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

Abstract

Artificial neural networks (ANNs) can be used to replace traditional methods in various fields, making signal processing more efficient and meeting the real-time processing requirements of the Internet of Things (IoT). As a special type of ANN, recently 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) to retrieve the Brillouin frequency shift (BFS), which could be used as the indicator in temperature/strain sensing, etc. However, 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, FNN only needs to be trained once with the proposed method. 150.62 km BOTDA is built to verify the performance of the trained FNN. Simulation and experimental results show that the proposed method is promising in BOTDA because of its high computational efficiency and wide adaptability.

Time-Efficient Convolutional Neural Network-Assisted Brillouin Optical Frequency Domain Analysis

“…The CNN model was trained and evaluated with real experimental data that were collected using the setup and parameters reported in Section 2.1 . In contrast to synthetic data, where artificial white Gaussian noise is added to ideal BGS in order to increase the generalizability of the model [ 13 , 14 ], the experimental data contains the actual noise that arises from the optical components [ 19 ]. The data were collected from measurements under controlled temperature conditions using a temperature chamber.…”

“…It has been shown that machine learning can provide solutions to many problems related to and enhancing the performance of the distributed fiber optic sensors [ 11 ]. Particularly in BOTDA sensing, machine learning algorithms based on artificial neural networks (ANN) [ 12 , 13 , 14 ] and support vector machines (SVM) [ 15 ] were implemented to extract the Brillouin frequency shift (BFS) outperforming conventional algorithms based on Lorentzian curve fitting (LCF). Because the extraction of temperature or strain necessitates the estimation of the temperature or strain coefficient, respectively, machine learning models were trained to predict the measurand of interest directly from the Brillouin gain spectrum providing a more compact solution [ 16 , 17 , 18 ].…”

Application of Raman and Brillouin Scattering Phenomena in Distributed Optical Fiber Sensing

“…The method offers the construction of 96,100 gain spectra along a 38.44km fiber only in 0.46 s suggesting potentials for methods with enhanced speed and power efficiency compared to implementations with a single processor. A technique for BFS reconstruction based on Feed-forward Neural Networks (FNN) has also been proposed and demonstrated to offer more efficient measurements compared to curve fitting methods opening doors for implementations exploiting machine learning algorithms [56]. In addition, discrimination of distributed strain and temperature by employing the excitation of acoustic modes which appear in multiple peaks of the BGS in a single mode fiber has been demonstrated [57], proving the potential for exploiting multiple acoustic, as opposed to optical, modes for measurement.…”

Distributed Brillouin frequency shift extraction via a convolutional neural network

“…Recently, other methods, such as cross-correlation 5,7 , principal component analysis (PCA) 8 , and machine learning methods, have been proposed to analyze the BGS [9][10][11][12][13] . Although these algorithms can achieve better results than LCF under certain conditions, they also have some drawbacks.…”