Sensor inteligente em fibra ótica para localização de deformações em estruturas planas

• Ano de defesa: 2014
• Autor(a) principal: Ribeiro, Fabiano
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Tecnológica Federal do Paraná; Curitiba; Programa de Pós-Graduação em Engenharia Elétrica e Informática Industrial
• Palavras-chave em Português: Redes neurais (Computação); Deformações (Mecânica); Engenharia elétrica; Neural networks (Computer science); Deformations (Mechanics); Electric engineering
• Link de acesso: http://repositorio.utfpr.edu.br/jspui/handle/1/836

In this work the applicability of fiber Bragg grantings as tools for the analysis of impacts on planar structures was studied. In a first step, Bragg grantings were characterized and their thermal and strain sensitivities were determined. The experiments were carried out with four fiber Bragg gratings. Being that their responses in λ along 0.3 second were used to train and test a multilayer perceptron artificial neural network. The locations of impacts in quadrants were supplied by the artificial neural network. The results demonstrate that such location can be predicted with correct classification rate of approximately 90.0% in validation step. Another RNA was implemented to locate impact coordinates, wich allowed a quantitative analysis of errors by performing a comparison of the desired value and the output value provided by the RNA on the location of an impact on a plan. The largest mean error (Em) to the target value was 0,401 cm for the coordinate x and 0,703 cm for y, considering five different points of impact in the test step.