Back propagation neutral network based signal acquisition for Brillouin distributed optical fiber sensors

Abstract

This manuscript proposes a method based on back propagation (BP) neural network and the spectral subtraction method to quickly obtain sensing information in Brillouin fiber optics sensors. BP neural network's characteristics which can realize any complex nonlinear mapping help to determine the frequency shift section(s) information. The training function, transfer function and number of hidden layer nodes of BP neural network are determined with experimental data. The experimental results show that comparing with traditional Lorentz fitting algorithm and edge detection with Sobel operator, the BP neural network is about 1/12 in terms of time complexity with the Lorentz algorithm, about 1/9 with the edge detection based on Sobel operator; while the respective accuracy on determine the frequency shifted section(s) has improved by 79.4% and 27.9%.

Recent Advances in Machine Learning for Fiber Optic Sensor Applications

“…Acceleration of the data processing is an important task for the big data generated from BOTDA technologies. Numerous solutions have been proposed in the literature [97][98][99][100][101][102][103] that can be Reproduced with permission. [42] Copyright 2020, Royal Society of Chemistry.…”

Classification and discrimination of real and fake blood based on photoacoustic spectroscopy combined with particle swarm optimized wavelet neural networks

“…In this work, the WNN algorithm [ 21 ] was used to classify and discriminate real and fake blood because it combines the wavelet transform and the artificial neural network. It has the great capacities of strong learning, self-adaptability and fault tolerance because it avoids nonlinear optimization problems, including the blindness of structure design and local optimization of BPNN [ 22 ]. The basic structure of WNN is shown in Fig.…”

Recent development in artificial neural network based distributed fiber optic sensors

“…The ANN learning essentially consists of modifying the weights of the connections between the neurons, where the initial weights are modified by an algorithm. The weights connecting the neurons of different layers are optimized by back-propagation (BP) algorithm [26]. Without the process of estimation of BFS, the ANN with optimized weights generate the temperature distribution along the sensing fiber.…”