Prediction of Damage Location in Composite Plates using Artificial　Neural Network Modeling

摘要

Composite is one of the most widely used industrial materials because of high strength, low weight, and high corrosionresistance properties. Different parts of composite structures are normally joined using adhesives or fasteners that areprone to defects and damages. A reliable method for prediction of the defect location is needed for an efficient structuralhealth monitoring (SHM) process. Heterodyne effect is recently utilized for damage detection in the bonding zone ofcomposite structures where debonding is expected to change the linear characteristics of the system into nonlinearcharacteristics. This paper briefly introduces this novel defect locating approach in composite plates using theheterodyne effect. For the first time, an Artificial Neural Network methodology is utilized with heterodyne effect methodto find the defect location in composite plates. The main objective of this article is to develop a neural network basedmethodology for prediction of damage location, particularly for the bond inspection of composite plates.