Evaluation of Delamination Damage on Composite Plates using an Artificial Neural Network for the Radiographic Image Analysis

Drilling carbon/epoxy laminates is a common operation in manufacturing and assembly. However, it is necessary to adapt the drilling operations to the drilling tools correctly to avoid the high risk of delamination. Delamination can severely affect the mechanical properties of the parts produced. Production of high quality holes with minimal damage is a key challenge. In this article, delamination caused in laminate plates by drilling is evaluated from radiographic images. To accomplish this goal, a novel solution based on an artificial neural network is employed in the analysis of the radiographic images.