Preliminary study of artificial intelligence-based fuel-rod pattern analysis of low-quality tomographic image of fuel assembly

Saerom Seong; Sei Hwan Choi; Jae Joon Ahn; Hyung joo Choi; Yong Hyun Chung; Sei Hwan You; Yeon Soo Yeom; Hyun Joon Choi; Chul Hee Min

doi:10.1016/j.net.2022.05.013

Preliminary study of artificial intelligence-based fuel-rod pattern analysis of low-quality tomographic image of fuel assembly

Saerom Seong, Sei Hwan Choi, Jae Joon Ahn, Hyung joo Choi, Yong Hyun Chung, Sei Hwan You, Yeon Soo Yeom, Hyun Joon Choi, Chul Hee Min

Radiological Science

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

Abstract

Single-photon emission computed tomography is one of the reliable pin-by-pin verification techniques for spent-fuel assemblies. One of the challenges with this technique is to increase the total fuel assembly verification speed while maintaining high verification accuracy. The aim of the present study, therefore, was to develop an artificial intelligence (AI) algorithm-based tomographic image analysis technique for partial-defect verification of fuel assemblies. With the Monte Carlo (MC) simulation technique, a tomographic image dataset consisting of 511 fuel-rod patterns of a 3 × 3 fuel assembly was generated, and with these images, the VGG16, GoogLeNet, and ResNet models were trained. According to an evaluation of these models for different training dataset sizes, the ResNet model showed 100% pattern estimation accuracy. And, based on the different tomographic image qualities, all of the models showed almost 100% pattern estimation accuracy, even for low-quality images with unrecognizable fuel patterns. This study verified that an AI model can be effectively employed for accurate and fast partial-defect verification of fuel assemblies.

Original language	English
Journal	Nuclear Engineering and Technology
DOIs	https://doi.org/10.1016/j.net.2022.05.013
Publication status	Published - 2022 Oct

Bibliographical note

Funding Information:
This research was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2021R1I1A1A01059875), the Nuclear Safety Research Program through the Korea Foundation Of Nuclear Safety (KoFONS) using financial resources granted by the Nuclear Safety and Security Commission (NSSC) of the Republic of Korea (No. 2101073), the Korea Institute of Energy Technology Evaluation and Planning (KETEP), and the Ministry of Trade, Industry & Energy (MOTIE) of the Republic of Korea (No. G032579811).

Publisher Copyright:
© 2022 Korean Nuclear Society

All Science Journal Classification (ASJC) codes

Nuclear Energy and Engineering

Access to Document

10.1016/j.net.2022.05.013

Cite this

@article{2c6b6ef23bc74bb08d2ec72ef396347f,

title = "Preliminary study of artificial intelligence-based fuel-rod pattern analysis of low-quality tomographic image of fuel assembly",

abstract = "Single-photon emission computed tomography is one of the reliable pin-by-pin verification techniques for spent-fuel assemblies. One of the challenges with this technique is to increase the total fuel assembly verification speed while maintaining high verification accuracy. The aim of the present study, therefore, was to develop an artificial intelligence (AI) algorithm-based tomographic image analysis technique for partial-defect verification of fuel assemblies. With the Monte Carlo (MC) simulation technique, a tomographic image dataset consisting of 511 fuel-rod patterns of a 3 × 3 fuel assembly was generated, and with these images, the VGG16, GoogLeNet, and ResNet models were trained. According to an evaluation of these models for different training dataset sizes, the ResNet model showed 100% pattern estimation accuracy. And, based on the different tomographic image qualities, all of the models showed almost 100% pattern estimation accuracy, even for low-quality images with unrecognizable fuel patterns. This study verified that an AI model can be effectively employed for accurate and fast partial-defect verification of fuel assemblies.",

author = "Saerom Seong and Choi, {Sei Hwan} and Ahn, {Jae Joon} and Choi, {Hyung joo} and Chung, {Yong Hyun} and You, {Sei Hwan} and Yeom, {Yeon Soo} and Choi, {Hyun Joon} and Min, {Chul Hee}",

note = "Funding Information: This research was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2021R1I1A1A01059875), the Nuclear Safety Research Program through the Korea Foundation Of Nuclear Safety (KoFONS) using financial resources granted by the Nuclear Safety and Security Commission (NSSC) of the Republic of Korea (No. 2101073), the Korea Institute of Energy Technology Evaluation and Planning (KETEP), and the Ministry of Trade, Industry & Energy (MOTIE) of the Republic of Korea (No. G032579811). Publisher Copyright: {\textcopyright} 2022 Korean Nuclear Society",

year = "2022",

month = oct,

doi = "10.1016/j.net.2022.05.013",

language = "English",

journal = "Nuclear Engineering and Technology",

issn = "1738-5733",

publisher = "Korean Nuclear Society",

}

TY - JOUR

T1 - Preliminary study of artificial intelligence-based fuel-rod pattern analysis of low-quality tomographic image of fuel assembly

AU - Seong, Saerom

AU - Choi, Sei Hwan

AU - Ahn, Jae Joon

AU - Choi, Hyung joo

AU - Chung, Yong Hyun

AU - You, Sei Hwan

AU - Yeom, Yeon Soo

AU - Choi, Hyun Joon

AU - Min, Chul Hee

N1 - Funding Information: This research was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2021R1I1A1A01059875), the Nuclear Safety Research Program through the Korea Foundation Of Nuclear Safety (KoFONS) using financial resources granted by the Nuclear Safety and Security Commission (NSSC) of the Republic of Korea (No. 2101073), the Korea Institute of Energy Technology Evaluation and Planning (KETEP), and the Ministry of Trade, Industry & Energy (MOTIE) of the Republic of Korea (No. G032579811). Publisher Copyright: © 2022 Korean Nuclear Society

PY - 2022/10

Y1 - 2022/10

N2 - Single-photon emission computed tomography is one of the reliable pin-by-pin verification techniques for spent-fuel assemblies. One of the challenges with this technique is to increase the total fuel assembly verification speed while maintaining high verification accuracy. The aim of the present study, therefore, was to develop an artificial intelligence (AI) algorithm-based tomographic image analysis technique for partial-defect verification of fuel assemblies. With the Monte Carlo (MC) simulation technique, a tomographic image dataset consisting of 511 fuel-rod patterns of a 3 × 3 fuel assembly was generated, and with these images, the VGG16, GoogLeNet, and ResNet models were trained. According to an evaluation of these models for different training dataset sizes, the ResNet model showed 100% pattern estimation accuracy. And, based on the different tomographic image qualities, all of the models showed almost 100% pattern estimation accuracy, even for low-quality images with unrecognizable fuel patterns. This study verified that an AI model can be effectively employed for accurate and fast partial-defect verification of fuel assemblies.

AB - Single-photon emission computed tomography is one of the reliable pin-by-pin verification techniques for spent-fuel assemblies. One of the challenges with this technique is to increase the total fuel assembly verification speed while maintaining high verification accuracy. The aim of the present study, therefore, was to develop an artificial intelligence (AI) algorithm-based tomographic image analysis technique for partial-defect verification of fuel assemblies. With the Monte Carlo (MC) simulation technique, a tomographic image dataset consisting of 511 fuel-rod patterns of a 3 × 3 fuel assembly was generated, and with these images, the VGG16, GoogLeNet, and ResNet models were trained. According to an evaluation of these models for different training dataset sizes, the ResNet model showed 100% pattern estimation accuracy. And, based on the different tomographic image qualities, all of the models showed almost 100% pattern estimation accuracy, even for low-quality images with unrecognizable fuel patterns. This study verified that an AI model can be effectively employed for accurate and fast partial-defect verification of fuel assemblies.

UR - http://www.scopus.com/inward/record.url?scp=85132220815&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85132220815&partnerID=8YFLogxK

U2 - 10.1016/j.net.2022.05.013

DO - 10.1016/j.net.2022.05.013

M3 - Article

AN - SCOPUS:85132220815

SN - 1738-5733

JO - Nuclear Engineering and Technology

JF - Nuclear Engineering and Technology

ER -

Preliminary study of artificial intelligence-based fuel-rod pattern analysis of low-quality tomographic image of fuel assembly

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this