Feasibility study of strain and temperature discrimination in a BOTDA system via artificial neural networks

Abstract

Automatic discrimination between strain and temperature in a Brillouin optical time domain analyzer via artificial neural networks is proposed and discussed in this paper. Using a standard monomode optical fiber as the sensing element, the ability of the proposed solution to detect the known changes that the Brillouin gain spectrum exhibits depending on the applied temperature and/or strain will be studied. Experimental results, where different simultaneous strain and temperature situations have been considered, will show the feasibility of this technique.