Discrimination of strain and temperature in Brillouin Optical Time Domain Analyzers via Artificial Neural Networks

Big structures monitoring is a relevant issue due to their size and trouble to find damages. The goal of this thesis is the achievement of a discrimination between temperature and strain effects occurring on a fiber. The use of distributed OFSs is of big help: the work is based on a BOTDA configuration to retrieve the BGSs along the FUT and use ANNs to analyze them. A maximum of around 70% in some cases for strain and temperature and a unique 86.7% of success for strain selection are reached