APPLICATION OF NEURAL NETWORK ALGORITHMS TO DETERMINE THE CENTRAL WAVE LENGTH IN PROBLEMS OF FIBER-OPTIC SENSORICS

Abstract

The paper considers the practical aspects of the use of neural network algorithms in the application of determining the central wavelength of fiber Bragg gratings used as sensitive elements of sensors in fiber optic sensor networks. The problem was formulated to determine the central wavelength of a single sensor, the parameters of which were obtained on a low-resolution spectrum analyzer. The configuration of the neural network, the algorithm for the formation of the training and control data set are determined. The results of training the neural network of the chosen configuration showed that the proposed approach allows determining the position of the central wavelength with a resolution of two and a half orders of magnitude higher than the resolution with which the initial data was discretized.