电路相关Ultra-sound and artificial intelligence applied to the diagnostic of insulations in the field.pdfVIP

Ultra-sound and Artificial Intelligence Applied to the Diagnostic of Insulations in the Field Ferreira, T. V., Germano, A. D., Costa, E. G. Department of Electrical Engineering Federal University of Campina Grande Campina Grande, Paraíba, Brazil tarso@dee.ufcg.edu.br Abstract—This work studies the feasibility of implementing a very helpful in tasks like this, where the patterns can be very system for diagnosis in the field of electrical insulation based on similar to each other. ultrasonic noise and artificial neural networks. Such system, proved functional under laboratory conditions, extracts spectral The technique was published in previous papers, and information from the ultrasonic noise emitted by the corona showed its viability under laboratory conditions [2]. This time discharges that occur in electric equipment and correlates it it is applied in a substation, where the ultrasound signals are with degrees of pollution previously defined. To achieve this detected from several high voltage equipments, such as classification, artificial neural networks are employed. The instrumentation transformers, insulator strings, circuit results show the viability of the method in the field, but they also breakers, switches, etc. The signals are also collected from show that its reliability is proportional to the size and diversity transmission tower insulator strings. The results show the