Neural network based nondestructive evaluation of sandwich composites

A neural network using a combination of complementary vibration and thermal damage detection signatures is proposed. Sandwich composites consisting of two carbon fiber/epoxy matrix face sheets laminated onto a urethane foam core were experimentally and analytically characterized for vibration, and thermal response. The numerical models developed were later used to establish neural network training data. Results show that the network can successfully detect damage when using just a single method vibration or thermography fails.