Distributed Brillouin frequency shift extraction via a convolutional neural network

Distributed optical fiber Brillouin sensors detect the temperature and strain along a fiber according to the local Brillouin frequency shift (BFS), which is usually calculated by the measured Brillouin spectrum using Lorentzian curve fitting. In addition, cross-correlation, principal component analysis, and machine learning methods have been proposed for the more efficient extraction of BFS. However, existing methods only process the Brillouin spectrum individually, ignoring the correlation in the time domain, indicating that there is still room for improvement. Here, we propose and experimentally demonstrate a BFS extraction convolutional neural network (BFSCNN) to retrieve the distributed BFS directly from the measured two-dimensional data. Simulated ideal Brillouin spectra with various parameters are used to train the BFSCNN. Both the simulation and experimental results show that the extraction accuracy of the BFSCNN is better than that of the traditional curve fitting algorithm with a much shorter processing time. The BFSCNN has good universality and robustness and can effectively improve the performances of existing Brillouin sensors.