Metodologia para Estimar a Vida Útil de Para-raios de Óxido de Zinco Baseada na Aplicação do Sistema Neuro-Fuzzy Adaptativo

This work presents a methodology to be used estimate the Metal Oxide Surge Arresters’ (MOSAs’) useful life, based on prediction model Adaptive Neuro-Fuzzy Inference System (ANFIS). For this purpose, database consisting of MOSA’s total leakage current was used. Thus, it possible build time series composed values third harmonic component current. is one indicators MOSAs’ degradation level most in surge arresters monitoring. Subsequently, forecasting models artificial intelligence (ANFIS and Support Vector Regression - SVR) were implemented, evaluated, compared. During implementations, ANFIS tested with three distinct membership functions: Gaussian, Generalized Bell-Shaped, Pi-Shaped; SVR different kernel Linear, Polynomial. The performance each implemented evaluated using determination coefficient training phase mean absolute percentage error, validation phase. Considering results obtained by e models, found that forecasts made Gaussian function accurate forecasts. proposed methodology, which applies function, life.