Produção Nacional
Revisado por pares
Nonlinear Autoregressive Neural Network Models for Prediction of Transformer Oil-Dissolved Gas Concentrations
2018; Multidisciplinary Digital Publishing Institute; Volume: 11; Issue: 7 Linguagem: Inglês
10.3390/en11071691
ISSN1996-1073
AutoresFábio Henrique Pereira, Francisco Elânio Bezerra, S. Toledo Piza Júnior, Josemir Belo dos Santos, Ivan Eduardo Chabu, Gilberto Francisco Martha de Souza, F. J. Micerino, Sílvio Ikuyo Nabeta,
Tópico(s)Energy Load and Power Forecasting
ResumoTransformers are one of the most important part in a power system and, especially in key-facilities, they should be closely and continuously monitored. In this context, methods based on the dissolved gas ratios allow to associate values of gas concentrations with the occurrence of some faults, such as partial discharges and thermal faults. So, an accurate prediction of oil-dissolved gas concentrations is a valuable tool to monitor the transformer condition and to develop a fault diagnosis system. This study proposes a nonlinear autoregressive neural network model coupled with the discrete wavelet transform for predicting transformer oil-dissolved gas concentrations. The data fitting and accurate prediction ability of the proposed model is evaluated in a real world example, showing better results in relation to current prediction models and common time series techniques.
Referência(s)