Using a Neural Network Model to Analyze Uncertainties in Estimating the Stressed State of Metal in the Main Coolant Pipeline of an NPP with VVER Reactors under Seismic Loads
DOI:
https://doi.org/10.24160/1993-6982-2025-2-119-127Keywords:
uncertainty analysis, neural network model, main coolant pipeline, computer codes, strength, seismic loadsAbstract
The problem of using the uncertainty analysis methodology when performing strength calculations is addressed. This issue is relevant for substantiating reliable operation of nuclear power plants with pressurized water reactors. As a consequence of measurement errors and the empirical nature of the models, the results obtained by using computer codes contain uncertainty. The use of these codes requires significant time and large hardware resources of computation stations. The use of neural network (NN) models can reduce significantly the computation time while maintaining the correctness of the results. A mode of seismic impact on a pipeline with a postulated defect is analyzed. Seismic load calculations were carried out in compliance with the requirements of the regulatory documentation (STO, NP) adopted by the State Atomic Energy Corporation Rosatom. Based on the calculation results, a stress variation time history was obtained for the entire period of seismic impact. Based on the results obtained, a neural network model was developed using special software, followed by testing it. The computation results have shown that the absolute error does not exceed 1 MPa, and the relative error is within 1%. The obtained results have demonstrated the relevance of using NN models not only for seismic load, but also for other impacts on the pipeline within the probabilistic safety assessment framework.
References
2. РБ-166—20. Рекомендации по оценке погрешностей и неопределенностей результатов расчетных анализов безопасности атомных станций.
3. Воробьев Ю.Б., Кузнецов В.Д., Мансури М. Оценка влияния неопределённых факторов при анализе аварийных процессов на АЭС с ВВЭР // Теплоэнергетика. 2006. № 9. С. 16—21.
4. Мансури М. Анализ неопределенностей параметров при моделировании динамических процессов в контурах АЭС с ВВЭР: дис. … канд. техн. наук. М.: НИУ «МЭИ», 2005.
5. Моисеенко Е.В., Мосунова Н.А. Методика оценки неопределённостей результатов расчёта для задач обоснования безопасности объектов использования атомной энергии // Вопросы радиационной безопасности. 2018. № 2. С. 24—34.
6. NUREG/CR-1397. Risk Methodology for Geologic Disposal of Radioactive Waste: Small Sample Sensitivity Analysis Technologies for Computer Models, with an Application to Risk Assessment. Sandia National Laboratories, 1980.
7. Grant F. e. a. Seismic Fragility and Seismic Margin Guidance for Seismic Probabilistic Risk Assessments. Washington: Electric Power Research Institute, 2018.
8. Пояснительная записка 320.04.00.00.000 ПЗ. Трубопровод главный циркуляционный. Подольск: ОКБ «Гидропресс», 1979.
9. Mathcad 15.0 PTC [Электрон. ресурс] https://community.ptc.com/sejnu66972/attachments/sejnu66972/PTCMathcad/86291/2/RTF_MC15_F000.pdf (дата обращения 17.09.2024).
10. Хмельницкая АЭС. База данных по ЯППУ 43-923.203.007.БД.02. Подольск: ОКБ «Гидропресс».
11. Шарый Н.В. и др. Прочность основного оборудования и трубопроводов реакторных установок ВВЭР. М.: ИздАТ, 2004.
12. MATLAB Release Notes. Natick: Mathworks Inc., 2020.
---
Для цитирования: Аванов А.В. Использование нейросетевой модели для анализа неопределенностей к оценке напряженного состояния металла главного циркуляционного трубопровода АЭС с ВВЭР при сейсмических нагрузках // Вестник МЭИ. 2025. № 2. С. 119—127. DOI: 10.24160/1993-6982-2025-2-119-127
#
1. Chigarev A.V., Kravchuk A.S., Smalyuk A.F. ANSYS dlya Inzhenerov. M.: Mashinostroenie-1, 2004. (in Russian).
2. RB-166—20. Rekomendatsii po Otsenke Pogreshnostey i Neopredelennostey Rezul'tatov Raschetnykh Analizov Bezopasnosti Atomnykh Stantsiy. (in Russian).
3. Vorob'ev Yu.B., Kuznetsov V.D., Mansuri M. Otsenka Vliyaniya Neopredelennykh Faktorov pri Analize Avariynykh Protsessov na AES s VVER. Teploenergetika. 2006;9:16—21. (in Russian).
4. Mansuri M. Analiz Neopredelennostey Parametrov pri Modelirovanii Dinamicheskikh Protsessov v Konturakh AES s VVER: Dis. … Kand. Tekhn. Nauk. M.: NIU «MEI», 2005. (in Russian).
5. Moiseenko E.V., Mosunova N.A. Metodika Otsenki Neopredelennostey Rezul'tatov Rascheta dlya Zadach Obosnovaniya Bezopasnosti Ob'ektov Ispol'zovaniya Atomnoy Energii. Voprosy Radiatsionnoy Bezopasnosti. 2018;2:24—34. (in Russian).
6. NUREG/CR-1397. Risk Methodology for Geologic Disposal of Radioactive Waste: Small Sample Sensitivity Analysis Technologies for Computer Models, with an Application to Risk Assessment. Sandia National Laboratories, 1980.
7. Grant F. e. a. Seismic Fragility and Seismic Margin Guidance for Seismic Probabilistic Risk Assessments. Washington: Electric Power Research Institute, 2018.
8. Poyasnitel'naya Zapiska 320.04.00.00.000 PZ. Truboprovod Glavnyy Tsirkulyatsionnyy. Podol'sk: OKB «Gidropress», 1979. (in Russian).
9. Mathcad 15.0 PTC [Elektron. Resurs] https://community.ptc.com/sejnu66972/attachments/sejnu66972/PTCMathcad/86291/2/RTF_MC15_F000.pdf (Data Obrashcheniya 17.09.2024).
10. Khmel'nitskaya AES. Baza Dannykh po YAPPU 43-923.203.007.BD.02. Podol'sk: OKB «Gidropress».(in Russian).
11. Sharyy N.V. i dr. Prochnost' Osnovnogo Oborudovaniya i Truboprovodov Reaktornykh Ustanovok VVER. M.: IzdAT, 2004. (in Russian).
12. MATLAB Release Notes. Natick: Mathworks Inc., 2020
---
For citation: Avanov A.V. Using a Neural Network Model to Analyze Uncertainties in Estimating the Stressed State of Metal in the Main Coolant Pipeline of an NPP with VVER Reactors under Seismic Loads. Bulletin of MPEI. 2025;2:119—127. (in Russian). DOI: 10.24160/1993-6982-2025-2-119-127
