility. In this paper, a neural network technique is developed for identifying the damage occurence in the side shell of a ship's structure. The side shell is modeled as a stiffened plate. The input to the network is the autocorrelation function of the vibration response of the structure. The response was obtained using a finite element model of the structure. The output is a single function Gr(zr,żr), which was formed by adding together the damping and a part of the restoring forces. The function is used to identify not only the damage occurence in the model but also its extent and location. The results show that the method presented in this work is successful in identifying the occurence of damage. The detection of the extent and location of damage is promising, however, more work has to be done in this area.

AB - Visual inspection of large and complex structures such as a ship is difficult and costly due to problems of accessibility. In this paper, a neural network technique is developed for identifying the damage occurence in the side shell of a ship's structure. The side shell is modeled as a stiffened plate. The input to the network is the autocorrelation function of the vibration response of the structure. The response was obtained using a finite element model of the structure. The output is a single function Gr(zr,żr), which was formed by adding together the damping and a part of the restoring forces. The function is used to identify not only the damage occurence in the model but also its extent and location. The results show that the method presented in this work is successful in identifying the occurence of damage. The detection of the extent and location of damage is promising, however, more work has to be done in this area.

KW - Autocorrelation functions

KW - Crack detection

KW - Neural networks

KW - Parametric identification

KW - Vibration of stiffened plates

UR - http://www.scopus.com/inward/record.url?scp=0037023583&partnerID=8YFLogxK

U2 - 10.1016/S0029-8018(01)00077-4

DO - 10.1016/S0029-8018(01)00077-4

M3 - Article

AN - SCOPUS:0037023583

SN - 0029-8018

VL - 29

SP - 1187

EP - 1200

JO - Ocean Engineering

JF - Ocean Engineering

IS - 10

ER -

Damage identification in a ship's structure using neural networks

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this