Optimized Feedforward Neural Network Training for Efficient Brillouin Frequency Shift Retrieval in Fiber

Artificial neural networks (ANNs) can be used to replace the traditional methods in various fields, making signal processing more efficient and meeting the real-time processing requirements of the Internet of Things (IoT). Recently, as a special type of ANN, the feedforward neural network (FNN) has been used to replace the time-consuming Lorentzian curve fitting (LCF) method in Brillouin optical time-domain analysis (BOTDA) system to retrieve the Brillouin frequency shift (BFS), which could be used as the indicator in temperature/strain sensing and so on. However, the FNN needs to be re-trained if the generalization ability is not satisfactory, or the frequency scanning step is changing in the experiment. This is a cumbersome and inefficient process. In this paper, the FNN only needs to be trained once with the proposed method, and 150.62 km BOTDA is built to verify the performance of the trained FNN. The simulation and experimental results show that the proposed method is promising in BOTDA because of its high computational efficiency and wide adaptability.