Journal of Radiation Industry (방사선산업학회지)

Korean Society of Radiation Industry (한국방사선산업학회)
권호 표지
DOI QR코드

DOI QR Code

Development of an Anomaly Detection Algorithm for Verification of Radionuclide Analysis Based on Artificial Intelligence in Radioactive Wastes

방사성폐기물 핵종분석 검증용 이상 탐지를 위한 인공지능 기반 알고리즘 개발

  • Seungsoo Jang (Division of Advanced Nuclear Engineering, Pohang University of Science and Technology) ;
  • Jang Hee Lee (Division of Advanced Nuclear Engineering, Pohang University of Science and Technology) ;
  • Young-su Kim (Decommissioning Technology Research Division / Korea Atomic Energy Research Institute) ;
  • Jiseok Kim (HANARO Utilization Division / Korea Atomic Energy Research Institute) ;
  • Jeen-hyeng Kwon (HANARO Utilization Division / Korea Atomic Energy Research Institute) ;
  • Song Hyun Kim (Department of Energy Policy & Engineering, KEPCO International Nuclear Graduate School)
  • 장승수 (포항공과대학교 첨단원자력공학부) ;
  • 이장희 (포항공과대학교 첨단원자력공학부) ;
  • 김영수 (한국원자력연구원 해체기술연구부) ;
  • 김지석 (한국원자력연구원 하나로이용부) ;
  • 권진형 (한국원자력연구원 하나로이용부) ;
  • 김송현 (한국전력 국제원자력대학원대학교 에너지정책학과)
  • Received : 2022.11.04
  • Accepted : 2023.03.27
  • Published : 2023.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

The amount of radioactive waste is expected to dramatically increase with decommissioning of nuclear power plants such as Kori-1, the first nuclear power plant in South Korea. Accurate nuclide analysis is necessary to manage the radioactive wastes safely, but research on verification of radionuclide analysis has yet to be well established. This study aimed to develop the technology that can verify the results of radionuclide analysis based on artificial intelligence. In this study, we propose an anomaly detection algorithm for inspecting the analysis error of radionuclide. We used the data from 'Updated Scaling Factors in Low-Level Radwaste' (NP-5077) published by EPRI (Electric Power Research Institute), and resampling was performed using SMOTE (Synthetic Minority Oversampling Technique) algorithm to augment data. 149,676 augmented data with SMOTE algorithm was used to train the artificial neural networks (classification and anomaly detection networks). 324 NP-5077 report data verified the performance of networks. The anomaly detection algorithm of radionuclide analysis was divided into two modules that detect a case where radioactive waste was incorrectly classified or discriminate an abnormal data such as loss of data or incorrectly written data. The classification network was constructed using the fully connected layer, and the anomaly detection network was composed of the encoder and decoder. The latter was operated by loading the latent vector from the end layer of the classification network. This study conducted exploratory data analysis (i.e., statistics, histogram, correlation, covariance, PCA, k-mean clustering, DBSCAN). As a result of analyzing the data, it is complicated to distinguish the type of radioactive waste because data distribution overlapped each other. In spite of these complexities, our algorithm based on deep learning can distinguish abnormal data from normal data. Radionuclide analysis was verified using our anomaly detection algorithm, and meaningful results were obtained.

Keywords

Acknowledgement

본 연구는 한국원자력연구원의 도전창의 집단기술연구사업 지원을 받았으며(NRF-2021M2D2A20184452161082139290201), 한국수력원자력(주)의 지원(No. 2020-Tech-14), 한국에너지기술평가원의 에너지기술개발사업지원(No. 20203210100390)으로 수행되었습니다.

References

  1. Kim CL. 2016. Nuclear Decommissioning Waste Management Trends. Konetic Report 2016-138 
  2. Kim TW, Choi KS, Kang KD and Ha JH. 2008. Method for Determining Transportation Grade for HIC Containing Spent Resin Using Radioactivity Analysis. J. Nucl. Fuel Cycle Waste Technol. 6(1): 11-15. 
  3. Nuclear Safety and Security Commission. 2019. Investigation Results on the Errors in Nuclide Analysis of Radioactive Waste at the Korea Atomic Energy Research Institute, 103rd Nuclear Safety and Security Commission, Report: 1. 
  4. Lee KM, Hong DS, Kim TG, Bae SM, Shon JS and Hong GP. 2004. Radioactive Wastes Assay Technique & Equipment. KAERI/TR-2879/2004. 
  5. Li F, Wang J, Ge L, Hu F, Cheng F and Sun K. 2019. Research on gamma spectrum semi-quantitative analysis based on convolutional neural network. J. Phys.: Conf. Ser. 1423:012005. 
  6. Kamuda M, Zhao J and Huff K. 2020. A comparison of machine learning methods for automated gamma-ray spectroscopy. Nucl. Instrum. Methods Phys. Res. A. 954:161385. https://doi.org/10.1016/j.nima.2018.10.063 
  7. Shumaker E, Stinnett J and Hero AO. 2020. Twin Artificial Neural Networks for Gamma Ray Spectra Comparison. 2020 ETI Annual Workshop. 
  8. Gomez-Fernandez M, Wong WK, Tokuhiro A, Welter K, Alhawsawi AM, Yang H and Higley K. 2021. Isotope identification using deep learning: An explanation. Nucl Instrum Methods Phys. Res. A. 988:164925. https://doi.org/10.1016/j.nima.2020.164925 
  9. Chalapathy R and Chawla S. 2019. Deep Learning for Anomaly Detection: A Survey. arXiv:1901.03407v2. 
  10. Pang G, Shen C, Cao L and Hengel AV. 2020. Deep Learning for Anomaly Detection: A Review. arXiv:2007.02500v3. 
  11. Lee GJ, Paek MH, Park JG, Han BS, Cheong JH, Lee HC, Yang JY, Hong HK and Park JB. 1995. A Study on the Establishment of the Regulatory Guide to the Characteristics and Classi fication Cri teria of Low and Intermediate Level Radioactive Waste. KINS/HR-111. 
  12. Han SJ, Lee HY, Kim BG and An EM. 2021. Analysis and Consideration of the Establishment of a Multiplexed Channel for Domestic RI Waste Nuclide Analysis. J. Radiol. Sci. Technol. 44(4): 351-358. https://doi.org/10.17946/JRST.2021.44.4.351 
  13. Best WT and Miller AD. 1987. Updated Scailing Factors in Low-Level Radwaste. EPRI NP-5077, Project 1557-6, Final Report. 
  14. Tyagi AK and Chahal P. 2019. Artificial Intelligence and Machine Learning Algorithms. pp. 188-219. In: Challenges and Applications for Implementing Machine Learning in Computer Vision(Kashyap R and Kumar AV), IGI Global, Hershey. PA. 
  15. Wang J, Xu M, Wang H and Zhang J. 2006. Classification of Imbalanced Data by Using the SMOTE Algorithm and Locally Linear Embedding. ICSP2006 Proceeding. 
  16. Teknomo K. 2006. K-means clustering tutorial. Available online at http://people.revoledu.com/kardi/tutorial/kMean/