EXTRACTION DE CARACTÉRISTIQUES AUTOMATIQUES PAR APPRENTISSAGE PAR TRANSFERT POUR LA PROTECTION DES LIGNES DE TRANSMISSION
Transfer learning for transmission lines protection
DOI :
https://doi.org/10.59277/RRST-EE.2023.4.3Mots-clés :
Intelligence informatique, Détection de fautes, Apprentissage automatique, Systèmes électriques, Lignes de transmissionRésumé
Ce travail propose un modèle de détection et de classification des défauts basé sur l'apprentissage profond avec des exigences assouplies en matière d'ensemble de données. La partie la plus ardue de toute solution basée sur le deep learning est la disponibilité de grands ensembles de données étiquetés. La méthode proposée utilise un modèle d'apprentissage profond pré-entraîné comme point de départ, puis recycle le poids adapté dans un arrangement de transfert pour les applications de classificateur de défauts. Cette stratégie accélère la formation et réduit le besoin d’exigences exhaustives en matière d’ensembles de données étiquetées en tirant parti d’un modèle existant. Le modèle proposé extrait automatiquement les caractéristiques des signaux d'entrée pour décider de l'état des lignes de transport d'électricité, éliminant ainsi le besoin complexe de créer manuellement des caractéristiques pour les algorithmes de classification des défauts. Le modèle est minutieusement testé pour une large gamme de tests de performances. (L'ensemble de données utilisé dans ce travail est accessible au public à cette URL : https://www.kaggle.com/datasets/fezanrafique/wsccc9busfaultdataset).
Références
(1) A. Mukherjee, P.K. Kundu, A. Das, Transmission line faults in power system and the different algorithms for identification, classification and localization: a brief review of methods, J. Inst. Eng. Ser. B, 102, 4, pp. 855–877 (2021).
(2) S. Belagoune, N. Bali, A. Bakdi, B. Baadji, K. Atif, Deep learning through LSTM classification and regression for transmission line fault detection, diagnosis and location in large-scale multi-machine power systems, Meas. J. Int. Meas. Confed., 177, December 2020, p. 109330 (2021).
(3) Y. Lecun, Y. Bengio, G. Hinton, Deep learning, Nature, 521, 7553, pp. 436–444 (2015).
(4) K. Chen, C. Huang, and J. He, Fault detection, classification and location for transmission lines and distribution systems: a review on the methods, High Volt., 1, 1, pp. 25–33 (2016).
(5) Z. He, L. Fu, S. Lin, Z. Bo, Fault detection and classification in EHV transmission line based on wavelet singular entropy, IEEE Trans. Power Deliv., 25, 4, pp. 2156–2163 (2010).
(6) C. Pang, M. Kezunovic, Fast distance relay scheme for detecting symmetrical fault during power swing, IEEE Trans. Power Deliv., 25, 4, pp. 2205–2212 (2010).
(7) S.R. Fahim, Y. Sarker, S.K. Sarker, M.R.I. Sheikh, S.K. Das, Self attention convolutional neural network with time series imaging based feature extraction for transmission line fault detection and classification, Electr. Power Syst. Res., 187, no. February, p. 106437 (2020).
(8) H. Yang, X. Liu, D. Zhang, T. Chen, C. Li, W. Huang, Machine learning for power system protection and control, Electr. J., 34, 1, p. 106881 (2021).
(9) E. Hossain, I. Khan, F. Un-Noor, S.S. Sikander, M.S.H. Sunny, Application of Big Data and Machine Learning in Smart Grid, and Associated Security Concerns: A Review, IEEE Access, 7, pp. 13960–13988 (2019).
(10) M. Jaya Bharata Reddy, P. Gopakumar, D.K. Mohanta, A novel transmission line protection using DOST and SVM, Eng. Sci. Technol. an Int. J., 19, 2, pp. 1027–1039 (2016).
(11) H.R. Baghaee, D. Mlakic, S. Nikolovski, T. Dragicevic, Support Vector Machine-Based Islanding and Grid Fault Detection in Active Distribution Networks, IEEE J. Emerg. Sel. Top. Power Electron., 8, 3, pp. 2385–2403 (Sep. 2020).
(12) S. Kar, S.R. Samantaray, M.D. Zadeh, “Data-Mining Model Based Intelligent Differential Microgrid Protection Scheme, IEEE Syst. J., 11, 2, pp. 1161–1169 (2017).
(13) 13. D.P. Mishra, S.R. Samantaray, G. Joos, A combined wavelet and data-mining based intelligent protection scheme for microgrid, IEEE Trans. Smart Grid, 7, 5, pp. 2295–2304 (2016).
(14) 14. H. Lee et al., An explainable deep-learning algorithm for the detection of acute intracranial haemorrhage from small datasets, Nat. Biomed. Eng., 3, 3, pp. 173–182 (2019).
(15) Z. He, S. Lin, Y. Deng, X. Li, Q. Qian, A rough membership neural network approach for fault classification in transmission lines, Int. J. Electr. Power Energy Syst., 61, pp. 429–439 (2014).
(16) K. Chen, J. Hu, J. He, Detection and Classification of Transmission Line Faults Based on Unsupervised Feature Learning and Convolutional Sparse Autoencoder, IEEE Trans. Smart Grid, 9, 3, pp. 1748–1758 (2018).
(17) F. Rafique, L. Fu, R. Mai, End to end machine learning for fault detection and classification in power transmission lines, Electr. Power Syst. Res., 199, June, p. 107430 (2021).
(18) K. Weiss, T.M. Khoshgoftaar, D.D. Wang, A survey of transfer learning, J Big Data., vol. 3, no. 1. Springer International Publishing, 2016.
(19) S. Bozinovski, Reminder of the First Paper on Transfer Learning in Neural Networks, 1976, Informatica, 44, 3 (Sep. 2020).
(20) F. Zhuang et al., A comprehensive survey on transfer learning, Proc. IEEE, 109, 1, pp. 43–76 (2021).
(21) S.J. Pan, Q. Yang, A Survey on Transfer Learning, IEEE Trans. Knowl. Data Eng., 22, 10, pp. 1345–1359 (Oct. 2010).
(22) H. Jiang, L. Chang, Q. Li, D. Chen, Deep transfer learning enable end-to-end steering angles prediction for self-driving car, 2020 IEEE Intelligent Vehicles Symposium (IV), IV, pp. 405–412 (Oct. 2020).
(23) G. Liang, L. Zheng, A transfer learning method with deep residual network for pediatric pneumonia diagnosis, Comput. Methods Programs Biomed., 187, p. 104964 (2020).
(24) Mohebbanaaz, L.V.R. Kumar, Y.P. Sai, A new transfer learning approach to detect cardiac arrhythmia from ECG signals, Signal, Image Video Process., 16, 7, pp. 1945–1953 (2022).
(25) K. Weimann, T.O.F. Conrad, Transfer learning for ECG classification, Sci. Rep., 11, 1, pp. 1–12 (2021).
(26) C. Pan, J. Huang, J. Gong, X. Yuan, Few-Shot Transfer Learning for Text Classification with Lightweight Word Embedding Based Models, IEEE Access, 7, pp. 53296–53304 (2019).
(27) ***Nota uses AI to make roadways safer and more efficient. https://resources.nvidia.com/en-us-metropolis-software-success-stories/embedded-nota-soluti (accessed Apr. 10, 2022).
(28) A. Krizhevsky, I. Sutskever, G.E. Hinton, ImageNet classification with deep convolutional neural networks, Commun. ACM, 60, 6, pp. 84–90 (2017).
(29) N.E. Huang et al., The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis, Proc. R. Soc. London. Ser. A Math. Phys. Eng. Sci., 454, 1971, pp. 903–995 (Mar. 1998).
(30) A.S. Al-Hinai, Voltage collapse prediction for interconnected power systems. West Virginia University (2000).
Téléchargements
Publiée
Numéro
Rubrique
Licence
(c) Copyright REVUE ROUMAINE DES SCIENCES TECHNIQUES — SÉRIE ÉLECTROTECHNIQUE ET ÉNERGÉTIQUE 2023
Ce travail est disponible sous licence Creative Commons Attribution - Pas d'Utilisation Commerciale - Pas de Modification 4.0 International.
