DEVELOPMENT OF AN INTEGRATED APPROACH TO ELECTRICAL EQUIPMENT FAULT DETECTION USING CONVOLUTIONAL NEURAL NETWORKS
Abstract
Electrical equipment (EE) is a key part of industrial electrical systems where unexpected mechanical failures in operation can cause serious consequences (disruption of the technological process, reduction in the quality and quantity of manufactured products and emergencies). For timely detection of such faults, as well as to ensure normal operation of the systems, it is required to conduct regular assessment of EE technical state using modern computer technologies under conditions of incomplete and fuzzy information. To solve this problem, we propose an approach using quantization and convolutional neural networks (CNNs) which differs from existing approaches by complex processing of thermograms obtained with a thermal imaging device; images with black-and-white and color graphs obtained from instruments or built based on statistical data. This approach provides an opportunity to improve the accuracy of classification of various EE malfunctions, reduce unscheduled equipment failures due to prompt decisionmaking regarding the EE technical state under conditions of incomplete and fuzzy information. The review of studies in this subject area by both Russian and foreign scientists reflects a number of successful experiments on the use of CNNs. The CNN developed to classify faults outputs a class number to which the current state of the equipment relates (class 1 – serviceable EE; class 2 – serviceable EE with small deviations). This paper considers a generalized scheme and algorithm of a complex approach to EE fault detection with their detailed description. The study results were obtained when diagnosing the asynchronous motor АИР63А4У1 and confirm the validity and objectivity of using the proposed approach
References
1. Cheng Li, Zixuan Yu, Mingsong Zhuo Research on fault detection method of infrared thermal imaging
for power equipment based on deep learning // IOP Conference Series: Earth and Environmental Science.
– 2021. – Vol. 714. – P. 1-9. – DOI: 10.1088/1755-1315/714/4/0420 45.
2. Wang W., He Y., Han X., Li Y. Functional failure diagnosis method of manufacturing system based on
dynamic Bayesian network // International Conference on Sensing, Diagnostics, Prognostics, and Control.
– 2020. – P. 93-97. – DOI: 10.1109/SDPC49476.2020. 9353184.
3. Чернова А.Д., Косенко А.А. Автоматизация распознавания дефектов оборудования электриче-
ских сетей с помощью искусственных нейронных сетей // Вестник ЮУрГУ. Серия «Энергети-
ка». – 2023. – Т. 23, № 3. – С. 62-71. – DOI: 10.14529/power230306.
4. Колоденкова А.Е., Верещагина С.С., Фаворская Е.А., Осипова Е.А. Разработка метода оценки
технического состояния электрооборудования с использованием взвешенных нечётких правил
// Онтология проектирования. – 2024. – Т. 14, № 1 (51). – С. 134-144. DOI: 10.18287/2223-9537-
2024-14-1-134-144.
5. Сазыкин В.Г., Кудряков А.Г. Проблемы изношенного электрооборудования в современной
энергетике // Международный научно-исследовательский журнал. – 2015. – № 7 (38). – С. 89-91.
6. Грабчак Е.П., Грабчак Э.П., Логинов Е.Л., Романова Ю.А. Проблемы замены изношенного обору-
дования в электроэнергетике России: приоритеты модернизации в контексте обеспечения надеж-
ности и безопасности // Проблемы безопасности и чрезвычайных ситуаций. – 2019. – С. 38-43.
– DOI: 10.36535/0869-4176-2019-05-5.
7. Vakhnina V.V., Markov E.V. Developing fuzzy model using the key gas method to determine the defects
occurring in oil power transformers // International Conference on Industrial Engineering, Applications
and Manufacturing. – 2024. – P. 451-455. – DOI: 10.1109/ICIEAM60818.2024.10553816.
8. Jan B., Parveen S., Khan S.A. ANN based multi-stage binary classification technique for incipient
fault diagnosis of oil immersed transformer // International Conference on Industry 4.0 Technology
(I4Tech). – 2022. – P. 1-6. – DOI: 10.1109/I4Tech55392.2022. 9952593.
9. Yatsugi K., Kone S.E.M.P., Mizuno Y. Faulty class diagnosis of three phase induction motor bearing using stator current spectral features and machine learning algorithms // 9th International Conference on Condition Monitoring and Diagnosis. – 2022. – P. 112-117. – DOI: 10.23919/CMD54214.2022. 9991672.
10. Jiménez-Guarneros M., Morales-Perez C., Rangel-Magdaleno J.d.J. Diagnostic of combined mechanical
and electrical faults in ASD-powered induction motor using MODWT and a lightweight 1-D CNN
// IEEE Transactions on Industrial Informatics. – 2022. – Vol. 18, No. 7. – P. 4688-4697. – DOI:
10.1109/TII.2021. 3120975.
11. Gaber I.M., Shalash O., Hamad M.S. Optimized inter-turn short circuit fault diagnosis for induction
motors using neural networks with LeLeRU // IEEE Conference on Power Electronics and Renewable
Energy. – 2023. – P. 1-5. – DOI: 10.1109/CPERE56564. 2023.10119618.
12. Goh Y.-J. Fault Diagnostics of 3-phase Induction Motor using CNN with Park’s Vector Approach
Input Data Configuration // 10th International Conference on Mechatronics and Robotics Engineering.
– 2024. – P. 234-239. – DOI: 10.1109/ICMRE60776.2024. 10532185.
13. Saxena Lalit Niblack’s binarization method and its modifications to real-time applications: a review //
Artificial Intelligence Review. – 2019. – P. 673-705.
14. Янковский А.А., Бугрий А.Н. Критерии выбора метода бинаризации при обработке изображений
лабораторных анализов // АСУ и приборы автоматики. – 2010. – № 153. – С. 53-56.
15. Федоров А. Бинаризация черно-белых изображений: состояние и перспективы развития. – Ре-
жим доступа: http://itclaim.ru/Library/Books/ITS/ wwwbook/ist4b/its4/fyodorov.htm/ (дата обраще-
ния: 15.07.2024).
16. Зотикова А.А., Иванова Е.А. Обзор алгоритмов компьютерного зрения // Цифровизация эконо-
мики: направления, методы, инструменты. – 2023. – С. 436-439.
17. Пехота А.Н., Галушко В.Н., Громыко И.Л. Технология использования сверточных нейронных
сетей при диагностике состояния трансформаторов // Вестник Полоцкого государственного
университета. Серия Фундаментальные науки. – 2021. – № 12. – С. 63-69.
18. Shah S., Tembhurne J. Object detection using convolutional neural networks and transformer-based
models: a review // Journal of Electrical Systems and Inf. Technol. – 2023. – 10, 54.
– https://doi.org/10.1186/s43067-023-00123-z.
19. Pandey S., Bharti J. Review of different binarization techniques used in different areas of image analysis
// Evolution in Signal Processing and Telecommunication Networks: Proceedings of Sixth International
Conference on Microelectronics, Electromagnetics and Telecommunications (ICMEET
2021), Vol. 2. – Singapore: Springer Singapore, 2022. – P. 249-268.
20. Kang H., Stamoulis I. Gaussian Image Binarization //International Journal of Image and Graphics.
– 2021. – Vol. 21, No. 04. – P. 2150047.
