Damage detection in steel plates using discrete cosine transformation techniques and artificial neural network

Abstract

In this paper, a simple method for crack identification in steel plates based on the Frame Energy based Discrete Cosine Transformation [DCT] moments 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. Frame Energy based DCT moment 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 moment features with the damage or undamaged locations of the steel plate. The effectiveness of the system is validated through simulation.