Machine learning‐based evaluation technology of 3D spatial distribution of residual radioactivity in large‐scale radioactive structures
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
During the decommissioning of nuclear and particle accelerator facilities, a considerable amount of large-scale radioactive waste may be generated. Accurately defining the activation level of the waste is crucial for proper disposal. However, directly measuring the internal radioactivity distribution poses challenges. This study introduced a novel technology employing machine learning to assess the internal radioactivity distribution based on external measurements. Random radioactivity distribution within a structure were established, and the photon spectrum measured by detectors from outside the structure was simulated using the FLUKA Monte-Carlo code. Through training with spectrum data corresponding to various radioactivity distributions, an evaluation model for radioactivity using simulated data was developed by above Monte-Carlo simulation. Convolutional Neural Network and Transformer methods were utilized to establish the evaluation model. The machine learning construction involves 5425 simulation datasets, and 603 datasets, which were used to obtain the evaluated results. Preprocessing was applied to the datasets, but the evaluation model using raw spectrum data showed the best evaluation results. The estimation of the intensity and shape of the radioactivity distribution inside the structure was achieved with a relative error of 10%. Additionally, the evaluation based on the constructed model takes only a few seconds to complete the process
Abstract
During the decommissioning of nuclear and particle accelerator facilities, a considerable amount of large-scale radioactive waste may be generated. Accurately defining the activation level of the waste is crucial for proper disposal. However, directly measuring the internal radioactivity distribution poses challenges. This study introduced a novel technology employing machine learning to assess the internal radioactivity distribution based on external measurements. Random radioactivity distribution within a structure were established, and the photon spectrum measured by detectors from outside the structure was simulated using the FLUKA Monte-Carlo code. Through training with spectrum data corresponding to various radioactivity distributions, an evaluation model for radioactivity using simulated data was developed by above Monte-Carlo simulation. Convolutional Neural Network and Transformer methods were utilized to establish the evaluation model. The machine learning construction involves 5425 simulation datasets, and 603 datasets, which were used to obtain the evaluated results. Preprocessing was applied to the datasets, but the evaluation model using raw spectrum data showed the best evaluation results. The estimation of the intensity and shape of the radioactivity distribution inside the structure was achieved with a relative error of 10%. Additionally, the evaluation based on the constructed model takes only a few seconds to complete the process
참고문헌 (51)
- T. S. LaGuardia, "Nuclear Decommissioning", pp.49~86 (2012), Woodhead Publishing
- H. S. Park, "A study of the decommissioning procedure of an activated structure through an evaluation of the decommissioning cost for a research reactor", Prog. Nucl. Energy, 91, pp.399~410 (2016)
- D. Deng, "Radioactive waste : a review", Water Environ. Res, 92(10), pp.1818~1825 (2020)
- C. Bayliss, "Nuclear Decommissioning, Waste Management, and Environmental Site Remediation" (2003), Elsevier
- Maine Yankee Decommissioning Experience Report, 1011734, "C. Wood", Electric Power Research Institute (EPRI), ~ (2005)
- Connecticut Yankee Decommissioning Experience Report: Detailed Experiences 1996–2006, "S. Bushart", EPRI, ~ (2006)
- T. Satoh, "Strategy Selection for the Decommissioning of Nuclear Facilities", pp.115~ (2004)
- A. Hermanne, "Evaluation of the Radiological and Economic Consequences of Decommissioning Particle Accelerators", ~ (1999)
- F. Aspe, "Classification and categorization of the constrained environments in nuclear", radiological installations under decommissioning and dismantling processes, 2020, pp.124, 103347~
- P. E. Lainetti, "Cutting techniques for facilities dismantling in decommissioning projects", J. Energy Power Eng, 10, pp.513~521 (2016)
- N. Chae, "Aerodynamic diameter and radioactivity distributions of radioactive aerosols from activated metals cutting for nuclear power plant decommissioning", J. Hazard Mater, 369, pp.727~745 (2019)
- S. Kawasaki, "Radioactivity measurement of drum package waste by a computed-tomography technique", International Journal of Radiation Applications and Instrumentation. Part A, Appl. Radiat. Isot, 41(10–11), pp.983~987 (1990)
- B. Y. Min, "Separation of radionuclide from dismantled concrete waste", J. Korean Radioactive Waste Soc, 7(2), pp.79~86 (2009)
- M. Cometto, "Activation analysis of concrete and graphite in the experimental reactor RUS", Radiat. Protect. Dosim, 115(1–4), pp.104~109 (2005)
- M. Bakhtiari, "Study on concrete activation reduction in a PET cyclotron vault", J. Radiat. Protect. Res, 45(3), pp.130~141 (2020)
- G. Y. Cha, "The effects of impurity composition and concentration in reactor structure material on neutron activation inventory in pressurized water reactor", J. Nucl. Fuel Cycle Waste Technol, 14(2), pp.91~100 (2016)
- B. Lee, "Radiological analysis for radioactivity depth distribution in activated concrete using gamma-ray spectrometry", Appl. Radiat. Isot, 169, pp.109558~ (2021)
- X. Hou, "Radiochemical analysis of radionuclides difficult to measure for waste characterization in decommissioning of nuclear facilities", J. Radioanal. Nucl. Chem, 273(1), pp.43~48 (2007)
- T. Sukegawa, "Evaluation of methodology on radioactive inventory estimation in the Japan power demonstration reactor decommissioning program", J. Nucl. Sci. Technol, 37(sup1), pp.367~371 (2000)
- D. Wang, "Machine learningbased multifunctional optical spectrum analysis technique", IEEE Access, 7, pp.19726~19737 (2019)
- S. Wang, "Machine learning and radiology", Med. Image Anal, 16(5), pp.933~951 (2012)
- A. G´eron, "Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow" (2022), O’Reilly Media, Inc
- L. Moroney, "Ai and Machine Learning for Coders" (2020), O’Reilly Media
- Y. LeCun, "Backpropagation applied to handwritten zip code recognition", Neural Comput, 1(4), pp.541~551 (1989)
- I. Goodfellow, "Deep Learning" (2016), MIT press
- J. Gu, "Recent advances in convolutional neural networks", Pattern Recogn, 77, pp.354~377 (2018)
- T. Guo, "Simple convolutional neural network on image classification", 2017 IEEE 2nd International Conference on Big Data Analysis (ICBDA), pp.721~724 (2017), IEEE
- S. M. Anwar, "Medical image analysis using convolutional neural networks : a review", J. Med. Syst, 42, pp.1~13 (2018)
- G. Battistoni, "Overview of the FLUKA code", Ann. Nucl. Energy, 82, pp.10~18 (2015)
- I. Muraina, "Ideal dataset splitting ratios in machine learning algorithms : general concerns for data scientists and data analysts", 7th International Mardin Artuklu Scientific Research Conference (2022)
- D. Steinkraus, "Using GPUs for machine learning algorithms", Eighth International Conference on Document Analysis and Recognition (ICDAR’05), pp.1115~1120 (2005), IEEE
- P. Li, "Heterospark: A Heterogeneous Cpu", gpu Spark Platform for Machine Learning Algorithms, 2015 (2015), 347~348[DOI]
- A. Paszke, "Pytorch: an imperative style, high-performance deep learning library", Adv. Neural Inf. Process. Syst, 32 (2019)
- Q. Wang, "Evaluation of the radioactivity in concrete from accelerator facilities", J. Radioanal. Nucl. Chem, 273(1), pp.55~58 (2007)
- K. Masumoto, "Evaluation of radioactivity induced in the accelerator building and its application to decontamination work", J. Radioanal. Nucl. Chem, 255, pp.465~469 (2003)
- J. Tabak, "Probability and Statistics: the Science of Uncertainty" (2014), Infobase Publishing
- A. Taheri, "Determination of Gaussian energy broadening parameters for organic scintillators", J. Instrum, 11(5), pp.P05020~ (2016)
- E. Eftekhari Zadeh, "Gaussian energy broadening function of an HPGe detector in the range of 40 keV to 1. 46 MeV", J. Exp. Phys, 2014 (2014)
- X. Zhang, "Understanding the learning mechanism of convolutional neural networks in spectral analysis", Anal. Chim. Acta, 1119, pp.41~51 (2020)
- An Overview of Convolutional Neural Network Architectures for Deep Learning, "J. Murphy", Microway Inc, 1~22 (2016)
- S. Kiranyaz, "1D convolutional neural networks and applications : a survey", Mech. Syst. Signal Process, 151, pp.107398~ (2021)
- C. Cheng, "Fast 2D convolution algorithms for convolutional neural networks", IEEE Trans. Circuits Syst. I : Regular Pap, 67(5), pp.1678~1691 (2020)
- K. He, "Deep residual learning for image recognition", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.770~778 (2016)
- J. Long, "Fully convolutional networks for semantic segmentation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.3431~3440 (2015)
- A. Odena, "Deconvolution and checkerboard artifacts", Distill, 1(10), pp.e3~ (2016)
- Y. Ding, "A novel time–frequency Transformer based on self–attention mechanism and its application in fault diagnosis of rolling bearings", Mech. Syst. Signal Process, 168, pp.108616~ (2022)
- F. Amer, "Transformer machine learning language model for auto-alignment of long-term and short-term plans in construction", Autom. ConStruct, 132, pp.103929~ (2021)
- A. Vaswani, "Attention is all you need", Adv. Neural Inf. Process. Syst, 30 (2017)