2D Temperature Field Reconstruction Using Optical Frequency Domain Reflectometry and Machine-Learning Algorithms

Alexey Wolf; Nikita Shabalov; Vladimir Kamynin; Alexey Kokhanovskiy

doi:10.3390/s22207810

2D Temperature Field Reconstruction Using Optical Frequency Domain Reflectometry and Machine-Learning Algorithms

Sensors (Basel). 2022 Oct 14;22(20):7810. doi: 10.3390/s22207810.

Authors

Alexey Wolf¹, Nikita Shabalov^{1

2}, Vladimir Kamynin³, Alexey Kokhanovskiy²

Affiliations

¹ Institute of Automation and Electrometry SB RAS, 1 Acad. Koptyug Ave., 630090 Novosibirsk, Russia.
² Physics Department, Novosibirsk State University, 1 Pirogov St., 630090 Novosibirsk, Russia.
³ Prokhorov General Physics Institute of the RAS, 38 Vavilov St., 119991 Moscow, Russia.

Abstract

We present experimental results on the reconstruction of the 2D temperature field on the surface of a 250 × 250 mm sensor panel based on the distributed frequency shift measured by an optical backscatter reflectometer. A linear regression and a feed-forward neural network algorithm, trained by varying the temperature field and capturing thermal images of the panel, are used for the reconstruction. In this approach, we do not use any information about the exact trajectory of the fiber, material properties of the sensor panel, and a temperature sensitivity coefficient of the fiber. Mean absolute errors of 0.118 °C and 0.086 °C are achieved in the case of linear regression and feed-forward neural network, respectively.

Keywords: fiber-optic sensor; machine learning; optical frequency domain reflectometry.

MeSH terms

Algorithms*
Machine Learning*
Neural Networks, Computer
Temperature

Grants and funding

121030500067-5/State Budget of the Russian Federation