Fuzzy clustering as a tool for reducing subjectivity in the diagnosis of polymer insulators
Article Sidebar
Main Article Content
Abstract
The diagnosis of polymer insulators is a relevant topic of study and may present a high subjectivity. Thus, the present work aims to propose a methodology based on fuzzy clustering to reduce subjectivity in the diagnosis of polymer insulators. 60 polymer insulators with different degradation levels and nominal voltage of 138 kV were tested. The insulators were classified through visual inspection in three degradation levels: low, intermediate and critical. Then, the insulators were submitted to the following monitoring techniques: ultraviolet radiation detection, infrared thermography and ultrasound noise detection. Data from inspections were extracted and processed. For each monitoring method besides visual inspection, samples were grouped in three clusters. The clusters were associated to the degradation levels through detailed data analysis. A diagnosis was stablished considering the clusters from the three monitoring methods and results were compared to the diagnosis considering the visual inspection, and the most critical condition among them was considered. Five of the insulators presented a higher degradation level than the one stablished through visual inspection, so the methodology used would ensure the removal or supervision of the equipment. The proposed methodology reduces subjectivity in the diagnosis of polymer insulators while adding an unsupervised factor in the classification of its operational state.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Los autores conservan los derechos de autor y ceden a la revista el derecho de la primera publicación y pueda editarlo, reproducirlo, distribuirlo, exhibirlo y comunicarlo en el país y en el extranjero mediante medios impresos y electrónicos. Asimismo, asumen el compromiso sobre cualquier litigio o reclamación relacionada con derechos de propiedad intelectual, exonerando de responsabilidad a la Editorial Tecnológica de Costa Rica. Además, se establece que los autores pueden realizar otros acuerdos contractuales independientes y adicionales para la distribución no exclusiva de la versión del artículo publicado en esta revista (p. ej., incluirlo en un repositorio institucional o publicarlo en un libro) siempre que indiquen claramente que el trabajo se publicó por primera vez en esta revista.
References
R. MARTINS. Desenvolvimento de isolador polimérico inteligente. Curitiba: Departamento de Engenharia e Ciência dos Materiais. Tese de Doutorado. Universidade Federal do Paraná – UFPR, 2015.
Y. G. PUSHPA, N. VASUDEV. Artificial Pollution Testing of Polymeric Insulators by CIGRE Round Robin Method – Withstand & Flashover Characteristics. In: 3rd International Conference on Condition Assessment Techniques in Electrical Systems (CATCON), 2017.
A. KHALED, A. EL-HAG, K. ASSALEH. Equivalent Salt Deposit Density Prediction of Outdoor Polymer Insulators during Salt Fog Test. 2016 IEEE Conference on Electrical Insulation and Dielectric Phenomena (CEIDP), p. 786–789, 2016.
Y. KIM, K. SHONG. The characteristics of UV strength according to corona discharge from polymer insulators using a UV sensor and optic lens. IEEE Transactions on Power Delivery, v. 26, n. 3, p. 1579–1584, 2011.
I. M. A. M. KARUNARATHNA, K. T. L. KARUNATHILAKA, W. M. H. M. WANASINGHE, G. K. L. SAMPATH, J. R. LUCAS, R. SAMARASINGHE. Monitoring System for Outdoor Insulators. In: 2018 2nd International Conference On Electrical Engineering (EECon), Colombo, 2018.
K-E, B. BRITO. Extração de Atributos de Fáculas de Imagens Ultravioletas de Isoladores Poliméricos. [s.l.]. Dissertação (Mestrado em Engenharia Elétrica).Universidade Federal de Campina Grande, 2017.
L. FANGCHENG, W. SHENGHUI, L. HEMING. Insulator pollution grade evaluation based on ultraviolet imaging and fuzzy logic inferenceAsia-Pacific Power and Energy Engineering Conference, APPEEC. Anais...2010
S. K. POLISETTY, A. EL-HAG, S. JAYARAM. Classification of Common Discharges in Outdoor Insulation Using Acoustic Signals and Artificial Neural Network. High Voltage, p. 2–13, 2019.
E. S. DOMINGUES. Improved Condition Monitoring of Composite Insulators. [s.l.] The University of Manchester, 2012.
D. PERNEBAYEVA, A. IRMANOVA, D. SADYKOVA, M. BAGHERI, A. JAMES. High voltage outdoor insulator surface condition evaluation using aerial insulator images. High Voltage, v. 4, n. 3, p. 178–185, 2019.
D. SONI. Supervised vs. Unsupervised Learning. Towards Data Science, 2018. Disponivel em: https://towardsdatascience.com. Acesso em: 17 de Junho de 2020.
C. P. G. GUEDES. Classificação das Condições de Degradação de Isoladores Poliméricos pelos Níveis de Radiação UV e a Lógica Fuzzy. [s.l.] Universidade Federal de Campina Grande, 2015.
G. R. LIMA. Aprimoramento da Classificação de Isoladores Poliméricos por Medições Termográficas e Radiação UV usando Processamento de Imagens e RNA. [s.l.] Universidade Federal de Campina Grande, 2017.
T. V. FERREIRA, A. D. GERMANO, E. G. COSTA. Ultrasound and artificial intelligence applied to the pollution estimation in insulations. IEEE Transactions on Power Delivery, v. 27, n. 2, p. 583–589, 2012.
P. H. V. ROCHA. Estimação da poluição de isoladores em linhas de transmissão a partir da irradiação de RF. Tese (Doutorado em Engenharia Elétrica). Universidade Federal de Campina Grande – UFCG. Campina Grande, 2017.
P. H. V. ROCHA, E. G. COSTA, A. R. SERRES, G. V. R. XAVIER, J. E. B. PEIXOTO, R. I. LINS. Inspection in overhead insulators through the analysis of the irradiated RF spectrum. Electrical Power and Energy Systems, v. 113, 2019.
B. DIAS. Gestão Técnica de Isoladores Poliméricos Utilizando Aprendizado de Máquina. [s.1]. Tese de Doutorado. Universidade Federal de Campina Grande – UFCG, 2021.
W. PEDRYCZ. Knowledge-Based Clustering. Haboken, Nova Jersey: John Wiley & Sons, Inc., 2005.
R. XU, D. C. WUNSCH II. Clustering. Haboken, Nova Jersey: John Wiley & Sons, Inc., 2009.
R. S. GORUR. Condition Assessment of Polymer Insulators. PSERC Seminar Presentation, 2006, p. 37.
T. V. FERREIRA, A. D. GERMANO, E. G. COSTA. Ultrasound and artificial intelligence applied to the pollution estimation in insulations. IEEE Transactions on Power Delivery, v. 27, n. 2, p. 583–589, 2012.
FLORENTINO, M. T. B.; COSTA, E. G. DA; FERREIRA, T. V.; GERMANO, A. D. Spectral subband centroid energy vectors algorithm and artificial neural networks for acoustic emission pattern classification. Advances in Electrical and Computer Engineering, v. 19, n. 3, p. 49–56, 2019.
E. HANCER, B. XUE, M. ZHANG. A survey on feature selection approaches for clustering. In: Artificial Intelligence Review, v. 53, 2020.
M. HAINDL, P. OMOL, D. VERVERIDIS, C. KOTROPOULOS. Feature selection based on mutual correlation. In: Carrasco Ochoa JA, Kittler J, Martínez-Trinidad JF (eds) Progress in pattern recognition, imageanalysis and applications. Springer, Berlin, pp 569–577, 2006.