Electrical Resistivity Reconstruction of Graphite Moderator Bricks From Multi-Frequency Measurements and Artificial Neural NetworksCitation formats

Standard

Electrical Resistivity Reconstruction of Graphite Moderator Bricks From Multi-Frequency Measurements and Artificial Neural Networks. / Tesfalem, Henok.

In: IEEE Sensors Journal, Vol. 21, No. 15, 9430562, 01.08.2021, p. 17005-17016.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

Bibtex

@article{76fe5f890b9c441eb3eba54cc70814b0,
title = "Electrical Resistivity Reconstruction of Graphite Moderator Bricks From Multi-Frequency Measurements and Artificial Neural Networks",
abstract = "This paper discusses an artificial neural inversion approach for non-destructive testing of the graphite moderator bricks that make up the cores of Advanced Gas-Cooled Reactors (AGR). The study employed fully connected feedforward neural networks consisting of four hidden layers and trained with backpropagation approach using Levenberg-Marquardt optimisation algorithm. The approach is based on multi-frequency (MF) eddy current (EC) measurements, and combinations of simulated and measured datasets from a laboratory sample and one of the operating reactor core, along with different regularisation parameters were used to train and test the networks. Various types of artificially generated errors were added to the data during training procedures, which in turn allowed for error tolerance and improved the generalisation of the ANNs to unseen test datasets. First, the ANN was tested using unseen simulated data, followed by the measurements collected from laboratory sample and one of the operating reactor core. The first test from the unseen simulated data showed mean profile error ranging between 1.30% and 8.20%, whereas the profiles estimated from reactor core measurements showed mean profile error ranging between 1.84% and 17.80% when compared with the resistivity measurements from trepanned graphite sample taken out of the reactor core. Further comparison of the network outputs against the profiles estimated using traditional iterative inversion algorithm indicates reasonable agreement between the two approaches with the exception of one case, but the solution time for the ANN was found to be over three orders of magnitude faster than the iterative inversion algorithm.",
keywords = "Graphite, artificial neural networks, eddy currents, multi-frequency, non-destructive testing, resistivity profile",
author = "Henok Tesfalem",
note = "Funding Information: Manuscript received March 11, 2021; revised April 26, 2021; accepted May 11, 2021. Date of publication May 13, 2021; date of current version July 30, 2021. This work was supported by the U.K. Engineering and Physical Science Research Council and EDF Energy through the EPSRC/University of Manchester under Grant IAA 212. The associate editor coordinating the review of this article and approving it for publication was Dr. Andre E. Lazzaretti. (Corresponding author: Henok Tesfalem.) Henok Tesfalem, Joel Hampton, Adam D. Fletcher, and Anthony J. Peyton are with the Department of Electrical and Electronic Engineering, University of Manchester, Manchester M13 9PL, U.K. (e-mail: henok.tesfalem@manchester.ac.uk). Matthew Brown is with EDF-Energy, Gloucester GL4 3RS, U.K. Digital Object Identifier 10.1109/JSEN.2021.3080127 Publisher Copyright: {\textcopyright} 2001-2012 IEEE.",
year = "2021",
month = aug,
day = "1",
doi = "10.1109/JSEN.2021.3080127",
language = "English",
volume = "21",
pages = "17005--17016",
journal = "IEEE Sensors Journal",
issn = "1530-437X",
publisher = "IEEE",
number = "15",

}

RIS

TY - JOUR

T1 - Electrical Resistivity Reconstruction of Graphite Moderator Bricks From Multi-Frequency Measurements and Artificial Neural Networks

AU - Tesfalem, Henok

N1 - Funding Information: Manuscript received March 11, 2021; revised April 26, 2021; accepted May 11, 2021. Date of publication May 13, 2021; date of current version July 30, 2021. This work was supported by the U.K. Engineering and Physical Science Research Council and EDF Energy through the EPSRC/University of Manchester under Grant IAA 212. The associate editor coordinating the review of this article and approving it for publication was Dr. Andre E. Lazzaretti. (Corresponding author: Henok Tesfalem.) Henok Tesfalem, Joel Hampton, Adam D. Fletcher, and Anthony J. Peyton are with the Department of Electrical and Electronic Engineering, University of Manchester, Manchester M13 9PL, U.K. (e-mail: henok.tesfalem@manchester.ac.uk). Matthew Brown is with EDF-Energy, Gloucester GL4 3RS, U.K. Digital Object Identifier 10.1109/JSEN.2021.3080127 Publisher Copyright: © 2001-2012 IEEE.

PY - 2021/8/1

Y1 - 2021/8/1

N2 - This paper discusses an artificial neural inversion approach for non-destructive testing of the graphite moderator bricks that make up the cores of Advanced Gas-Cooled Reactors (AGR). The study employed fully connected feedforward neural networks consisting of four hidden layers and trained with backpropagation approach using Levenberg-Marquardt optimisation algorithm. The approach is based on multi-frequency (MF) eddy current (EC) measurements, and combinations of simulated and measured datasets from a laboratory sample and one of the operating reactor core, along with different regularisation parameters were used to train and test the networks. Various types of artificially generated errors were added to the data during training procedures, which in turn allowed for error tolerance and improved the generalisation of the ANNs to unseen test datasets. First, the ANN was tested using unseen simulated data, followed by the measurements collected from laboratory sample and one of the operating reactor core. The first test from the unseen simulated data showed mean profile error ranging between 1.30% and 8.20%, whereas the profiles estimated from reactor core measurements showed mean profile error ranging between 1.84% and 17.80% when compared with the resistivity measurements from trepanned graphite sample taken out of the reactor core. Further comparison of the network outputs against the profiles estimated using traditional iterative inversion algorithm indicates reasonable agreement between the two approaches with the exception of one case, but the solution time for the ANN was found to be over three orders of magnitude faster than the iterative inversion algorithm.

AB - This paper discusses an artificial neural inversion approach for non-destructive testing of the graphite moderator bricks that make up the cores of Advanced Gas-Cooled Reactors (AGR). The study employed fully connected feedforward neural networks consisting of four hidden layers and trained with backpropagation approach using Levenberg-Marquardt optimisation algorithm. The approach is based on multi-frequency (MF) eddy current (EC) measurements, and combinations of simulated and measured datasets from a laboratory sample and one of the operating reactor core, along with different regularisation parameters were used to train and test the networks. Various types of artificially generated errors were added to the data during training procedures, which in turn allowed for error tolerance and improved the generalisation of the ANNs to unseen test datasets. First, the ANN was tested using unseen simulated data, followed by the measurements collected from laboratory sample and one of the operating reactor core. The first test from the unseen simulated data showed mean profile error ranging between 1.30% and 8.20%, whereas the profiles estimated from reactor core measurements showed mean profile error ranging between 1.84% and 17.80% when compared with the resistivity measurements from trepanned graphite sample taken out of the reactor core. Further comparison of the network outputs against the profiles estimated using traditional iterative inversion algorithm indicates reasonable agreement between the two approaches with the exception of one case, but the solution time for the ANN was found to be over three orders of magnitude faster than the iterative inversion algorithm.

KW - Graphite

KW - artificial neural networks

KW - eddy currents

KW - multi-frequency

KW - non-destructive testing

KW - resistivity profile

U2 - 10.1109/JSEN.2021.3080127

DO - 10.1109/JSEN.2021.3080127

M3 - Article

VL - 21

SP - 17005

EP - 17016

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

SN - 1530-437X

IS - 15

M1 - 9430562

ER -