Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

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

  • Dong Xiao (College of Information Science and Engineering, Northeastern University) ;
  • Zixuan Zhang (College of Information Science and Engineering, Northeastern University) ;
  • Jianxin Li (College of Information Science and Engineering, Northeastern University) ;
  • Yanhua Fu (JangHo Architecture College, Northeastern University)
  • Received : 2023.12.18
  • Accepted : 2024.04.25
  • Published : 2024.09.25
Download PDF
⟨ Previous Next ⟩

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.

Keywords

Acknowledgement

This work was supported by the National Key R&D Program of China (Grant 2022YFB2703304), the Liaoning Revitalization Talents Program (Grant XLYC2008020), the National Natural Science Foundation of China (Grant 52074064), the Natural Science Foundation of Science and Technology Department of Liaoning Province (Grant 2021-BS-054), and the Fundamental Research Funds for the Central Universities of China (Grant N2404013, N2404015).

References

  1. IAEA, The Fukushima Daiichi Accident, Non-serial Publications, INTERNATIONAL ATOMIC ENERGY AGENCY, Vienna, 2015. URL: https://www.iaea.org/publications/10962/the-fukushima-daiichi-accident.
  2. Xingyu Wang, Methods for Evaluating the Consequences of Nuclear Accidents and Their New Developments, Atomic Energy Press, China, 2003.
  3. X. Li, S. Sun, X. Hu, H. Huang, H. Li, Y. Morino, S. Wang, X. Yang, J. Shi, S. Fang, 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 (2019) 120770.
  4. Matthew A. Goodwin, Ashley V. Davies, Richard Britton, Harry S. Miley, Paul W. Eslinger, Ian Hoffman, Kurt Ungar, Pawel Mekarski, Adrian Botti, Radionuclide measurements of the international monitoring system, J. Environ. Radioact. 272 (2024) 107357.
  5. O. Tichy, V. Smidl, R. Hofman, Nikolaos Evangeliou, Source term estimation of multi-specie atmospheric release of radiation from gamma dose rates, Q. J. R. Meteorol. Soc. 144 (2018) 2781-2797.
  6. H.-J. Jeong, E.-H. Kim, K.-S. Suh, W.-T. Hwang, M.-H. Han, H.-K. Lee, Determination of the source rate released into the environment from a nuclear power plant, Radiat. Protect. Dosim. 113 (2005) 308-313.
  7. X. Davoine, M. Bocquet, Inverse modelling-based reconstruction of the chernobyl source term available for long-range transport, Atmos. Chem. Phys. 7 (2007) 1549-1564.
  8. S.-X. Huang, J.-P. Zhang, W.-D. Yang, Z.-F. Wang, F. Hu, F. Liu, L. Sheng, Q.-C. Zeng, et al., Predicting and controlling nuclear accident hazards: issues and challenges, Aerosol Air Qual. Res. 16 (2016) 417-429.
  9. L. Delle Monache, J.K. Lundquist, B. Kosovic, G. Johannesson, K.M. Dyer, R. D. Aines, F.K. Chow, R.D. Belles, W.G. Hanley, S.C. Larsen, et al., Bayesian inference and Markov chain Monte Carlo sampling to reconstruct a contaminant source on a continental scale, J. Appl. Meteorol. Climatol. 47 (2008) 2600-2613.
  10. O. Tichy, V. Smidl, R. Hofman, K. Sindelarova, M. Hyza, A. Stohl, Bayesian inverse modeling and source location of an unintended 131 i release in europe in the fall of 2011, Atmos. Chem. Phys. 17 (2017) 12677-12696.
  11. O. Saunier, A. Mathieu, D. Didier, M. Tombette, D. Qu'elo, V. Winiarek, M. Bocquet, 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 (2013) 11403-11421.
  12. I. Kovalets, S. Andronopoulos, R. Hofman, P. Seibert, I. Ievdin, Advanced method for source term estimation and status of its integration in jrodos, Radioprotection 51 (2016) S121-S124.
  13. X. Zhang, G. Su, H. Yuan, J. Chen, Q. Huang, Modified ensemble kalman filter for nuclear accident atmospheric dispersion: prediction improved and source estimated, J. Hazard Mater. 280 (2014) 143-155.
  14. S. Sun, H. Li, S. Fang, 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 (2017) 64-74.
  15. Z.-P. Wang, H.-N. Wu, Source term estimation with unknown number of sources using improved cuckoo search algorithm, in: 2020 39th Chinese Control Conference (CCC), IEEE, 2020, pp. 1075-1080.
  16. D. Ma, W. Tan, Z. Zhang, J. Hu, Parameter identification for continuous point emission source based on tikhonov regularization method coupled with particle swarm optimization algorithm, J. Hazard Mater. 325 (2017) 239-250.
  17. Y. Liu, Y. Jiang, X. Zhang, Y. Pan, Y. Qi, Combined grey wolf optimizer algorithm and corrected Gaussian diffusion model in source term estimation, Processes 10 (2022) 1238.
  18. Siho Jang, Juryong Park, Hyun-Ha Lee, Chun-Sil Jin, Eung Soo Kim, Comparative study on gradient-free optimization methods for inverse source-term estimation of radioactive dispersion from nuclear accidents, J. Hazard Mater. 461 (2024) 132519.
  19. Xinwen Dong, Sheng Fang, Shuhan Zhuang, Yuhan Xu, Yungang Zhao, Li Sheng, Objective inversion of the continuous atmospheric 137Cs release following the Fukushima accident, J. Hazard Mater. 447 (2023) 130786.
  20. Sheng Fang, Xinwen Dong, Shuhan Zhuang, Zhijie Tian, Tianfeng Chai, Yuhan Xu, Yungang Zhao, Li Sheng, Xuan Ye, Wei Xiong, Oscillation-free source term inversion of atmospheric radionuclide releases with joint model bias corrections and non-smooth competing priors, J. Hazard Mater. 440 (2022) 129806.
  21. S. Qiu, B. Chen, R. Wang, Z. Zhu, Y. Wang, X. Qiu, Atmospheric dispersion prediction and source estimation of hazardous gas using artificial neural network, particle swarm optimization and expectation maximization, Atmos. Environ. 178 (2018) 158-163.
  22. Y. Ling, Q. Yue, T. Huang, Q. Shan, D. Hei, X. Zhang, W. Jia, 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 (2021) 125546.
  23. Y. Ling, C. Liu, Q. Shan, D. Hei, X. Zhang, C. Shi, W. Jia, J. Wang, Inversion method for multiple nuclide source terms in nuclear accidents based on deep learning fusion model, Atmosphere 14 (2023) 148.
  24. Yongsheng Ling, Chengfeng Liu, Qing Shan, Daqian Hei, Xiaojun Zhang, Chao Shi, Wenbao Jia, Yue Qi, Jing Wang, 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 (2024) 133388.
  25. M. Chino, H. Nakayama, H. Nagai, H. Terada, G. Katata, H. Yamazawa, 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 (2011) 1129-1134.
  26. G. Steinhauser, A. Brandl, T.E. Johnson, Comparison of the chernobyl and fukushima nuclear accidents: a review of the environmental impacts, Sci. Total Environ. 470 (2014) 800-817.
  27. IAEA, 955: Generic Assessment Procedures for Determining Protective Actions during a Reactor Accident, INTERNATIONAL ATOMIC ENERGY AGENCY, Vienna, 1997.
  28. ICRP. Nuclear Decay Data for Dosimetric Calculations (ICRP Publication 107), Ann. ICRP 38 (3) (2008).
  29. L. Deng, S. Liu, Snow ablation optimizer: a novel metaheuristic technique for numerical optimization and engineering design, Expert Syst. Appl. 225 (2023) 120069.
  30. H.R. Tizhoosh, Opposition-based learning: a new scheme for machine intelligence, in: International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA- IAWTIC'06), vol. 1, IEEE, 2005, pp. 695-701.
  31. S. Mirjalili, Sca: a sine cosine algorithm for solving optimization problems, Knowl. Base Syst. 96 (2016) 120-133.
  32. G.-B. Huang, Q.-Y. Zhu, C.-K. Siew, Extreme learning machine: theory and applications, Neurocomputing 70 (2006) 489-501.
  33. D.U. Zhan-long, L.I. Xiao-min, X.I. Lei-ping, M.A.O. Qiong, Improved sensitivity-analysis based pruning extreme learning machine, Control Decis. 29 (2014) 1003-1008.
  34. R. Li, X. Wang, L. Lei, Y. Song, l_{21}-norm based loss function and regularization extreme learning machine, IEEE Access 7 (2018) 6575-6586.