Extraction of temperature distribution using deep neural networks for BOTDA sensing system

Abstract

Extraction of temperature distribution using the method of deep neural networks (DNN) for Brillouin optical time domain analyzer (BOTDA) system is demonstrated experimentally. After appropriate training of DNN model, temperature distribution information along the fiber under test could be directly extracted from the experimentally obtained local Brillouin gain spectrums (BGS) using DNN without the need of calculating Brillouin frequency shift (BFS) and transforming it to temperature as conventional Lorentz curve fitting (LCF) method does. The results of Temperature extraction using DNN show comparable accuracy to that of using conventional LCF method.