Title :
Application of frame energy based DCT moments for the damage diagnosis in steel plates using FLNN
Author :
Paulraj, M.P. ; Yaacob, Sazali ; Abdul Majid, M.S. ; Krishnan, Prasad
Author_Institution :
Sch. of Mechatron. Eng., Univ. Malaysia Perlis, Arau, Malaysia
Abstract :
This paper discusses the application of frame energy based Discrete Cosine Transformation (DCT) moment features for the detection of damages in steel plates. A simple experimental model is devised to suspend the steel plates in a free-free condition. Experimental modal analysis methods are analyzed and protocols are formed to capture vibration signals from the steel plate using accelerometers when subjected to external impulse. Algorithms based on frame energy based DCT moment feature extraction are developed and prominent features are extracted. A Functional Link Neural Network (FLNN) is modeled to classify the condition of the steel plate. The output of the network model is validated using Falhman testing criterion and the results are compared.
Keywords :
accelerometers; discrete cosine transforms; feature extraction; mechanical testing; neural nets; plates (structures); signal detection; steel; structural engineering computing; vibrations; FLNN; Falhman testing criterion; accelerometers; damage detection; damage diagnosis; experimental modal analysis methods; experimental model; external impulse; frame energy based DCT moments; frame energy based discrete cosine transformation moment feature extraction; free-free condition; functional link neural network; steel plates; vibration signals; DCT moments; Discrete Cosine Transformation; Experimental Modal Analysis; Falhman criterion; Frame energy; Functional Link Neural Network; Structural Health Monitoring;
Conference_Titel :
Research and Development (SCOReD), 2012 IEEE Student Conference on
Conference_Location :
Pulau Pinang
Print_ISBN :
978-1-4673-5158-4
DOI :
10.1109/SCOReD.2012.6518623
