Preview

Nuclear Safety

Advanced search

Application of hierarchical agglomerative clustering to create a basic classes library of a VVER 1000/1200 reactor facility

https://doi.org/10.26583/gns-2023-01-05

Abstract

In reactor plants with a water-water power reactor (VVER), free, weakly fixed and foreign objects may appear in the main circulation circuit, posing a threat to the integrity of the equipment and the safety of the reactor plant. For the purpose of early detection of these objects, the NPP is equipped with a system for detecting loose/weakly fixed objects (SOSP).

In addition to the detection of loose/weakly fixed objects, the functions of the SOSP include the classification of registered events.

The possibility of applying the classification algorithm is based on the fact that the signals from the operation of standard equipment are highly repeatable, even in the presence of noise, while a free object is characterized by a large stochastic component and its own deterministic class cannot be formed for it.

Classification reduces the number of false alarms, allowing you to select signals from regular operations, while signals from one process must be assigned to one class.

The idea of ​​the article is to "train" SOSP on a certain archive of data characterizing the normal functioning of the reactor plant, create a library of "base" classes and set the boundaries of each class so that, on the one hand, take into account the possible variability of signal parameters due to noise.

Having defined the base classes, we can state that if a newly received signal falls into one of the classes, then it reflects the regular operation of the RI, while signals that do not fall into any of the classes may be the result of the appearance of a free/weakly fixed object.

The article analyzes a lot of events accumulated in the archive of one of the existing SOSP.

Their clustering was carried out, as a result of which the classes of events corresponding to regular technological operations were identified.

For each class, the center of the class and the allowable limits of deviations from the center are calculated.

All class centers obtained are benchmarks against which the SOSP either classifies a newly detected event in real time or characterizes it as "unclassified".

About the Authors

Gennadiy V. Arkadov
Joint Stock Company "Scientific and Technical Center "Diaprom"
Russian Federation


Irina V. Trykova
Joint Stock Company "Scientific and Technical Center "Diaprom"
Russian Federation


Denis V. Zvyagincev
Joint Stock Company "Scientific and Technical Center "Diaprom"
Russian Federation


Konstantin I. Kotsoev
Joint Stock Company "Scientific and Technical Center "Diaprom", Bauman Moscow State Technical University
Russian Federation


References

1. Центр диагностики «Диапром». Сопровождение эксплуатации. – URL: http://www.diaprom.com/about/operation (дата обращения: 21.11.2022).

2. Центр диагностики «Диапром». Система обнаружения свободных предметов в главном циркуляционном контуре ВВЭР-1000 (СОСП). – URL: http://www.diaprom.com/projects/?p=2 (дата обращения: 21.11.2022).

3. Аркадов, Г.В. Системы диагностирования ВВЭР / Г.В. Аркадов, В.И. Павелко, Б.М. Финкель. – Москва : Энергоатомиздат, 2010. – 391 с.

4. Воронов, А.В. Опыт использования систем обнаружения свободных и слабозакрепленных предметов в контуре циркуляции теплоносителя реакторных установок Нововоронежской АЭС / А.В. Воронов, М.Т. Слепов // Известия вузов. Ядерная энергетика. – 2022. – № 2. – С. 15-26.

5. Максимов, И.В. Метод локализации удара для системы обнаружения свободных предметов в контуре циркуляции теплоносителя реакторных установок с ВВЭР / И.В. Максимов, В.В. Перевезенцев // Известия вузов. Ядерная энергетика. – 2019. – № 4. – С. 28-38.

6. Центр диагностики «Диапром». «Молоток импульсный ИМ-1». – URL: http://www.diaprom.com/products/?p=14 (дата обращения: 21.11.2022).

7. Чабан, Л.Н. Теория и алгоритмы распознавания образов / Л.Н. Чабан. – Москва : Московский государственный университет геодезии и картографии, 2004. – 70 с.

8. Аркадов, Г.В. Кластеризация акустических событий в главном циркуляционном контуре реакторной установки с ВВЭР-1000/1200, обусловленных штатными технологическими операциями / Г. В. Аркадов, И. В. Трыкова, К. И. Коцоев // Глобальная ядерная безопасность. – 2022. – № 3(44). – С. 43-55.

9. Jain, A.K. Algorithms for Clastering Data / A.K. Jain, R.C. Dubes– Englewood Cliffs (NJ): Prentice-Hall, 1988. – 304 р.

10. Implementing Agglomerative Clustering using Sklearn – URL: https://www.geeksforgeeks.org/implementing-agglomerative-clustering-using-sklearn/ (дата обращения: 21.11.2022).

11. Жамбю, М. Иерархический кластер-анализ и соответствия / М. Жамбю – Москва : Финансы и статистика, 1988. – 345 с.

12. Древовидная схема. – URL: https://ru.wikipedia.org/wiki/Древовидная_схема (дата обращения: 21.11.2022).

13. Sneath, P.H.A. Numerical taxonomy: The principles and practices of numerical classification / P.H.A. Sneath, R.R. Sokal – San-Francisco: Freeman, 1973. – 573 p. (in English).

14. Ward J.H. Hierarchical grouping to optimize an objective function / J.H. Ward // J. of the American Statistical Association. – 1963. V.58. Р. 236-244.


Review

For citations:


Arkadov G.V., Trykova I.V., Zvyagincev D.V., Kotsoev K.I. Application of hierarchical agglomerative clustering to create a basic classes library of a VVER 1000/1200 reactor facility. Nuclear Safety. 2023;(1):54-66. (In Russ.) https://doi.org/10.26583/gns-2023-01-05

Views: 232


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.


ISSN 2305-414X (Print)
ISSN 2499-9733 (Online)