ARTIFICIAL INTELLIGENCE SYSTEM FOR ONLINE MONITORING OF UNDERGROUND POWER CABLE LINES BASED ON DEEP LEARNING TECHNOLOGIES
Keywords:
кабельная линия, мониторинг, глубокое обученение, CNN, LSTM.Abstract
The paper describes an artificial intelligence system for detecting, classifying and localizing faults in a three-phase power underground medium voltage cable line using deep neural networks based on CNN and LSTM models, using specialized software to obtain a large data set for training deep neural networks, and outlines the procedure preparation of data required for training.
References
Patel B, Bera P. Detection of power swing and fault during power swing using Lissajous figure // IEEE trans power deliv. 2018. N 33(6). P. 3019–3027
K. R. K, Dash PK, A new real-time fast discrete S-transform for cross-differential protection of shunt-compensated power systems // IEEE Trans Power Deliv. 2013. N 28(1). P. 402–410
Mohd Amiruddin AAA, Zabiri H, Taqvi SAA, Tufa LD Neural network applications in fault diagnosis and detection: an overview of implementations in engineering-related systems // Neural Comput Appl. 2020. N 32(2). P. 447–472
Верзунов С.Н. Применение глубоких нейронных сетей для краткосрочного прогноза дальности видимости // Проблемы автоматики и управления. 2019. № 1 (36). С. 118-130.
Zhang F, Liu Q, Liu Y, Tong N, Chen S, Zhang C. Novel fault location method for power systems based on attention mechanism and double structure GRU neural network // IEEE Access. 2020. N 8 P. 75237–75248
Qiao M, Yan S, Tang X, Xu C. Deep convolutional and LSTM recurrent neural networks for rolling bearing fault diagnosis under strong noises and variable loads // IEEE Access. 2020. N 8. P. 66257–66269
Антонио Джулли, Суджит Пал. Библиотека Keras – инструмент глубокого обучения. – М.: ДМК Пресс, 2018. – 294 с.
Swaminathan, R., Mishra, S., Routray, A. et al. A CNN-LSTM-based fault classifier and locator for underground cables // Neural Comput & Applic. 2021. https://doi.org/10.1007/s00521-021-06153-w
https://arxiv.org/abs/1609.03499v2 (дата обращения: 07.06.21)
https://arxiv.org/abs/1412.6980v9 (дата обращения: 07.06.21)
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2021 Верзунов С.Н.
This work is licensed under a Creative Commons Attribution 4.0 International License.
