Standard

2D Temperature Field Reconstruction Using Optical Frequency Domain Reflectometry and Machine-Learning Algorithms. / Wolf, Alexey; Shabalov, Nikita; Kamynin, Vladimir et al.

In: Sensors (Basel, Switzerland), Vol. 22, No. 20, 14.10.2022.

Research output: Contribution to journal › Article › peer-review

Harvard

Wolf, A, Shabalov, N, Kamynin, V & Kokhanovskiy, A 2022, '2D Temperature Field Reconstruction Using Optical Frequency Domain Reflectometry and Machine-Learning Algorithms', Sensors (Basel, Switzerland), vol. 22, no. 20. https://doi.org/10.3390/s22207810

APA

Wolf, A., Shabalov, N., Kamynin, V., & Kokhanovskiy, A. (2022). 2D Temperature Field Reconstruction Using Optical Frequency Domain Reflectometry and Machine-Learning Algorithms. Sensors (Basel, Switzerland), 22(20). https://doi.org/10.3390/s22207810

Vancouver

Wolf A, Shabalov N, Kamynin V, Kokhanovskiy A. 2D Temperature Field Reconstruction Using Optical Frequency Domain Reflectometry and Machine-Learning Algorithms. Sensors (Basel, Switzerland). 2022 Oct 14;22(20). doi: 10.3390/s22207810

Author

Wolf, Alexey ; Shabalov, Nikita ; Kamynin, Vladimir et al. / 2D Temperature Field Reconstruction Using Optical Frequency Domain Reflectometry and Machine-Learning Algorithms. In: Sensors (Basel, Switzerland). 2022 ; Vol. 22, No. 20.

BibTeX

@article{27cce80fbd594d8ea5bee9a89552142d,
title = "2D Temperature Field Reconstruction Using Optical Frequency Domain Reflectometry and Machine-Learning Algorithms",
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",
author = "Alexey Wolf and Nikita Shabalov and Vladimir Kamynin and Alexey Kokhanovskiy",
year = "2022",
month = oct,
day = "14",
doi = "10.3390/s22207810",
language = "English",
volume = "22",
journal = "Sensors",
issn = "1424-3210",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "20",

}

RIS

TY - JOUR

T1 - 2D Temperature Field Reconstruction Using Optical Frequency Domain Reflectometry and Machine-Learning Algorithms

AU - Wolf, Alexey

AU - Shabalov, Nikita

AU - Kamynin, Vladimir

AU - Kokhanovskiy, Alexey

PY - 2022/10/14

Y1 - 2022/10/14

N2 - 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.

AB - 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.

KW - fiber-optic sensor

KW - machine learning

KW - optical frequency domain reflectometry

UR - http://www.scopus.com/inward/record.url?scp=85140932918&partnerID=8YFLogxK

U2 - 10.3390/s22207810

DO - 10.3390/s22207810

M3 - Article

C2 - 36298159

AN - SCOPUS:85140932918

VL - 22

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 20

ER -

ID: 38647982