Monitoramento on-line e diagnóstico inteligente da qualidade dielétrica do isolamento líquido de transformadores de potência

Abstract

The monitoring and diagnosis of incipient fault in power transformers immerses in oil are directly related to the assessment of the isolation system conditions. In this research, it is established the concept of monitoring and diagnosis, after that, on-line monitoring techniques are discussed. A pre-diagnosis system is elaborated based on use of a monitoring on-line device, Hydran® GE, to classify the situation gravity of the detected fault. Once detected a fault situation, intelligent modules of incipient fault diagnosis, by neural networks, can be used to identification of internal fault of the equipment. To complete the checking of the dielectric quality of the isolate liquid, it is also described an intelligent algorithm, based on neural networks, to diagnosis of the oil estate through physical-chemical attribute. The relation between physical-chemical attributes and chromatographic ones regarding to mineral oil were also verified. It was developed, then, the dissolved gases esteem through physicalchemical characteristics. The on-line monitoring modules, diagnosis of oil estate and incipient fault, besides dissolved gases esteem, constitute a computation aid system to operation and maintenance. The implemented system presents satisfied results in a thermoelectric power plant.