Keywords
partial discharge
neural networks
failures
How to Cite
Abstract
This article presents the Analysis of Partial Discharge using Neural Techniques. Rotating machines used in the industry tend to have insulation failures caused by a lack of maintenance and ignorance of their status. It is important to carry out periodic tests and continuous evaluations of the state of the insulation to guarantee the correct operation of the machines. One of the methods used to detect these faults is Partial Discharge. Which consist of small discharges produced in a portion of gas that is dissolved in the oil or dielectric that constitutes the insulation of electrical machines. In this research work, an analysis of two works developed around partial discharges is carried out, where artificial intelligence techniques have been implemented. The results showed the high effectiveness of neural networks to achieve the classification of partial discharges and contribute to the maintenance of high-power electrical equipment.
Keywords: high voltage electrical equipment, partial discharge, neural networks, failures
References
Grimón, Y. (2012) Algoritmo de clasificación de imágenes usando redes neuronales.
Cadena J. and Cadena J. (2008) Aplicación de redes neuronales probabilísticas en la detección de fallas incipientes en transformadores. Universidad Tecnológica de Pereira.
Carvajal, A. García, V. and Asiaín, T. (2008) Diagnóstico en línea de motores de gran capacidad mediante la detección de descargas parciales utilizando técnicas de banda ultra ancha. Revista información tecnológica vol. 19 N° 1 enero 2008. Centro e información tecnológica, La Serena, Chile.
Krivda, A., Blackmore, P. and Birtwhistle, D. "Materials in overhead distribution networks. IEEETansactions on dielectrics and electrical insulation". Vol. 6. N°5 1999.
Magrashi, A. (1997) Pattern recognition of partial discharges using Matlab tools. Sultan Qaboos University, Oman.
Suárez, F. “Proceso Neuronal para Análisis de Descargas Parciales en la empresa CORPOELEC, de Ciudad Guayana, Venezuela”. Rev. Hallazgos 21. Vol. 3, Num. 02. Pp 169-180. Junio 2018.
Suárez, F., Sucre, P., and Almeida, G., “Inteligencia artificial en el proceso de obtención de alumina”, Rev. Universidad, Ciencia y Tecnología. Vol. 22, Num. 88. Pp. 48-56. Julio 2019.
Gómez, M. (2007) “Ejemplo de aplicación de una red de retropropagación” [Online] Available: www.iiia.cisc. es.
Nooraii, A. (2003) “Applying Multivariable Control Technology At Alcoa World Alumina” (Paper presented at the Honeywell User’s Group Annual Meeting, Brisbane, Australia.
Rumelhard, D., Hinton, G and Willians, R. (1986)“Learning representations by backpropagation errors”. Nature.
Bryson, A. and HO, Y. (1969) “Applied optimal control” Blasted. New York.
Mason, D. (1998) “Process Control Technology Saving Energy” Australian Energy News, 10.