Damage detection in steel plates using Artificial Neural Networks

Author

Krishnan, R. Pranesh ; Rahiman, Mohd Hafiz Fazalul ; Yaacob, Sazali ; Majid, M.S.A. ; Paulraj, M.P.

Author_Institution

Sch. of Mechatron. Eng., Univ. Malaysia Perlis, Arau, Malaysia

fYear

2009

fDate

4-6 June 2009

Firstpage

1

Lastpage

4

Abstract

In this paper, a simple method for crack identification in steel plates based on frame energy based discrete cosine transformation (DCT) is presented. A simple experimental procedure is also proposed to measure the vibration at different positions of the steel plate. The plate is excited by an impulse signal and made to vibrate. Energy based DCT features are then extracted from the vibration signals which are measured at different locations. A simple neural network model is developed, trained by back propagation (BP), to associate the frame energy based DCT features with the damage or undamaged locations of the steel plate. The effectiveness of the system is validated through simulation.

Keywords

backpropagation; condition monitoring; discrete cosine transforms; feature extraction; mechanical engineering computing; neural nets; plates (structures); vibrations; artificial neural networks; backpropagation; damage detection; discrete cosine transformation; feature extraction; health monitoring; steel plates; vibration signals; Accelerometers; Artificial neural networks; Condition monitoring; Data acquisition; Discrete cosine transforms; Fault detection; Frequency; Steel; Testing; Vibration measurement; Back Propagation neural network; Damage Detection; Discrete Cosine Transformation; Time domain;

fLanguage

English

Publisher

ieee

Conference_Titel

Control, Automation, Communication and Energy Conservation, 2009. INCACEC 2009. 2009 International Conference on

Conference_Location

Perundurai, Tamilnadu

Print_ISBN

978-1-4244-4789-3

Type

conf

Filename

5204365