본문 바로가기
KERD
논문KCI 등재

Source term inversion of nuclear accidents based on ISAO-SAELM model

Li Jianxin|Xiao Dong|Zhang Zixuan|Fu Yanhua
한국원자력학회 (Korean Nuclear Society)|2024.09|Nuclear Engineering and Technology|제56권 제9호|pp. 3914-3924|DOI 10.1016/j.net.2024.04.038

0

조회

0

다운로드

0

인용

0

참고문헌

키워드

Nuclear accidentOptimization algorithmSource term inversionExtreme learning machine
주제분류원자력공학

초록

The release source term of radioactivity becomes a critical foundation for emergency response and accident consequence assessment after a nuclear accident Rapidly and accurately inverting the source term remains an urgent scientific challenge. Today source term inversion based on meteorological data and gamma dose rate measurements is a common method. But gamma dose rate actually includes all nuclides information, and the composition of radioactive nuclides is generally uncertain. This paper introduces a novel nuclear accident source term inversion model, which is Improve Snow Ablation Optimizer-Sensitivity Analysis Pruning Extreme Learning Machine (ISAO-SAELM) model. The model inverts the release rates of 11 radioactive nuclides (I-131, Xe-133, Cs- 137, Kr-88, Sr-91, Te-132, Mo-99, Ba-140, La-140, Ce-144, Sb-129). It does not require the use of the physical field of the reactor to obtain prior information and establish a dispersion model. And the robustness is validated through noise analysis test. The mean absolute errors of the release rates of 11 nuclides are 15.52 %, 15.28 %, 15.70 %, 14.99 %, 14.85 %, 15.61 %, 15.96 %, 15.42 %, 15.84 %, 15.13 %, 17.72 %, which show the significant superiority of ISAO-SAELM. ISAO-SAELM model not only achieves notable advancements in accuracy but also receives validation in terms of practicality and feasibility.

Abstract

The release source term of radioactivity becomes a critical foundation for emergency response and accident consequence assessment after a nuclear accident Rapidly and accurately inverting the source term remains an urgent scientific challenge. Today source term inversion based on meteorological data and gamma dose rate measurements is a common method. But gamma dose rate actually includes all nuclides information, and the composition of radioactive nuclides is generally uncertain. This paper introduces a novel nuclear accident source term inversion model, which is Improve Snow Ablation Optimizer-Sensitivity Analysis Pruning Extreme Learning Machine (ISAO-SAELM) model. The model inverts the release rates of 11 radioactive nuclides (I-131, Xe-133, Cs- 137, Kr-88, Sr-91, Te-132, Mo-99, Ba-140, La-140, Ce-144, Sb-129). It does not require the use of the physical field of the reactor to obtain prior information and establish a dispersion model. And the robustness is validated through noise analysis test. The mean absolute errors of the release rates of 11 nuclides are 15.52 %, 15.28 %, 15.70 %, 14.99 %, 14.85 %, 15.61 %, 15.96 %, 15.42 %, 15.84 %, 15.13 %, 17.72 %, which show the significant superiority of ISAO-SAELM. ISAO-SAELM model not only achieves notable advancements in accuracy but also receives validation in terms of practicality and feasibility.

참고문헌 (34)

  1. "The Fukushima Daiichi Accident, Non-serial Publications" (2015)[URL]
  2. Xingyu Wang, "Methods for Evaluating the Consequences of Nuclear Accidents and Their New Developments" (2003), Atomic Energy Press
  3. X. Li, "Source inversion of both long-and short-lived radionuclide releases from the fukushima daiichi nuclear accident using on-site gamma dose rates", J. Hazard Mater, 379, pp.120770~ (2019)
  4. Matthew A. Goodwin, "Radionuclide measurements of the international monitoring system", J. Environ. Radioact, 272, pp.107357~ (2024)
  5. O. Tichý, "Source term estimation of multi-specie atmospheric release of radiation from gamma dose rates", Q. J. R. Meteorol. Soc, 144, pp.2781~2797 (2018)
  6. H. -J. Jeong, "Determination of the source rate released into the environment from a nuclear power plant", Radiat. Protect. Dosim, 113, pp.308~313 (2005)
  7. X. Davoine, "Inverse modelling-based reconstruction of the chernobyl source term available for long-range transport", Atmos. Chem. Phys, 7, pp.1549~1564 (2007)
  8. S. -X. Huang, "Predicting and controlling nuclear accident hazards : issues and challenges", Aerosol Air Qual. Res, 16, pp.417~429 (2016)
  9. L. Delle Monache, "Bayesian inference and Markov chain Monte Carlo sampling to reconstruct a contaminant source on a continental scale", J. Appl. Meteorol. Climatol, 47, pp.2600~2613 (2008)
  10. O. Tichý, "Bayesian inverse modeling and source location of an unintended 131 i release in europe in the fall of 2011", Atmos. Chem. Phys, 17, pp.12677~12696 (2017)
  11. O. Saunier, "An inverse modeling method to assess the source term of the fukushima nuclear power plant accident using gamma dose rate observations", Atmos. Chem. Phys, 13, pp.11403~11421 (2013)
  12. I. Kovalets, "Advanced method for source term estimation and status of its integration in jrodos", Radioprotection, 51, pp.S121~S124 (2016)
  13. X. Zhang, "Modified ensemble kalman filter for nuclear accident atmospheric dispersion : prediction improved and source estimated", J. Hazard Mater, 280, pp.143~155 (2014)
  14. S. Sun, "A forward-backward coupled source term estimation for nuclear power plant accident : a case study of loss of coolant accident scenario", Ann. Nucl. Energy, 104, pp.64~74 (2017)
  15. Z. -P. Wang, "Source term estimation with unknown number of sources using improved cuckoo search algorithm", 2020 39th Chinese Control Conference (CCC), pp.1075~1080 (2020), IEEE
  16. D. Ma, "Parameter identification for continuous point emission source based on tikhonov regularization method coupled with particle swarm optimization algorithm", J. Hazard Mater, 325, pp.239~250 (2017)
  17. Y. Liu, "Combined grey wolf optimizer algorithm and corrected Gaussian diffusion model in source term estimation", Processes, 10, pp.1238~ (2022)
  18. Siho Jang, "Comparative study on gradient-free optimization methods for inverse source-term estimation of radioactive dispersion from nuclear accidents", J. Hazard Mater, 461, pp.132519~ (2024)
  19. Xinwen Dong, "Objective inversion of the continuous atmospheric 137Cs release following the Fukushima accident", J. Hazard Mater, 447, pp.130786~ (2023)
  20. Sheng Fang, "Oscillation-free source term inversion of atmospheric radionuclide releases with joint model bias corrections and non-smooth competing priors", J. Hazard Mater, 440, pp.129806~ (2022)
  21. S. Qiu, "Atmospheric dispersion prediction and source estimation of hazardous gas using artificial neural network, particle swarm optimization and expectation maximization", Atmos. Environ, 178, pp.158~163 (2018)
  22. Y. Ling, "Multi-nuclide source term estimation method for severe nuclear accidents from sequential gamma dose rate based on a recurrent neural network", J. Hazard Mater, 414, pp.125546~ (2021)
  23. Y. Ling, "Inversion method for multiple nuclide source terms in nuclear accidents based on deep learning fusion model", Atmosphere, 14, pp.148~ (2023)
  24. Yongsheng Ling, "Source term inversion of short-lived nuclides in complex nuclear accidents based on machine learning using off-site gamma dose rate", J. Hazard Mater, 465, pp.133388~ (2024)
  25. M. Chino, "Preliminary estimation of release amounts of 131i and 137cs acciden-tally discharged from the fukushima daiichi nuclear power plant into the atmosphere", J. Nucl. Sci. Technol, 48, pp.1129~1134 (2011)
  26. G. Steinhauser, "Comparison of the chernobyl and fukushima nuclear accidents : a review of the environmental impacts", Sci. Total Environ, 470, pp.800~817 (2014)
  27. 955: Generic Assessment Procedures for Determining Protective Actions during a Reactor Accident, "IAEA", INTERNATIONAL ATOMIC ENERGY AGENCY, ~ (1997)
  28. ICRP, "Nuclear Decay Data for Dosimetric Calculations (ICRP Publication 107)" (2008)
  29. L. Deng, "Snow ablation optimizer : a novel metaheuristic technique for numerical optimization and engineering design", Expert Syst. Appl, 225, pp.120069~ (2023)
  30. H. R. Tizhoosh, "Opposition-based learning: a new scheme for machine intelligence", International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA- IAWTIC’06), 1, pp.695~701 (2005), IEEE
  31. S. Mirjalili, "Sca : a sine cosine algorithm for solving optimization problems", Knowl. Base Syst, 96, pp.120~133 (2016)
  32. G. -B. Huang, "Extreme learning machine : theory and applications", Neurocomputing, 70, pp.489~501 (2006)
  33. D. U. Zhan-long, "Improved sensitivityanalysis based pruning extreme learning machine", Control Decis, 29, pp.1003~1008 (2014)
  34. R. Li, "l_{21}-norm based loss function and regularization extreme learning machine", IEEE Access, 7, pp.6575~6586 (2018)

관련 논문AI추천

Optimization of emission strategies for airborne radioactive material from nuclear facilities under normal operating conditionsChen Renjie, Chen Zhenping, Guo Qian, Liu Qiaoxu, Lu Zeyu, Zhang Zhitao, Zhao Zhiyuan한국원자력학회 · Nuclear Engineering and Technology2025 · 제57권 제6호방사성물질의 방사선원항 추정을 위한 인공지능 및 드론 적용에 관한 연구김송현, 김주연, 신성균, 이민재, 이윤종, 이장희, 장승수, 조우성, 한상수(사)한국방사선산업학회 · 방사선산업학회지2022 · 제16권 제4호Machine learning-based categorization of source terms for risk assessment of nuclear power plants김성엽, 조재현, 진경호한국원자력학회 · Nuclear Engineering and Technology2022 · 제54권 제9호Improvement of doses rate prediction using the Kalman Filter-based algorithm and effective decay constant correction정솔, 이철우, 정효준, 한문희한국원자력학회 · Nuclear Engineering and Technology2024 · 제56권 제7호A machine learning informed prediction of severe accident progressions in nuclear power plants김성중, 송진호한국원자력학회 · Nuclear Engineering and Technology2024 · 제56권 제6호Solving partial differential equation for atmospheric dispersion of radioactive material using physics-informed neural network김기범, 허균영한국원자력학회 · Nuclear Engineering and Technology2023 · 제55권 제6호

이 간행물의 다른 논문 (49건)

Generation of security system defense strategies based on evolutionary game theoryZhu Xiang, Wang Yongdong, Liu Chunqiang, Dai Mingguang, Du Qianwen, Zou Bowenpp. 3463-3471Extended cognitive reliability and error analysis method for advanced control rooms of nuclear power plantsLiu Xin, Yan Shengyuan, Zhang Xiaodanpp. 3472-3482Real-time measurements and modeling of sodium combustion aerosol dynamics in test chamber to improve the evaluation of SFR containment aerosol behaviourBalasubramanian Venkatraman, Kumar Amit, Pujala Usha, Venkatesan Subramanian, Pavan Narayanam Sujathapp. 3483-3490Hybrid vibro-acoustic model reduction for model updating in nuclear power plant pipeline with undetermined boundary conditions정변영, 오승인, 길진영, 김진균, 조용범, 신진원, 신현아pp. 3491-3500Titanium alloys: A closer-look at mechanical, gamma-ray, neutron, and transmission properties of different grade alloys through MCNPcode applicationKilic G., ALMisned Ghada, Guler Omer, Sen Baykal Duygu, Tekin H.O.pp. 3501-3511
원문 보기