Power transformers thermal modeling using an Enhanced Set-Membership Multivariable Gaussian Evolving Fuzzy System

Abstract

Knowledge of temperature distribution in power transformers is essential for the management of electrical distribution systems. Monitoring the hot-spot temperature of a power transformer can extend its lifetime. In this work, we present two new models based on Set-Membership filtering: the Set-Membership evolving Multivariable Gaussian and the Enhanced Set-Membership evolving Multivariable Gaussian. Both approaches are acting by adjusting the learning rate in the evolving fuzzy modeling system. To evaluate its performance were applied synthetic data sets, as benchmarks, and data for thermal modeling of real power transformers, under two load conditions: with and without an overload condition. The obtained results are compared with the performance of the original evolving Multivariable Gaussian and with other classical models suggested in the literature. Both proposed models obtained lower errors and presenting a competitive number of rules, suggesting that the models are flexible and efficient approaches in these scenarios.