Evaluation of delamination damage on composite plates using an artificial neura...

• Author(s): Victor Hugo Costa de Albuquerque ; João Manuel Ribeiro da Silva Tavares
• Date: 2010
• Persistent ID: http://hdl.handle.net/10216/43872
• Origin: Repositório Aberto da Universidade do Porto
• Subject(s): Ciências tecnológicas; Tecnologia; Tecnologia de computadores; Processamento de imagem
• Document Type: Article
• Language: English

Description

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 paper, 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.