The Use of ANFIS Networks to Identify Defects in Thermal and Mechanical Equipment of Thermal and Nuclear Power Plants
Abstract
The article discusses the methods of using artificial intelligence in the field of technical diagnostics of hidden defects in power equipment of thermal and nuclear power plants. Special attention is paid to the principles of building diagnostic systems based on neural-fuzzy networks such as ANFIS with the use of expert knowledge bases and production rules. The concept of determining pre-emergency states of nuclear power plant thermal and mechanical equipment by recognizing the parametric images of a process defect is implemented. Within the framework of the presented research, mathematical and thermohydraulic models of a tubular heat exchanger and a neural-fuzzy expert ANFIS system for determining heat exchanger defects based on pattern recognition have been developed. A version of using the developed diagnostic system model as part of a power plant automated control system as a process operator support system is proposed.
References
2. Оклей П.И. Отказы оборудования и аварии на теплоэлектростанциях России: причины, следствия и последствия // Микроэкономика. 2015. №. 6. С. 46—53.
3. Острейковский В.А., Швыряев Ю.В. Безопасность атомных станций. Вероятностный анализ. М.: Физматлит, 2008.
4. Chopra S. e. a. Taxonomy of Adaptive Neuro-fuzzy Inference System in Modern Engineering Sciences // Computational Intelligence and Neurosci. 2021. V. 2021(1). Pp. 1—14.
5. Ma J., Jiang J. Applications of Fault Detection and Diagnosis Methods in Nuclear Power Plants: a Review // Progress in Nuclear Energy. 2011. V. 53. Pp. 255—266.
6. Анохин Ф.Н., Калинушкин А.Е., Горбаев В.А., Сивоконь В.П. Состояние и перспективы систем поддержки операторов АЭС // Известия вузов. Серия «Ядерная энергетика». 2016. № 2. С. 5—16.
7. Hsieha M.-H. e. a. A Decision Support System for Identifying Abnormal Operating Procedures in a Nuclear Power Plant // Nuclear Eng. and Design. 2012. V. 249. Pp. 413—418.
8. Galbally J., Galbally D. A Pattern Recognition Approach Based on DTW for Automatic Transient Identification in Nuclear Power Plants // Annals of Nuclear Energy. 2015. V. 81. Pp. 287—300.
9. O’Connor P., Kleyner A. Practical Reliability Engineering. N.-Y.: John Wiley & Son, 2012.
10. Айвазян С.А. и др. Прикладная статистика: основы моделирования и первичная обработка данных. М.: Финансы и статистика, 1983.
11. Кривин В.В., Шпицер В.Я., Бекетов В.Г., Ишигов И.О., Толстов В.А. Концепция мониторинга оборудования АЭС на основе непараметрической статистики и обученной нейросети // Глобальная ядерная безопасность. 2020. № 1(34). C. 81—89.
12. Джексон П. Введение в экспертные системы. М.: Издат. дом Вильямс, 2001.
13. Jang J.-S.R. ANFIS: Adaptive-network-based Fuzzy Inference System // IEEE Trans. Systems, Man and Cybernetics. 1993. V. 23(3). Pp. 665—685.
14. Хабаров С.П., Шилкина М.Л. Основы моделирования технических систем. Среда Simintech. СПб.: Лань, 2019.
15. Золотоносов Я.Д., Багоутдинова А.Г., Золотоносов А.Я. Трубчатые теплообменники. Моделирование, расчет. СПб.: Лань, 2018.
16. Sada S.O., Ikpeseni S.C. Evaluation of ANN and ANFIS Modeling Ability in the Prediction of AISI 1050 Steel Machining Performance // Heliyon. 2021. V. 7(2). P. e06136.
17. Tightiz L. e. a. An Intelligent System Based on Optimized ANFIS and Association Rules for Power Transformer Fault Diagnosis // ISA Trans. 2020. V. 103. Pp. 63—74.
18. Mwaura A.M., Liu Y.K. Adaptive Neuro-fuzzy Inference System (ANFIS) Based Modelling of Incipient Steam Generator Tube Rupture Diagnosis // Annals of Nuclear Energy. 2021. V. 157. P. 108262.
---
Для цитирования: Герасимов Н.Г., Проталинский О.М. Идентификация дефектов тепломеханического оборудования тепловых и атомных электростанций на базе ANFIS-сетей // Вестник МЭИ. 2025. № 3. С. 126—134. DOI: 10.24160/1993-6982-2025-3-126-134
---
Конфликт интересов: авторы заявляют об отсутствии конфликта интересов
#
1. Belov V.V., Pergamenshchik B.K. Krupnye Avarii na TES i Ikh Vliyanie na Komponovochnye Resheniya Glavnykh Korpusov. Vestnik MGSU. 2013;4:61—69. (in Russian).
2. Okley P.I. Otkazy Oborudovaniya i Avarii na Teploelektrostantsiyakh Rossii: Prichiny, Sledstviya i Posledstviya. Mikroekonomika. 2015;6:46—53. (in Russian).
3. Ostreykovskiy V.A., Shvyryaev Yu.V. Bezopasnost' Atomnykh Stantsiy. Veroyatnostnyy Analiz. M.: Fizmatlit, 2008. (in Russian).
4. Chopra S. e. a. Taxonomy of Adaptive Neuro-fuzzy Inference System in Modern Engineering Sciences. Computational Intelligence and Neurosci. 2021;2021(1):1—14.
5. Ma J., Jiang J. Applications of Fault Detection and Diagnosis Methods in Nuclear Power Plants: a Review. Progress in Nuclear Energy. 2011;53:255—266.
6. Anokhin F.N., Kalinushkin A.E., Gorbaev V.A., Sivokon' V.P. Sostoyanie i Perspektivy Sistem Podderzhki Operatorov AES. Izvestiya Vuzov. Seriya «Yadernaya Energetika». 2016;2:5—16. (in Russian).
7. Hsieha M.-H. e. a. A Decision Support System for Identifying Abnormal Operating Procedures in a Nuclear Power Plant. Nuclear Eng. and Design. 2012;249:413—418.
8. Galbally J., Galbally D. A Pattern Recognition Approach Based on DTW for Automatic Transient Identification in Nuclear Power Plants. Annals of Nuclear Energy. 2015;81:287—300.
9. O’Connor P., Kleyner A. Practical Reliability Engineering. N.-Y.: John Wiley & Son, 2012.
10. Ayvazyan S.A. i dr. Prikladnaya Statistika: Osnovy Modelirovaniya i Pervichnaya Obrabotka Dannykh. M.: Finansy i Statistika, 1983. (in Russian).
11. Krivin V.V., Shpitser V.Ya., Beketov V.G., Ishigov I.O., Tolstov V.A. Kontseptsiya Monitoringa Oborudovaniya AES na Osnove Neparametricheskoy Statistiki i Obuchennoy Neyroseti. Global'naya Yadernaya Bezopasnost'. 2020;1(34):81—89. (in Russian).
12. Dzhekson P. Vvedenie v Ekspertnye Sistemy. M.: Izdat. Dom Vil'yams, 2001. (in Russian).
13. Jang J.-S.R. ANFIS: Adaptive-network-based Fuzzy Inference System. IEEE Trans. Systems, Man and Cybernetics. 1993;23(3):665—685.
14. Khabarov S.P., Shilkina M.L. Osnovy Modelirovaniya Tekhnicheskikh Sistem. Sreda Simintech. SPb.: Lan', 2019. (in Russian).
15. Zolotonosov Ya.D., Bagoutdinova A.G., Zolotonosov A.Ya. Trubchatye Teploobmenniki. Modelirovanie, Raschet. SPb.: Lan', 2018. (in Russian).
16. Sada S.O., Ikpeseni S.C. Evaluation of ANN and ANFIS Modeling Ability in the Prediction of AISI 1050 Steel Machining Performance. Heliyon. 2021;7(2):e06136.
17. Tightiz L. e. a. An Intelligent System Based on Optimized ANFIS and Association Rules for Power Transformer Fault Diagnosis. ISA Trans. 2020;103:63—74.
18. Mwaura A.M., Liu Y.K. Adaptive Neuro-fuzzy Inference System (ANFIS) Based Modelling of Incipient Steam Generator Tube Rupture Diagnosis. Annals of Nuclear Energy. 2021;157:108262
---
For citation: Gerasimov N.G., Protalinskiy O.M. The Use of ANFIS Networks to Identify Defects in Thermal and Mechanical Equipment of Thermal and Nuclear Power Plants. Bulletin of MPEI. 2025;3:126—134. (in Russian). DOI: 10.24160/1993-6982-2025-3-126-134
---
Conflict of interests: the authors declare no conflict of interest